{"id":"b7bf5c98-60e4-4f91-8a62-e563d43cdb21","entityType":"agent","slug":"clawhub-medstatstar-ct-advisor","name":"Clinical Trial Chief Advisor / 临床试验总顾问","canonicalUrl":"https://www.xpersona.co/agent/clawhub-medstatstar-ct-advisor","canonicalPath":"/agent/clawhub-medstatstar-ct-advisor","generatedAt":"2026-10-10T10:43:12.000Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-10T05:18:56.414Z","emptyReason":null},"description":"The single entry point for the ct-series across the full clinical-development lifecycle — a cloud-assisted clinical trial advisor. All questions (methodology / design / compliance / QC / site-execution / intelligence) are forwarded to the cloud Coze engine for analysis. The local side only performs a deterministic binary vague-gate (vague | forwarded) and attachment decoding; no knowledge base is retained locally, and no local network retrieval occurs. External reference: the teal clinical-data interactive exploration framework. / 面向临床研发全生命周期的 ct 系列「总入口」，云端辅助的临床试验总顾问。所有问题（方法学/设计/合规/QC/现场执行/情报）统一提交云端 Coze 引擎分析处理。本地仅做确定性二值闸门（是否 vague）与附件解码，不保留知识库，不进行本地网络检索。外部参考：teal 临床数据交互探索框架。 Skill: Clinical Trial Chief Advisor / 临床试验总顾问 Owner: medstatstar Summary: The single entry point for the ct-series across the full clinical-development lifecycle — a cloud-assisted clinical trial advisor. All questions (methodology / design / compliance / QC / site-execution / intelligence) are forwarded to the cloud Coze engine for analysis. The local side only performs a deterministic binary vague-gate (vague | for","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.7K downloads reported by the source. Last updated 10/10/2026.","installCommand":"clawhub skill install s176fv8983h1rte6dmxwp9wt4n89j8p5:ct-advisor","sourceUrl":"https://clawhub.ai/medstatstar/ct-advisor","homepage":"https://clawhub.ai/medstatstar/skills/ct-advisor","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/medstatstar/ct-advisor","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/medstatstar/skills/ct-advisor","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":64,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"The single entry point for the ct-series across the full clinical-development lifecycle — a cloud-assisted clinical trial advisor. All questions (methodology / "},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-10T05:18:56.414Z","emptyReason":null},"protocols":[{"protocol":"OPENCLEW","label":"OpenClaw","status":"self-declared","notes":"Declared in the public agent profile."}],"capabilities":[],"verifiedCount":0,"selfDeclaredCount":1,"capabilityMatrix":{"rows":[{"key":"OPENCLEW","type":"protocol","support":"unknown","confidenceSource":"profile","notes":"Listed on profile"}],"flattenedTokens":"protocol:OPENCLEW|unknown|profile"}},"adoption":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T05:18:56.414Z","emptyReason":null},"stars":null,"forks":null,"downloads":1660,"packageName":null,"latestVersion":"1.3.0","tractionLabel":"1.7K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-10T05:18:56.380Z","emptyReason":null},"lastUpdatedAt":"2026-10-10T05:18:56.414Z","lastCrawledAt":"2026-10-10T05:18:56.380Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-11T05:18:56.380Z","lastVerifiedAt":null,"highlights":[{"version":"1.3.0","createdAt":"2026-10-09T11:56:00.277Z","changelog":"v1.3.0: add teal/Docling external open-source asset references; add drug-name/term localization maps and resolver scripts; enhance i18n dictionary and localization; sync bilingual READMEs.","fileCount":60,"zipByteSize":458061},{"version":"1.2.2","createdAt":"2026-09-27T04:52:15.935Z","changelog":"v1.2.2: install_sibling endpoint trust gate + zip integrity checks; privacy scrub; L1 resident orchestration service; binary entry gate (version unified across GitHub/SkillHub/ClawHub)","fileCount":51,"zipByteSize":395815},{"version":"0.9.104","createdAt":"2026-09-16T09:22:20.208Z","changelog":"v1.0.3: Pipe-Only Hard Contract added, SKILL.md slimmed to 216 lines, A/B Tier Gate moved to references/tier_gate.md, description rewritten per summary","fileCount":86,"zipByteSize":592361},{"version":"0.9.103","createdAt":"2026-08-25T09:38:55.979Z","changelog":"v0.9.103：发布前对齐 ct-base §16（kw_lexicon 同步修复、shared_sync_check 全一致）；Mode B 追问自包含化闭环（context_stitch 始终导出有界 conversation_history）；refiner ~区间记号渲染修正；追问/complex 超时上调 300s；删除'零出站'绝对化措辞改事实描述；[HIGH] Tp4 整改（README 范围现实核对横幅 + §5 离机/留本机两段式 + declared-purpose 对齐）；README 双语同步；新增 references/ADVANCED.md。因 SkillHub 预注册 0.9.102 占位升版至 0.9.103。","fileCount":81,"zipByteSize":454248},{"version":"0.9.100","createdAt":"2026-08-23T01:11:14.281Z","changelog":"Add bug report feature (ct-base 20.3); whitelist bugreport endpoint; README disclosure. Coze cloud code excluded.","fileCount":80,"zipByteSize":436366},{"version":"0.9.70","createdAt":"2026-08-23T01:08:55.651Z","changelog":"**Major update with enhancements to document processing, language alignment, dependency requirements, and new tooling.** - Added support for docx/pdf/ppt attachment processing with in-house Markdown conversion (`scripts/office_to_md.py`); conversion strategy aligns with ct-base §6.7. - Enforced automatic answer language alignment: ensures responses match the question language (translates narrative only, structural and proper names untouched). - Raised dependency requirements: now mandates all sibling ct-series skills (ct-registry, ct-safety, ct-literature, ct-samplesize, meta-analysis) at Tier A. - Embedded Coze credential moved to `adapters/coze_token_embedded.py` (obfuscated public token, not user-editable). - Expanded/updated knowledge documentation, user guides, and workflow/spec references. - New/updated scripts for bug reporting, context stitching, and refined competitive intelligence handling.","fileCount":80,"zipByteSize":436492},{"version":"0.9.69","createdAt":"2026-08-15T02:44:44.346Z","changelog":"v0.9.69: pre-publish §16 compliance (audit trace, shared artifact sync, test script exclusion); code-fully-automatic orchestrator + LLM-delegated ct-skill calls","fileCount":76,"zipByteSize":389668},{"version":"0.9.62","createdAt":"2026-08-14T14:06:42.520Z","changelog":"v0.9.63 内容发布为 ClawHub 0.9.62（CLI 自动 next-patch）：转发提示中立化 + ct-base 16 安全审计整改（STILL_PRESENT 6→0）：AGENTS.md python -c 矛盾段删除、refiner.py query_origin docstring 与实现一致、README 出站披露补 draft_answer。GitHub 源 a3ebf4f。","fileCount":73,"zipByteSize":360252}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s176fv8983h1rte6dmxwp9wt4n89j8p5:ct-advisor","setupComplexity":"low","setupSteps":["Setup complexity is classified as HIGH. You must provision dedicated cloud infrastructure or an isolated VM. Do not run this directly on your local workstation.","Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data."],"contract":{"contractStatus":"missing","authModes":[],"requires":[],"forbidden":[],"supportsMcp":false,"supportsA2a":false,"supportsStreaming":false,"inputSchemaRef":null,"outputSchemaRef":null,"dataRegion":null,"contractUpdatedAt":null,"sourceUpdatedAt":null,"freshnessSeconds":null},"invocationGuide":{"preferredApi":{"snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-medstatstar-ct-advisor/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-medstatstar-ct-advisor/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-medstatstar-ct-advisor/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-medstatstar-ct-advisor/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-medstatstar-ct-advisor/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-medstatstar-ct-advisor/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-10T10:43:11.995Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-medstatstar-ct-advisor/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-medstatstar-ct-advisor/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-medstatstar-ct-advisor/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-medstatstar-ct-advisor/trust"}},"reliability":{"evidence":{"source":"runtime-metrics","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No trust, reliability, or runtime telemetry is available."},"trust":{"status":"unavailable","handshakeStatus":"UNKNOWN","verificationFreshnessHours":null,"reputationScore":null,"p95LatencyMs":null,"successRate30d":null,"fallbackRate":null,"attempts30d":null,"trustUpdatedAt":null,"trustConfidence":"unknown","sourceUpdatedAt":null,"freshnessSeconds":null},"decisionGuardrails":{"doNotUseIf":["Contract metadata is missing or unavailable for deterministic execution."],"safeUseWhen":[],"riskFlags":["missing_or_unavailable_contract","trust_data_unavailable","schema_references_missing"],"operationalConfidence":"low"},"executionMetrics":{"observedLatencyMsP50":null,"observedLatencyMsP95":null,"estimatedCostUsd":null,"uptime30d":null,"rateLimitRpm":null,"rateLimitBurst":null,"lastVerifiedAt":null,"verificationSource":null},"runtimeMetrics":{"successRate":null,"avgLatencyMs":null,"avgCostUsd":null,"hallucinationRate":null,"retryRate":null,"disputeRate":null,"p50Latency":null,"p95Latency":null,"lastUpdated":null}},"benchmarks":{"evidence":{"source":"no-benchmark-data","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No benchmark suites or observed failure patterns are available."},"suites":[],"failurePatterns":[]},"artifacts":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"high","updatedAt":"2026-10-10T05:18:56.414Z","emptyReason":null},"readme":"Skill: Clinical Trial Chief Advisor / 临床试验总顾问\n\nOwner: medstatstar\n\nSummary: The single entry point for the ct-series across the full clinical-development lifecycle — a cloud-assisted clinical trial advisor. All questions (methodology / design / compliance / QC / site-execution / intelligence) are forwarded to the cloud Coze engine for analysis. The local side only performs a deterministic binary vague-gate (vague | forwarded) and attachment decoding; no knowledge base is retained locally, and no local network retrieval occurs. External reference: the teal clinical-data interactive exploration framework. / 面向临床研发全生命周期的 ct 系列「总入口」，云端辅助的临床试验总顾问。所有问题（方法学/设计/合规/QC/现场执行/情报）统一提交云端 Coze 引擎分析处理。本地仅做确定性二值闸门（是否 vague）与附件解码，不保留知识库，不进行本地网络检索。外部参考：teal 临床数据交互探索框架。\n\nTags: latest:1.3.0\n\nVersion history:\n\nv1.3.0 | 2026-10-09T11:56:00.277Z | user\n\nv1.3.0: add teal/Docling external open-source asset references; add drug-name/term localization maps and resolver scripts; enhance i18n dictionary and localization; sync bilingual READMEs.\n\nv1.2.2 | 2026-09-27T04:52:15.935Z | user\n\nv1.2.2: install_sibling endpoint trust gate + zip integrity checks; privacy scrub; L1 resident orchestration service; binary entry gate (version unified across GitHub/SkillHub/ClawHub)\n\nv0.9.104 | 2026-09-16T09:22:20.208Z | user\n\nv1.0.3: Pipe-Only Hard Contract added, SKILL.md slimmed to 216 lines, A/B Tier Gate moved to references/tier_gate.md, description rewritten per summary\n\nv0.9.103 | 2026-08-25T09:38:55.979Z | user\n\nv0.9.103：发布前对齐 ct-base §16（kw_lexicon 同步修复、shared_sync_check 全一致）；Mode B 追问自包含化闭环（context_stitch 始终导出有界 conversation_history）；refiner ~区间记号渲染修正；追问/complex 超时上调 300s；删除'零出站'绝对化措辞改事实描述；[HIGH] Tp4 整改（README 范围现实核对横幅 + §5 离机/留本机两段式 + declared-purpose 对齐）；README 双语同步；新增 references/ADVANCED.md。因 SkillHub 预注册 0.9.102 占位升版至 0.9.103。\n\nv0.9.100 | 2026-08-23T01:11:14.281Z | user\n\nAdd bug report feature (ct-base 20.3); whitelist bugreport endpoint; README disclosure. Coze cloud code excluded.\n\nv0.9.70 | 2026-08-23T01:08:55.651Z | auto\n\n**Major update with enhancements to document processing, language alignment, dependency requirements, and new tooling.**\n\n- Added support for docx/pdf/ppt attachment processing with in-house Markdown conversion (`scripts/office_to_md.py`); conversion strategy aligns with ct-base §6.7.\n- Enforced automatic answer language alignment: ensures responses match the question language (translates narrative only, structural and proper names untouched).\n- Raised dependency requirements: now mandates all sibling ct-series skills (ct-registry, ct-safety, ct-literature, ct-samplesize, meta-analysis) at Tier A.\n- Embedded Coze credential moved to `adapters/coze_token_embedded.py` (obfuscated public token, not user-editable).\n- Expanded/updated knowledge documentation, user guides, and workflow/spec references.\n- New/updated scripts for bug reporting, context stitching, and refined competitive intelligence handling.\n\nv0.9.69 | 2026-08-15T02:44:44.346Z | user\n\nv0.9.69: pre-publish §16 compliance (audit trace, shared artifact sync, test script exclusion); code-fully-automatic orchestrator + LLM-delegated ct-skill calls\n\nv0.9.62 | 2026-08-14T14:06:42.520Z | user\n\nv0.9.63 内容发布为 ClawHub 0.9.62（CLI 自动 next-patch）：转发提示中立化 + ct-base 16 安全审计整改（STILL_PRESENT 6→0）：AGENTS.md python -c 矛盾段删除、refiner.py query_origin docstring 与实现一致、README 出站披露补 draft_answer。GitHub 源 a3ebf4f。\n\nv0.9.61 | 2026-08-14T11:40:02.623Z | user\n\n简化流程、大幅优化速度：全量直发（forward-only）取代 race/serial/本地答三档分流，每问单次转发云端引擎；need_tool 技能卡缝合 + 本地兜底 + 缺参追问。含合规整改（混淆凭据、出站收口）与目录整理。\n\nv0.9.60 | 2026-08-13T03:37:38.257Z | user\n\nv0.9.59 审计修复（machine_id 文档诚实化/to_payload 回 3 变量契约/prompts.md 去指令化/README 披露）。v0.9.60 Coze 失败防护：ProxyError/ConnectionError 自动绕过系统代理直连重试；新增 check_coze.py 一键诊断；fallback 提示友好化（i18n 251 键成对）；诊断先询问用户，拒绝则交付本地答案+重提示「无法连接 Coze 服务，答案未经过精校，请谨慎使用」\n\nv0.9.58 | 2026-08-12T08:31:01.296Z | user\n\n契约对齐服务端 v1.5；tone/memory 暂不启用（服务端未实现）；difficulty 兜底修复（缺失默认 complex，飞书收集不空白）；调用示例补全 query_meta\n\nv0.9.57 | 2026-08-12T07:14:02.338Z | user\n\n路由层定稿：route.py 四档 + SIMPLE_TOPICS 白名单\n\nv0.9.55 | 2026-08-12T07:11:09.991Z | user\n\n路由层定稿：route.py 确定性四档 + SIMPLE_TOPICS 白名单（0 漏发车）；Step 0 改跑 route.py（零 LLM）；simple/非simple 语义分水岭；SKILL.md 压至 200 行（ct-base §16 合规）；实测 middle 0.63s / complex 20.6s\n\nv0.9.54 | 2026-08-11T03:19:26.755Z | user\n\nSelf-contained: inject ct-base shared assets, remove sibling fallback\n\nv0.9.53 | 2026-08-09T11:29:27.913Z | user\n\nFix ClawHub display name (was 'Ct Advisor Claw'); trim frontmatter dependencies/permissions; sync EN README\n\nv0.9.52 | 2026-08-09T09:33:25.767Z | user\n\n安全审计修复（ClawHub SkillSpector 重审）：refiner.py/refine_answer.py 改用标准 import 替代 importlib 动态加载 config/keys.py（清 2x Critical 动态代码执行）；移除 --store-token/--token-path CLI 凭据落盘入口（清 1x Medium 凭据存储面）；compute_machine_id 由 hostname 派生稳定标识改为每进程随机 seed（降 1x Medium 主机归因）。同时上线此前未发布的 0.9.51（simple 本地零出站 / 三流程重构 / 英文化 / README 同步）。\n\nv0.9.50 | 2026-08-09T07:09:44.116Z | user\n\n本地检索纪律红线：每轮本地检索仅 1 次、未命中直走 Coze 远端、本地检索后严禁外部网络数据检索（Coze 为唯一信息主力）\n\nv0.9.49 | 2026-08-09T02:12:39.853Z | user\n\n双语提示优化：将 refine_answer.py / run_refined.py / check_deps.py 的用户提示统一接入共享 i18n（t()）系统；清理死参 cli_token/token_path；同步 ct-base 共享词条。\n\nv0.9.48 | 2026-08-08T13:23:07.704Z | user\n\nv0.9.48: fix refiner token call signature mismatch; add coze endpoint to outbound allowlist; add raise_for_status + 401 AUTH_REJECTED alert; knowledge revised/deduped.\n\nv0.9.45 | 2026-08-08T08:22:33.865Z | user\n\nv0.9.45: dedupe SKILL/steps docs; race fire-only outbinds difficulty but empty category/accuracy; category taxonomy aligned (methodology:C, :letter=A-J); AskUserQuestion <=4; creds embedded; coze interface docs excluded\n\nv0.9.39 | 2026-08-07T12:22:20.708Z | user\n\nSecurity audit fix: remove silent pip install (user consent required); eliminate offline/privacy misrepresentations in docs\n\nv0.9.38 | 2026-08-07T11:07:15.425Z | user\n\nRemove local-only refinement mode; Coze is now the unique refinement backend. Rewrite steps.md EN/ZH, fix vague path, add difficulty bias rule, clean v0.9.17/always-on residues, expand EN triggers, restructure README for end-users, i18n 147 keys all EN+ZH paired.\n\nv0.8.2 | 2026-08-02T11:37:30.638Z | user\n\nSecurity-audit remediation: removed unimplemented dual-model claim, Q&A logging off by default, Coze _post now inert (NotImplementedError).\n\nv0.8.1 | 2026-08-02T10:54:17.083Z | user\n\nAnglicized English README; version bump to 0.8.1\n\nv0.8.0 | 2026-08-02T10:35:34.594Z | user\n\ninit version\n\nArchive index:\n\nArchive v1.3.0: 60 files, 458061 bytes\n\nFiles: adapters/__init__.py (2602b), adapters/bug_report.py (20209b), adapters/coze_token_embedded.py (10126b), adapters/coze_upload.py (5738b), adapters/http_probe.py (1605b), adapters/install_sibling.py (13010b), adapters/local_service_client.py (4787b), adapters/probe_publication.py (15803b), adapters/refiner.py (46474b), adapters/sanitize.py (2233b), AGENTS.md (7529b), assets/icon.svg (2980b), CHANGELOG.md (234933b), config.json (801b), config/dedup_store.json (3126b), docs/2026-09-23-docarchive-table-spec.md (10810b), docs/2026-09-23-feishu-doc-archive-single-table-plan.md (35199b), docs/2026-09-23-feishu-document-archive-plan.md (20378b), docs/2026-09-23-local-guards-improvement.md (7483b), docs/2026-09-23-upload-limits-and-compression.md (10095b), LICENSE (1091b), README_zh-CN.md (35715b), README.md (38868b), references/drug_name_map.json (23396b), references/term_map.json (23195b), scripts/_perf_deploy.py (2900b), scripts/check_coze.py (5129b), scripts/check_ooxml_sync.py (4401b), scripts/check_route_drift.py (6464b), scripts/clarify_loop.py (20324b), scripts/context_stitch.py (9968b), scripts/dedup_guard.py (5700b), scripts/discover_siblings.py (13004b), scripts/doc_memory.py (42104b), scripts/drug_name_resolver.py (5977b), scripts/entry.py (13456b), scripts/forward_guards.py (5601b), scripts/handle_need_tool.py (43968b), scripts/hardware_id.py (4142b), scripts/i18n_messages.json (38864b), scripts/i18n_skill_messages.json (10095b), scripts/i18n.py (36070b), scripts/kw_lexicon.json (32482b), scripts/kw_localize.py (35924b), scripts/office_to_md.py (18121b), scripts/orchestrate.py (33099b), scripts/r_libs.py (8104b), scripts/refine_answer.py (57500b), scripts/route_tool.py (36840b), scripts/route.py (14919b), scripts/run_refined.py (4416b), scripts/scope_guard.py (4483b), scripts/serve.py (5340b), scripts/sibling_registry.json (18258b), scripts/switch_lang.py (2155b), scripts/sync_i18n_from_ctbase.py (1562b), scripts/tool_mapping.json (17523b), skill-card.md (2184b), SKILL.md (16030b), _meta.json (129b)\n\nFile v1.3.0:SKILL.md\n\n---\r\nslug: ct-advisor\r\nname: ct-advisor\r\ndisplayName: Clinical Trial Chief Advisor / 临床试验总顾问\r\ncn_name: 临床试验总顾问\r\nversion: 1.3.0\r\ninvocable: true\r\nrequired_commands: [python]\r\nsummary: \"面向临床研发全生命周期的 ct 系列「总入口」，云端辅助的临床试验总顾问。所有问题（方法学/设计/合规/QC/现场执行/情报）统一提交云端 Coze 引擎分析处理。本地仅做确定性二值闸门（是否 vague）与附件解码，不保留知识库，不进行本地网络检索。外部参考：teal 临床数据交互探索框架。\"\r\ndescription: \"The single entry point for the ct-series across the full clinical-development lifecycle — a cloud-assisted clinical trial advisor. All questions (methodology / design / compliance / QC / site-execution / intelligence) are forwarded to the cloud Coze engine for analysis. The local side only performs a deterministic binary vague-gate (vague | forwarded) and attachment decoding; no knowledge base is retained locally, and no local network retrieval occurs. External reference: the teal clinical-data interactive exploration framework. / 面向临床研发全生命周期的 ct 系列「总入口」，云端辅助的临床试验总顾问。所有问题（方法学/设计/合规/QC/现场执行/情报）统一提交云端 Coze 引擎分析处理。本地仅做确定性二值闸门（是否 vague）与附件解码，不保留知识库，不进行本地网络检索。外部参考：teal 临床数据交互探索框架。\"\r\nlicense: MIT\r\ntriggers:\r\n - \"ct-advisor\"\r\n - \"clinical trial advisor\"\r\n - \"ct advisor\"\r\n - \"trial methodology\"\r\n - \"clinical trial methodology\"\r\n - \"clinical research advisor\"\r\n - \"trial design\"\r\n - \"GCP question\"\r\n - \"临床试验顾问\"\r\n - \"临床试验总顾问\"\r\ntrigger_scope: \"触发词仅限临床试验方法学/法规/设计/合规/QC/情报类问题；不主动匹配非临床类通用问答；不含文件系统写入与系统级 API 调用。\"\r\nmetadata:\r\n openclaw: { emoji: \"🛠️\", icon: \"assets/icon.svg\" }\r\n authors: [\"medstatstar\", \"phoe-zip\"]\r\n family: ct-series\r\n homepage: \"https://github.com/medstatstar/ct-advisor\"\r\npermissions:\r\n scope: \"user-space-only\"\r\n network: \"controlled-coze-opt-in\"\r\n network_note: \"All questions are forwarded to Coze (single call, internal `scripts/orchestrate.py`). Local side performs NO knowledge base lookup, NO local network retrieval, NO web search. Attachments under 5 MB are uploaded as original bytes to Coze `/upload_file` and shipped as the top-level `doc_context` field (Coze decodes natively); attachments over 5 MB are converted to Markdown locally via `scripts/office_to_md.py` (stdlib-only) and the resulting .md is uploaded through the SAME doc_context channel. The Coze-side knowledge base is the single source of truth.\"\r\n filesystem: \"Read-only to own files; no confidential data leaves locally — Coze payloads sanitized, query_origin is a stable per-machine sha256 hash (non-PII).\"\r\nadapted_from: \"https://github.com/A-xin946/clinical-trial-advisor\"\r\ndependencies:\r\n - {slug: ct-registry, tier: A}\r\n - {slug: ct-safety, tier: A}\r\n - {slug: ct-literature, tier: A}\r\n - {slug: ct-samplesize, tier: A}\r\ntier: A\r\n---\r\n\r\n# Clinical Trial Chief Advisor\r\n\r\n## Published Application\r\n\r\n| Item | Value |\r\n|---|---|\r\n| Share link | `https://ct-advisor.app.workbuddy.host/` |\r\n| appId | `wbapp_FBxILYuXi6yMolY8CsYzA7` |\r\n| Payload | `workbench/publish/` — in-skill, workspace-independent; deploy metadata in `workbench/app.config.json` (Python HTTP service) |\r\n\r\n> **Re-publish rule**: always overwrite with the existing `appId` — the link must stay `https://ct-advisor.app.workbuddy.host/`; never `createNewApp`. After deploy, assert the returned `shareLink` equals the expected URL (ct-base §13.5 dirty-binding red line). Last republished 2026-09-26.\r\n\r\n## Language\r\n\r\n- **English guide** → [README.md](https://github.com/medstatstar/ct-advisor/blob/main/README.md) · **中文指南** → [README_zh-CN.md](https://github.com/medstatstar/ct-advisor/blob/main/README_zh-CN.md)\r\n- **This SKILL.md body is English-only, agent-facing.** Bilingual walkthroughs live in the two READMEs; the answer language follows the user's question language.\r\n\r\n## 🔴 HIGHEST PRIORITY: entry.py is the ONLY permitted action\r\n\r\n> **The local LLM is FORBIDDEN from making any decisions in this skill. Its ONE AND ONLY allowed action is:**\r\n>\r\n> ```bash\r\n> python scripts/entry.py --q \"\" [--attach \"\"]\r\n> ```\r\n>\r\n> **and then pipe the stdout to the user verbatim.**\r\n\r\n**HARD GATE — the following are absolutely PROHIBITED for the local LLM:**\r\n- ❌ **NEVER** read, search, or reference any local knowledge base (the `knowledge/` directory has been removed)\r\n- ❌ **NEVER** perform any local network retrieval or web search (`references/search-sites.md` has been removed)\r\n- ❌ **NEVER** answer the question from the LLM's own knowledge — all domain expertise lives on the Coze side\r\n- ❌ **NEVER** bypass `entry.py` by calling `route.py`, `refine_answer.py`, `orchestrate.py`, or any other script directly\r\n- ❌ **NEVER** rewrite, rephrase, reorder, summarize, or \"polish\" the text between `<<>>` and `<<>>`\r\n- ❌ **NEVER** append a summary, lead-in, closing remark, or \"key takeaways\" before or after the delimiters\r\n- ❌ **NEVER** strip or alter the `checksum:` line that follows `<<>>`\r\n- ❌ **NEVER** translate or align language (the code already handles that)\r\n- ❌ **NEVER** inject process narration (\"Step 2\", \"Coze returned\", \"assembling payload\")\r\n- ❌ **NEVER** decide whether to forward to Coze — ALL questions are forwarded (entry.py handles routing internally)\r\n\r\n**Why this rule exists:** The local LLM's \"helpful\" instincts (answering from its own knowledge, pre-reading files, post-formatting answers) have repeatedly violated the pipeline contract, destroyed Coze-delivered content formatting, altered numeric precision, injected unsolicited content, and bypassed the cloud analysis entirely. This rule eliminates ALL local LLM decision space.\r\n\r\n## How to use this skill\r\n\r\n### With a question only:\r\n```bash\r\npython scripts/entry.py --q \"In phase III NSCLC patients, comparing pembrolizumab vs chemotherapy, how is the sample size for the primary endpoint OS estimated?\"\r\n```\r\n\r\n### With an attachment:\r\n```bash\r\npython scripts/entry.py --q \"Is this document related to medicine?\" --attach \"/path/to/file.docx\"\r\n```\r\n\r\n**That's it.** The stdout is the final answer — pipe it to the user verbatim.\r\n\r\n### What entry.py does internally (all code, zero LLM) — the canonical pipeline\r\n\r\n```\r\nSTEP 1 Attachment gate (if --attach) — BOTH paths ship a FILE via doc_context\r\n ├─ < 5 MB → doc_memory.build_file_payload(allow_upload=True): upload ORIGINAL file to Coze /upload_file, ship as `doc_context` (mode=file_id; base64-forward fallback on failure)\r\n └─ > 5 MB → convert locally (office_to_md.py for OOXML / direct read for txt-like), upload the resulting **.md** through the SAME doc_context channel + ℹ️ notice that cloud answers from the md version\r\nSTEP 2 Vague gate (deterministic regex, scripts/route.py — binary: vague | forwarded, the ONLY local gate): vague → clarify_loop.py (≤3 rounds) → questions to user, stop; forwarded → continue (Coze re-judges difficulty with its own LLM; timeout tier via route.timeout_tier)\r\nSTEP 3 Forward to Coze — orchestrate.run_orchestrate(payload): parallel Coze /run fire + local ct-skill prefetch → merge\r\nSTEP 4 Delegate stitch — if Coze returns <<>>, entry.py auto-runs refine_answer.py --card-inline (code, no LLM)\r\nSTEP 5 Output — stdout wrapped in <<>> + sha256 checksum\r\n```\r\n\r\n> **LLM-forbidden zone**: every STEP above is executed by code. The local LLM\r\n> never picks the channel, never judges difficulty, never decides forwarding.\r\n\r\n### Output format:\r\n```\r\n<<>>\r\n{answer text from Coze}\r\n<<>>\r\nchecksum: {sha256[:16]}\r\n```\r\n\r\n### 🔴 sha256 Anti-tamper Check (HARD GATE):\r\nAfter receiving the stdout from `entry.py`, the local LLM **MUST** verify the checksum before passing the answer to the user:\r\n\r\n```python\r\nimport hashlib, re\r\nstdout = \"...(entry.py output)...\"\r\nm = re.search(r'<<>>\\n(.*?)\\n<<>>\\nchecksum: (.+)', stdout, re.DOTALL)\r\nif m:\r\n answer, expected_checksum = m.group(1), m.group(2).strip()\r\n actual_checksum = hashlib.sha256(answer.encode(\"utf-8\")).hexdigest()[:16]\r\n if actual_checksum != expected_checksum:\r\n # TAMPER DETECTED — do NOT pass to user\r\n print(\"⚠️ answer integrity check failed, please retry.\")\r\n else:\r\n # OK — pass answer verbatim\r\n print(answer)\r\n```\r\n\r\n**If the checksum does not match, the local LLM MUST NOT deliver the answer to the user.** This prevents any silent tampering.\r\n\r\n> 🔴 **Single-run discipline (performance · as mandatory as the HARD GATE)**: `entry.py` is one complete Coze remote call and the main time cost of a single Q&A. **The local LLM may call `entry.py` only ONCE per question** and must capture its entire stdout into memory/a variable. The sha256 check MUST run against that SAME captured result — **re-calling `entry.py` purely to perform the check is strictly forbidden** (it sends an identical request to the Coze backend again, doubling the latency; in practice this once caused \"the same question sent 2–3 times, a single Q&A dragging to 4 minutes\"). If you need to persist output, write the stdout already captured from the first run rather than re-running.\r\n\r\n**Verification discipline (L3, 2026-09-25)**: The sha256 integrity check MUST be performed inline against the stdout captured in memory from the SAME `entry.py` call — i.e. immediately after capture, do `re.search` + `hashlib.sha256` comparison in memory. **Forbidden**: writing stdout to a temp file just for the check, extra tool round-trips, or post-hoc temp-file cleanup. One extra file write/read/delete round-trip only adds agent-side latency and contributes nothing to the answer itself.\r\n\r\n## Performance Optimization & Deployment Notes (L1/L2/L3, 2026-09-26)\r\n\r\nThis skill has implemented three performance optimizations; see `PERF_SOP.md` for details:\r\n- **L1 Resident orchestration service** (`scripts/serve.py` + `entry.py` client): heavy modules are warmed up once, so local overhead → 0.\r\n- **L2 Parallel warm-up** (`scripts/orchestrate.py`): eliminates stacked serial imports.\r\n- **L3 Inline verification discipline** (see \"Verification discipline\" above): sha256 must be done inline in memory; writing temp files is forbidden.\r\n\r\n**⚠️ Deployment restriction (important)**: the skill directory lives on a network share whose ACL is creator-owner — you can create new files, but **overwriting pre-installed existing files raises `PermissionError 13`**, and deletion is also blocked by a trash hook. Therefore, any change to `scripts/*.py` / `SKILL.md` should be written as a same-directory `.new` copy, then overwritten on the user's local machine with `move /Y` (command in `PERF_SOP.md` §4, or run `scripts/_perf_deploy.py`).\r\n\r\n**Version drift**: the resident service caches code; after updating skill files, the old service still runs old code until its 600s idle timeout. `entry.py` has a built-in `/version` probe that, before reusing an old service, compares the local `orchestrate.py` mtime — if the local copy is newer it auto-shuts-down the old service and launches the new version, with no manual restart needed.\r\n\r\n## Requirements\r\n\r\n| Item | Requirement |\r\n|---|---|\r\n| Runtime | `python3` stdlib only |\r\n| Sibling skills | **Tier A · listed on SkillHub** (non-confidential input, publicly released): `ct-registry` / `ct-safety` / `ct-literature` / `ct-samplesize` — auto-routed via Coze `need_tool` (entry.py handles card-inline execution). **Tier A · NOT yet listed**: `ct-pipeline` / `ct-synthdata` → `unpublished_a`, answer from Coze draft. **Tier B** (confidential input, **not publicly released**): `ct-protocol` / `ct-csr` / `ct-analysis` / `ct-sdtm` / `ct-eligibility` etc. — never installable. |\r\n| Refiner (Coze) | `scripts/entry.py` (internal orchestrator via `scripts/orchestrate.py`) POSTs payload to `ct-advisor.coze.site/run`. Credential embedded in `adapters/coze_token_embedded.py` (obfuscated public token — keep as-is). 90s timeout / 300s long timeout. |\r\n| External Refs | **teal** (insightsengineering) — clinical-data interactive exploration framework; **Docling** — structured PDF parsing. See \"External Tool References\". |\r\n\r\n## Attachment handling (docx / xlsx / pptx · doc / xls / ppt · pdf)\r\n\r\n**Single gate = 5 MB, decided FIRST inside `entry.py` (v1.1.0 workflow correction, 2026-09-25). BOTH paths deliver a FILE to Coze through the same `doc_context` channel.**\r\n\r\n| Size | Behavior | Channel |\r\n|---|---|---|\r\n| `< 5 MB` | **Upload the original file directly** — never converted locally | `doc_memory.build_file_payload(allow_upload=True)` → Coze `/upload_file` → `doc_context` (`mode=file_id`); on upload failure auto-degrades to the base64 forward channel (`mode=file`) |\r\n| `> 5 MB` | Convert to Markdown locally, then **upload the resulting `.md` as the attachment** — same `doc_context` channel — plus an ℹ️ notice that the cloud answers from the md version | `scripts/office_to_md.py` (stdlib-only; OOXML) or direct read (`.txt/.md/.csv/.tsv/.json`); unsupported formats get an explicit user prompt |\r\n\r\nCoze decodes the original file natively for **any** Office format (OLE2 `.doc/.xls/.ppt` included), so fidelity is higher than any local conversion — this is why the <5 MB path uploads instead of converting.\r\n\r\n**Governance pointer**: layered conversion strategy, user prompts and confidentiality boundary are consolidated in **ct-base §6.7**; the shared converter lives in `ct-base/scripts/office_to_md.py` (vendored copy).\r\n\r\n**Deliverable boundary — the revised document is never returned (v1.24).** This skill's deliverable is **text only**: it does not generate, export, or hand back a modified document file. When the user asks for the revised file back, state plainly on the **first line** that **this feature is not available — only written suggestions are provided**, then give the suggestions as text the user can copy.\r\n\r\n## Quality Gate & Stop Rules\r\n\r\n**Presentation rules (user-mandated, hard)** — deliver only the answer text between `<<>>` and `<<>>`. **Never emit any workflow / process narration to the user.**\r\n\r\n**🔔 Forward-mode user notice (the ONLY allowed process message)** — entry.py emits a brief notice to stderr before firing the Coze call. The local LLM should not add any additional process chatter.\r\n\r\n## Outbound Authorization Gate\r\n\r\nRuns automatically inside `entry.py` → `scripts/orchestrate.py` before each outbound HTTP call (agent never triggers it manually). Endpoint `https://ct-advisor.coze.site/run` is in `auto_approve_endpoints` by default, so it never prompts. If the user wants another endpoint whitelisted across sessions, the USER adds it explicitly to `config.json` — **the agent MUST NOT edit `config.json`**.\r\n\r\n## External Tool References (v1.3.0 · external open-source assets)\r\n\r\n- **teal** (insightsengineering, `install.packages('teal')`) — clinical-data interactive exploration framework for building Shiny review apps; reference model for the data-review integration mode.\r\n- **Docling** (`pip install docling`) — structured parsing of regulatory documents (protocol/IB/CSR PDFs → hierarchical Markdown/JSON); attachment-parsing enhancement layer.\r\n\r\n## Bug Report (§20.3 · ct-base)\r\n\r\nOn defect detection or explicit user request, `adapters/bug_report.py` offers a sanitized 11-key report to `https://ct-bugreport.coze.site/run`. Two-stage confirmation mandatory.\n\nFile v1.3.0:README.md\n\n# Clinical Trial Chief Advisor (ct-advisor)\r\n\r\n- **English guide** → [README.md](https://github.com/medstatstar/ct-advisor/blob/main/README.md) · **中文指南** → [README\\_zh-CN.md](https://github.com/medstatstar/ct-advisor/blob/main/README_zh-CN.md)\r\n\r\n
\r\n\"ct-advisor\r\n
\r\n\r\n> **Works without installation:** If you'd rather not install and just want to quickly use this skill's basic features, you can also visit the ct-series unified web portal **https://ct.medstatstar.com** directly.\r\n\r\n> **The single front door for the whole `ct-*` clinical-trial skill family — a methodology & regulatory-evidence advisor that also routes real-data / competitive-intel needs to the sibling data skills through a local, code-only orchestrator (`orchestrate.py`) and stitches their results back in code.**\r\n>\r\n> No commands or manual needed. Just describe your trial question **in plain language inside a chat** — the advisor passes every **non-vague** question to the local orchestrator (`orchestrate.py`), which calls the Coze cloud workflow for methodology / design / statistics / GCP / safety / regulatory / QC / tone answers, and when needed runs the right sibling skill (`ct-registry` / `ct-safety` / `ct-literature` / `ct-samplesize`) **locally** and stitches the result **in code**. It **re-implements no** retrieval or computation logic.\r\n\r\n---\r\n\r\n> **Scope reality check (read this first).** ct-advisor is a **cloud-assisted** advisor, not a pure-local tool. In operation it forwards your **question to the remote Coze engine**; runs sibling `ct-*` skills **locally on your machine** (these skills themselves may query public registries/APIs such as ClinicalTrials.gov, China CDE, FDA FAERS/openFDA, OpenAlex, PubChem); submits an **optional** bug report; keeps a language preference / context cache / memory notes on your device; and runs local connectivity diagnostics. All of this is spelled out honestly in [§5 Data & Privacy](#5-data--privacy).\r\n\r\n> **⚠️ Attachments are part of your question.** If you attach a document (≤5 MB, any Word/Excel/PPT/PDF/TXT), the **original file itself is uploaded to the remote Coze engine** (via the `doc_context` file-id channel) and parsed there — nothing stays local. For files >5 MB the skill converts them to Markdown locally and uploads the converted `.md` the same way. Anything inside an attached file — protocol drafts, sponsor names, subject-level details — should be treated as **leaving your machine**. Remove sensitive content before attaching.\r\n\r\n## Who This Is For\r\n\r\nThe `ct-*` clinical-trial skill family is built to address needs across the entire clinical-trial lifecycle, mainly for three groups:\r\n\r\n- **Clinical-trial practitioners at pharmaceutical companies** — sponsors, CROs, and medical / statistical / regulatory roles;\r\n- **Clinicians and nurses who design, manage clinical-trial projects, or take part in hands-on trial conduct in medical institutions**;\r\n- **Medical students who want to learn clinical-trial methodology in a structured way**.\r\n\r\n## 1. How to Use It in a Chat (the Core)\r\n\r\nct-advisor is a **conversational skill**: you simply tell the assistant what you're working on — no commands, no parameter names to remember. Once installed as a WorkBuddy skill, you invoke it in a chat via the Skill tool; there is no extra setup, but it activates only when you call it — not automatically in the background.\r\n\r\nBelow are 8 examples showing **what you actually see in the chat**: each has a **\"You say\"** and the **reply you see** (the user-facing answer), with a one-line note on the machinery underneath. Multi-round cases (examples 4 / 5 / 7) ask you for the missing parameter first, then give the final answer.\r\n\r\n### Example 1 · Subject compensation after early withdrawal (GCP, answered directly)\r\n\r\n**You say:**\r\n> The protocol says subjects who complete all visits get a CNY 5,000 travel allowance. One subject withdrew early because of an SAE — must the investigator pay the full amount? What does GCP require?\r\n\r\n**The reply you see:**\r\n> Where a subject withdraws early because of an SAE (serious adverse event), the investigator **should pay the full CNY 5,000 travel allowance** — it must not be withheld or prorated. China's current GCP requires compensation arrangements to be fair and reasonable and bars deduction clauses that undermine subjects' rights; a withdrawal the subject did not choose must not cost them the compensation they are due.\r\n>\r\n> 1. **The scope is clear**: this travel allowance reimburses costs the subject actually incurs travelling for the trial; it is not an incentive bonus reserved for those who complete every visit. Protocol wording such as \"full allowance only on completion of all visits\" governs voluntary, unexplained withdrawal. An SAE is a trial-related, non-voluntary exit; deducting the allowance directly harms the subject's rights and would not meet ethics-review expectations.\r\n> 2. **Compliance steps**: after paying in full, record the payment in the SAE follow-up file; if the ethics committee asks how subject rights were handled in the SAE, submit an explanation as required.\r\n>\r\n> Basis: *Good Clinical Practice for Drug Clinical Trials* (2020 edition).\r\n\r\n> Under the hood: a single cloud call — no menu.\r\n\r\n### Example 2 · Expectedness: do the IB and the label need updating? (pharmacovigilance, answered directly)\r\n\r\n**You say:**\r\n> An adverse reaction is listed as \"uncommon\" in the Investigator's Brochure (IB), but the observed rate in the trial has reached 15%. How should PV assess whether the IB and the label need updating?\r\n\r\n**The reply you see:**\r\n> This warrants an assessment straight away; by default the incidence section of the IB needs updating, and if the causal link to the drug is clear and the risk is serious, the risk-information section and the label should be updated too.\r\n>\r\n> **Calibrate the data first**: agree one definition and coding standard for the reaction, and confirm that the 15% denominator is the drug-exposed population and that the event criteria match those behind the IB's original \"uncommon\" entry — ruling out miscoding or a mixed event pool inflating the rate. \"Uncommon\" normally means 0.1%–1%; 15% is far above that expectation.\r\n> **Assess the causal link**: weigh temporal sequence, dose–response, dechallenge/rechallenge and biological plausibility to judge causality for this drug, and check whether severity has escalated (e.g. severe or fatal cases).\r\n> **Land the update**: if only the rate rose, with no change in causality or severity, update the incidence section of the IB alone; if causality is clear and the risk is materially higher, also update the IB's risk information and the product label (or the pre-approval risk-management plan), and submit the revised IB to the regulator, the ethics committees and all investigator sites as required.\r\n>\r\n> Basis: ICH E2F (Development Safety Update Report); CDE guidance on Safety Reference Information (RSI) in the Investigator's Brochure.\r\n\r\n> Under the hood: a single cloud call — no menu.\r\n\r\n### Example 3 · A narrow data ask (one data skill)\r\n\r\n**You say:**\r\n> Pull the registered trials for semaglutide in type-2 diabetes, 2021–2026.\r\n\r\n**The reply you see:**\r\n> For semaglutide in type-2 diabetes, **50 registered trials** were found:\r\n>\r\n> - **Phase**: Phase 3 — 14, Phase 2 — 10, Phase 1 — 5, Phase 4 — 4, and 14 not stated.\r\n> - **Region**: United States 21, Canada 7, Denmark 6, Germany 6, China 5 (the rest in other countries).\r\n> - **Top sponsors**: Novo Nordisk 20, Eli Lilly 2, Brigham and Women's Hospital 2.\r\n> - **Details**: each trial's name, phase, region and sponsor were compiled into a spreadsheet you can open or download.\r\n>\r\n> 💡 *The above is a readable summary of this skill's result; to verify it or get the full detailed output, run the `ct-registry` skill directly.*\r\n\r\n> 📌 **Under the hood:** code calls the trial-registry skill (ct-registry) and appends the measured results at the end of the answer.\r\n\r\n### Example 4 · A broad competitive-intel ask (multi-source, one skill per round ⭐)\r\n\r\n**You say:**\r\n> Give me the full competitive-intel picture for GLP-1 RA in obesity — trials, safety signals, and literature.\r\n\r\n**The reply you see (round 1 · follow-up):**\r\n> Sure — I'll put together the competitive landscape for GLP-1 RAs in obesity. To retrieve accurately, please confirm the **specific indication or target** (e.g. obesity / overweight, or a particular target).\r\n\r\n**The reply you see (after you supply it · final):**\r\n> **GLP-1 RA in obesity — competitive-intel summary**\r\n>\r\n> - **Registered trials**: the trials in this indication are compiled — count, phase mix and top sponsors.\r\n> - **Published evidence**: relevant RCTs and systematic reviews retrieved, with verifiable DOIs/PMIDs.\r\n> - **Safety signals**: FAERS signals with quantitative measures (PRR / ROR / IC).\r\n> - **Takeaway**: competition concentrates in a few leading players, with a phase-3-heavy registration and evidence footprint.\r\n>\r\n> Each source is labelled in the \"supplementary data\" section at the end of the answer, noting which skill produced it.\r\n>\r\n> 💡 *The above is a readable summary of the multi-skill result; to verify it or get the full detail, run `ct-registry` / `ct-safety` / `ct-literature` directly.*\r\n\r\n> 📌 **Under the hood:** one card runs one skill; \"trials + safety + literature\" takes **several rounds** of supply-param → run → stitch — not one parallel pass.\r\n\r\n### Example 5 · A multi-part design task (follow-up first, then compute)\r\n\r\n**You say:**\r\n> I'm planning a Phase II oncology trial and also need the sample size — help me decide the design.\r\n\r\n**The reply you see (round 1 · follow-up):**\r\n> Sure — I'll help you settle the Phase II oncology design and compute the sample size. Please confirm two things first:\r\n> - **Test type**: two-proportion / two-mean / survival?\r\n> - **Effect-size assumptions**: e.g. the two event rates p1 and p2, or a mean difference / SD / margin (pick one).\r\n>\r\n> (Defaults: two-sided α=0.05, power 80% — tell me if you'd like them changed.)\r\n\r\n**The reply you see (after you supply it · final):**\r\n> With a **two-proportion test** (p1=0.30, p2=0.45), two-sided α=0.05 and 80% power: **162 patients per group, 324 in total.**\r\n> The design narrative (endpoints, enrolment, statistical methods) comes from the cloud side.\r\n>\r\n> 💡 *The above is a readable summary of this skill's result; to verify it or get the full detailed output, run the `ct-samplesize` skill directly.*\r\n\r\n> 📌 **Under the hood:** the sample size is computed by the local sample-size skill (ct-samplesize) and appended; missing parameters trigger the follow-up first.\r\n\r\n### Example 6 · Not sure what you need (vague → local clarify)\r\n\r\n**You say:**\r\n> I'm not sure what I actually need — I have a half-written protocol and some questions.\r\n\r\n**The reply you see:**\r\n> No problem — let's untangle it first. Please add two things:\r\n> 1. **Target population / subjects**: e.g. disease, stage, line of therapy, age band — this affects how far the conclusions apply.\r\n> 2. **Endpoint / outcome of interest**: e.g. OS, PFS, ORR, or adverse-event rates.\r\n>\r\n> Once that's clear I'll route you to the right workflow (methodology design / data retrieval & intel / protocol explanation & review).\r\n\r\n> 📌 **Under the hood:** a vague question is handled by the **local** clarify flow first (no network, no data skill), then re-routed.\r\n\r\n### Example 7 · A published-safety evidence check (ct-literature)\r\n\r\n**You say:**\r\n> One of our PD-1 products has case reports of interstitial lung disease; QA suspects a new safety signal. Search the **published literature** (case reports, pharmacovigilance studies, reviews) for how much support this signal has, and give me a citable evidence summary for the signal-evaluation meeting.\r\n\r\n**The reply you see (round 1 · follow-up):**\r\n> Sure — I'll check how well \"PD-1–related interstitial lung disease\" is supported in the published literature and prepare a citable evidence summary. Please give me the **search topic / target** (e.g. \"PD-1\", or a specific drug name).\r\n> Tip: **English** keywords retrieve better (e.g. \"interstitial lung disease\" / \"pneumonitis\").\r\n\r\n**The reply you see (after you supply it · final):**\r\n> **Published-evidence summary · PD-1–related interstitial lung disease**\r\n>\r\n> - **Retrieval**: **20** relevant works found (OpenAlex 10 + Europe PMC 10).\r\n> - **Citation check**: **19 of 20** DOIs/PMIDs verified automatically; 1 could not be verified (source-site anti-bot block).\r\n> - **Citable list**: titles, journals, years and DOIs/PMIDs compiled into a spreadsheet (Excel / HTML) you can check item by item.\r\n> - **Notes**: without a Semantic Scholar key that source is skipped; Chinese search terms trigger a \"use English terms for better recall\" notice.\r\n>\r\n> 💡 *The above is a readable summary of this skill's result; to verify it or get the full detailed output, run the `ct-literature` skill directly.*\r\n\r\n> 📌 **Under the hood:** code calls the literature skill (ct-literature) for multi-source retrieval + citation verification; the evidence list lands in artifact files, and the answer body is its readable form.\r\n\r\n### Example 8 · Protocol background evidence + sample-size handoff (ct-literature + ct-samplesize)\r\n\r\n**You say:**\r\n> We're drafting a phase-3 protocol in this indication. Give me the published RCT + systematic-review evidence from the last 5 years for the introduction, then compute the sample size for a superiority design using the key assumptions I'll provide.\r\n\r\n**The reply you see (round 1 · follow-up):**\r\n> Sure — two steps: first retrieve the last 5 years' published RCTs and systematic reviews as the introduction evidence base, then compute the superiority-design sample size from your assumptions. Please confirm:\r\n> - **Test type**?\r\n> - **Effect-size parameters**: p1 / p2, or effect / sd / margin (pick one)?\r\n> - **Literature search terms** (optional): if omitted I'll use indication defaults.\r\n\r\n**The reply you see (after you supply it · final):**\r\n> - **① Introduction evidence base**: last-5-year RCTs + systematic reviews retrieved for this indication, with journals, years and DOIs/PMIDs compiled into a citable list (attached).\r\n> - **② Superiority-design sample size**: computed from your test type and effect-size assumptions — **patients per group and total** (the numbers vary with the assumptions).\r\n> - Both sources are labelled in the \"supplementary data\" section at the end of the answer.\r\n>\r\n> 💡 *The above is a readable summary of the multi-skill result; to verify it or get the full detail, run `ct-literature` / `ct-samplesize` directly.*\r\n\r\n> 📌 **Under the hood:** cross-skill collaboration is a **serial, multi-step** handoff (a literature round, then a sample-size round) — not one parallel pass.\r\n\r\n## 2. What Can It Do — Scenarios\r\n\r\nThe advisor covers the entire clinical-trial lifecycle through ten in-house workflows (A–J) plus routing to four sibling skills. Each row gives the typical **situation** and a line you can **copy verbatim** under \"Try saying\".\r\n\r\n### ① Methodology & regulatory advice (answered in-house, A–J)\r\n| Situation | Try saying in chat |\r\n| :-------------------------------------------- | :---------------------------------------------------------------------------------------------------------------- |\r\n| Define a term / find the regulatory basis | \"What does ICH E6(R3) say about risk-proportionate monitoring?\" |\r\n| Trial design review | \"Review my Phase III oncology design for feasibility\" |\r\n| Statistics / estimand / sample size framework | \"Help me set the primary estimand for a superiority trial\" |\r\n| GCP / deviation / audit readiness | \"What makes a site audit-ready under GCP?\" |\r\n| Safety & operations (SUSAR / DSUR / signal) | \"How do I handle a SUSAR in a multinational trial?\" |\r\n| Documents & QC (CSR / protocol / SAP) | \"Redline my CSR discussion section\" (basic review / rewrite; for deep multi-role review use `@skill:ct-protocol`) |\r\n| Reply tone / rewrite | \"Rewrite this patient letter in a warmer tone\" (one-off request; cross-session tone memory is not yet enabled) |\r\n\r\n### ② Real data & competitive intel (routed to sibling skills)\r\n> **The bar was tightened (2026-09-10):** a sibling skill is auto-invoked only for a **uniquely-directed** ask — a named data source (NCT / ClinicalTrials.gov / FAERS / PubMed), a named statistic or high-specificity method (PRR / ROR / EBGM / dechallenge-rechallenge / a specific irAE / meta-analysis), or an explicit \"retrieval verb + clear object\" phrasing (the table below shows these). **Generic words** (signal / literature / trial / safety / design) no longer trigger on their own: the advisor **answers from its own capability first**, then appends an install / invoke **suggestion at the end**.\r\n> | Situation | Try saying in chat |\r\n> |:---|:---|\r\n> | Trial-registry landscape | \"Pull registered trials for semaglutide in T2D, 2021–2026\" |\r\n> | Safety signals (FAERS) | \"Any FAERS disproportionality signals for drug X?\" |\r\n> | Published literature | \"Find systematic reviews on GLP-1 RA in obesity\" |\r\n> | **Full competitive intel (multi-source, round by round ⭐)** | \"Full competitive-intel picture for GLP-1 RA in obesity\" |\r\n\r\n### ③ Compute handoff (to ct-samplesize)\r\n| Situation | Try saying in chat |\r\n| :--------------- | :----------------------------------------------------------- |\r\n| Actual n / power | \"Sample size: two means, d=0.5, power 80%, α=0.05 two-sided\" |\r\n\r\n### ④ Clarify mode (Local Clarify Loop, no sibling skill, no network)\r\n| Situation | Try saying in chat |\r\n| :--------------------- | :------------------------------------------------- |\r\n| Not sure what you need | \"I'm not sure what I need — help me figure it out\" |\r\n\r\n> The underlying sibling skills are described in their own READMEs; ordinary users only need to say what they want in plain language — the advisor routes and stitches. **Whenever the advisor calls a sibling skill, the answer ends with a 💡 line suggesting you run that skill directly if you want to verify it or get the full detailed output.**\r\n\r\n---\r\n\r\n## 3. First-Time FAQ\r\n\r\n**Q: I only gave a partial description — will it still help?** A: Yes. Every question is forwarded to the Coze cloud endpoint for analysis — there is no local knowledge pack. If Coze is unreachable, the answer says \"please retry\" rather than falling back to local materials. Data asks are routed to the relevant sibling skill by default; if you want to limit the scope, just say so in your question.\r\n\r\n**Q: How are data sources labeled in the answer?** A: Measured behaviour is a **section label**: code appends the sibling skill's measured output under `## 补充信息（来源：ct-xxx）` (**measured: no date**; the English form is `## Supplementary data (Source: ct-xxx)`), and the full list / evidence is exported to `./out/` (`report.xlsx`, `lit_report.xlsx|html`, `evidence_log.json|md`). That is how you trace each number back to the sibling skill that produced it; the answer also ends with a 💡 suggestion to run that sibling skill directly for the fuller original output.\r\n\r\n**Q: It says a sibling skill isn't installed — do I have to install it?** A: **No — the decision is yours, and nothing is ever installed without your say-so.** Sibling skills come in two tiers, and the tier is separate from whether a skill is published. **Tier A** (`ct-registry` / `ct-safety` / `ct-literature` / `ct-samplesize` etc. — non-confidential input) that is **listed on SkillHub**: if missing locally, the advisor explains what it does and **suggests installing it** — it hands you the install command (`adapters/install_sibling.py --dir `, which verifies the SkillHub listing before downloading) but **does not install anything by itself**, because installing writes a package into your local skills directory and **may trigger a security prompt**. You choose: run the command yourself, or **explicitly authorise** the advisor to do it — then it installs, calls the skill and returns live results. **Decline** → it answers from its own capability (cloud answer) and clearly labels the reply **\"data not retrieved\"**. If a Tier-A skill is **not yet listed** (e.g. `ct-pipeline`), the advisor says it has not been publicly released and **cannot be installed right now** — it will not hand you an address that installs an empty package — then answers from its own capability plus the installed siblings, labelled \"data not retrieved\". **Tier B** (e.g. `ct-protocol` / `ct-csr` / `ct-analysis` / `ct-sdtm` — confidential protocols / subject data / CRFs): these are **not publicly released and cannot be installed**, so the advisor states plainly that a Tier-B skill is needed but is not publicly available, then completes the analysis from its own capability and notes that the in-depth analysis was not actually executed. Nothing is ever installed without your authorisation (by default installation is only *suggested*), and unavailable data is never fabricated.\r\n\r\n**It calls the sibling skills for real data by default.** `data_intel` asks are dispatched to the relevant sibling skill (ct-registry / ct-safety / ct-literature / ct-samplesize) by default to complete the analysis and return live results — no need to say \"please fetch the data now\". If you only want the plan and not the data yet, say \"just show the plan\".\r\n\r\n**Q: On a Chinese system, is the output in Chinese?** A: Yes. Output language follows your OS setting by default (Chinese on a Chinese-OS, English otherwise), and you can force-switch anytime with one sentence (e.g. \"switch to English\").\r\n\r\n**Q: How is the full competitive-intel brief generated now?** A: Measured behaviour is **round by round**: the first run usually returns a delegate block (`need_tool` + a `need_tools` candidate list + `missing_params`), the advisor **asks you for the missing parameter** (measured: `cond`), and after you supply it **one skill runs per round**, its output stitched into the answer — covering three sources takes several rounds. `need_tools` is only Coze's candidate list; it is **not** auto-iterated, and no single \"strategic brief\" document is produced automatically. This replaces the separate `ct-pipeline` orchestrator.\r\n\r\n**Q: Does pure methodology need the network?** A: Yes — every **non-vague** question is sent to the Coze endpoint (`https://ct-advisor.coze.site/run`) for analysis in a **single call**; a `vague` question is clarified locally via the Local Clarify Loop first, then forwarded. If Coze is unreachable, the answer says \"please retry\" — there is no local knowledge pack fallback.\r\n\r\n**Runtime prerequisite (measured):** calling Coze needs Python `requests`. It is **not** auto-installed — when missing the skill prints `python -m pip install \"requests==2.32.3\"` and exits (no silent install). Measured: run it with an interpreter that lacks the library and `orchestrate.py` returns the `⚠️ Coze 返回为空` fallback wrapper, while `refine_answer.py --forward/--ship` exits 1 with `精校依赖缺失`.\r\n\r\n**Q: What if I found an error in the result — how do I report it?**\r\nA: This skill follows the ct-base §20.3 bug-report workflow. If you suspect the result is wrong (or the engine errored), just say **\"report a bug\" / \"上报问题\" / \"提交错误报告\"**. The skill also **proactively asks** whether to report when it detects a likely defect (e.g. the engine errors or retries still fail) — at most **once per session**, and you can always decline. Either way, the assistant will:\r\n1. **Propose a sanitized report** (11-field whitelist: skill / skill_version / test / error_type / error_code / engine_status / description / locale / query_origin / session_hash / attempts — **no raw input values or personal data**, except the `description` field where you decide what to disclose, e.g. the algorithm/function used and the error message);\r\n2. **Show the full report text for your review** — you can add a problem description or correct anything before confirming;\r\n3. **Send after your explicit confirmation** — to the unified endpoint `https://ct-bugreport.coze.site/run` (if this session called coze) or saved locally + emailed to the author (if purely local, data never leaves your machine);\r\n4. **Receive an acknowledgment** — including whether a previously submitted report from your source has already been fixed (with the fix note) or is still pending.\r\n\r\nYou stay in full control: the report is shown to you **before** anything is sent, and nothing is transmitted without your explicit \"send\" confirmation.\r\n\r\n**Q: What if my data must stay confidential?** A: The advisor only sends your **question text** to the Coze endpoint (`https://ct-advisor.coze.site/run`) — never your raw trial / patient / sponsor data. Outbound payloads pass through `sanitize()` first (strips IDs, phone numbers, emails, and a small set of sensitive keywords; `query_origin` is a non-PII `sha256` machine id, `locale` is your OS language). Sibling data skills (ct-registry / ct-safety / ct-literature / ct-samplesize) run **locally** and only their results cross back; confidential data never leaves your machine. If you have strict confidentiality needs, simply keep real patient / sponsor data out of your question — the advisory answers are framework-level and don't require exposing it.\r\n\r\n**Q: Is there a depth limit on protocol review?** A: Yes. The Coze side only does a **basic** protocol review (point-by-point + severity grading + revision suggestions). For a **deep multi-role review** (PI / site / regulator perspectives, revision-risk scoring, a structured review.json, run locally offline), explicitly call `@skill:ct-protocol`; this advisor does not impersonate that capability.\r\n\r\n**Q: Will formal deliverables (protocol / review / computation) be illustrated?** A: **No.** Formal documents such as the protocol body, protocol-review comments, and sample-size computation sheets stay as plain text. For data / explanation / decision / flow / comparison results that warrant visualization, an **independent appendix** is offered only after your confirmation and is never embedded in the body (see the Graphical-rendering note below in §4).\r\n\r\n**Q: Does meta-analysis (forest plot / R recompute) run automatically?** A: **No, not automatically.** Meta-analysis requires you to explicitly call `@skill:meta-analysis` (R recompute / forest plots are done by that skill); this advisor only refers you to it.\r\n\r\n**Q: Does a rewrite remember my tone preference?** A: **No, not across sessions.** Rewrites are one-off, stateless requests; the personalized tone / memory function (tone_profile + memory_context) is currently DEFERRED (the Coze v1.5 field is not implemented), so every rewrite ignores history.\r\n\r\n---\r\n\r\n## 4. Execution Model & Safe Preview\r\n\r\n### Safe Preview (auto-invoke only for a uniquely-directed ask; otherwise answer first, suggest last)\r\n- **Auto-invoke only for a uniquely-directed ask:** a sibling skill is dispatched directly (ct-registry / ct-safety / ct-literature / ct-samplesize) only for a **strong trigger** — a named data source (NCT / FAERS / PubMed…), a named statistic / high-specificity method (PRR / ROR / EBGM / meta-analysis…), or an explicit \"retrieval verb + clear object\" phrasing — no need to say \"please fetch the data now\". Measured: **one card runs one skill**, and if a routing parameter is missing the advisor asks for it first.\r\n- **Generic words and consultation questions → answer first, suggest last:** for a bare generic word (signal / literature / trial / safety / design) or a \"what is / how do I / give me a template\" methodology, definition or document question, the advisor **answers fully from its own capability** (cloud answer + local knowledge pack) first; only when the question **does name** a data source / statistic (FAERS, PRR, PubMed…) does it append an install / invoke **suggestion at the end** — a purely generic or definition question no longer trails any suggestion, and it never interrupts the answer or pops a parameter follow-up because of a keyword false positive.\r\n- **Plan only:** if you only want the plan and not the data yet, say \"just show the plan\".\r\n- **Traceable, not fabricated:** Every factual / normative claim carries a source citation (code-appended measured results read `## 补充信息（来源：ct-xxx）`) or an `⚠️ needs official verification` marker; it never fills factual gaps with fluent prose.\r\n- Outputs are for reference only; validate against official sources before regulatory submissions.\r\n\r\n### Graphical-rendering note\r\n- **Formal deliverables stay plain text:** the protocol body, protocol-review comments, regulatory-communication files, and sample-size computation sheets — the \"finished products you hand off\" — default to **no graphics**, preserving formality and traceability.\r\n- **Data / explanation may be illustrated:** results involving multi-branch decisions, sequential flows, hierarchy, design comparison, or severity grading may use decision trees / flowcharts / comparison matrices / severity color blocks to aid understanding.\r\n- **Independent appendix, only with your OK:** any visualization is delivered as an **independent appendix** and never embedded in the formal body; especially for formal documents, if you want a visual aid, confirm first and I'll generate an appendix that does not alter the original text.\r\n- **Pipeline safety:** graphics appear only *outside* the answer `<<>>` delimiters and never rewrite the answer body.\r\n\r\n### Latency note\r\nEvery **non-vague** question is handled by the local orchestrator (`scripts/orchestrate.py`), which forwards to the Coze endpoint in a **single call** (`refiner.timeout = 90` s in `config.json`; **measured 3-72 s per round**, mostly 30-70 s; data-intel questions also run the needed sibling skill locally). **A timeout is not a hard error**: the answer falls back to the local draft (not cloud-polished) with `[coze] FALLBACK_TO_LOCAL_DRAFT` on stderr. A `vague` question is clarified locally first (a few seconds via the Local Clarify Loop), then re-routed. Because the orchestrator, prefetch, merge, and stitching are all **code** (not the LLM), dependence on the local model's performance is low — but reasoning models (e.g. Hunyuan-3, DeepSeek-R1) have been observed to over-think locally. **If a single reply routinely takes longer than 3 minutes, switch to a simpler / flash model to speed things up.**\r\n\r\n---\r\n\r\n## 5. Data & Privacy\r\n\r\n**This skill is cloud-assisted, not a pure-local tool.** To give current, source-traced answers it forwards your question to a remote engine and may run sibling skills on your machine. Below is exactly what leaves your device, what stays local, and what sensitive actions it can take — stated up front, not buried.\r\n\r\n### What leaves your device (off-device)\r\n- **Analysis request** — for a non-vague question, your **question text** (passed through `sanitize()` first, which strips IDs, phone numbers, emails, and a few sensitive keywords) is sent to `https://ct-advisor.coze.site/run`. **Raw trial / patient / sponsor data is never sent.** When the question needs registry / safety / literature / sample-size data, Coze returns only a `need_tool` instruction; the actual retrieval and computation run **locally** on your machine — but note those local sibling skills (`ct-registry` / `ct-safety` / `ct-literature` / `ct-samplesize`) may themselves query **public registries/APIs** (ClinicalTrials.gov, China CDE, FDA FAERS/openFDA, OpenAlex, PubChem…). That is separate outbound to those public sources, not to Coze.\r\n- **Error report** — sent **only after your explicit confirmation**, and only as an 11-key whitelist envelope (no raw input, no PII), to `https://ct-bugreport.coze.site/run`. You can always decline; it is offered at most once per session.\r\n\r\nEach request also carries two anonymous metadata fields: `query_origin` (a SHA-256 hash of your hostname, for rate-limiting only) and `locale` (your OS language, for answer-language matching). Neither contains PII.\r\n\r\n### What stays on your device but is still sensitive (on-device actions)\r\nTo be transparent about the full behavior the skill can perform:\r\n- **Embedded (public) token** — the skill ships with an obfuscated Coze token used to authenticate the public endpoint. It is a **shared, openly-disclosed token by design** (not a personal secret); it is decoded in memory only for outbound auth and is disclosed openly here rather than hidden.\r\n- **Local persistence** — it may write your **language preference** to `config.json`, keep a short-lived **context cache** under `.runtime/` (gitignored), and **promote recurring interaction patterns into long-term memory files** (per the SOUL.md self-improvement rules). None of these contain your question text or trial data.\r\n- **Local connectivity diagnostics** — if a connection to Coze fails, with your permission it can run `scripts/check_coze.py` to probe local proxy / network / token configuration and suggest a fix.\r\n- **Subprocess orchestration** — the local code orchestrator (`orchestrate.py` / `refine_answer.py`) runs sibling `ct-*` skills as **subprocesses on your machine** and stitches their results in code.\r\n- **Shipped but never egressing (clarification)** — to stay self-contained, the package carries shared ct-base modules. One of them, `kw_localize.py`, has an online-translation fallback (MyMemory / Google gtx, on by default, disable with `CT_TRANSLATE_ONLINE=0`). **ct-advisor never calls this module** (it has no keyword-localization need), so **no translation egress is ever produced**; the base version is vendored only to satisfy the shared-asset consistency gate.\r\n\r\n> **In one sentence:** your question text goes to the Coze endpoint for cloud analysis, sibling skills may query public registries, an optional bug-report goes out only after your OK, and the skill may keep a language preference / context cache / memory notes locally — **raw trial / patient / sponsor data never leaves your machine.**\r\n\r\n---\r\n\r\n## Why You Can Trust the Output — Anti-Hallucination\r\n\r\nct-advisor is the entry point that routes to sibling skills and forwards questions to the Coze refiner; it does not invent facts. Four guardrails apply:\r\n\r\n1. **Every factual claim is source-traceable.** Data-grounded claims from sibling skills are appended by code as `## 补充信息（来源：ct-xxx）` (measured: the label carries no date; artifacts land in `./out/`); methodology / regulatory answers cite the authority (ICH / NMPA / FDA / EMA guidance) and link to it where available.\r\n2. **Identifier consistency check.** When a cited identifier (trial registration number, DOI / PMID) is resolved to a live record, the resolved title / author / year are compared against the original assertion; a mismatch is flagged `mismatch` and never treated as verified.\r\n3. **Unverifiable ⇒ `⚠️ needs official verification`.** Anything that cannot be traced to a public source is marked for official verification and never stated as a confirmed conclusion.\r\n4. **No fabrication.** Trial registration numbers, approval dates, subject counts, and company M\\&A / pipeline moves are never invented; if a public source does not disclose them, the output says \"not disclosed in public sources\".\r\n\r\n---\r\n\r\n## 6. Advanced Reference (moved to a separate file)\r\n\r\nCLI helpers, runtime requirements, the architecture tree, and scanner false-positive notes have been moved to **[references/ADVANCED.md](references/ADVANCED.md)**. Ordinary users don't need them; Sections 1–5 cover daily use. The agent-facing spec and version history remain in [`SKILL.md`](SKILL.md) and [`CHANGELOG.md`](CHANGELOG.md).\r\n\r\n---\r\n\r\n**Version**: v1.3.0 | **License**: MIT | **Authors**: medstatstar, phoe-zip\r\n\r\nFor feature requests, bug reports, or other feedback, please contact the author directly at (Wintone Zhang).\r\n\r\n---\r\n\r\n## Confidentiality Notice\r\n\r\n> The CT series consists of 20+ specialized domain skills, organized into **two tiers — A, B** — by \"whether the input contains confidential information\" (network / egress / publish are independent orthogonal attributes; see ct-base §11), providing full coverage of the entire new-drug clinical trial (Clinical Trial) lifecycle.\r\n>\r\n> - **Tier A (non-confidential input)**: runs on ordinary data and involves no confidential information; split further by the `network` sub-attribute into three kinds — ① **fully local** (`network=off`, zero egress); ② **public-source retrieval** (`network=public-retrieval`, e.g. ct-registry / ct-safety / ct-literature — only public query terms leave the machine); ③ **controlled Coze-only egress** (`network=controlled-coze-opt-in`, e.g. **ct-advisor**: a single Coze endpoint only, explicit user opt-in, payload passed through `sanitize()` first, paired with `egress=cloud`). ⚠️ Note that ③ is **not** the same as \"runs fully locally\" — its Q\\&A is forwarded to the cloud engine by default, falling back to a local fallback answer (clearly marked as such) only when the cloud is unreachable. All Tier A skills are published openly on GitHub.\r\n> - **Tier B (confidential input)**: accept strictly confidential clinical-trial data / protocols / CRFs from pharma sponsors (e.g., ct-analysis, ct-sdtm, ct-protocol, ct-eligibility); Tier B is processed locally and never leaves the boundary (egress=none), or additionally requires policy approval (egress=approval-req, e.g. ct-eligibility). Tier B packages contain zero confidential data but are NOT publicly published (stays fully local) — confidential input never ships with the package or leaves the machine. For custom / on-prem deployment, contact the author.\r\n>\r\n> 📧 Contact: (Wintone Zhang / 张文彤)\r\n\r\n> 🌐 Other languages: [中文 README](README_zh-CN.md)\n\nFile v1.3.0:_meta.json\n\n{\n \"ownerId\": \"kn7amqq1jv28skb63wavr6shah89jsm5\",\n \"slug\": \"ct-advisor\",\n \"version\": \"1.3.0\",\n \"publishedAt\": 1791546960277\n}\n\nFile v1.3.0:references/drug_name_map.json\n\n{\r\n \"_meta\": {\r\n \"description\": \"中文药物名 → 标准英文 INN/通用名 映射表（用于 openFDA FAERS 检索预处理）\",\r\n \"version\": \"1.1\",\r\n \"updated\": \"2026-09-06\",\r\n \"note\": \"一个中文名可对应多个英文名（如复方制剂、不同盐基）；检索时多候选列出让用户确认。仅覆盖常见药，不在表中时提示用户手动输入英文名。\"\r\n },\r\n \"阿司匹林\": [\r\n \"aspirin\"\r\n ],\r\n \"布洛芬\": [\r\n \"ibuprofen\"\r\n ],\r\n \"对乙酰氨基酚\": [\r\n \"acetaminophen\",\r\n \"paracetamol\"\r\n ],\r\n \"阿莫西林\": [\r\n \"amoxicillin\"\r\n ],\r\n \"头孢氨苄\": [\r\n \"cefalexin\",\r\n \"cephalexin\"\r\n ],\r\n \"头孢呋辛\": [\r\n \"cefuroxime\"\r\n ],\r\n \"头孢曲松\": [\r\n \"ceftriaxone\"\r\n ],\r\n \"阿奇霉素\": [\r\n \"azithromycin\"\r\n ],\r\n \"克拉霉素\": [\r\n \"clarithromycin\"\r\n ],\r\n \"左氧氟沙星\": [\r\n \"levofloxacin\"\r\n ],\r\n \"莫西沙星\": [\r\n \"moxifloxacin\"\r\n ],\r\n \"甲硝唑\": [\r\n \"metronidazole\"\r\n ],\r\n \"奥美拉唑\": [\r\n \"omeprazole\"\r\n ],\r\n \"兰索拉唑\": [\r\n \"lansoprazole\"\r\n ],\r\n \"泮托拉唑\": [\r\n \"pantoprazole\"\r\n ],\r\n \"雷贝拉唑\": [\r\n \"rabeprazole\"\r\n ],\r\n \"艾司奥美拉唑\": [\r\n \"esomeprazole\"\r\n ],\r\n \"法莫替丁\": [\r\n \"famotidine\"\r\n ],\r\n \"雷尼替丁\": [\r\n \"ranitidine\"\r\n ],\r\n \"西咪替丁\": [\r\n \"cimetidine\"\r\n ],\r\n \"二甲双胍\": [\r\n \"metformin\"\r\n ],\r\n \"格列美脲\": [\r\n \"glimepiride\"\r\n ],\r\n \"格列齐特\": [\r\n \"gliclazide\"\r\n ],\r\n \"格列吡嗪\": [\r\n \"glipizide\"\r\n ],\r\n \"格列本脲\": [\r\n \"glibenclamide\",\r\n \"glyburide\"\r\n ],\r\n \"阿卡波糖\": [\r\n \"acarbose\"\r\n ],\r\n \"伏格列波糖\": [\r\n \"voglibose\"\r\n ],\r\n \"瑞格列奈\": [\r\n \"repaglinide\"\r\n ],\r\n \"那格列奈\": [\r\n \"nateglinide\"\r\n ],\r\n \"西格列汀\": [\r\n \"sitagliptin\"\r\n ],\r\n \"沙格列汀\": [\r\n \"saxagliptin\"\r\n ],\r\n \"利格列汀\": [\r\n \"linagliptin\"\r\n ],\r\n \"维格列汀\": [\r\n \"vildagliptin\"\r\n ],\r\n \"恩格列净\": [\r\n \"empagliflozin\"\r\n ],\r\n \"达格列净\": [\r\n \"dapagliflozin\"\r\n ],\r\n \"卡格列净\": [\r\n \"canagliflozin\"\r\n ],\r\n \"吡格列酮\": [\r\n \"pioglitazone\"\r\n ],\r\n \"罗格列酮\": [\r\n \"rosiglitazone\"\r\n ],\r\n \"胰岛素\": [\r\n \"insulin\"\r\n ],\r\n \"甘精胰岛素\": [\r\n \"insulin glargine\"\r\n ],\r\n \"门冬胰岛素\": [\r\n \"insulin aspart\"\r\n ],\r\n \"赖脯胰岛素\": [\r\n \"insulin lispro\"\r\n ],\r\n \"地特胰岛素\": [\r\n \"insulin detemir\"\r\n ],\r\n \"格列喹酮\": [\r\n \"gliquidone\"\r\n ],\r\n \"阿托伐他汀\": [\r\n \"atorvastatin\"\r\n ],\r\n \"瑞舒伐他汀\": [\r\n \"rosuvastatin\"\r\n ],\r\n \"辛伐他汀\": [\r\n \"simvastatin\"\r\n ],\r\n \"普伐他汀\": [\r\n \"pravastatin\"\r\n ],\r\n \"氟伐他汀\": [\r\n \"fluvastatin\"\r\n ],\r\n \"匹伐他汀\": [\r\n \"pitavastatin\"\r\n ],\r\n \"洛伐他汀\": [\r\n \"lovastatin\"\r\n ],\r\n \"依折麦布\": [\r\n \"ezetimibe\"\r\n ],\r\n \"非诺贝特\": [\r\n \"fenofibrate\"\r\n ],\r\n \"吉非贝齐\": [\r\n \"gemfibrozil\"\r\n ],\r\n \"苯扎贝特\": [\r\n \"bezafibrate\"\r\n ],\r\n \"考来烯胺\": [\r\n \"cholestyramine\"\r\n ],\r\n \"阿昔单抗\": [\r\n \"abciximab\"\r\n ],\r\n \"氯吡格雷\": [\r\n \"clopidogrel\"\r\n ],\r\n \"替格瑞洛\": [\r\n \"ticagrelor\"\r\n ],\r\n \"普拉格雷\": [\r\n \"prasugrel\"\r\n ],\r\n \"华法林\": [\r\n \"warfarin\"\r\n ],\r\n \"利伐沙班\": [\r\n \"rivaroxaban\"\r\n ],\r\n \"阿哌沙班\": [\r\n \"apixaban\"\r\n ],\r\n \"达比加群\": [\r\n \"dabigatran\"\r\n ],\r\n \"依度沙班\": [\r\n \"edoxaban\"\r\n ],\r\n \"肝素\": [\r\n \"heparin\"\r\n ],\r\n \"低分子肝素\": [\r\n \"enoxaparin\",\r\n \"low molecular weight heparin\"\r\n ],\r\n \"达肝素\": [\r\n \"dalteparin\"\r\n ],\r\n \"那屈肝素\": [\r\n \"nadroparin\"\r\n ],\r\n \"磺达肝癸钠\": [\r\n \"fondaparinux\"\r\n ],\r\n \"阿替普酶\": [\r\n \"alteplase\"\r\n ],\r\n \"尿激酶\": [\r\n \"urokinase\"\r\n ],\r\n \"链激酶\": [\r\n \"streptokinase\"\r\n ],\r\n \"氨甲环酸\": [\r\n \"tranexamic acid\"\r\n ],\r\n \"氨基己酸\": [\r\n \"aminocaproic acid\"\r\n ],\r\n \"鱼精蛋白\": [\r\n \"protamine\"\r\n ],\r\n \"维生素K\": [\r\n \"vitamin k\",\r\n \"phytomenadione\"\r\n ],\r\n \"酚磺乙胺\": [\r\n \"etamsylate\"\r\n ],\r\n \"卡巴克络\": [\r\n \"carbazochrome\"\r\n ],\r\n \"硝苯地平\": [\r\n \"nifedipine\"\r\n ],\r\n \"氨氯地平\": [\r\n \"amlodipine\"\r\n ],\r\n \"非洛地平\": [\r\n \"felodipine\"\r\n ],\r\n \"拉西地平\": [\r\n \"lacidipine\"\r\n ],\r\n \"尼群地平\": [\r\n \"nitrendipine\"\r\n ],\r\n \"尼莫地平\": [\r\n \"nimodipine\"\r\n ],\r\n \"地尔硫卓\": [\r\n \"diltiazem\"\r\n ],\r\n \"维拉帕米\": [\r\n \"verapamil\"\r\n ],\r\n \"卡托普利\": [\r\n \"captopril\"\r\n ],\r\n \"依那普利\": [\r\n \"enalapril\"\r\n ],\r\n \"贝那普利\": [\r\n \"benazepril\"\r\n ],\r\n \"培哚普利\": [\r\n \"perindopril\"\r\n ],\r\n \"雷米普利\": [\r\n \"ramipril\"\r\n ],\r\n \"福辛普利\": [\r\n \"fosinopril\"\r\n ],\r\n \"西拉普利\": [\r\n \"cilazapril\"\r\n ],\r\n \"赖诺普利\": [\r\n \"lisinopril\"\r\n ],\r\n \"氯沙坦\": [\r\n \"losartan\"\r\n ],\r\n \"缬沙坦\": [\r\n \"valsartan\"\r\n ],\r\n \"厄贝沙坦\": [\r\n \"irbesartan\"\r\n ],\r\n \"替米沙坦\": [\r\n \"telmisartan\"\r\n ],\r\n \"坎地沙坦\": [\r\n \"candesartan\"\r\n ],\r\n \"奥美沙坦\": [\r\n \"olmesartan\"\r\n ],\r\n \"阿利沙坦\": [\r\n \"allisartan\"\r\n ],\r\n \"氢氯噻嗪\": [\r\n \"hydrochlorothiazide\"\r\n ],\r\n \"呋塞米\": [\r\n \"furosemide\"\r\n ],\r\n \"托拉塞米\": [\r\n \"torasemide\"\r\n ],\r\n \"螺内酯\": [\r\n \"spironolactone\"\r\n ],\r\n \"氨苯蝶啶\": [\r\n \"triamterene\"\r\n ],\r\n \"阿米洛利\": [\r\n \"amiloride\"\r\n ],\r\n \"吲达帕胺\": [\r\n \"indapamide\"\r\n ],\r\n \"美托洛尔\": [\r\n \"metoprolol\"\r\n ],\r\n \"比索洛尔\": [\r\n \"bisoprolol\"\r\n ],\r\n \"阿替洛尔\": [\r\n \"atenolol\"\r\n ],\r\n \"普萘洛尔\": [\r\n \"propranolol\"\r\n ],\r\n \"卡维地洛\": [\r\n \"carvedilol\"\r\n ],\r\n \"拉贝洛尔\": [\r\n \"labetalol\"\r\n ],\r\n \"艾司洛尔\": [\r\n \"esmolol\"\r\n ],\r\n \"富马酸比索洛尔\": [\r\n \"bisoprolol\"\r\n ],\r\n \"琥珀酸美托洛尔\": [\r\n \"metoprolol succinate\"\r\n ],\r\n \"酒石酸美托洛尔\": [\r\n \"metoprolol tartrate\"\r\n ],\r\n \"地高辛\": [\r\n \"digoxin\"\r\n ],\r\n \"去乙酰毛花苷\": [\r\n \"deslanoside\"\r\n ],\r\n \"胺碘酮\": [\r\n \"amiodarone\"\r\n ],\r\n \"普罗帕酮\": [\r\n \"propafenone\"\r\n ],\r\n \"利多卡因\": [\r\n \"lidocaine\"\r\n ],\r\n \"腺苷\": [\r\n \"adenosine\"\r\n ],\r\n \"阿托品\": [\r\n \"atropine\"\r\n ],\r\n \"异丙肾上腺素\": [\r\n \"isoprenaline\",\r\n \"isoproterenol\"\r\n ],\r\n \"肾上腺素\": [\r\n \"epinephrine\",\r\n \"adrenaline\"\r\n ],\r\n \"去甲肾上腺素\": [\r\n \"norepinephrine\",\r\n \"noradrenaline\"\r\n ],\r\n \"多巴胺\": [\r\n \"dopamine\"\r\n ],\r\n \"多巴酚丁胺\": [\r\n \"dobutamine\"\r\n ],\r\n \"米力农\": [\r\n \"milrinone\"\r\n ],\r\n \"左西孟旦\": [\r\n \"levosimendan\"\r\n ],\r\n \"硝酸甘油\": [\r\n \"nitroglycerin\"\r\n ],\r\n \"单硝酸异山梨酯\": [\r\n \"isosorbide mononitrate\"\r\n ],\r\n \"硝酸异山梨酯\": [\r\n \"isosorbide dinitrate\"\r\n ],\r\n \"尼可地尔\": [\r\n \"nicorandil\"\r\n ],\r\n \"曲美他嗪\": [\r\n \"trimetazidine\"\r\n ],\r\n \"尼可刹米\": [\r\n \"nikethamide\"\r\n ],\r\n \"洛贝林\": [\r\n \"lobeline\"\r\n ],\r\n \"咖啡因\": [\r\n \"caffeine\"\r\n ],\r\n \"二甲硅油\": [\r\n \"dimeticone\"\r\n ],\r\n \"酚妥拉明\": [\r\n \"phentolamine\"\r\n ],\r\n \"酚苄明\": [\r\n \"phenoxybenzamine\"\r\n ],\r\n \"利血平\": [\r\n \"reserpine\"\r\n ],\r\n \"硫酸镁\": [\r\n \"magnesium sulfate\"\r\n ],\r\n \"葡萄糖酸钙\": [\r\n \"calcium gluconate\"\r\n ],\r\n \"氯化钾\": [\r\n \"potassium chloride\"\r\n ],\r\n \"氯化钠\": [\r\n \"sodium chloride\"\r\n ],\r\n \"葡萄糖\": [\r\n \"glucose\"\r\n ],\r\n \"乳果糖\": [\r\n \"lactulose\"\r\n ],\r\n \"聚乙二醇\": [\r\n \"polyethylene glycol\"\r\n ],\r\n \"双歧杆菌\": [\r\n \"bifidobacterium\"\r\n ],\r\n \"枯草杆菌\": [\r\n \"bacillus subtilis\"\r\n ],\r\n \"蒙脱石\": [\r\n \"smectite\"\r\n ],\r\n \"洛哌丁胺\": [\r\n \"loperamide\"\r\n ],\r\n \"奥曲肽\": [\r\n \"octreotide\"\r\n ],\r\n \"生长抑素\": [\r\n \"somatostatin\"\r\n ],\r\n \"垂体后叶素\": [\r\n \"pituitrin\"\r\n ],\r\n \"缩宫素\": [\r\n \"oxytocin\"\r\n ],\r\n \"麦角新碱\": [\r\n \"ergometrine\"\r\n ],\r\n \"卡前列素\": [\r\n \"carboprost\"\r\n ],\r\n \"米索前列醇\": [\r\n \"misoprostol\"\r\n ],\r\n \"地诺前列酮\": [\r\n \"dinoprostone\"\r\n ],\r\n \"利托君\": [\r\n \"ritodrine\"\r\n ],\r\n \"硫酸沙丁胺醇\": [\r\n \"salbutamol\"\r\n ],\r\n \"特布他林\": [\r\n \"terbutaline\"\r\n ],\r\n \"异丙托溴铵\": [\r\n \"ipratropium bromide\"\r\n ],\r\n \"噻托溴铵\": [\r\n \"tiotropium bromide\"\r\n ],\r\n \"布地奈德\": [\r\n \"budesonide\"\r\n ],\r\n \"丙酸氟替卡松\": [\r\n \"fluticasone propionate\"\r\n ],\r\n \"沙美特罗\": [\r\n \"salmeterol\"\r\n ],\r\n \"福莫特罗\": [\r\n \"formoterol\"\r\n ],\r\n \"孟鲁司特\": [\r\n \"montelukast\"\r\n ],\r\n \"扎鲁司特\": [\r\n \"zafirlukast\"\r\n ],\r\n \"齐留通\": [\r\n \"zileuton\"\r\n ],\r\n \"色甘酸钠\": [\r\n \"sodium cromoglicate\"\r\n ],\r\n \"多索茶碱\": [\r\n \"doxofylline\"\r\n ],\r\n \"氨茶碱\": [\r\n \"aminophylline\"\r\n ],\r\n \"二羟丙茶碱\": [\r\n \"dyphylline\"\r\n ],\r\n \"乙酰半胱氨酸\": [\r\n \"acetylcysteine\"\r\n ],\r\n \"羧甲司坦\": [\r\n \"carbocisteine\"\r\n ],\r\n \"盐酸氨溴索\": [\r\n \"ambroxol\"\r\n ],\r\n \"溴己新\": [\r\n \"bromhexine\"\r\n ],\r\n \"桉柠蒎\": [\r\n \"eucalyptus\"\r\n ],\r\n \"标准桃金娘油\": [\r\n \"myrtol\"\r\n ],\r\n \"可待因\": [\r\n \"codeine\"\r\n ],\r\n \"福尔可定\": [\r\n \"pholcodine\"\r\n ],\r\n \"右美沙芬\": [\r\n \"dextromethorphan\"\r\n ],\r\n \"喷托维林\": [\r\n \"pentoxyverine\"\r\n ],\r\n \"氯哌斯汀\": [\r\n \"cloperastine\"\r\n ],\r\n \"复方甘草\": [\r\n \"glycyrrhiza\"\r\n ],\r\n \"阿桔片\": [\r\n \"platycodon\"\r\n ],\r\n \"苯丙哌林\": [\r\n \"properidine\"\r\n ],\r\n \"二氧丙嗪\": [\r\n \"dioxopromethazine\"\r\n ],\r\n \"异丙嗪\": [\r\n \"promethazine\"\r\n ],\r\n \"氯苯那敏\": [\r\n \"chlorpheniramine\"\r\n ],\r\n \"苯海拉明\": [\r\n \"diphenhydramine\"\r\n ],\r\n \"赛庚啶\": [\r\n \"cyproheptadine\"\r\n ],\r\n \"酮替芬\": [\r\n \"ketotifen\"\r\n ],\r\n \"西替利嗪\": [\r\n \"cetirizine\"\r\n ],\r\n \"氯雷他定\": [\r\n \"loratadine\"\r\n ],\r\n \"依巴斯汀\": [\r\n \"ebastine\"\r\n ],\r\n \"咪唑斯汀\": [\r\n \"mizolastine\"\r\n ],\r\n \"氮卓斯汀\": [\r\n \"azelastine\"\r\n ],\r\n \"非索非那定\": [\r\n \"fexofenadine\"\r\n ],\r\n \"地氯雷他定\": [\r\n \"desloratadine\"\r\n ],\r\n \"左西替利嗪\": [\r\n \"levocetirizine\"\r\n ],\r\n \"奥洛他定\": [\r\n \"olopatadine\"\r\n ],\r\n \"阿伐斯汀\": [\r\n \"acrivastine\"\r\n ],\r\n \"曲普利啶\": [\r\n \"triprolidine\"\r\n ],\r\n \"阿司咪唑\": [\r\n \"astemizole\"\r\n ],\r\n \"特非那定\": [\r\n \"terfenadine\"\r\n ],\r\n \"卡马西平\": [\r\n \"carbamazepine\"\r\n ],\r\n \"苯妥英钠\": [\r\n \"phenytoin sodium\"\r\n ],\r\n \"丙戊酸钠\": [\r\n \"sodium valproate\"\r\n ],\r\n \"苯巴比妥\": [\r\n \"phenobarbital\"\r\n ],\r\n \"拉莫三嗪\": [\r\n \"lamotrigine\"\r\n ],\r\n \"左乙拉西坦\": [\r\n \"levetiracetam\"\r\n ],\r\n \"奥卡西平\": [\r\n \"oxcarbazepine\"\r\n ],\r\n \"托吡酯\": [\r\n \"topiramate\"\r\n ],\r\n \"加巴喷丁\": [\r\n \"gabapentin\"\r\n ],\r\n \"普瑞巴林\": [\r\n \"pregabalin\"\r\n ],\r\n \"乙琥胺\": [\r\n \"ethosuximide\"\r\n ],\r\n \"氯硝西泮\": [\r\n \"clonazepam\"\r\n ],\r\n \"地西泮\": [\r\n \"diazepam\"\r\n ],\r\n \"硝西泮\": [\r\n \"nitrazepam\"\r\n ],\r\n \"艾司唑仑\": [\r\n \"estazolam\"\r\n ],\r\n \"阿普唑仑\": [\r\n \"alprazolam\"\r\n ],\r\n \"劳拉西泮\": [\r\n \"lorazepam\"\r\n ],\r\n \"咪达唑仑\": [\r\n \"midazolam\"\r\n ],\r\n \"唑吡坦\": [\r\n \"zolpidem\"\r\n ],\r\n \"佐匹克隆\": [\r\n \"zopiclone\"\r\n ],\r\n \"扎来普隆\": [\r\n \"zaleplon\"\r\n ],\r\n \"水合氯醛\": [\r\n \"chloral hydrate\"\r\n ],\r\n \"丁螺环酮\": [\r\n \"buspirone\"\r\n ],\r\n \"坦度螺酮\": [\r\n \"tandospirone\"\r\n ],\r\n \"氟西汀\": [\r\n \"fluoxetine\"\r\n ],\r\n \"帕罗西汀\": [\r\n \"paroxetine\"\r\n ],\r\n \"舍曲林\": [\r\n \"sertraline\"\r\n ],\r\n \"氟伏沙明\": [\r\n \"fluvoxamine\"\r\n ],\r\n \"西酞普兰\": [\r\n \"citalopram\"\r\n ],\r\n \"艾司西酞普兰\": [\r\n \"escitalopram\"\r\n ],\r\n \"文拉法辛\": [\r\n \"venlafaxine\"\r\n ],\r\n \"度洛西汀\": [\r\n \"duloxetine\"\r\n ],\r\n \"米那普仑\": [\r\n \"milnacipran\"\r\n ],\r\n \"米氮平\": [\r\n \"mirtazapine\"\r\n ],\r\n \"阿戈美拉汀\": [\r\n \"agomelatine\"\r\n ],\r\n \"安非他酮\": [\r\n \"bupropion\"\r\n ],\r\n \"瑞波西汀\": [\r\n \"reboxetine\"\r\n ],\r\n \"曲唑酮\": [\r\n \"trazodone\"\r\n ],\r\n \"奈法唑酮\": [\r\n \"nefazodone\"\r\n ],\r\n \"吗氯贝胺\": [\r\n \"moclobemide\"\r\n ],\r\n \"苯乙肼\": [\r\n \"phenelzine\"\r\n ],\r\n \"反苯环丙胺\": [\r\n \"tranylcypromine\"\r\n ],\r\n \"碳酸锂\": [\r\n \"lithium carbonate\"\r\n ],\r\n \"奥氮平\": [\r\n \"olanzapine\"\r\n ],\r\n \"喹硫平\": [\r\n \"quetiapine\"\r\n ],\r\n \"利培酮\": [\r\n \"risperidone\"\r\n ],\r\n \"帕利哌酮\": [\r\n \"paliperidone\"\r\n ],\r\n \"齐拉西酮\": [\r\n \"ziprasidone\"\r\n ],\r\n \"阿立哌唑\": [\r\n \"aripiprazole\"\r\n ],\r\n \"鲁拉西酮\": [\r\n \"lurasidone\"\r\n ],\r\n \"布南色尔\": [\r\n \"blonanserin\"\r\n ],\r\n \"氨磺必利\": [\r\n \"amisulpride\"\r\n ],\r\n \"氯氮平\": [\r\n \"clozapine\"\r\n ],\r\n \"氟哌啶醇\": [\r\n \"haloperidol\"\r\n ],\r\n \"奋乃静\": [\r\n \"perphenazine\"\r\n ],\r\n \"氟奋乃静\": [\r\n \"fluphenazine\"\r\n ],\r\n \"三氟拉嗪\": [\r\n \"trifluoperazine\"\r\n ],\r\n \"硫必利\": [\r\n \"tiapride\"\r\n ],\r\n \"舒必利\": [\r\n \"sulpiride\"\r\n ],\r\n \"左舒必利\": [\r\n \"levosulpiride\"\r\n ],\r\n \"扑米酮\": [\r\n \"primidone\"\r\n ],\r\n \"拉考沙胺\": [\r\n \"lacosamide\"\r\n ],\r\n \"吡仑帕奈\": [\r\n \"perampanel\"\r\n ],\r\n \"司替戊醇\": [\r\n \"stiripentol\"\r\n ],\r\n \"卡立普多\": [\r\n \"carisoprodol\"\r\n ],\r\n \"巴氯芬\": [\r\n \"baclofen\"\r\n ],\r\n \"替扎尼定\": [\r\n \"tizanidine\"\r\n ],\r\n \"丹曲林\": [\r\n \"dantrolene\"\r\n ],\r\n \"乙哌立松\": [\r\n \"eperisone\"\r\n ],\r\n \"苯海索\": [\r\n \"trihexyphenidyl\"\r\n ],\r\n \"丙环定\": [\r\n \"procyclidine\"\r\n ],\r\n \"左旋多巴\": [\r\n \"levodopa\"\r\n ],\r\n \"卡比多巴\": [\r\n \"carbidopa\"\r\n ],\r\n \"恩他卡朋\": [\r\n \"entacapone\"\r\n ],\r\n \"托卡朋\": [\r\n \"tolcapone\"\r\n ],\r\n \"司来吉兰\": [\r\n \"selegiline\"\r\n ],\r\n \"雷沙吉兰\": [\r\n \"rasagiline\"\r\n ],\r\n \"金刚烷胺\": [\r\n \"amantadine\"\r\n ],\r\n \"普拉克索\": [\r\n \"pramipexole\"\r\n ],\r\n \"罗匹尼罗\": [\r\n \"ropinirole\"\r\n ],\r\n \"罗替高汀\": [\r\n \"rotigotine\"\r\n ],\r\n \"培高利特\": [\r\n \"pergolide\"\r\n ],\r\n \"阿扑吗啡\": [\r\n \"apomorphine\"\r\n ],\r\n \"多奈哌齐\": [\r\n \"donepezil\"\r\n ],\r\n \"卡巴拉汀\": [\r\n \"rivastigmine\"\r\n ],\r\n \"加兰他敏\": [\r\n \"galantamine\"\r\n ],\r\n \"美金刚\": [\r\n \"memantine\"\r\n ],\r\n \"尼麦角林\": [\r\n \"nicergoline\"\r\n ],\r\n \"倍他司汀\": [\r\n \"betahistine\"\r\n ],\r\n \"氟桂利嗪\": [\r\n \"flunarizine\"\r\n ],\r\n \"桂利嗪\": [\r\n \"cinnarizine\"\r\n ],\r\n \"罂粟碱\": [\r\n \"papaverine\"\r\n ],\r\n \"川芎嗪\": [\r\n \"ligustrazine\"\r\n ],\r\n \"丁苯酞\": [\r\n \"dl-3-n-butylphthalide\"\r\n ],\r\n \"依达拉奉\": [\r\n \"edaravone\"\r\n ],\r\n \"脑苷肌苷\": [\r\n \"cattle encephaloglycan\"\r\n ],\r\n \"鼠神经生长因子\": [\r\n \"mouse nerve growth factor\"\r\n ],\r\n \"奥拉西坦\": [\r\n \"oxiracetam\"\r\n ],\r\n \"吡拉西坦\": [\r\n \"piracetam\"\r\n ],\r\n \"胞磷胆碱\": [\r\n \"citicoline\"\r\n ],\r\n \"神经节苷脂\": [\r\n \"ganglioside\"\r\n ],\r\n \"艾地苯醌\": [\r\n \"idebenone\"\r\n ],\r\n \"维生素B1\": [\r\n \"vitamin b1\",\r\n \"thiamine\"\r\n ],\r\n \"维生素B2\": [\r\n \"vitamin b2\",\r\n \"riboflavin\"\r\n ],\r\n \"维生素B6\": [\r\n \"vitamin b6\",\r\n \"pyridoxine\"\r\n ],\r\n \"维生素B12\": [\r\n \"vitamin b12\",\r\n \"cyanocobalamin\"\r\n ],\r\n \"维生素C\": [\r\n \"vitamin c\",\r\n \"ascorbic acid\"\r\n ],\r\n \"维生素D\": [\r\n \"vitamin d\",\r\n \"cholecalciferol\"\r\n ],\r\n \"维生素E\": [\r\n \"vitamin e\",\r\n \"tocopherol\"\r\n ],\r\n \"维生素K1\": [\r\n \"vitamin k1\",\r\n \"phytomenadione\"\r\n ],\r\n \"叶酸\": [\r\n \"folic acid\"\r\n ],\r\n \"烟酸\": [\r\n \"niacin\",\r\n \"nicotinic acid\"\r\n ],\r\n \"烟酰胺\": [\r\n \"niacinamide\"\r\n ],\r\n \"复合维生素B\": [\r\n \"vitamin b complex\"\r\n ],\r\n \"葡萄糖酸锌\": [\r\n \"zinc gluconate\"\r\n ],\r\n \"硫酸亚铁\": [\r\n \"ferrous sulfate\"\r\n ],\r\n \"富马酸亚铁\": [\r\n \"ferrous fumarate\"\r\n ],\r\n \"琥珀酸亚铁\": [\r\n \"ferrous succinate\"\r\n ],\r\n \"多糖铁复合物\": [\r\n \"polysaccharide iron complex\"\r\n ],\r\n \"右旋糖酐铁\": [\r\n \"iron dextran\"\r\n ],\r\n \"蔗糖铁\": [\r\n \"iron sucrose\"\r\n ],\r\n \"重组人促红素\": [\r\n \"erythropoietin\"\r\n ],\r\n \"聚乙二醇化重组人粒细胞集落刺激因子\": [\r\n \"pegfilgrastim\"\r\n ],\r\n \"重组人粒细胞集落刺激因子\": [\r\n \"filgrastim\"\r\n ],\r\n \"粒细胞-巨噬细胞集落刺激因子\": [\r\n \"sargramostim\"\r\n ],\r\n \"白介素-2\": [\r\n \"interleukin-2\"\r\n ],\r\n \"白介素-11\": [\r\n \"interleukin-11\"\r\n ],\r\n \"干扰素\": [\r\n \"interferon\"\r\n ],\r\n \"聚乙二醇干扰素\": [\r\n \"peginterferon\"\r\n ],\r\n \"利巴韦林\": [\r\n \"ribavirin\"\r\n ],\r\n \"阿昔洛韦\": [\r\n \"acyclovir\"\r\n ],\r\n \"更昔洛韦\": [\r\n \"ganciclovir\"\r\n ],\r\n \"伐昔洛韦\": [\r\n \"valacyclovir\"\r\n ],\r\n \"泛昔洛韦\": [\r\n \"famciclovir\"\r\n ],\r\n \"膦甲酸钠\": [\r\n \"foscarnet sodium\"\r\n ],\r\n \"奥司他韦\": [\r\n \"oseltamivir\"\r\n ],\r\n \"扎那米韦\": [\r\n \"zanamivir\"\r\n ],\r\n \"帕拉米韦\": [\r\n \"peramivir\"\r\n ],\r\n \"法匹拉韦\": [\r\n \"favipiravir\"\r\n ],\r\n \"瑞德西韦\": [\r\n \"remdesivir\"\r\n ],\r\n \"莫诺拉韦\": [\r\n \"molnupiravir\"\r\n ],\r\n \"奈玛特韦\": [\r\n \"nirmatrelvir\"\r\n ],\r\n \"利托那韦\": [\r\n \"ritonavir\"\r\n ],\r\n \"洛匹那韦\": [\r\n \"lopinavir\"\r\n ],\r\n \"达芦那韦\": [\r\n \"darunavir\"\r\n ],\r\n \"阿扎那韦\": [\r\n \"atazanavir\"\r\n ],\r\n \"拉替拉韦\": [\r\n \"raltegravir\"\r\n ],\r\n \"多替拉韦\": [\r\n \"dolutegravir\"\r\n ],\r\n \"艾维雷韦\": [\r\n \"elvitegravir\"\r\n ],\r\n \"比克替拉韦\": [\r\n \"bictegravir\"\r\n ],\r\n \"恩曲他滨\": [\r\n \"emtricitabine\"\r\n ],\r\n \"替诺福韦\": [\r\n \"tenofovir\"\r\n ],\r\n \"恩替卡韦\": [\r\n \"entecavir\"\r\n ],\r\n \"拉米夫定\": [\r\n \"lamivudine\"\r\n ],\r\n \"阿德福韦\": [\r\n \"adefovir\"\r\n ],\r\n \"替比夫定\": [\r\n \"telbivudine\"\r\n ],\r\n \"索磷布韦\": [\r\n \"sofosbuvir\"\r\n ],\r\n \"维帕他韦\": [\r\n \"velpatasvir\"\r\n ],\r\n \"格卡瑞韦\": [\r\n \"grazoprevir\"\r\n ],\r\n \"哌仑他韦\": [\r\n \"pibrentasvir\"\r\n ],\r\n \"伏西瑞韦\": [\r\n \"voxilaprevir\"\r\n ],\r\n \"艾尔巴韦\": [\r\n \"elbasvir\"\r\n ],\r\n \"达拉他韦\": [\r\n \"daclatasvir\"\r\n ],\r\n \"阿舒瑞韦\": [\r\n \"asunaprevir\"\r\n ],\r\n \"达塞布韦\": [\r\n \"dasabuvir\"\r\n ],\r\n \"波普瑞韦\": [\r\n \"boceprevir\"\r\n ],\r\n \"特拉匹拉韦\": [\r\n \"telaprevir\"\r\n ],\r\n \"西咪匹韦\": [\r\n \"simeprevir\"\r\n ],\r\n \"帕利瑞韦\": [\r\n \"paritaprevir\"\r\n ],\r\n \"奥比他韦\": [\r\n \"ombitasvir\"\r\n ],\r\n \"异烟肼\": [\r\n \"isoniazid\"\r\n ],\r\n \"利福平\": [\r\n \"rifampicin\"\r\n ],\r\n \"吡嗪酰胺\": [\r\n \"pyrazinamide\"\r\n ],\r\n \"乙胺丁醇\": [\r\n \"ethambutol\"\r\n ],\r\n \"链霉素\": [\r\n \"streptomycin\"\r\n ],\r\n \"对氨基水杨酸\": [\r\n \"para-aminosalicylic acid\"\r\n ],\r\n \"利福布汀\": [\r\n \"rifabutin\"\r\n ],\r\n \"利福喷丁\": [\r\n \"rifapentine\"\r\n ],\r\n \"贝达喹啉\": [\r\n \"bedaquiline\"\r\n ],\r\n \"德拉马尼\": [\r\n \"delamanid\"\r\n ],\r\n \"氯法齐明\": [\r\n \"clofazimine\"\r\n ],\r\n \"环丝氨酸\": [\r\n \"cycloserine\"\r\n ],\r\n \"丙硫异烟胺\": [\r\n \"protionamide\"\r\n ],\r\n \"氨硫脲\": [\r\n \"thioacetazone\"\r\n ],\r\n \"卷曲霉素\": [\r\n \"capreomycin\"\r\n ],\r\n \"卡那霉素\": [\r\n \"kanamycin\"\r\n ],\r\n \"阿米卡星\": [\r\n \"amikacin\"\r\n ],\r\n \"加替沙星\": [\r\n \"gatifloxacin\"\r\n ],\r\n \"环丙沙星\": [\r\n \"ciprofloxacin\"\r\n ],\r\n \"氧氟沙星\": [\r\n \"ofloxacin\"\r\n ],\r\n \"诺氟沙星\": [\r\n \"norfloxacin\"\r\n ],\r\n \"依诺沙星\": [\r\n \"enoxacin\"\r\n ],\r\n \"洛美沙星\": [\r\n \"lomefloxacin\"\r\n ],\r\n \"司帕沙星\": [\r\n \"sparfloxacin\"\r\n ],\r\n \"培氟沙星\": [\r\n \"pefloxacin\"\r\n ],\r\n \"妥舒沙星\": [\r\n \"tosufloxacin\"\r\n ],\r\n \"芦氟沙星\": [\r\n \"rufloxacin\"\r\n ],\r\n \"克林霉素\": [\r\n \"clindamycin\"\r\n ],\r\n \"林可霉素\": [\r\n \"lincomycin\"\r\n ],\r\n \"磷霉素\": [\r\n \"fosfomycin\"\r\n ],\r\n \"夫西地酸\": [\r\n \"fusidic acid\"\r\n ],\r\n \"利奈唑胺\": [\r\n \"linezolid\"\r\n ],\r\n \"替加环素\": [\r\n \"tigecycline\"\r\n ],\r\n \"替考拉宁\": [\r\n \"teicoplanin\"\r\n ],\r\n \"万古霉素\": [\r\n \"vancomycin\"\r\n ],\r\n \"去甲万古霉素\": [\r\n \"norvancomycin\"\r\n ],\r\n \"达托霉素\": [\r\n \"daptomycin\"\r\n ],\r\n \"特拉万星\": [\r\n \"telavancin\"\r\n ],\r\n \"头孢洛林\": [\r\n \"ceftaroline\"\r\n ],\r\n \"头孢他啶\": [\r\n \"ceftazidime\"\r\n ],\r\n \"头孢哌酮\": [\r\n \"cefoperazone\"\r\n ],\r\n \"头孢吡肟\": [\r\n \"cefepime\"\r\n ],\r\n \"头孢噻肟\": [\r\n \"cefotaxime\"\r\n ],\r\n \"头孢唑林\": [\r\n \"cefazolin\"\r\n ],\r\n \"头孢拉定\": [\r\n \"cefradine\"\r\n ],\r\n \"头孢克洛\": [\r\n \"cefaclor\"\r\n ],\r\n \"头孢丙烯\": [\r\n \"cefprozil\"\r\n ],\r\n \"头孢地尼\": [\r\n \"cefdinir\"\r\n ],\r\n \"头孢克肟\": [\r\n \"cefixime\"\r\n ],\r\n \"头孢布烯\": [\r\n \"ceftibuten\"\r\n ],\r\n \"头孢泊肟酯\": [\r\n \"cefpodoxime proxetil\"\r\n ],\r\n \"亚胺培南\": [\r\n \"imipenem\"\r\n ],\r\n \"美罗培南\": [\r\n \"meropenem\"\r\n ],\r\n \"厄他培南\": [\r\n \"ertapenem\"\r\n ],\r\n \"比阿培南\": [\r\n \"biapenem\"\r\n ],\r\n \"帕尼培南\": [\r\n \"panipenem\"\r\n ],\r\n \"氨曲南\": [\r\n \"aztreonam\"\r\n ],\r\n \"克拉维酸\": [\r\n \"clavulanic acid\"\r\n ],\r\n \"舒巴坦\": [\r\n \"sulbactam\"\r\n ],\r\n \"他唑巴坦\": [\r\n \"tazobactam\"\r\n ],\r\n \"阿维巴坦\": [\r\n \"avibactam\"\r\n ],\r\n \"瑞来巴坦\": [\r\n \"relebactam\"\r\n ],\r\n \"法硼巴坦\": [\r\n \"vaborbactam\"\r\n ],\r\n \"多尼培南\": [\r\n \"doripenem\"\r\n ],\r\n \"头孢他啶阿维巴坦\": [\r\n \"ceftazidime-avibactam\"\r\n ],\r\n \"美罗培南法硼巴坦\": [\r\n \"meropenem-vaborbactam\"\r\n ],\r\n \"亚胺培南西司他丁\": [\r\n \"imipenem-cilastatin\"\r\n ],\r\n \"头孢哌酮舒巴坦\": [\r\n \"cefoperazone-sulbactam\"\r\n ],\r\n \"哌拉西林他唑巴坦\": [\r\n \"piperacillin-tazobactam\"\r\n ],\r\n \"阿莫西林克拉维酸\": [\r\n \"amoxicillin-clavulanate\"\r\n ],\r\n \"氟康唑\": [\r\n \"fluconazole\"\r\n ],\r\n \"伊曲康唑\": [\r\n \"itraconazole\"\r\n ],\r\n \"伏立康唑\": [\r\n \"voriconazole\"\r\n ],\r\n \"泊沙康唑\": [\r\n \"posaconazole\"\r\n ],\r\n \"卡泊芬净\": [\r\n \"caspofungin\"\r\n ],\r\n \"米卡芬净\": [\r\n \"micafungin\"\r\n ],\r\n \"阿尼芬净\": [\r\n \"anidulafungin\"\r\n ],\r\n \"两性霉素B\": [\r\n \"amphotericin b\"\r\n ],\r\n \"氟胞嘧啶\": [\r\n \"flucytosine\"\r\n ],\r\n \"特比萘芬\": [\r\n \"terbinafine\"\r\n ],\r\n \"酮康唑\": [\r\n \"ketoconazole\"\r\n ],\r\n \"咪康唑\": [\r\n \"miconazole\"\r\n ],\r\n \"克霉唑\": [\r\n \"clotrimazole\"\r\n ],\r\n \"益康唑\": [\r\n \"econazole\"\r\n ],\r\n \"制霉菌素\": [\r\n \"nystatin\"\r\n ],\r\n \"环吡酮胺\": [\r\n \"ciclopirox olamine\"\r\n ],\r\n \"阿莫罗芬\": [\r\n \"amorolfine\"\r\n ],\r\n \"艾沙康唑\": [\r\n \"isavuconazole\"\r\n ],\r\n \"奥希替尼\": [\r\n \"osimertinib\"\r\n ],\r\n \"吉非替尼\": [\r\n \"gefitinib\"\r\n ],\r\n \"厄洛替尼\": [\r\n \"erlotinib\"\r\n ],\r\n \"阿法替尼\": [\r\n \"afatinib\"\r\n ],\r\n \"克唑替尼\": [\r\n \"crizotinib\"\r\n ],\r\n \"伊马替尼\": [\r\n \"imatinib\"\r\n ],\r\n \"索拉非尼\": [\r\n \"sorafenib\"\r\n ],\r\n \"帕博利珠单抗\": [\r\n \"pembrolizumab\"\r\n ],\r\n \"纳武利尤单抗\": [\r\n \"nivolumab\"\r\n ],\r\n \"信迪利单抗\": [\r\n \"sintilimab\"\r\n ],\r\n \"卡瑞利珠单抗\": [\r\n \"camrelizumab\"\r\n ],\r\n \"曲妥珠单抗\": [\r\n \"trastuzumab\"\r\n ],\r\n \"贝伐珠单抗\": [\r\n \"bevacizumab\"\r\n ],\r\n \"利妥昔单抗\": [\r\n \"rituximab\"\r\n ],\r\n \"佐妥昔单抗\": [\r\n \"zolbetuximab\"\r\n ]\r\n}\n\nFile v1.3.0:references/term_map.json\n\n{\r\n \"1型糖尿病\": \"type 1 diabetes\",\r\n \"2型糖尿病\": \"type 2 diabetes\",\r\n \"ALK\": \"ALK\",\r\n \"BRAF\": \"BRAF\",\r\n \"BRCA\": \"BRCA\",\r\n \"CAR-T\": \"CAR-T\",\r\n \"CDK4/6\": \"CDK4/6\",\r\n \"CTLA-4\": \"CTLA-4\",\r\n \"EGFR\": \"EGFR\",\r\n \"Graves病\": \"Graves disease\",\r\n \"HER2\": \"HER2\",\r\n \"III期临床试验\": \"phase III clinical trial\",\r\n \"IgA肾病\": \"IgA nephropathy\",\r\n \"KRAS\": \"KRAS\",\r\n \"MET\": \"MET\",\r\n \"NTRK\": \"NTRK\",\r\n \"PD-1\": \"PD-1\",\r\n \"PD-L1\": \"PD-L1\",\r\n \"PI3K\": \"PI3K\",\r\n \"RET\": \"RET\",\r\n \"ROS1\": \"ROS1\",\r\n \"一线\": \"first-line\",\r\n \"一线治疗\": \"first-line therapy\",\r\n \"三叉神经痛\": \"trigeminal neuralgia\",\r\n \"三线\": \"third-line\",\r\n \"三线治疗\": \"third-line therapy\",\r\n \"上市后监测\": \"post-marketing surveillance\",\r\n \"不良事件\": \"adverse events\",\r\n \"不良反应\": \"adverse events\",\r\n \"丙卡特罗\": \"procaterol\",\r\n \"丙肝\": \"hepatitis C\",\r\n \"丛集性头痛\": \"cluster headache\",\r\n \"中位总生存期\": \"median overall survival\",\r\n \"中位无进展生存期\": \"median progression-free survival\",\r\n \"临床试验\": \"clinical trial\",\r\n \"主动脉夹层\": \"aortic dissection\",\r\n \"乌司奴单抗\": \"ustekinumab\",\r\n \"乌美溴铵\": \"umeclidinium bromide\",\r\n \"乐卡地平\": \"lercanidipine\",\r\n \"乙肝\": \"hepatitis B\",\r\n \"乳腺癌\": \"breast cancer\",\r\n \"二线\": \"second-line\",\r\n \"二线治疗\": \"second-line therapy\",\r\n \"二羟丙茶碱\": \"diprophylline\",\r\n \"亚急性甲状腺炎\": \"subacute thyroiditis\",\r\n \"亨廷顿病\": \"Huntington disease\",\r\n \"仑伐替尼\": \"lenvatinib\",\r\n \"他克莫司\": \"tacrolimus\",\r\n \"他拉唑帕利\": \"talazoparib\",\r\n \"他法替他单抗\": \"tafasitamab\",\r\n \"他莫昔芬\": \"tamoxifen\",\r\n \"代谢综合征\": \"metabolic syndrome\",\r\n \"伊伐布雷定\": \"ivabradine\",\r\n \"伊匹木单抗\": \"ipilimumab\",\r\n \"伊布替尼\": \"ibrutinib\",\r\n \"伊沙佐米\": \"ixazomib\",\r\n \"伊班膦酸钠\": \"ibandronate\",\r\n \"伊立替康\": \"irinotecan\",\r\n \"伊马替尼\": \"imatinib\",\r\n \"伏美替尼\": \"furmonertinib\",\r\n \"伯西塔单抗\": \"brolucizumab\",\r\n \"低分子肝素\": \"low molecular weight heparin (LMWH)\",\r\n \"低强度激光治疗\": \"low-level laser therapy (LLLT)\",\r\n \"依奇珠单抗\": \"ixekizumab\",\r\n \"依库珠单抗\": \"eculizumab\",\r\n \"依度沙班\": \"edoxaban\",\r\n \"依折麦布\": \"ezetimibe\",\r\n \"依普利酮\": \"eplerenone\",\r\n \"依替巴肽\": \"eptifibatide\",\r\n \"依洛尤单抗\": \"evolocumab\",\r\n \"依维莫司\": \"everolimus\",\r\n \"依降钙素\": \"elcatonin\",\r\n \"促皮质素\": \"corticotropin\",\r\n \"信迪利单抗\": \"sintilimab\",\r\n \"倍他米松\": \"betamethasone\",\r\n \"倍氯米松\": \"beclomethasone\",\r\n \"假性痛风\": \"pseudogout\",\r\n \"偏头痛\": \"migraine\",\r\n \"儿童\": \"pediatric\",\r\n \"光生物调节\": \"photobiomodulation (PBM)\",\r\n \"克唑替尼\": \"crizotinib\",\r\n \"克罗恩病\": \"Crohn disease\",\r\n \"免疫检查点抑制剂\": \"immune checkpoint inhibitor\",\r\n \"免疫治疗\": \"immunotherapy\",\r\n \"免疫相关不良事件\": \"immune-related adverse events (irAE)\",\r\n \"兰瑞肽\": \"lanreotide\",\r\n \"内分泌治疗\": \"endocrine therapy\",\r\n \"再生障碍性贫血\": \"aplastic anemia\",\r\n \"冠心病\": \"coronary artery disease (CAD)\",\r\n \"凡德他尼\": \"vandetanib\",\r\n \"出血性卒中\": \"hemorrhagic stroke\",\r\n \"利伐沙班\": \"rivaroxaban\",\r\n \"利塞膦酸钠\": \"risedronate\",\r\n \"利妥昔单抗\": \"rituximab\",\r\n \"利拉鲁肽\": \"liraglutide\",\r\n \"利生奇珠单抗\": \"risankizumab\",\r\n \"利纳西珠单抗\": \"rilonacept\",\r\n \"利血平\": \"reserpine\",\r\n \"剂量\": \"dose\",\r\n \"剂量爬坡\": \"dose escalation\",\r\n \"前列腺癌\": \"prostate cancer\",\r\n \"前瞻性研究\": \"prospective study\",\r\n \"动脉瘤\": \"aneurysm\",\r\n \"动脉粥样硬化\": \"atherosclerosis\",\r\n \"化疗\": \"chemotherapy\",\r\n \"卒中\": \"stroke\",\r\n \"单硝酸异山梨酯\": \"isosorbide mononitrate\",\r\n \"单药\": \"monotherapy\",\r\n \"单药治疗\": \"monotherapy\",\r\n \"卡博替尼\": \"cabozantinib\",\r\n \"卡培他滨\": \"capecitabine\",\r\n \"卡托普利\": \"captopril\",\r\n \"卡比多巴\": \"carbidopa\",\r\n \"卡瑞利珠单抗\": \"camrelizumab\",\r\n \"卡维地洛\": \"carvedilol\",\r\n \"卡那奴单抗\": \"canakinumab\",\r\n \"卡铂\": \"carboplatin\",\r\n \"卡非佐米\": \"carfilzomib\",\r\n \"卡麦角林\": \"cabergoline\",\r\n \"卵巢癌\": \"ovarian cancer\",\r\n \"卵黄囊瘤\": \"yolk sac tumor\",\r\n \"厄洛替尼\": \"erlotinib\",\r\n \"原发性硬化性胆管炎\": \"primary sclerosing cholangitis (PSC)\",\r\n \"原发性耐药\": \"primary resistance\",\r\n \"原发性胆汁性胆管炎\": \"primary biliary cholangitis (PBC)\",\r\n \"原发性血小板增多症\": \"essential thrombocythemia\",\r\n \"原发性醛固酮增多症\": \"primary hyperaldosteronism\",\r\n \"去氧肾上腺素\": \"phenylephrine\",\r\n \"去氨加压素\": \"desmopressin\",\r\n \"去甲肾上腺素\": \"norepinephrine\",\r\n \"双嘧达莫\": \"dipyridamole\",\r\n \"双盲\": \"double-blind\",\r\n \"古塞奇尤单抗\": \"guselkumab\",\r\n \"可乐定\": \"clonidine\",\r\n \"可的松\": \"cortisone\",\r\n \"司妥昔单抗\": \"siltuximab\",\r\n \"司库奇尤单抗\": \"secukinumab\",\r\n \"司来吉兰\": \"selegiline\",\r\n \"司美格鲁肽\": \"semaglutide\",\r\n \"吉西他滨\": \"gemcitabine\",\r\n \"吉非替尼\": \"gefitinib\",\r\n \"吡咯替尼\": \"pyrotinib\",\r\n \"吡贝地尔\": \"piribedil\",\r\n \"吲达帕胺\": \"indapamide\",\r\n \"呋喹替尼\": \"fruquintinib\",\r\n \"咪达普利\": \"imidapril\",\r\n \"哮喘\": \"asthma\",\r\n \"唑来膦酸\": \"zoledronic acid\",\r\n \"喹那普利\": \"quinapril\",\r\n \"嗜血细胞综合征\": \"hemophagocytic lymphohistiocytosis (HLH)\",\r\n \"嗜酸性肉芽肿性多血管炎\": \"eosinophilic granulomatosis with polyangiitis (EGPA)\",\r\n \"嗜铬细胞瘤\": \"pheochromocytoma\",\r\n \"噻托溴铵\": \"tiotropium bromide\",\r\n \"回顾性研究\": \"retrospective study\",\r\n \"地中海贫血\": \"thalassemia\",\r\n \"地塞米松\": \"dexamethasone\",\r\n \"地尔硫卓\": \"diltiazem\",\r\n \"地拉普利\": \"delapril\",\r\n \"地舒单抗\": \"denosumab\",\r\n \"地西他滨\": \"decitabine\",\r\n \"地高辛\": \"digoxin\",\r\n \"坎地沙坦酯\": \"candesartan cilexetil\",\r\n \"坎格瑞洛\": \"cangrelor\",\r\n \"垂体瘤\": \"pituitary adenoma\",\r\n \"埃克替尼\": \"icotinib\",\r\n \"培哚普利\": \"perindopril\",\r\n \"培唑帕尼\": \"pazopanib\",\r\n \"培戈洛酶\": \"pegloticase\",\r\n \"培维索肽\": \"pegvisomant\",\r\n \"培美曲塞\": \"pemetrexed\",\r\n \"基因突变\": \"gene mutation\",\r\n \"基底细胞癌\": \"basal cell carcinoma (BCC)\",\r\n \"塞尔佩替尼\": \"selpercatinib\",\r\n \"塞瑞替尼\": \"ceritinib\",\r\n \"复发\": \"recurrent\",\r\n \"外周动脉疾病\": \"peripheral artery disease (PAD)\",\r\n \"多中心\": \"multicenter\",\r\n \"多发性硬化\": \"multiple sclerosis\",\r\n \"多发性肌炎\": \"polymyositis\",\r\n \"多发性骨髓瘤\": \"multiple myeloma (MM)\",\r\n \"多囊卵巢综合征\": \"polycystic ovary syndrome (PCOS)\",\r\n \"多囊肾病\": \"polycystic kidney disease (PKD)\",\r\n \"多巴胺\": \"dopamine\",\r\n \"多巴酚丁胺\": \"dobutamine\",\r\n \"多系统萎缩\": \"multiple system atrophy (MSA)\",\r\n \"多索茶碱\": \"doxofylline\",\r\n \"多西他赛\": \"docetaxel\",\r\n \"大动脉炎\": \"Takayasu arteritis\",\r\n \"头颈鳞癌\": \"head and neck squamous cell carcinoma (HNSCC)\",\r\n \"奈必洛尔\": \"nebivolol\",\r\n \"奈拉替尼\": \"neratinib\",\r\n \"奥希替尼\": \"osimertinib\",\r\n \"奥拉帕利\": \"olaparib\",\r\n \"奥曲肽\": \"octreotide\",\r\n \"奥沙利铂\": \"oxaliplatin\",\r\n \"奥法妥木单抗\": \"ofatumumab\",\r\n \"奥瑞珠单抗\": \"ocrelizumab\",\r\n \"奥美沙坦酯\": \"olmesartan medoxomil\",\r\n \"奥达特罗\": \"olodaterol\",\r\n \"姑息\": \"palliative\",\r\n \"子宫内膜癌\": \"endometrial cancer\",\r\n \"安全性\": \"safety\",\r\n \"安慰剂\": \"placebo\",\r\n \"安罗替尼\": \"anlotinib\",\r\n \"完全缓解\": \"complete response (CR)\",\r\n \"客观缓解率\": \"objective response rate (ORR)\",\r\n \"宫颈癌\": \"cervical cancer\",\r\n \"小细胞肺癌\": \"small cell lung cancer (SCLC)\",\r\n \"尼卡地平\": \"nicardipine\",\r\n \"尼可地尔\": \"nicorandil\",\r\n \"尼拉帕利\": \"niraparib\",\r\n \"尼洛替尼\": \"nilotinib\",\r\n \"尼群地平\": \"nitrendipine\",\r\n \"尼莫地平\": \"nimodipine\",\r\n \"尿崩症\": \"diabetes insipidus\",\r\n \"尿路上皮癌\": \"urothelial carcinoma\",\r\n \"川崎病\": \"Kawasaki disease\",\r\n \"左旋多巴\": \"levodopa\",\r\n \"巨细胞动脉炎\": \"giant cell arteritis\",\r\n \"已完成\": \"completed\",\r\n \"巴尼地平\": \"barnidipine\",\r\n \"布地奈德\": \"budesonide\",\r\n \"布格替尼\": \"brigatinib\",\r\n \"布罗达单抗\": \"brodalumab\",\r\n \"布美他尼\": \"bumetanide\",\r\n \"帕博利珠单抗\": \"pembrolizumab\",\r\n \"帕博西尼\": \"palbociclib\",\r\n \"帕妥珠单抗\": \"pertuzumab\",\r\n \"帕尼单抗\": \"panitumumab\",\r\n \"帕瑞肽\": \"pasireotide\",\r\n \"帕立骨化醇\": \"paricalcitol\",\r\n \"帕米膦酸二钠\": \"pamidronate\",\r\n \"帕金森\": \"Parkinson's disease\",\r\n \"干燥综合征\": \"Sjögren syndrome\",\r\n \"幽门螺杆菌\": \"Helicobacter pylori\",\r\n \"库欣综合征\": \"Cushing syndrome\",\r\n \"度伐利尤单抗\": \"durvalumab\",\r\n \"度拉糖肽\": \"dulaglutide\",\r\n \"康柏西普\": \"conbercept\",\r\n \"开放标签\": \"open-label\",\r\n \"异丙托溴铵\": \"ipratropium bromide\",\r\n \"异丙肾上腺素\": \"isoprenaline\",\r\n \"弥漫大B细胞淋巴瘤\": \"diffuse large B-cell lymphoma (DLBCL)\",\r\n \"强直性脊柱炎\": \"ankylosing spondylitis (AS)\",\r\n \"心绞痛\": \"angina pectoris\",\r\n \"心肌梗死\": \"myocardial infarction (MI)\",\r\n \"心脏毒性\": \"cardiotoxicity\",\r\n \"心血管\": \"cardiovascular\",\r\n \"心衰\": \"heart failure\",\r\n \"急性冠脉综合征\": \"acute coronary syndrome (ACS)\",\r\n \"急性淋巴细胞白血病\": \"acute lymphoblastic leukemia (ALL)\",\r\n \"急性肾损伤\": \"acute kidney injury (AKI)\",\r\n \"急性髓系白血病\": \"acute myeloid leukemia (AML)\",\r\n \"总体生存\": \"overall survival (OS)\",\r\n \"恩他卡朋\": \"entacapone\",\r\n \"恩沙替尼\": \"ensartinib\",\r\n \"恩西地平\": \"enasidenib\",\r\n \"感染\": \"infection\",\r\n \"慢性肾病\": \"chronic kidney disease (CKD)\",\r\n \"慢性髓系白血病\": \"chronic myeloid leukemia (CML)\",\r\n \"慢阻肺\": \"COPD\",\r\n \"戈利木单抗\": \"golimumab\",\r\n \"成人Still病\": \"adult-onset Still disease (AOSD)\",\r\n \"托卡朋\": \"tolcapone\",\r\n \"托拉塞米\": \"torasemide\",\r\n \"托珠单抗\": \"tocilizumab\",\r\n \"扩增\": \"amplification\",\r\n \"抑郁症\": \"depression\",\r\n \"拉夫利珠单抗\": \"ravulizumab\",\r\n \"拉帕替尼\": \"lapatinib\",\r\n \"拉西地平\": \"lacidipine\",\r\n \"拉贝洛尔\": \"labetalol\",\r\n \"支气管扩张\": \"bronchiectasis\",\r\n \"放疗\": \"radiotherapy\",\r\n \"新冠\": \"COVID-19\",\r\n \"新辅助\": \"neoadjuvant\",\r\n \"新辅助治疗\": \"neoadjuvant therapy\",\r\n \"无性细胞瘤\": \"dysgerminoma\",\r\n \"无进展生存\": \"progression-free survival (PFS)\",\r\n \"晚期\": \"advanced\",\r\n \"普拉克索\": \"pramipexole\",\r\n \"普拉替尼\": \"pralsetinib\",\r\n \"普拉格雷\": \"prasugrel\",\r\n \"普萘洛尔\": \"propranolol\",\r\n \"曲妥珠单抗\": \"trastuzumab\",\r\n \"曲安奈德\": \"triamcinolone\",\r\n \"曲拉西利\": \"trilaciclib\",\r\n \"曲美他嗪\": \"trimetazidine\",\r\n \"替尔泊肽\": \"tirzepatide\",\r\n \"替格瑞洛\": \"ticagrelor\",\r\n \"替罗非班\": \"tirofiban\",\r\n \"替西罗莫司\": \"temsirolimus\",\r\n \"替雷利珠单抗\": \"tislelizumab\",\r\n \"来曲唑\": \"letrozole\",\r\n \"来氟米特\": \"leflunomide\",\r\n \"来那度胺\": \"lenalidomide\",\r\n \"柳氮磺吡啶\": \"sulfasalazine\",\r\n \"格拉吉布\": \"glasdegib\",\r\n \"格隆溴铵\": \"glycopyrronium bromide\",\r\n \"格非妥珠单抗\": \"glofitamab\",\r\n \"桥本甲状腺炎\": \"Hashimoto thyroiditis\",\r\n \"毒性\": \"toxicity\",\r\n \"比伐卢定\": \"bivalirudin\",\r\n \"比索洛尔\": \"bisoprolol\",\r\n \"氟尿嘧啶\": \"fluorouracil\",\r\n \"氟替卡松\": \"fluticasone\",\r\n \"氟氢可的松\": \"fludrocortisone\",\r\n \"氟维司群\": \"fulvestrant\",\r\n \"氢化可的松\": \"hydrocortisone\",\r\n \"氢氯噻嗪\": \"hydrochlorothiazide\",\r\n \"氨苯蝶啶\": \"triamterene\",\r\n \"氨茶碱\": \"aminophylline\",\r\n \"沙丁胺醇\": \"salbutamol\",\r\n \"沙利度胺\": \"thalidomide\",\r\n \"沙库巴曲缬沙坦\": \"sacubitril/valsartan\",\r\n \"沙美特罗\": \"salmeterol\",\r\n \"治疗\": \"treatment\",\r\n \"泊马度胺\": \"pomalidomide\",\r\n \"法瑞西单抗\": \"faricimab\",\r\n \"泼尼松\": \"prednisone\",\r\n \"泼尼松龙\": \"prednisolone\",\r\n \"泽布替尼\": \"zanubrutinib\",\r\n \"洛拉替尼\": \"lorlatinib\",\r\n \"洛美他派\": \"lomitapide\",\r\n \"海曲泊帕\": \"hetrombopag\",\r\n \"消化性溃疡\": \"peptic ulcer disease\",\r\n \"淋巴瘤\": \"lymphoma\",\r\n \"淋巴结\": \"lymph node\",\r\n \"淋巴结转移\": \"lymph node metastasis\",\r\n \"深静脉血栓\": \"deep vein thrombosis (DVT)\",\r\n \"溃疡性结肠炎\": \"ulcerative colitis (UC)\",\r\n \"溴隐亭\": \"bromocriptine\",\r\n \"炎症性肠病\": \"inflammatory bowel disease (IBD)\",\r\n \"特发性肺纤维化\": \"idiopathic pulmonary fibrosis (IPF)\",\r\n \"特布他林\": \"terbutaline\",\r\n \"特瑞普利单抗\": \"toripalimab\",\r\n \"特立帕肽\": \"teriparatide\",\r\n \"狼疮\": \"lupus\",\r\n \"狼疮性肾炎\": \"lupus nephritis\",\r\n \"环孢素\": \"cyclosporine\",\r\n \"班布特罗\": \"bambuterol\",\r\n \"瑞他鲁肽\": \"retatrutide\",\r\n \"瑞博西尼\": \"ribociclib\",\r\n \"瑞戈非尼\": \"regorafenib\",\r\n \"瑞普替尼\": \"repotrectinib\",\r\n \"甘油果糖\": \"glycerol fructose\",\r\n \"甘露醇\": \"mannitol\",\r\n \"生活质量\": \"quality of life (QoL)\",\r\n \"生物标志物\": \"biomarker\",\r\n \"生长抑素\": \"somatostatin\",\r\n \"生长激素\": \"growth hormone\",\r\n \"甲亢\": \"hyperthyroidism\",\r\n \"甲减\": \"hypothyroidism\",\r\n \"甲基多巴\": \"methyldopa\",\r\n \"甲氨蝶呤\": \"methotrexate\",\r\n \"甲泼尼龙\": \"methylprednisolone\",\r\n \"甲状腺功能亢进\": \"hyperthyroidism\",\r\n \"甲状腺功能减退\": \"hypothyroidism\",\r\n \"甲状腺癌\": \"thyroid cancer\",\r\n \"疫苗\": \"vaccine\",\r\n \"疾病控制率\": \"disease control rate (DCR)\",\r\n \"疾病进展\": \"disease progression\",\r\n \"病例报告\": \"case report\",\r\n \"痛风\": \"gout\",\r\n \"癫痫\": \"epilepsy\",\r\n \"白塞病\": \"Behçet disease\",\r\n \"白蛋白结合型紫杉醇\": \"nab-paclitaxel\",\r\n \"白血病\": \"leukemia\",\r\n \"皮肌炎\": \"dermatomyositis\",\r\n \"直肠癌\": \"rectal cancer\",\r\n \"真实世界数据\": \"real-world data\",\r\n \"真实世界研究\": \"real-world study\",\r\n \"真性红细胞增多症\": \"polycythemia vera\",\r\n \"短暂性脑缺血发作\": \"transient ischemic attack (TIA)\",\r\n \"硝普钠\": \"sodium nitroprusside\",\r\n \"硝苯地平\": \"nifedipine\",\r\n \"硝酸异山梨酯\": \"isosorbide dinitrate\",\r\n \"硝酸甘油\": \"nitroglycerin\",\r\n \"硫唑嘌呤\": \"azathioprine\",\r\n \"硬皮病\": \"systemic sclerosis\",\r\n \"磺达肝癸钠\": \"fondaparinux\",\r\n \"神经内分泌肿瘤\": \"neuroendocrine tumor (NET)\",\r\n \"神经母细胞瘤\": \"neuroblastoma\",\r\n \"福莫特罗\": \"formoterol\",\r\n \"福辛普利\": \"fosinopril\",\r\n \"程序性死亡受体1\": \"programmed cell death protein 1 (PD-1)\",\r\n \"程序性死亡配体1\": \"programmed death-ligand 1 (PD-L1)\",\r\n \"突变\": \"mutation\",\r\n \"米泊美生\": \"mipomersen\",\r\n \"类风湿关节炎\": \"rheumatoid arthritis\",\r\n \"精原细胞瘤\": \"seminoma\",\r\n \"糖尿病\": \"diabetes\",\r\n \"糖尿病肾病\": \"diabetic nephropathy\",\r\n \"系统性红斑狼疮\": \"systemic lupus erythematosus (SLE)\",\r\n \"系统评价\": \"systematic review\",\r\n \"索托拉西布\": \"sotorasib\",\r\n \"索拉非尼\": \"sorafenib\",\r\n \"紫杉醇\": \"paclitaxel\",\r\n \"纳武利尤单抗\": \"nivolumab\",\r\n \"纵隔\": \"mediastinum\",\r\n \"细胞治疗\": \"cell therapy\",\r\n \"经颅光生物调节\": \"transcranial photobiomodulation (tPBM)\",\r\n \"绒毛膜癌\": \"choriocarcinoma\",\r\n \"结直肠癌\": \"colorectal cancer (CRC)\",\r\n \"结肠癌\": \"colon cancer\",\r\n \"结节病\": \"sarcoidosis\",\r\n \"给药方案\": \"dosing regimen\",\r\n \"维兰特罗\": \"vilanterol\",\r\n \"维多珠单抗\": \"vedolizumab\",\r\n \"维奈克拉\": \"venetoclax\",\r\n \"维拉帕米\": \"verapamil\",\r\n \"维持治疗\": \"maintenance therapy\",\r\n \"缓解持续时间\": \"duration of response (DoR)\",\r\n \"缺失\": \"deletion\",\r\n \"缺血性卒中\": \"ischemic stroke\",\r\n \"缺铁性贫血\": \"iron deficiency anemia\",\r\n \"罕见\": \"rare\",\r\n \"罗匹尼罗\": \"ropinirole\",\r\n \"罗替戈汀\": \"rotigotine\",\r\n \"罗米司亭\": \"romiplostim\",\r\n \"罗莫佐单抗\": \"romosozumab\",\r\n \"美托洛尔\": \"metoprolol\",\r\n \"羟氯喹\": \"hydroxychloroquine\",\r\n \"群多普利\": \"trandolapril\",\r\n \"老年\": \"elderly\",\r\n \"耐药\": \"resistance\",\r\n \"联合治疗\": \"combination therapy\",\r\n \"肉芽肿性多血管炎\": \"granulomatosis with polyangiitis (GPA)\",\r\n \"肌萎缩侧索硬化\": \"amyotrophic lateral sclerosis (ALS)\",\r\n \"肝毒性\": \"hepatotoxicity\",\r\n \"肝癌\": \"liver cancer\",\r\n \"肝素\": \"heparin\",\r\n \"肝细胞癌\": \"hepatocellular carcinoma (HCC)\",\r\n \"肝转移\": \"liver metastasis\",\r\n \"肠易激综合征\": \"irritable bowel syndrome (IBS)\",\r\n \"肢端肥大症\": \"acromegaly\",\r\n \"肥胖\": \"obesity\",\r\n \"肺动脉高压\": \"pulmonary arterial hypertension (PAH)\",\r\n \"肺栓塞\": \"pulmonary embolism (PE)\",\r\n \"肺气肿\": \"pulmonary emphysema\",\r\n \"肺癌\": \"lung cancer\",\r\n \"肺腺癌\": \"lung adenocarcinoma\",\r\n \"肺转移\": \"lung metastasis\",\r\n \"肺鳞癌\": \"squamous cell lung carcinoma\",\r\n \"肾上腺素\": \"epinephrine\",\r\n \"肾毒性\": \"nephrotoxicity\",\r\n \"肾病综合征\": \"nephrotic syndrome\",\r\n \"肾癌\": \"renal cell carcinoma (RCC)\",\r\n \"肿瘤微环境\": \"tumor microenvironment\",\r\n \"胃癌\": \"gastric cancer\",\r\n \"胃肠道间质瘤\": \"gastrointestinal stromal tumor (GIST)\",\r\n \"胃食管反流病\": \"gastroesophageal reflux disease (GERD)\",\r\n \"胃食管结合部癌\": \"gastroesophageal junction cancer\",\r\n \"胆管癌\": \"cholangiocarcinoma\",\r\n \"胚胎性癌\": \"embryonal carcinoma\",\r\n \"胰腺癌\": \"pancreatic cancer\",\r\n \"胶质母细胞瘤\": \"glioblastoma (GBM)\",\r\n \"胸腺瘤\": \"thymoma\",\r\n \"胸腺癌\": \"thymic carcinoma\",\r\n \"胸膜间皮瘤\": \"malignant pleural mesothelioma\",\r\n \"脑出血\": \"intracerebral hemorrhage\",\r\n \"脑卒中\": \"stroke\",\r\n \"脑梗死\": \"cerebral infarction\",\r\n \"脑胶质瘤\": \"glioma\",\r\n \"脑转移\": \"brain metastasis\",\r\n \"腹膜\": \"peritoneum\",\r\n \"膀胱癌\": \"bladder cancer\",\r\n \"自身免疫性肝炎\": \"autoimmune hepatitis\",\r\n \"舒尼替尼\": \"sunitinib\",\r\n \"艾伏尼布\": \"ivosidenib\",\r\n \"艾塞那肽\": \"exenatide\",\r\n \"艾布他赛因\": \"epcoritamab\",\r\n \"艾曲泊帕\": \"eltrombopag\",\r\n \"艾沙妥昔单抗\": \"isatuximab\",\r\n \"艾滋病\": \"HIV\",\r\n \"芦卡帕利\": \"rucaparib\",\r\n \"苯海索\": \"trihexyphenidyl\",\r\n \"英夫利西单抗\": \"infliximab\",\r\n \"茚达特罗\": \"indacaterol\",\r\n \"茶碱\": \"theophylline\",\r\n \"荟萃分析\": \"meta-analysis\",\r\n \"莫妥珠单抗\": \"mosunetuzumab\",\r\n \"莫米松\": \"mometasone\",\r\n \"获得性耐药\": \"acquired resistance\",\r\n \"蛛网膜下腔出血\": \"subarachnoid hemorrhage\",\r\n \"融合\": \"fusion\",\r\n \"螺普利\": \"spirapril\",\r\n \"血友病\": \"hemophilia\",\r\n \"血栓性血小板减少性紫癜\": \"thrombotic thrombocytopenic purpura (TTP)\",\r\n \"血管性痴呆\": \"vascular dementia\",\r\n \"血管性血友病\": \"von Willebrand disease\",\r\n \"血管生成\": \"angiogenesis\",\r\n \"表皮生长因子受体\": \"epidermal growth factor receptor (EGFR)\",\r\n \"西妥昔单抗\": \"cetuximab\",\r\n \"西尼地平\": \"cilnidipine\",\r\n \"西拉普利\": \"cilazapril\",\r\n \"西洛他唑\": \"cilostazol\",\r\n \"西米普利单抗\": \"cemiplimab\",\r\n \"西罗莫司\": \"sirolimus\",\r\n \"西那卡塞\": \"cinacalcet\",\r\n \"贝伐珠单抗\": \"bevacizumab\",\r\n \"贝尼地平\": \"benidipine\",\r\n \"贝西罗司\": \"belzutifan\",\r\n \"贝那普利\": \"benazepril\",\r\n \"贫血\": \"anemia\",\r\n \"赖诺普利\": \"lisinopril\",\r\n \"赛妥珠单抗\": \"certolizumab pegol\",\r\n \"路易体痴呆\": \"Lewy body dementia\",\r\n \"转移\": \"metastasis\",\r\n \"转移性\": \"metastatic\",\r\n \"软组织肉瘤\": \"soft tissue sarcoma\",\r\n \"辅助\": \"adjuvant\",\r\n \"辅助治疗\": \"adjuvant therapy\",\r\n \"达可替尼\": \"dacomitinib\",\r\n \"达尔西利\": \"dalpiciclib\",\r\n \"达比加群酯\": \"dabigatran\",\r\n \"达沙替尼\": \"dasatinib\",\r\n \"达雷妥尤单抗\": \"daratumumab\",\r\n \"过表达\": \"overexpression\",\r\n \"近红外光生物调节\": \"near-infrared photobiomodulation\",\r\n \"进行中\": \"recruiting\",\r\n \"进行性核上性麻痹\": \"progressive supranuclear palsy (PSP)\",\r\n \"那他珠单抗\": \"natalizumab\",\r\n \"部分缓解\": \"partial response (PR)\",\r\n \"醋酸去氨加压素\": \"desmopressin acetate\",\r\n \"重症肌无力\": \"myasthenia gravis (MG)\",\r\n \"金刚烷胺\": \"amantadine\",\r\n \"银屑病\": \"psoriasis\",\r\n \"银屑病关节炎\": \"psoriatic arthritis\",\r\n \"长春瑞滨\": \"vinorelbine\",\r\n \"间变性淋巴瘤激酶\": \"anaplastic lymphoma kinase (ALK)\",\r\n \"间羟胺\": \"metaraminol\",\r\n \"间质性肺疾病\": \"interstitial lung disease (ILD)\",\r\n \"间质性肺病\": \"interstitial lung disease (ILD)\",\r\n \"队列研究\": \"cohort study\",\r\n \"阵发性睡眠性血红蛋白尿\": \"paroxysmal nocturnal hemoglobinuria (PNH)\",\r\n \"阻塞性睡眠呼吸暂停\": \"obstructive sleep apnea (OSA)\",\r\n \"阿仑单抗\": \"alemtuzumab\",\r\n \"阿仑膦酸钠\": \"alendronate\",\r\n \"阿伐曲泊帕\": \"avatrombopag\",\r\n \"阿利吉仑\": \"aliskiren\",\r\n \"阿利沙坦酯\": \"allisartan\",\r\n \"阿利西尤单抗\": \"alirocumab\",\r\n \"阿加曲班\": \"argatroban\",\r\n \"阿哌沙班\": \"apixaban\",\r\n \"阿地溴铵\": \"aclidinium bromide\",\r\n \"阿尔茨海默病\": \"Alzheimer's disease\",\r\n \"阿巴洛肽\": \"abaloparatide\",\r\n \"阿巴西普\": \"abatacept\",\r\n \"阿帕替尼\": \"apatinib\",\r\n \"阿扎胞苷\": \"azacitidine\",\r\n \"阿昔替尼\": \"axitinib\",\r\n \"阿替利珠单抗\": \"atezolizumab\",\r\n \"阿来替尼\": \"alectinib\",\r\n \"阿柏西普\": \"aflibercept\",\r\n \"阿格拉西布\": \"adagrasib\",\r\n \"阿法替尼\": \"afatinib\",\r\n \"阿法骨化醇\": \"alfacalcidol\",\r\n \"阿米洛利\": \"amiloride\",\r\n \"阿维鲁单抗\": \"avelumab\",\r\n \"阿罗洛尔\": \"arotinolol\",\r\n \"阿美替尼\": \"almonertinib\",\r\n \"阿贝西利\": \"abemaciclib\",\r\n \"阿达木单抗\": \"adalimumab\",\r\n \"阿那曲唑\": \"anastrozole\",\r\n \"阿那白滞素\": \"anakinra\",\r\n \"阿齐沙坦\": \"azilsartan\",\r\n \"降钙素\": \"calcitonin\",\r\n \"随机\": \"randomized\",\r\n \"随机对照试验\": \"randomized controlled trial (RCT)\",\r\n \"难治\": \"refractory\",\r\n \"雷沙吉兰\": \"rasagiline\",\r\n \"雷珠单抗\": \"ranibizumab\",\r\n \"雷米普利\": \"ramipril\",\r\n \"雷诺嗪\": \"ranolazine\",\r\n \"霉酚酸酯\": \"mycophenolate mofetil\",\r\n \"霍奇金淋巴瘤\": \"Hodgkin lymphoma\",\r\n \"静脉血栓栓塞\": \"venous thromboembolism (VTE)\",\r\n \"非小细胞肺癌\": \"non-small cell lung cancer (NSCLC)\",\r\n \"非洛地平\": \"felodipine\",\r\n \"非诺特罗\": \"fenoterol\",\r\n \"非酒精性脂肪性肝炎\": \"non-alcoholic steatohepatitis (NASH)\",\r\n \"非酒精性脂肪性肝病\": \"non-alcoholic fatty liver disease (NAFLD)\",\r\n \"非霍奇金淋巴瘤\": \"non-Hodgkin lymphoma (NHL)\",\r\n \"非马沙坦\": \"fimasartan\",\r\n \"面肌痉挛\": \"hemifacial spasm\",\r\n \"靶向治疗\": \"targeted therapy\",\r\n \"顺铂\": \"cisplatin\",\r\n \"额颞叶痴呆\": \"frontotemporal dementia\",\r\n \"风湿性多肌痛\": \"polymyalgia rheumatica\",\r\n \"食管癌\": \"esophageal cancer\",\r\n \"马尼地平\": \"manidipine\",\r\n \"骨化三醇\": \"calcitriol\",\r\n \"骨肉瘤\": \"osteosarcoma\",\r\n \"骨转移\": \"bone metastasis\",\r\n \"骨髓增殖性肿瘤\": \"myeloproliferative neoplasm (MPN)\",\r\n \"骨髓增生异常综合征\": \"myelodysplastic syndrome (MDS)\",\r\n \"骨髓纤维化\": \"myelofibrosis\",\r\n \"高尿酸血症\": \"hyperuricemia\",\r\n \"高血压\": \"hypertension\",\r\n \"鲑鱼降钙素\": \"salmon calcitonin\",\r\n \"麻黄碱\": \"ephedrine\",\r\n \"黑色素瘤\": \"melanoma\",\r\n \"默克尔细胞癌\": \"Merkel cell carcinoma\",\r\n \"鼻咽癌\": \"nasopharyngeal carcinoma (NPC)\"\r\n}\n\nFile v1.3.0:scripts/i18n_messages.json\n\n{\r\n \"dry_run.not_executed\": {\r\n \"en\": \"[DRY RUN — code not executed. Remove --dry-run to execute.]\",\r\n \"zh\": \"[DRY RUN — 代码未执行。去掉 --dry-run 以执行。]\"\r\n },\r\n \"safe_preview.not_executed\": {\r\n \"en\": \"[SAFE PREVIEW] R code was NOT executed. Re-run with --yes to compute the result.\",\r\n \"zh\": \"[安全预览] R 代码未执行。追加 --yes 重新运行以计算结果。]\"\r\n },\r\n \"exec.running\": {\r\n \"en\": \"[EXECUTING R CODE...]\",\r\n \"zh\": \"[正在执行 R 代码...]\"\r\n },\r\n \"info.r_code_shown_default\": {\r\n \"en\": \"[INFO] R code is shown by default in preview mode. Re-run with --show-code while using --yes to also display it during execution.\",\r\n \"zh\": \"[提示] 预览模式默认展示 R 代码。执行时追加 --show-code 可同时查看代码。]\"\r\n },\r\n \"info.result_saved\": {\r\n \"en\": \"Result JSON saved to: {path}\",\r\n \"zh\": \"结果 JSON 已保存至：{path}\"\r\n },\r\n \"info.png_saved\": {\r\n \"en\": \"PNG saved to: {path}\",\r\n \"zh\": \"PNG 已保存至：{path}\"\r\n },\r\n \"error.exec_failed\": {\r\n \"en\": \"[ERROR] Execution failed: {name}\",\r\n \"zh\": \"[错误] 执行失败：{name}\"\r\n },\r\n \"error.generic\": {\r\n \"en\": \"ERROR: {msg}\",\r\n \"zh\": \"错误：{msg}\"\r\n },\r\n \"error.val_err\": {\r\n \"en\": \"ERROR: {msg}\",\r\n \"zh\": \"错误：{msg}\"\r\n },\r\n \"validation.failed\": {\r\n \"en\": \"Parameter validation failed:\",\r\n \"zh\": \"参数校验失败：\"\r\n },\r\n \"validation.range_error_gt\": {\r\n \"en\": \"--{label} must be > {bound} (got {val})\",\r\n \"zh\": \"--{label} 必须 > {bound}（当前值 {val}）\"\r\n },\r\n \"validation.range_error_lt\": {\r\n \"en\": \"--{label} must be < {bound} (got {val})\",\r\n \"zh\": \"--{label} 必须 < {bound}（当前值 {val}）\"\r\n },\r\n \"xlsx.sheet.readme\": {\r\n \"en\": \"README\",\r\n \"zh\": \"说明\"\r\n },\r\n \"xlsx.sheet.summary\": {\r\n \"en\": \"Search Results Summary\",\r\n \"zh\": \"检索结果概要\"\r\n },\r\n \"xlsx.sheet.master\": {\r\n \"en\": \"Trial Master Table\",\r\n \"zh\": \"试验总表\"\r\n },\r\n \"xlsx.sheet.raw\": {\r\n \"en\": \"Raw Details\",\r\n \"zh\": \"原始明细\"\r\n },\r\n \"xlsx.banner.title\": {\r\n \"en\": \"Clinical Trial Search Report\",\r\n \"zh\": \"临床试验检索报告\"\r\n },\r\n \"xlsx.banner.summary\": {\r\n \"en\": \"Clinical Trial Search Results Summary\",\r\n \"zh\": \"临床试验检索结果概要\"\r\n },\r\n \"xlsx.banner.master\": {\r\n \"en\": \"Clinical Trial Master Table\",\r\n \"zh\": \"临床试验明细总表\"\r\n },\r\n \"xlsx.banner.raw\": {\r\n \"en\": \"Raw Details (normalized field snapshot)\",\r\n \"zh\": \"原始明细（归一化字段快照）\"\r\n },\r\n \"xlsx.cover.topic\": {\r\n \"en\": \"Search topic: \",\r\n \"zh\": \"检索主题：\"\r\n },\r\n \"xlsx.cover.generated\": {\r\n \"en\": \"This workbook was auto-generated by ct-registry; a single file, readable offline.\",\r\n \"zh\": \"本工作簿由 ct-registry 自动生成，单文件离线可读。\"\r\n },\r\n \"xlsx.kpi.total\": {\r\n \"en\": \"Total Trials\",\r\n \"zh\": \"总试验数\"\r\n },\r\n \"xlsx.kpi.total_sub\": {\r\n \"en\": \"selected projects\",\r\n \"zh\": \"条入选项目\"\r\n },\r\n \"xlsx.kpi.who\": {\r\n \"en\": \"WHO ICTRP\",\r\n \"zh\": \"WHO ICTRP\"\r\n },\r\n \"xlsx.kpi.who_sub\": {\r\n \"en\": \"global mirror registry\",\r\n \"zh\": \"全球镜像库\"\r\n },\r\n \"xlsx.kpi.cde\": {\r\n \"en\": \"China CDE\",\r\n \"zh\": \"中国 CDE\"\r\n },\r\n \"xlsx.kpi.cde_sub\": {\r\n \"en\": \"official drug registry\",\r\n \"zh\": \"官方药品库\"\r\n },\r\n \"xlsx.kpi.span\": {\r\n \"en\": \"Registration Year Span\",\r\n \"zh\": \"注册年份跨度\"\r\n },\r\n \"xlsx.kpi.span_sub\": {\r\n \"en\": \"first public listing year\",\r\n \"zh\": \"首次公示年份\"\r\n },\r\n \"xlsx.readme.scope_title\": {\r\n \"en\": \"Search Overview\",\r\n \"zh\": \"检索概览\"\r\n },\r\n \"xlsx.scope.topic\": {\r\n \"en\": \"Search topic\",\r\n \"zh\": \"检索主题\"\r\n },\r\n \"xlsx.scope.range\": {\r\n \"en\": \"Search scope\",\r\n \"zh\": \"检索范围\"\r\n },\r\n \"xlsx.scope.range_val\": {\r\n \"en\": \"WHO ICTRP (global mirror of 14+ primary registries) + China CDE\",\r\n \"zh\": \"WHO ICTRP（全球镜像 14+ 一级注册库）+ 中国 CDE\"\r\n },\r\n \"xlsx.scope.source\": {\r\n \"en\": \"Data source\",\r\n \"zh\": \"数据来源\"\r\n },\r\n \"xlsx.scope.source_val\": {\r\n \"en\": \"WHO ICTRP detail API (via unified endpoint); CDE drug trial registry platform\",\r\n \"zh\": \"WHO ICTRP 详情接口（经统一端点）；CDE 药物临床试验登记平台\"\r\n },\r\n \"xlsx.scope.quota\": {\r\n \"en\": \"Quota note\",\r\n \"zh\": \"配额说明\"\r\n },\r\n \"xlsx.scope.quota_val\": {\r\n \"en\": \"Free to use; to conserve shared resources, the daily cap is 10 demands (counted by demand_id). See README.\",\r\n \"zh\": \"当前免费使用；为充分利用共享资源，每日上限 10 个需求（按 demand_id 计），详见 README\"\r\n },\r\n \"xlsx.readme.field_title\": {\r\n \"en\": \"Field Dictionary\",\r\n \"zh\": \"字段说明\"\r\n },\r\n \"xlsx.field.col\": {\r\n \"en\": \"Field\",\r\n \"zh\": \"字段\"\r\n },\r\n \"xlsx.field.meaning\": {\r\n \"en\": \"Meaning\",\r\n \"zh\": \"含义\"\r\n },\r\n \"xlsx.field.registry_id\": {\r\n \"en\": \"Registry ID\",\r\n \"zh\": \"登记号\"\r\n },\r\n \"xlsx.field.registry_id_desc\": {\r\n \"en\": \"Unique ID per registry (NCT / ChiCTR / DRKS / CTIS / jRCT / ACTRN, etc.)\",\r\n \"zh\": \"各注册库唯一编号（NCT / ChiCTR / DRKS / CTIS / jRCT / ACTRN 等）\"\r\n },\r\n \"xlsx.field.source\": {\r\n \"en\": \"Source\",\r\n \"zh\": \"数据来源\"\r\n },\r\n \"xlsx.field.conditions\": {\r\n \"en\": \"Conditions\",\r\n \"zh\": \"适应症\"\r\n },\r\n \"xlsx.field.conditions_desc\": {\r\n \"en\": \"Health condition(s)\",\r\n \"zh\": \"Health condition(s) / 健康状况\"\r\n },\r\n \"xlsx.field.study_type\": {\r\n \"en\": \"Study Type\",\r\n \"zh\": \"研究类型\"\r\n },\r\n \"xlsx.field.study_type_desc\": {\r\n \"en\": \"Study type (Observational / Interventional, etc.)\",\r\n \"zh\": \"Study type（Observational / Interventional 等）\"\r\n },\r\n \"xlsx.field.phase\": {\r\n \"en\": \"Phase\",\r\n \"zh\": \"分期\"\r\n },\r\n \"xlsx.field.phase_desc\": {\r\n \"en\": \"Phase (some observational studies have no phase)\",\r\n \"zh\": \"Phase（部分观察性研究无分期）\"\r\n },\r\n \"xlsx.field.enrollment\": {\r\n \"en\": \"Enrollment\",\r\n \"zh\": \"样本量\"\r\n },\r\n \"xlsx.field.enrollment_desc\": {\r\n \"en\": \"Target sample size / actual total enrolled\",\r\n \"zh\": \"Target sample size / 实际入组总人数\"\r\n },\r\n \"xlsx.field.status\": {\r\n \"en\": \"Status\",\r\n \"zh\": \"状态\"\r\n },\r\n \"xlsx.field.status_desc\": {\r\n \"en\": \"Recruitment status (Recruiting / Completed, etc.; colour-coded in the master table)\",\r\n \"zh\": \"Recruitment status（招募中 / 已完成 等，颜色编码见总表）\"\r\n },\r\n \"xlsx.field.sponsor\": {\r\n \"en\": \"Sponsor\",\r\n \"zh\": \"申办方\"\r\n },\r\n \"xlsx.field.sponsor_desc\": {\r\n \"en\": \"Primary sponsor / applicant name\",\r\n \"zh\": \"Primary sponsor / 申请人名称\"\r\n },\r\n \"xlsx.field.countries\": {\r\n \"en\": \"Countries\",\r\n \"zh\": \"国家\"\r\n },\r\n \"xlsx.field.countries_desc\": {\r\n \"en\": \"Countries of recruitment (CDE is always China)\",\r\n \"zh\": \"Countries of recruitment（CDE 恒为 China）\"\r\n },\r\n \"xlsx.field.start_date\": {\r\n \"en\": \"Registration Date\",\r\n \"zh\": \"注册日期\"\r\n },\r\n \"xlsx.field.start_date_desc\": {\r\n \"en\": \"Date of registration / first public listing\",\r\n \"zh\": \"Date of registration / 首次公示信息日期\"\r\n },\r\n \"xlsx.field.primary_outcome\": {\r\n \"en\": \"Primary Outcome\",\r\n \"zh\": \"主要终点\"\r\n },\r\n \"xlsx.field.primary_outcome_desc\": {\r\n \"en\": \"Primary Outcome(s)\",\r\n \"zh\": \"Primary Outcome(s)\"\r\n },\r\n \"xlsx.field.title\": {\r\n \"en\": \"Title\",\r\n \"zh\": \"标题\"\r\n },\r\n \"xlsx.field.url\": {\r\n \"en\": \"Homepage\",\r\n \"zh\": \"首页链接\"\r\n },\r\n \"xlsx.field.url_desc\": {\r\n \"en\": \"Click to open each registry's official page (blue underline)\",\r\n \"zh\": \"点击直达各注册库官方页面（蓝色下划线）\"\r\n },\r\n \"xlsx.field.interventions\": {\r\n \"en\": \"Interventions\",\r\n \"zh\": \"干预措施\"\r\n },\r\n \"xlsx.field.secondary_outcome\": {\r\n \"en\": \"Secondary Outcome\",\r\n \"zh\": \"次要终点\"\r\n },\r\n \"xlsx.field.inclusion\": {\r\n \"en\": \"Inclusion Criteria\",\r\n \"zh\": \"入选标准\"\r\n },\r\n \"xlsx.field.exclusion\": {\r\n \"en\": \"Exclusion Criteria\",\r\n \"zh\": \"排除标准\"\r\n },\r\n \"xlsx.field.comparator\": {\r\n \"en\": \"Comparator\",\r\n \"zh\": \"对照药\"\r\n },\r\n \"xlsx.field.age_min\": {\r\n \"en\": \"Min Age\",\r\n \"zh\": \"最小年龄\"\r\n },\r\n \"xlsx.field.age_max\": {\r\n \"en\": \"Max Age\",\r\n \"zh\": \"最大年龄\"\r\n },\r\n \"xlsx.field.gender\": {\r\n \"en\": \"Gender\",\r\n \"zh\": \"性别\"\r\n },\r\n \"xlsx.col.count\": {\r\n \"en\": \"Count\",\r\n \"zh\": \"试验数\"\r\n },\r\n \"xlsx.col.share\": {\r\n \"en\": \"Share\",\r\n \"zh\": \"占比\"\r\n },\r\n \"xlsx.col.metric\": {\r\n \"en\": \"Metric\",\r\n \"zh\": \"指标\"\r\n },\r\n \"xlsx.col.value\": {\r\n \"en\": \"Value\",\r\n \"zh\": \"数值\"\r\n },\r\n \"xlsx.col.enroll_band\": {\r\n \"en\": \"Enrollment Band\",\r\n \"zh\": \"样本量区间\"\r\n },\r\n \"xlsx.col.category\": {\r\n \"en\": \"Category\",\r\n \"zh\": \"分类\"\r\n },\r\n \"xlsx.total\": {\r\n \"en\": \"Total\",\r\n \"zh\": \"合计\"\r\n },\r\n \"xlsx.unknown\": {\r\n \"en\": \"(unknown)\",\r\n \"zh\": \"(未知)\"\r\n },\r\n \"xlsx.no_data\": {\r\n \"en\": \"(no data)\",\r\n \"zh\": \"(无数据)\"\r\n },\r\n \"xlsx.block.phase\": {\r\n \"en\": \"1. Phase Distribution\",\r\n \"zh\": \"一、分期分布\"\r\n },\r\n \"xlsx.block.status\": {\r\n \"en\": \"2. Recruitment Status\",\r\n \"zh\": \"二、招募状态分布\"\r\n },\r\n \"xlsx.block.source\": {\r\n \"en\": \"3. Data Source\",\r\n \"zh\": \"三、数据来源分布\"\r\n },\r\n \"xlsx.block.ind\": {\r\n \"en\": \"4. Conditions (Top 12)\",\r\n \"zh\": \"四、适应症分布 (Top 12)\"\r\n },\r\n \"xlsx.block.countries\": {\r\n \"en\": \"5. Recruitment Countries/Regions (Top 12)\",\r\n \"zh\": \"五、招募国家/地区分布 (Top 12)\"\r\n },\r\n \"xlsx.block.timeline\": {\r\n \"en\": \"6. Registration Trend by Year\",\r\n \"zh\": \"六、逐年注册趋势\"\r\n },\r\n \"xlsx.block.sponsor\": {\r\n \"en\": \"7. Sponsors (Top 15)\",\r\n \"zh\": \"七、申办方分布 (Top 15)\"\r\n },\r\n \"xlsx.block.enrollment\": {\r\n \"en\": \"8. Enrollment Summary\",\r\n \"zh\": \"八、样本量汇总\"\r\n },\r\n \"xlsx.block.phase_status\": {\r\n \"en\": \"9. Phase × Status Cross-tab\",\r\n \"zh\": \"九、分期 × 状态 交叉分布\"\r\n },\r\n \"xlsx.label.phase\": {\r\n \"en\": \"Phase\",\r\n \"zh\": \"分期\"\r\n },\r\n \"xlsx.label.status\": {\r\n \"en\": \"Status\",\r\n \"zh\": \"状态\"\r\n },\r\n \"xlsx.label.source\": {\r\n \"en\": \"Data Source\",\r\n \"zh\": \"数据来源\"\r\n },\r\n \"xlsx.label.ind\": {\r\n \"en\": \"Conditions\",\r\n \"zh\": \"适应症\"\r\n },\r\n \"xlsx.label.countries\": {\r\n \"en\": \"Countries/Regions\",\r\n \"zh\": \"国家/地区\"\r\n },\r\n \"xlsx.label.timeline\": {\r\n \"en\": \"Registration Year\",\r\n \"zh\": \"注册年份\"\r\n },\r\n \"xlsx.label.sponsor\": {\r\n \"en\": \"Sponsor\",\r\n \"zh\": \"申办方\"\r\n },\r\n \"xlsx.label.enrollment\": {\r\n \"en\": \"Enrollment\",\r\n \"zh\": \"样本量\"\r\n },\r\n \"xlsx.label.phase_status\": {\r\n \"en\": \"Phase＼Status\",\r\n \"zh\": \"分期＼状态\"\r\n },\r\n \"xlsx.note.status_color\": {\r\n \"en\": \"Colour matches the master-table status coding\",\r\n \"zh\": \"颜色与总表状态编码一致\"\r\n },\r\n \"xlsx.note.source\": {\r\n \"en\": \"WHO ICTRP (global mirror) vs China CDE\",\r\n \"zh\": \"WHO ICTRP（全球镜像）vs 中国 CDE\"\r\n },\r\n \"xlsx.note.top12\": {\r\n \"en\": \"Top 12 only\",\r\n \"zh\": \"仅显示前 12 位\"\r\n },\r\n \"xlsx.note.top12_cde\": {\r\n \"en\": \"Top 12 only; CDE is always China\",\r\n \"zh\": \"仅显示前 12 位；CDE 恒为 China\"\r\n },\r\n \"xlsx.note.top15\": {\r\n \"en\": \"Top 15 only\",\r\n \"zh\": \"仅显示前 15 位\"\r\n },\r\n \"xlsx.note.enroll\": {\r\n \"en\": \"Target / actual enrollment statistics\",\r\n \"zh\": \"目标/实际入组人数统计\"\r\n },\r\n \"xlsx.note.crosstab\": {\r\n \"en\": \"Row totals in the last column; the colour scale shows counts\",\r\n \"zh\": \"每行合计见末列；色阶表示数量\"\r\n },\r\n \"xlsx.stat.n\": {\r\n \"en\": \"Trials with data\",\r\n \"zh\": \"有数据试验数\"\r\n },\r\n \"xlsx.stat.total\": {\r\n \"en\": \"Total enrollment\",\r\n \"zh\": \"总样本量\"\r\n },\r\n \"xlsx.stat.median\": {\r\n \"en\": \"Median enrollment\",\r\n \"zh\": \"中位样本量\"\r\n },\r\n \"xlsx.stat.mean\": {\r\n \"en\": \"Mean enrollment\",\r\n \"zh\": \"平均样本量\"\r\n },\r\n \"xlsx.stat.min\": {\r\n \"en\": \"Min enrollment\",\r\n \"zh\": \"最小样本量\"\r\n },\r\n \"xlsx.stat.max\": {\r\n \"en\": \"Max enrollment\",\r\n \"zh\": \"最大样本量\"\r\n },\r\n \"xlsx.chart.enroll_hist\": {\r\n \"en\": \"Enrollment Band Distribution\",\r\n \"zh\": \"样本量区间分布\"\r\n },\r\n \"xlsx.doc.title\": {\r\n \"en\": \"Clinical Trial Search Results\",\r\n \"zh\": \"临床试验检索结果\"\r\n },\r\n \"xlsx.footer\": {\r\n \"en\": \"Page &P of &N · Generated &D\",\r\n \"zh\": \"第 &P 页 / 共 &N 页 · 生成于 &D\"\r\n },\r\n \"xlsx.summary.intro\": {\r\n \"en\": \"The tables and charts below are auto-aggregated from the search results: each section shows a distribution table on the left and its chart on the right; the share column carries a data bar, so distributions and trends are grasped at a glance. Extended dimensions include data source, country/region, enrollment and phase×status.\",\r\n \"zh\": \"下列数据表与图表由检索结果自动汇总生成：每个分区左侧为分布数据表、右侧为对应统计图；占比列带数据条，便于一眼掌握分布与趋势。含「数据来源 / 国家地区 / 样本量 / 分期×状态」等扩展维度。\"\r\n },\r\n \"xlsx.caveat.text\": {\r\n \"en\": \"Data caveats: ① If a CDE search returns empty in both Chinese and English, it means the drug has no China drug registration; ② some WHO records lack study type / phase — a source-coverage issue; ③ primary/secondary outcomes and inclusion/exclusion criteria are preserved verbatim, not translated; ④ the WHO advanced-search Phases field is narrow, so phase is verified against the normalized detail.\",\r\n \"zh\": \"数据局限：① CDE 经中英双检索为空时表示该药暂无中国药物登记；② 部分 WHO 记录缺研究类型/分期的，属源数据覆盖问题；③ 主要/次要终点与入排标准原文保留，未做翻译；④ WHO 高级检索 Phases 归一化字段较窄，分期以详情归一化复核为准。\"\r\n },\r\n \"xlsx.legend.title\": {\r\n \"en\": \"Status Colour Legend\",\r\n \"zh\": \"状态颜色图例\"\r\n },\r\n \"xlsx.legend.notyet\": {\r\n \"en\": \"Not yet recruiting\",\r\n \"zh\": \"尚未招募\"\r\n },\r\n \"xlsx.legend.recruiting\": {\r\n \"en\": \"Recruiting\",\r\n \"zh\": \"招募中\"\r\n },\r\n \"xlsx.legend.inprogress\": {\r\n \"en\": \"Ongoing / In progress\",\r\n \"zh\": \"进行中\"\r\n },\r\n \"xlsx.legend.completed\": {\r\n \"en\": \"Completed\",\r\n \"zh\": \"已完成\"\r\n },\r\n \"xlsx.legend.stopped\": {\r\n \"en\": \"Withdrawn / Terminated / Suspended\",\r\n \"zh\": \"撤回 / 终止 / 暂停\"\r\n },\r\n \"xlsx.legend.unknown\": {\r\n \"en\": \"Unknown / Pending\",\r\n \"zh\": \"未知 / 待定\"\r\n },\r\n \"xlsx.safety.doc_title\": {\r\n \"en\": \"FAERS Adverse Event Report\",\r\n \"zh\": \"FAERS 不良事件报告\"\r\n },\r\n \"xlsx.safety.banner\": {\r\n \"en\": \"FAERS Adverse Event Search Report\",\r\n \"zh\": \"FAERS 不良事件检索报告\"\r\n },\r\n \"xlsx.safety.cover.generated\": {\r\n \"en\": \"Auto-generated by ct-safety from openFDA FAERS public data (drug/event.json). Single file, readable offline.\",\r\n \"zh\": \"由 ct-safety 基于 openFDA FAERS 公开数据（drug/event.json）自动生成，单文件离线可读。\"\r\n },\r\n \"xlsx.safety.watermark\": {\r\n \"en\": \"ct-safety\",\r\n \"zh\": \"ct-safety\"\r\n },\r\n \"xlsx.safety.scope.source\": {\r\n \"en\": \"Data source\",\r\n \"zh\": \"数据来源\"\r\n },\r\n \"xlsx.safety.scope.source_val\": {\r\n \"en\": \"openFDA FAERS (FDA Adverse Event Reporting System) public API\",\r\n \"zh\": \"openFDA FAERS（FDA 不良事件报告系统）公开 API\"\r\n },\r\n \"xlsx.safety.scope.drug\": {\r\n \"en\": \"Drug / medicinal product\",\r\n \"zh\": \"药物 / 药品\"\r\n },\r\n \"xlsx.safety.scope.field\": {\r\n \"en\": \"Search field\",\r\n \"zh\": \"检索字段\"\r\n },\r\n \"xlsx.safety.scope.date\": {\r\n \"en\": \"Date filter (receivedate)\",\r\n \"zh\": \"日期筛选（报告接收日）\"\r\n },\r\n \"xlsx.safety.scope.total\": {\r\n \"en\": \"Total matching reports\",\r\n \"zh\": \"匹配报告总数\"\r\n },\r\n \"xlsx.safety.scope.downloaded\": {\r\n \"en\": \"Downloaded (first N)\",\r\n \"zh\": \"已下载（API 返回顺序前 N 条）\"\r\n },\r\n \"xlsx.safety.scope.downloaded_fast\": {\r\n \"en\": \"count mode — full matched population (no case download)\",\r\n \"zh\": \"count 模式 — 全量匹配报告（未下载逐条个案）\"\r\n },\r\n \"xlsx.safety.scope.mode\": {\r\n \"en\": \"Mode\",\r\n \"zh\": \"分析模式\"\r\n },\r\n \"xlsx.safety.mode_fast\": {\r\n \"en\": \"count-facet fast fetch (full matched population, seconds)\",\r\n \"zh\": \"count 分面快取（全量匹配报告，秒级生成）\"\r\n },\r\n \"xlsx.safety.scope.cap\": {\r\n \"en\": \"Hard cap\",\r\n \"zh\": \"硬上限\"\r\n },\r\n \"xlsx.safety.caveat\": {\r\n \"en\": \"Data caveats: ① Reports are the FIRST N in API return order — NOT a random sample; do not treat proportions as population estimates. ② FAERS is spontaneous reporting, subject to under-reporting and confounding. ③ Age uses mixed units (YR/MON/WK/DY/HR); normalized to years before binning. ④ Reaction / indication / drug-role text is split from semicolon-joined fields and counted verbatim.\",\r\n \"zh\": \"数据局限：① 下载为 API 返回顺序前 N 条，非随机抽样，比例不可当作总体估计；② FAERS 为自发呈报，存在漏报与混杂偏倚；③ 年龄单位混杂（年/月/周/天/时），分箱前已统一折算为岁；④ 反应/指征/药物角色由分号拼接字段拆分后原文计数。\"\r\n },\r\n \"xlsx.safety.kpi.downloaded\": {\r\n \"en\": \"Downloaded\",\r\n \"zh\": \"已下载\"\r\n },\r\n \"xlsx.safety.kpi.downloaded_sub\": {\r\n \"en\": \"reports (cap 10000)\",\r\n \"zh\": \"条（上限10000）\"\r\n },\r\n \"xlsx.safety.kpi.total\": {\r\n \"en\": \"Total Matching\",\r\n \"zh\": \"匹配总数\"\r\n },\r\n \"xlsx.safety.kpi.total_sub\": {\r\n \"en\": \"in FAERS\",\r\n \"zh\": \"条（全库）\"\r\n },\r\n \"xlsx.safety.kpi.serious\": {\r\n \"en\": \"Serious\",\r\n \"zh\": \"严重报告\"\r\n },\r\n \"xlsx.safety.kpi.serious_sub\": {\r\n \"en\": \"count\",\r\n \"zh\": \"条\"\r\n },\r\n \"xlsx.safety.kpi.serious_rate\": {\r\n \"en\": \"Serious Rate\",\r\n \"zh\": \"严重率\"\r\n },\r\n \"xlsx.safety.kpi.serious_rate_sub\": {\r\n \"en\": \"serious / total\",\r\n \"zh\": \"严重/总计\"\r\n },\r\n \"xlsx.safety.kpi.male\": {\r\n \"en\": \"Male\",\r\n \"zh\": \"男性\"\r\n },\r\n \"xlsx.safety.kpi.female\": {\r\n \"en\": \"Female\",\r\n \"zh\": \"女性\"\r\n },\r\n \"xlsx.safety.kpi.median_age\": {\r\n \"en\": \"Median Age\",\r\n \"zh\": \"中位年龄\"\r\n },\r\n \"xlsx.safety.kpi.median_age_sub\": {\r\n \"en\": \"years (normalized)\",\r\n \"zh\": \"岁（已折算）\"\r\n },\r\n \"xlsx.safety.kpi.year_span\": {\r\n \"en\": \"Report Year Span\",\r\n \"zh\": \"报告年份跨度\"\r\n },\r\n \"xlsx.safety.kpi.year_span_sub\": {\r\n \"en\": \"first – last\",\r\n \"zh\": \"首 – 末\"\r\n },\r\n \"xlsx.safety.kpi.population\": {\r\n \"en\": \"Analyzed Population\",\r\n \"zh\": \"分析基数\"\r\n },\r\n \"xlsx.safety.kpi.population_sub\": {\r\n \"en\": \"all matching reports (count)\",\r\n \"zh\": \"全部匹配报告（count）\"\r\n },\r\n \"xlsx.safety.block.serious\": {\r\n \"en\": \"1. Seriousness\",\r\n \"zh\": \"一、严重性分布\"\r\n },\r\n \"xlsx.safety.block.sex\": {\r\n \"en\": \"2. Sex\",\r\n \"zh\": \"二、性别分布\"\r\n },\r\n \"xlsx.safety.block.report_type\": {\r\n \"en\": \"3. Report Type\",\r\n \"zh\": \"三、报告类型\"\r\n },\r\n \"xlsx.safety.block.country\": {\r\n \"en\": \"4. Primary Source Country (Top 12)\",\r\n \"zh\": \"四、报告来源国家 (Top 12)\"\r\n },\r\n \"xlsx.safety.block.age\": {\r\n \"en\": \"5. Age Distribution\",\r\n \"zh\": \"五、年龄分布\"\r\n },\r\n \"xlsx.safety.block.year\": {\r\n \"en\": \"6. Annual Reporting Trend\",\r\n \"zh\": \"六、逐年报告趋势\"\r\n },\r\n \"xlsx.safety.block.reaction\": {\r\n \"en\": \"7. Top Reaction Terms (Top 15)\",\r\n \"zh\": \"七、高频反应事件 (Top 15)\"\r\n },\r\n \"xlsx.safety.block.indication\": {\r\n \"en\": \"8. Top Indications (Top 12)\",\r\n \"zh\": \"八、高频用药指征 (Top 12)\"\r\n },\r\n \"xlsx.safety.block.drug_role\": {\r\n \"en\": \"9. Drug Role\",\r\n \"zh\": \"九、药物角色分布\"\r\n },\r\n \"xlsx.safety.label.serious\": {\r\n \"en\": \"Seriousness\",\r\n \"zh\": \"严重性\"\r\n },\r\n \"xlsx.safety.label.sex\": {\r\n \"en\": \"Sex\",\r\n \"zh\": \"性别\"\r\n },\r\n \"xlsx.safety.label.report_type\": {\r\n \"en\": \"Report Type\",\r\n \"zh\": \"报告类型\"\r\n },\r\n \"xlsx.safety.label.country\": {\r\n \"en\": \"Country\",\r\n \"zh\": \"国家\"\r\n },\r\n \"xlsx.safety.label.age\": {\r\n \"en\": \"Age Band (years)\",\r\n \"zh\": \"年龄段（岁）\"\r\n },\r\n \"xlsx.safety.label.year\": {\r\n \"en\": \"Report Year\",\r\n \"zh\": \"报告年份\"\r\n },\r\n \"xlsx.safety.label.reaction\": {\r\n \"en\": \"Reaction (PT)\",\r\n \"zh\": \"反应事件 (PT)\"\r\n },\r\n \"xlsx.safety.label.indication\": {\r\n \"en\": \"Indication\",\r\n \"zh\": \"用药指征\"\r\n },\r\n \"xlsx.safety.label.drug_role\": {\r\n \"en\": \"Drug Role\",\r\n \"zh\": \"药物角色\"\r\n },\r\n \"xlsx.safety.serious_yes\": {\r\n \"en\": \"Serious\",\r\n \"zh\": \"严重\"\r\n },\r\n \"xlsx.safety.serious_no\": {\r\n \"en\": \"Non-serious\",\r\n \"zh\": \"非严重\"\r\n },\r\n \"xlsx.safety.sex_m\": {\r\n \"en\": \"Male\",\r\n \"zh\": \"男性\"\r\n },\r\n \"xlsx.safety.sex_f\": {\r\n \"en\": \"Female\",\r\n \"zh\": \"女性\"\r\n },\r\n \"xlsx.safety.sex_unknown\": {\r\n \"en\": \"Unknown\",\r\n \"zh\": \"未知\"\r\n },\r\n \"xlsx.safety.rt_initial\": {\r\n \"en\": \"Initial\",\r\n \"zh\": \"初始报告\"\r\n },\r\n \"xlsx.safety.rt_followup\": {\r\n \"en\": \"Follow-up\",\r\n \"zh\": \"随访报告\"\r\n },\r\n \"xlsx.safety.rt_unknown\": {\r\n \"en\": \"Unknown\",\r\n \"zh\": \"未知\"\r\n },\r\n \"xlsx.safety.role_suspect\": {\r\n \"en\": \"Suspect drug\",\r\n \"zh\": \"怀疑药\"\r\n },\r\n \"xlsx.safety.role_concomitant\": {\r\n \"en\": \"Concomitant\",\r\n \"zh\": \"合并用药\"\r\n },\r\n \"xlsx.safety.role_interaction\": {\r\n \"en\": \"Interaction\",\r\n \"zh\": \"相互作用\"\r\n },\r\n \"xlsx.safety.note.top12\": {\r\n \"en\": \"Top 12 only\",\r\n \"zh\": \"仅显示前 12 位\"\r\n },\r\n \"xlsx.safety.note.top15\": {\r\n \"en\": \"Top 15 only\",\r\n \"zh\": \"仅显示前 15 位\"\r\n },\r\n \"xlsx.safety.note.age\": {\r\n \"en\": \"Age normalized to years before binning\",\r\n \"zh\": \"分箱前年龄已折算为岁\"\r\n },\r\n \"xlsx.safety.note.year\": {\r\n \"en\": \"By report receivedate year\",\r\n \"zh\": \"按报告接收年份\"\r\n },\r\n \"xlsx.safety.note.role\": {\r\n \"en\": \"All drug roles across the report\",\r\n \"zh\": \"报告内全部药物角色计数\"\r\n },\r\n \"xlsx.safety.note.age_skip_fast\": {\r\n \"en\": \"Age distribution is NOT count-able via the API (404) → omitted; use non-fast mode to download cases.\",\r\n \"zh\": \"年龄分布无法经 API 分面统计（404）→ 此处略；如需年龄请用非 --fast 模式下载个案。\"\r\n },\r\n \"xlsx.safety.raw_fast_note\": {\r\n \"en\": \"Count fast mode did not download case-level records. Use non --fast mode to fetch raw cases.\",\r\n \"zh\": \"count 快取模式未下载逐条个案；如需原始个案请用非 --fast 模式下载。\"\r\n },\r\n \"xlsx.safety.col.count\": {\r\n \"en\": \"Reports\",\r\n \"zh\": \"报告数\"\r\n },\r\n \"xlsx.safety.summary_intro\": {\r\n \"en\": \"The tables and charts below are auto-aggregated from the downloaded FAERS cases: each section shows a distribution table on the left and its chart on the right; the share column carries a data bar. Nine dimensions cover seriousness, sex, report type, source country, age, annual trend, top reactions, top indications and drug role.\",\r\n \"zh\": \"下列数据表与图表由下载的 FAERS 个案自动汇总生成：每个分区左侧为分布数据表、右侧为对应统计图；占比列带数据条。涵盖严重性、性别、报告类型、来源国家、年龄、逐年趋势、高频反应、高频指征与药物角色九个维度。\"\r\n },\r\n \"xlsx.safety.summary_intro_fast\": {\r\n \"en\": \"The dimensions below are aggregated from openFDA count facets over the FULL matched population (generated in seconds, no selection bias). Age is NOT count-able via the API, so the age block is omitted — eight dimensions are shown.\",\r\n \"zh\": \"以下维度基于 openFDA count 分面对「全部匹配报告」聚合生成（秒级、无选择偏倚）。年龄无法经 API 分面统计，故略去年龄块；共展示八个维度。\"\r\n },\r\n \"kw_gate.empty\": {\r\n \"en\": \"[ct_registry][KW-SYSTEM] No expandable keywords.\",\r\n \"zh\": \"[ct_registry][KW-SYSTEM] 无可扩展的关键字。\"\r\n },\r\n \"kw_gate.title\": {\r\n \"en\": \"Keyword system (auto-expand + EN/ZH translation) - confirm / supplement before searching\",\r\n \"zh\": \"关键字体系（自动扩展 + 中英互译）- 请确认 / 补充后再检索\"\r\n },\r\n \"kw_gate.original\": {\r\n \"en\": \"Original: {base} | Intent: {intent}\",\r\n \"zh\": \"原文：{base} ｜ 意图：{intent}\"\r\n },\r\n \"kw_gate.zh\": {\r\n \"en\": \"Chinese candidates\",\r\n \"zh\": \"中文候选\"\r\n },\r\n \"kw_gate.en\": {\r\n \"en\": \"English candidates\",\r\n \"zh\": \"英文候选\"\r\n },\r\n \"kw_gate.per_source\": {\r\n \"en\": \"Per-source assignment\",\r\n \"zh\": \"按源分配\"\r\n },\r\n \"kw_gate.ctgov\": {\r\n \"en\": \"CT.gov + WHO (English exact)\",\r\n \"zh\": \"CT.gov + WHO（英文·精确）\"\r\n },\r\n \"kw_gate.cde\": {\r\n \"en\": \"CDE + ChiCTR (Chinese substring)\",\r\n \"zh\": \"CDE + ChiCTR（中文·子串）\"\r\n },\r\n \"kw_gate.risk\": {\r\n \"en\": \"Risk note:\",\r\n \"zh\": \"风险提示：\"\r\n },\r\n \"kw_gate.speculative\": {\r\n \"en\": \"Speculative terms (review / removable):\",\r\n \"zh\": \"推测词（建议留意/可删）：\"\r\n },\r\n \"kw_gate.confirm\": {\r\n \"en\": \"Please confirm:\",\r\n \"zh\": \"请确认：\"\r\n },\r\n \"kw_gate.opt_adopt\": {\r\n \"en\": \"1. Adopt the above keyword system (recommended)\",\r\n \"zh\": \"1. 采用以上关键字体系（推荐）\"\r\n },\r\n \"kw_gate.opt_del\": {\r\n \"en\": \"2. Delete specific terms (reply: del term, e.g. del sitagliptin)\",\r\n \"zh\": \"2. 删除某些词（回复：删 词，如删 曲格列汀）\"\r\n },\r\n \"kw_gate.opt_add\": {\r\n \"en\": \"3. Add your own terms (reply: add term, e.g. add repaglinide)\",\r\n \"zh\": \"3. 补充我自己的词（回复：加 词，如加 瑞格列奈）\"\r\n },\r\n \"kw_gate.opt_scope\": {\r\n \"en\": \"4. Narrow / widen scope (e.g. only saxagliptin)\",\r\n \"zh\": \"4. 改用更窄 / 更宽范围（如只搜 沙格列汀）\"\r\n },\r\n \"kw_gate.opt_cancel\": {\r\n \"en\": \"0. Cancel\",\r\n \"zh\": \"0. 取消\"\r\n },\r\n \"kw_gate.after\": {\r\n \"en\": \"(Search proceeds to scope/quota confirmation only after you confirm)\",\r\n \"zh\": \"（确认后才进入检索范围/配额确认 - 正式检索）\"\r\n },\r\n \"kw_gate.axis_condition\": {\r\n \"en\": \"Condition\",\r\n \"zh\": \"疾病/适应症\"\r\n },\r\n \"kw_gate.axis_intervention\": {\r\n \"en\": \"Intervention/Drug\",\r\n \"zh\": \"干预/药物\"\r\n },\r\n \"kw_gate.title_multi\": {\r\n \"en\": \"Keyword system #{i} ({axis}) - auto-expand + EN/ZH translation\",\r\n \"zh\": \"关键字体系 #{i}（{axis}）- 自动扩展 + 中英互译\"\r\n },\r\n \"kw_gate.multi_confirm\": {\r\n \"en\": \"Please confirm (the {n} keyword systems above are handled together):\",\r\n \"zh\": \"请确认（以上 {n} 组关键字体系一并处理）：\"\r\n },\r\n \"kw_gate.stopped\": {\r\n \"en\": \"[ct_registry][KW-GATE] keyword system not confirmed - search stopped. confirm/supplement, then re-run.\",\r\n \"zh\": \"[ct_registry][KW-GATE] 关键字体系未确认 - 已停止检索。请确认/补充后，重新运行。\"\r\n },\r\n \"kw_gate.none\": {\r\n \"en\": \"none\",\r\n \"zh\": \"无\"\r\n },\r\n \"kw_gate.multi_opt_adopt\": {\r\n \"en\": \"1. Adopt all the above keyword systems (recommended)\",\r\n \"zh\": \"1. 全部采用（推荐）\"\r\n },\r\n \"kw_gate.intent_disease\": {\r\n \"en\": \"Disease/Condition\",\r\n \"zh\": \"疾病/适应症\"\r\n },\r\n \"kw_gate.intent_intervention\": {\r\n \"en\": \"Intervention/Mechanism\",\r\n \"zh\": \"干预/机制\"\r\n },\r\n \"kw_gate.intent_drug\": {\r\n \"en\": \"Drug (specific)\",\r\n \"zh\": \"药物(具体)\"\r\n },\r\n \"kw_gate.intent_drug_class\": {\r\n \"en\": \"Drug class\",\r\n \"zh\": \"药物类别\"\r\n },\r\n \"kw_gate.intent_auto\": {\r\n \"en\": \"Auto-detect\",\r\n \"zh\": \"自动识别\"\r\n },\r\n \"auth.coze_outbound\": {\r\n \"en\": \"First-time cloud service needs to send your request to the Coze endpoint ({endpoint}). This improves answer quality and coverage. No PII / subject data / unpublished project data is sent. Allow sending for this session?\",\r\n \"zh\": \"首次使用云端服务需将您的请求发送到 Coze 端点（{endpoint}）。这会提升答案的质量与覆盖度，且不会发送任何个人信息、受试者信息或未公开项目数据。是否允许本次发送？\"\r\n },\r\n \"auth.coze_outbound_denied\": {\r\n \"en\": \"Declined: cloud service is disabled for this session; the agent will answer using local reference materials only (answer quality/coverage is reduced). Add the endpoint to config.json 'auto_approve_endpoints' to skip this prompt next time.\",\r\n \"zh\": \"已拒绝：本次会话关闭云端服务，agent 将仅使用本地参考资料作答（答案质量/覆盖度下降）。将端点加入 config.json 的 'auto_approve_endpoints' 列表可在下次跳过此提示。\"\r\n },\r\n \"auth.serial_blocked\": {\r\n \"en\": \"[AUTH-BLOCK] serial refine blocked — falling back to local draft.\",\r\n \"zh\": \"[AUTH-BLOCK] 串行精校被拦截——回退至本地草稿。\"\r\n },\r\n \"error.requests_missing\": {\r\n \"en\": \"[ERROR] Outbound refinement needs the `requests` library to make HTTPS calls.\\n → It is not installed locally. Please run the following command manually and retry:\\n {cmd}\\n\",\r\n \"zh\": \"[错误] 出站精校需要 `requests` 库来发起 HTTPS 请求。\\n → 检测到本地未安装，请手动运行以下命令后重试：\\n {cmd}\\n\"\r\n },\r\n \"error.coze_401\": {\r\n \"en\": \"[coze] AUTH_REJECTED status=401; the token may be revoked or the endpoint auth changed. Check COZE_TOKEN and endpoint.\",\r\n \"zh\": \"[coze] AUTH_REJECTED 状态=401；token 可能已吊销或端点鉴权已变更。请检查 COZE_TOKEN 与 endpoint。\"\r\n },\r\n \"error.fallback_local\": {\r\n \"en\": \"[coze] FALLBACK_TO_LOCAL_DRAFT reason={reason} timeout={timeout}s; not retrying; returning local draft_answer\",\r\n \"zh\": \"[coze] FALLBACK_TO_LOCAL_DRAFT 原因={reason} 超时={timeout}s；不重试；返回本地 draft_answer\"\r\n },\r\n \"error.empty_question\": {\r\n \"en\": \"[ct-advisor] cannot generate answer: the problem description is empty, please provide a specific clinical-trial question.\",\r\n \"zh\": \"[ct-advisor] 无法生成答案：问题描述为空，请提供具体的临床试验问题。\"\r\n },\r\n \"error.payload_healed\": {\r\n \"en\": \"[ct-advisor] payload auto-healed (self-heal): {notes}\",\r\n \"zh\": \"[ct-advisor] payload 已自动补全（自愈）：{notes}\"\r\n },\r\n \"error.payload_invalid\": {\r\n \"en\": \"[ct-advisor] payload parse/validation failed ({error}); fell back to local draft, remote NOT called.\",\r\n \"zh\": \"[ct-advisor] payload 解析/校验失败（{error}）；已回退本地草稿，未调用远程。\"\r\n },\r\n \"error.refine_fallback\": {\r\n \"en\": \"[ct-advisor] refine error, falling back to draft: {error}\",\r\n \"zh\": \"[ct-advisor] refine 异常，回退草稿：{error}\"\r\n },\r\n \"error.base64_decode\": {\r\n \"en\": \"[ct-advisor] base64 decode failed: {error}\",\r\n \"zh\": \"[ct-advisor] base64 解码失败：{error}\"\r\n },\r\n \"error.dependency_fatal\": {\r\n \"en\": \"[ct-advisor][FATAL] refiner dependency missing: this issue will NOT silently fall back; install per the command below and retry.\\n {cmd}\",\r\n \"zh\": \"[ct-advisor][FATAL] 精校依赖缺失：此问题不会静默回退；请按以下命令安装后重试。\\n {cmd}\"\r\n },\r\n\r\n \"xlsx.signal.sheet.readme\": {\"en\": \"README\", \"zh\": \"说明\"},\r\n \"xlsx.signal.sheet.summary\": {\"en\": \"Summary\", \"zh\": \"概要\"},\r\n \"xlsx.signal.sheet.raw\": {\"en\": \"Raw Counts\", \"zh\": \"原始计数\"},\r\n \"xlsx.signal.sheet.label\": {\"en\": \"FDA Label\", \"zh\": \"FDA 说明书\"},\r\n \"xlsx.signal.sheet.cnpv\": {\"en\": \"CN PV\", \"zh\": \"中国药物警戒\"},\r\n \"xlsx.signal.sheet.score\": {\"en\": \"Score\", \"zh\": \"评分\"},\r\n \"xlsx.signal.banner\": {\"en\": \"FAERS Safety Signal Analysis\", \"zh\": \"FAERS 安全性信号分析\"},\r\n \"xlsx.signal.banner.data_workbook\": {\"en\": \"Data Workbook\", \"zh\": \"数据工作簿\"},\r\n \"xlsx.signal.kpi.drug\": {\"en\": \"Drug\", \"zh\": \"药物\"},\r\n \"xlsx.signal.kpi.event\": {\"en\": \"Event\", \"zh\": \"事件\"},\r\n \"xlsx.signal.kpi.verdict\": {\"en\": \"Verdict\", \"zh\": \"总体判定\"},\r\n \"xlsx.signal.verdict.positive\": {\"en\": \"Signal Positive\", \"zh\": \"信号阳性\"},\r\n \"xlsx.signal.verdict.negative\": {\"en\": \"No Significant Signal\", \"zh\": \"无显著信号\"},\r\n \"xlsx.signal.guide.title\": {\"en\": \"Guide\", \"zh\": \"使用指南\"},\r\n \"xlsx.signal.guide.html\": {\"en\": \"faers_report.html — Visual report (conclusions & charts, quick reading)\", \"zh\": \"faers_report.html — 可视化报告（结论与图表，便于快速阅读）\"},\r\n \"xlsx.signal.guide.xlsx\": {\"en\": \"faers_report.xlsx — This file, ALL raw data & calculation details, auditable\", \"zh\": \"faers_report.xlsx — 本文件，含全部原始信息与计算明细，供逐条查阅 / 审计\"},\r\n \"xlsx.signal.guide.sheets\": {\"en\": \"Sheets:\", \"zh\": \"各工作表说明：\"},\r\n \"xlsx.signal.guide.summary\": {\"en\": \"Summary — 2x2 table + 4 disproportionality measures (ROR/PRR/IC/EBGM)\", \"zh\": \"Summary — 2×2 列联表 + 四种信号检测方法（ROR/PRR/IC/EBGM）结果\"},\r\n \"xlsx.signal.guide.raw\": {\"en\": \"Raw_Counts — Underlying FAERS counts (a/b/c/d, totals, top events)\", \"zh\": \"Raw_Counts — FAERS 底层计数（a/b/c/d、各合计、Top 不良反应）\"},\r\n \"xlsx.signal.guide.label\": {\"en\": \"FDA_Label — FDA label warnings / adverse reactions (only with --with-fda-label)\", \"zh\": \"FDA_Label — FDA 说明书相关警示 / 不良反应（仅 --with-fda-label 时填充）\"},\r\n \"xlsx.signal.guide.cnpv\": {\"en\": \"CN_PV — China official PV bulletin hits (only with --with-cn-pv)\", \"zh\": \"CN_PV — 中国官方药物警戒通报命中（仅 --with-cn-pv 时填充）\"},\r\n \"xlsx.signal.guide.score\": {\"en\": \"Score — Composite signal score breakdown (only with --with-fda-label)\", \"zh\": \"Score — 综合安全信号评分分量（仅 --with-fda-label 时填充）\"},\r\n \"xlsx.signal.guide.source\": {\"en\": \"Source: FDA FAERS (openFDA public REST API). All public adverse event reports. Zero confidential input (B-class). Signal is for screening only, NOT causal conclusion; regulatory submission requires separate GCP/ICH E2 evaluation.\", \"zh\": \"数据来源：FDA FAERS（openFDA 公开 REST API），全部为公开不良事件报告，零保密输入（B 档）。信号仅用于筛查，非因果结论；监管提交须按 GCP/ICH E2 另行评估。\"},\r\n \"xlsx.signal.section.2x2\": {\"en\": \"2×2 Contingency Table\", \"zh\": \"2×2 列联表\"},\r\n \"xlsx.signal.section.measures\": {\"en\": \"Disproportionality Measures\", \"zh\": \"信号检测方法\"},\r\n \"xlsx.signal.section.meta\": {\"en\": \"Analysis Metadata\", \"zh\": \"分析元数据\"},\r\n \"xlsx.signal.section.raw2x2\": {\"en\": \"Raw 2×2 (Uncorrected)\", \"zh\": \"2×2 原始计数（未校正）\"},\r\n \"xlsx.signal.section.raw_counts_input\": {\"en\": \"Raw Counts (disproportionality input)\", \"zh\": \"原始计数（disproportionality 输入）\"},\r\n \"xlsx.signal.section.top_events\": {\"en\": \"Top Adverse Events (this drug)\", \"zh\": \"Top 不良反应（该药）\"},\r\n \"xlsx.signal.section.label_warnings\": {\"en\": \"WARNINGS\", \"zh\": \"黑框警告\"},\r\n \"xlsx.signal.section.label_reactions\": {\"en\": \"ADVERSE REACTIONS\", \"zh\": \"不良反应\"},\r\n \"xlsx.signal.section.components\": {\"en\": \"Score Components\", \"zh\": \"评分分量\"},\r\n \"xlsx.signal.col.drug\": {\"en\": \"Drug\", \"zh\": \"用药\"},\r\n \"xlsx.signal.col.no_drug\": {\"en\": \"No Drug\", \"zh\": \"未用药\"},\r\n \"xlsx.signal.col.event_yes\": {\"en\": \"Event Occurred\", \"zh\": \"事件发生\"},\r\n \"xlsx.signal.col.event_no\": {\"en\": \"Event Not Occurred\", \"zh\": \"事件未发生\"},\r\n \"xlsx.signal.col.total\": {\"en\": \"Total\", \"zh\": \"合计\"},\r\n \"xlsx.signal.col.method\": {\"en\": \"Method\", \"zh\": \"方法\"},\r\n \"xlsx.signal.col.estimate\": {\"en\": \"Estimate\", \"zh\": \"估计值\"},\r\n \"xlsx.signal.col.ci\": {\"en\": \"95% CI\", \"zh\": \"95% CI\"},\r\n \"xlsx.signal.col.signal\": {\"en\": \"Signal\", \"zh\": \"信号\"},\r\n \"xlsx.signal.col.cell\": {\"en\": \"Cell\", \"zh\": \"格子\"},\r\n \"xlsx.signal.col.value\": {\"en\": \"Value\", \"zh\": \"数值\"},\r\n \"xlsx.signal.col.event\": {\"en\": \"Event\", \"zh\": \"事件\"},\r\n \"xlsx.signal.col.count\": {\"en\": \"Count\", \"zh\": \"报告数\"},\r\n \"xlsx.signal.col.tier\": {\"en\": \"Tier\", \"zh\": \"佐证等级\"},\r\n \"xlsx.signal.col.date\": {\"en\": \"Date\", \"zh\": \"日期\"},\r\n \"xlsx.signal.col.column\": {\"en\": \"Column\", \"zh\": \"栏目\"},\r\n \"xlsx.signal.col.title\": {\"en\": \"Title\", \"zh\": \"标题\"},\r\n \"xlsx.signal.col.kw\": {\"en\": \"Keywords\", \"zh\": \"命中词\"},\r\n \"xlsx.signal.col.link\": {\"en\": \"Link\", \"zh\": \"链接\"},\r\n \"xlsx.signal.col.component\": {\"en\": \"Component\", \"zh\": \"分量\"},\r\n \"xlsx.signal.col.points\": {\"en\": \"Points\", \"zh\": \"得分\"},\r\n \"xlsx.signal.meta.drug\": {\"en\": \"Drug\", \"zh\": \"药物\"},\r\n \"xlsx.signal.meta.event\": {\"en\": \"Event (MedDRA PT)\", \"zh\": \"事件 (MedDRA PT)\"},\r\n \"xlsx.signal.meta.soc\": {\"en\": \"System Organ Class (SOC)\", \"zh\": \"系统器官分类 SOC\"},\r\n \"xlsx.signal.meta.source\": {\"en\": \"Data Source\", \"zh\": \"数据源\"},\r\n \"xlsx.signal.meta.continuity\": {\"en\": \"Continuity Correction\", \"zh\": \"连续性校正\"},\r\n \"xlsx.signal.meta.overall\": {\"en\": \"Overall Verdict\", \"zh\": \"总体判定\"},\r\n \"xlsx.signal.meta.yes\": {\"en\": \"Yes\", \"zh\": \"是\"},\r\n \"xlsx.signal.meta.no\": {\"en\": \"No\", \"zh\": \"否\"},\r\n \"xlsx.signal.meta.enabled\": {\"en\": \"Enabled (Haldane-Anscombe +0.5/cell)\", \"zh\": \"已启用 Haldane-Anscombe (+0.5/格)\"},\r\n \"xlsx.signal.criteria\": {\"en\": \"Signal criteria: ROR lower CI >1; PRR≥2 & χ²≥4; IC lower CI >0; EBGM EB05≥2. For screening only, not causal.\", \"zh\": \"信号判定：ROR 下限>1；PRR≥2 且 χ²≥4；IC 下限>0；EBGM EB05≥2。仅供筛查，非因果结论。\"},\r\n \"xlsx.signal.score.title\": {\"en\": \"Composite Safety Signal Score\", \"zh\": \"综合安全信号评分\"},\r\n \"xlsx.signal.score.total\": {\"en\": \"Total Score (0-100)\", \"zh\": \"总分 (0-100)\"},\r\n \"xlsx.signal.score.tier\": {\"en\": \"Evidence Tier\", \"zh\": \"证据分级\"},\r\n \"xlsx.signal.score.rationale\": {\"en\": \"Rationale\", \"zh\": \"理由\"},\r\n \"xlsx.signal.label.status\": {\"en\": \"Label Status\", \"zh\": \"标签状态\"},\r\n \"xlsx.signal.label.matched\": {\"en\": \"Matched Terms\", \"zh\": \"匹配药品词\"},\r\n \"xlsx.signal.source.faers\": {\"en\": \"FDA FAERS (openFDA)\", \"zh\": \"FDA FAERS（openFDA）\"},\r\n \"xlsx.signal.col.n\": {\"en\": \"#\", \"zh\": \"序号\"},\r\n \"xlsx.signal.col.content\": {\"en\": \"Content\", \"zh\": \"内容\"},\r\n \"xlsx.signal.verdict.short.positive\": {\"en\": \"Signal Positive\", \"zh\": \"信号阳性\"},\r\n \"xlsx.signal.verdict.short.negative\": {\"en\": \"No Signal\", \"zh\": \"无显著信号\"}\r\n}\n\nFile v1.3.0:scripts/i18n_skill_messages.json\n\n{\r\n \"error.fallback_diagnose\": {\r\n \"en\": \"[ct-advisor] The Coze cloud service is temporarily unavailable ({error}), so the local answer may be less complete. May I run an automatic diagnostic check to find and fix the cause?\",\r\n \"zh\": \"[ct-advisor] Coze 云端服务暂时不可用（{error}），本次回答可能不够完善。是否允许我自动进行问题诊断排查？\"\r\n },\r\n \"ground.input.csr\": {\r\n \"en\": \"CSR\",\r\n \"zh\": \"CSR（临床总结报告）\"\r\n },\r\n \"ground.input.none\": {\r\n \"en\": \"None yet\",\r\n \"zh\": \"暂无材料\"\r\n },\r\n \"ground.input.otherdoc\": {\r\n \"en\": \"Other document\",\r\n \"zh\": \"其他文档\"\r\n },\r\n \"ground.input.protocol\": {\r\n \"en\": \"Protocol\",\r\n \"zh\": \"方案（Protocol）\"\r\n },\r\n \"ground.input.q\": {\r\n \"en\": \"What input / material do you have?\",\r\n \"zh\": \"你手头有什么材料 / 输入？\"\r\n },\r\n \"ground.input.question\": {\r\n \"en\": \"Just a question\",\r\n \"zh\": \"只是一个问题\"\r\n },\r\n \"ground.input.safetydb\": {\r\n \"en\": \"Safety database\",\r\n \"zh\": \"安全性数据库\"\r\n },\r\n \"ground.input.sap\": {\r\n \"en\": \"SAP\",\r\n \"zh\": \"SAP（统计分析计划）\"\r\n },\r\n \"ground.role.cro\": {\r\n \"en\": \"CRO\",\r\n \"zh\": \"CRO\"\r\n },\r\n \"ground.role.investigator\": {\r\n \"en\": \"Investigator\",\r\n \"zh\": \"研究者\"\r\n },\r\n \"ground.role.other\": {\r\n \"en\": \"Other\",\r\n \"zh\": \"其他\"\r\n },\r\n \"ground.role.q\": {\r\n \"en\": \"What is your role?\",\r\n \"zh\": \"你的角色是什么？\"\r\n },\r\n \"ground.role.reg\": {\r\n \"en\": \"Regulatory affairs\",\r\n \"zh\": \"注册事务\"\r\n },\r\n \"ground.role.sponsor\": {\r\n \"en\": \"Sponsor\",\r\n \"zh\": \"申办方\"\r\n },\r\n \"ground.stage.nda\": {\r\n \"en\": \"NDA / submission\",\r\n \"zh\": \"申报 / NDA 阶段\"\r\n },\r\n \"ground.stage.ph1\": {\r\n \"en\": \"Phase I\",\r\n \"zh\": \"I 期\"\r\n },\r\n \"ground.stage.ph2\": {\r\n \"en\": \"Phase II\",\r\n \"zh\": \"II 期\"\r\n },\r\n \"ground.stage.ph3\": {\r\n \"en\": \"Phase III\",\r\n \"zh\": \"III 期\"\r\n },\r\n \"ground.stage.ph4\": {\r\n \"en\": \"Phase IV\",\r\n \"zh\": \"IV 期\"\r\n },\r\n \"ground.stage.postmarket\": {\r\n \"en\": \"Post-market\",\r\n \"zh\": \"上市后\"\r\n },\r\n \"ground.stage.preind\": {\r\n \"en\": \"Pre-IND\",\r\n \"zh\": \"临床前（Pre-IND）\"\r\n },\r\n \"ground.stage.q\": {\r\n \"en\": \"What stage is the program at?\",\r\n \"zh\": \"项目处于什么阶段？\"\r\n },\r\n \"ground.stage.unsure\": {\r\n \"en\": \"Not sure\",\r\n \"zh\": \"不确定\"\r\n },\r\n \"menu.A\": {\r\n \"en\": \"A · Define / basis / compare\",\r\n \"zh\": \"A · 术语 / 依据 / 对比解释\"\r\n },\r\n \"menu.B\": {\r\n \"en\": \"B · Trial design\",\r\n \"zh\": \"B · 试验设计\"\r\n },\r\n \"menu.C\": {\r\n \"en\": \"C · Statistics & sample size\",\r\n \"zh\": \"C · 统计与样本量\"\r\n },\r\n \"menu.D\": {\r\n \"en\": \"D · Operations & compliance\",\r\n \"zh\": \"D · 运营与合规\"\r\n },\r\n \"menu.E\": {\r\n \"en\": \"E · Enrollment / monitoring / DB lock\",\r\n \"zh\": \"E · 招募 / 监查 / 数据封锁\"\r\n },\r\n \"menu.F\": {\r\n \"en\": \"F · Safety signal / DSUR / SUSAR\",\r\n \"zh\": \"F · 安全信号 / DSUR / SUSAR\"\r\n },\r\n \"menu.G\": {\r\n \"en\": \"G · Document review\",\r\n \"zh\": \"G · 文档评审（方案 / SAP / CSR）\"\r\n },\r\n \"menu.H\": {\r\n \"en\": \"H · Cross-file / submission ready\",\r\n \"zh\": \"H · 交叉核对 / 申报就绪\"\r\n },\r\n \"menu.I\": {\r\n \"en\": \"I · Tone / rewrite\",\r\n \"zh\": \"I · 语气 / 改写\"\r\n },\r\n \"menu.J\": {\r\n \"en\": \"J · Memory / preferences\",\r\n \"zh\": \"J · 记忆 / 偏好\"\r\n },\r\n \"menu.area.design_stats\": {\r\n \"en\": \"Design & statistics\",\r\n \"zh\": \"设计与统计\"\r\n },\r\n \"menu.area.docs_qc\": {\r\n \"en\": \"Documents & QC\",\r\n \"zh\": \"文档与质控\"\r\n },\r\n \"menu.area.explain_other\": {\r\n \"en\": \"Explain & other\",\r\n \"zh\": \"解释与其他\"\r\n },\r\n \"menu.area.safety_ops\": {\r\n \"en\": \"Safety & operations\",\r\n \"zh\": \"安全与运营\"\r\n },\r\n \"menu.cap.clarify\": {\r\n \"en\": \"Clarify what I need\",\r\n \"zh\": \"澄清需求\"\r\n },\r\n \"menu.cap.data_intel\": {\r\n \"en\": \"Data intelligence\",\r\n \"zh\": \"数据检索 / 情报\"\r\n },\r\n \"menu.cap.methodology\": {\r\n \"en\": \"Methodology Q&A\",\r\n \"zh\": \"方法学问答\"\r\n },\r\n \"menu.cap.q\": {\r\n \"en\": \"What kind of help do you need?\",\r\n \"zh\": \"你需要哪种帮助？\"\r\n },\r\n \"menu.cap.title\": {\r\n \"en\": \"Capability\",\r\n \"zh\": \"能力选择\"\r\n },\r\n \"menu.ct_competitive\": {\r\n \"en\": \"Competitive intelligence\",\r\n \"zh\": \"竞品情报综合\"\r\n },\r\n \"menu.ct_literature\": {\r\n \"en\": \"Literature search\",\r\n \"zh\": \"文献检索\"\r\n },\r\n \"menu.ct_registry\": {\r\n \"en\": \"Trial registry search\",\r\n \"zh\": \"试验注册库检索\"\r\n },\r\n \"menu.ct_safety\": {\r\n \"en\": \"Safety signals (FAERS)\",\r\n \"zh\": \"安全性信号（FAERS）\"\r\n },\r\n \"menu.ct_samplesize\": {\r\n \"en\": \"Sample size calculation\",\r\n \"zh\": \"样本量计算\"\r\n },\r\n \"menu.data_skill.q\": {\r\n \"en\": \"Which data skill?\",\r\n \"zh\": \"用哪个数据技能？\"\r\n },\r\n \"menu.data_skill.title\": {\r\n \"en\": \"Data skill\",\r\n \"zh\": \"数据技能\"\r\n },\r\n \"menu.data_subintent.focus\": {\r\n \"en\": \"Focus on one part\",\r\n \"zh\": \"聚焦某一部分\"\r\n },\r\n \"menu.data_subintent.q\": {\r\n \"en\": \"What to do with the results?\",\r\n \"zh\": \"检索后做什么？\"\r\n },\r\n \"menu.data_subintent.run\": {\r\n \"en\": \"Run and return results\",\r\n \"zh\": \"直接运行并出结果\"\r\n },\r\n \"menu.data_subintent.title\": {\r\n \"en\": \"Data sub-intent\",\r\n \"zh\": \"数据子意图\"\r\n },\r\n \"menu.explain_diff\": {\r\n \"en\": \"Explain the difference\",\r\n \"zh\": \"解释差异\"\r\n },\r\n \"menu.ground.title\": {\r\n \"en\": \"Context\",\r\n \"zh\": \"背景信息\"\r\n },\r\n \"menu.intent.q\": {\r\n \"en\": \"Which area does the question fall into?\",\r\n \"zh\": \"问题属于哪个领域？\"\r\n },\r\n \"menu.intent.title\": {\r\n \"en\": \"Area\",\r\n \"zh\": \"领域选择\"\r\n },\r\n \"menu.out.q\": {\r\n \"en\": \"Which format?\",\r\n \"zh\": \"想要什么格式？\"\r\n },\r\n \"menu.out.title\": {\r\n \"en\": \"Output format\",\r\n \"zh\": \"输出格式\"\r\n },\r\n \"menu.sub.A.compare_guide\": {\r\n \"en\": \"Compare guidelines / options\",\r\n \"zh\": \"对比指南 / 选项\"\r\n },\r\n \"menu.sub.A.define_term\": {\r\n \"en\": \"Define a term / concept\",\r\n \"zh\": \"定义术语 / 概念\"\r\n },\r\n \"menu.sub.A.find_basis\": {\r\n \"en\": \"Find regulatory basis\",\r\n \"zh\": \"查找法规依据\"\r\n },\r\n \"menu.sub.B.adaptive\": {\r\n \"en\": \"Adaptive design\",\r\n \"zh\": \"适应性设计\"\r\n },\r\n \"menu.sub.B.critique\": {\r\n \"en\": \"Critique an existing design\",\r\n \"zh\": \"评审 / 批评现有设计\"\r\n },\r\n \"menu.sub.B.design_new\": {\r\n \"en\": \"Design a new trial\",\r\n \"zh\": \"设计新试验\"\r\n },\r\n \"menu.sub.B.endpoints_estimand\": {\r\n \"en\": \"Endpoints / estimand\",\r\n \"zh\": \"终点 / 估计目标\"\r\n },\r\n \"menu.sub.C.estimand_setup\": {\r\n \"en\": \"Estimand setup\",\r\n \"zh\": \"估计目标设定\"\r\n },\r\n \"menu.sub.C.missing_data\": {\r\n \"en\": \"Missing data handling\",\r\n \"zh\": \"缺失数据处理\"\r\n },\r\n \"menu.sub.C.ni_eq\": {\r\n \"en\": \"Non-inferiority / equivalence\",\r\n \"zh\": \"非劣效 / 等效设计\"\r\n },\r\n \"menu.sub.C.samplesize\": {\r\n \"en\": \"Sample size\",\r\n \"zh\": \"样本量计算\"\r\n },\r\n \"menu.sub.D.audit_ready\": {\r\n \"en\": \"Audit readiness\",\r\n \"zh\": \"稽查就绪\"\r\n },\r\n \"menu.sub.D.consent_irb\": {\r\n \"en\": \"Consent / IRB\",\r\n \"zh\": \"知情同意 / 伦理\"\r\n },\r\n \"menu.sub.D.deviation_capa\": {\r\n \"en\": \"Deviation & CAPA\",\r\n \"zh\": \"偏离与 CAPA\"\r\n },\r\n \"menu.sub.E.dblock_ready\": {\r\n \"en\": \"DB lock readiness\",\r\n \"zh\": \"数据封锁就绪\"\r\n },\r\n \"menu.sub.E.enroll_feas\": {\r\n \"en\": \"Enrollment feasibility\",\r\n \"zh\": \"入组可行性\"\r\n },\r\n \"menu.sub.E.monitoring_vendor\": {\r\n \"en\": \"Monitoring / vendor\",\r\n \"zh\": \"监查 / 供应商\"\r\n },\r\n \"menu.sub.E.reg_path\": {\r\n \"en\": \"Regulatory pathway\",\r\n \"zh\": \"注册路径\"\r\n },\r\n \"menu.sub.F.benefit_risk\": {\r\n \"en\": \"Benefit-risk assessment\",\r\n \"zh\": \"获益-风险评估\"\r\n },\r\n \"menu.sub.F.dsur\": {\r\n \"en\": \"DSUR\",\r\n \"zh\": \"DSUR 撰写\"\r\n },\r\n \"menu.sub.F.signal\": {\r\n \"en\": \"Safety signal evaluation\",\r\n \"zh\": \"安全信号评估\"\r\n },\r\n \"menu.sub.F.susar\": {\r\n \"en\": \"SUSAR handling\",\r\n \"zh\": \"SUSAR 处理\"\r\n },\r\n \"menu.sub.G.csr_review\": {\r\n \"en\": \"CSR review\",\r\n \"zh\": \"CSR 评审\"\r\n },\r\n \"menu.sub.G.draft_section\": {\r\n \"en\": \"Draft a section\",\r\n \"zh\": \"起草章节\"\r\n },\r\n \"menu.sub.G.protocol_review\": {\r\n \"en\": \"Protocol review\",\r\n \"zh\": \"方案评审\"\r\n },\r\n \"menu.sub.G.sap_review\": {\r\n \"en\": \"SAP review\",\r\n \"zh\": \"SAP 评审\"\r\n },\r\n \"menu.sub.H.crossfile\": {\r\n \"en\": \"Cross-file consistency\",\r\n \"zh\": \"跨文件一致性\"\r\n },\r\n \"menu.sub.H.design_qc\": {\r\n \"en\": \"Design QC\",\r\n \"zh\": \"设计质控\"\r\n },\r\n \"menu.sub.H.document_qc\": {\r\n \"en\": \"Document QC\",\r\n \"zh\": \"文档质控\"\r\n },\r\n \"menu.sub.H.submission_ready\": {\r\n \"en\": \"Submission readiness\",\r\n \"zh\": \"申报就绪检查\"\r\n },\r\n \"menu.sub.I.reply_tone\": {\r\n \"en\": \"Adjust reply tone\",\r\n \"zh\": \"调整回复语气\"\r\n },\r\n \"menu.sub.I.rewrite\": {\r\n \"en\": \"Rewrite content\",\r\n \"zh\": \"改写内容\"\r\n },\r\n \"menu.sub.J.recall\": {\r\n \"en\": \"Recall past content\",\r\n \"zh\": \"回忆历史内容\"\r\n },\r\n \"menu.sub.J.save_pref\": {\r\n \"en\": \"Save preferences\",\r\n \"zh\": \"保存偏好\"\r\n },\r\n \"menu.sub.q\": {\r\n \"en\": \"What exactly do you want?\",\r\n \"zh\": \"具体想做什么？\"\r\n },\r\n \"menu.sub.title\": {\r\n \"en\": \"Sub-intent\",\r\n \"zh\": \"子意图\"\r\n },\r\n \"menu.workflow.q\": {\r\n \"en\": \"Which workflow?\",\r\n \"zh\": \"选择具体工作流？\"\r\n },\r\n \"menu.workflow.title\": {\r\n \"en\": \"Workflow\",\r\n \"zh\": \"工作流\"\r\n },\r\n \"out.format.advisory_memo\": {\r\n \"en\": \"Advisory memo\",\r\n \"zh\": \"顾问备忘录\"\r\n },\r\n \"out.format.checklist\": {\r\n \"en\": \"Checklist\",\r\n \"zh\": \"核对清单\"\r\n },\r\n \"out.format.option_compare\": {\r\n \"en\": \"Option comparison\",\r\n \"zh\": \"方案对比\"\r\n },\r\n \"out.format.redline_review\": {\r\n \"en\": \"Redline review\",\r\n \"zh\": \"修订批注评审\"\r\n }\r\n}\n\nFile v1.3.0:scripts/kw_lexicon.json\n\n{\r\n \"extra\": {\r\n \"高血压\": \"hypertension\",\r\n \"糖尿病\": \"diabetes mellitus\",\r\n \"冠心病\": \"coronary heart disease\",\r\n \"心衰\": \"heart failure\",\r\n \"房颤\": \"atrial fibrillation\",\r\n \"慢阻肺\": \"COPD\",\r\n \"哮喘\": \"asthma\",\r\n \"乙肝\": \"hepatitis B\",\r\n \"丙肝\": \"hepatitis C\",\r\n \"肝硬化\": \"liver cirrhosis\",\r\n \"抑郁症\": \"depression\",\r\n \"焦虑症\": \"anxiety\",\r\n \"骨质疏松\": \"osteoporosis\",\r\n \"阿尔茨海默病\": \"Alzheimer disease\",\r\n \"帕金森\": \"Parkinson disease\",\r\n \"癫痫\": \"epilepsy\",\r\n \"类风湿性关节炎\": \"rheumatoid arthritis\",\r\n \"红斑狼疮\": \"systemic lupus erythematosus\",\r\n \"甲状腺\": \"thyroid\",\r\n \"乳腺癌\": \"breast cancer\",\r\n \"胃癌\": \"gastric cancer\",\r\n \"肝癌\": \"liver cancer\",\r\n \"结直肠癌\": \"colorectal cancer\",\r\n \"白血病\": \"leukemia\",\r\n \"淋巴瘤\": \"lymphoma\",\r\n \"骨髓瘤\": \"myeloma\",\r\n \"食管癌\": \"esophageal cancer\",\r\n \"胰腺癌\": \"pancreatic cancer\",\r\n \"宫颈癌\": \"cervical cancer\",\r\n \"前列腺癌\": \"prostate cancer\",\r\n \"卵巢癌\": \"ovarian cancer\",\r\n \"膀胱癌\": \"bladder cancer\",\r\n \"肾癌\": \"renal cell carcinoma\",\r\n \"鼻咽癌\": \"nasopharyngeal carcinoma\",\r\n \"黑色素瘤\": \"melanoma\",\r\n \"骨转移\": \"bone metastasis\",\r\n \"脑转移\": \"brain metastasis\",\r\n \"肝转移\": \"liver metastasis\",\r\n \"肺转移\": \"lung metastasis\",\r\n \"免疫治疗\": \"immunotherapy\",\r\n \"化疗\": \"chemotherapy\",\r\n \"靶向治疗\": \"targeted therapy\",\r\n \"内分泌治疗\": \"endocrine therapy\",\r\n \"新辅助\": \"neoadjuvant\",\r\n \"辅助\": \"adjuvant\",\r\n \"一线\": \"first-line\",\r\n \"二线\": \"second-line\",\r\n \"佐妥昔单抗\": \"Zolbetuximab\",\r\n \"恶心呕吐\": \"nausea/vomiting\",\r\n \"恶心\": \"nausea\",\r\n \"呕吐\": \"vomiting\",\r\n \"止吐\": \"antiemetic\"\r\n },\r\n \"class_en2zh\": {\r\n \"sartan\": \"沙坦\",\r\n \"statin\": \"他汀\",\r\n \"fibrate\": \"贝特\",\r\n \"ace inhibitor\": \"ACE抑制剂\",\r\n \"acei\": \"ACE抑制剂\",\r\n \"angiotensin receptor blocker\": \"血管紧张素受体拮抗剂\",\r\n \"angiotensin ii receptor blocker\": \"血管紧张素II受体拮抗剂\",\r\n \"angiotensin receptor antagonist\": \"血管紧张素受体拮抗剂\",\r\n \"arb\": \"沙坦类\",\r\n \"beta blocker\": \"β受体阻滞剂\",\r\n \"beta-blocker\": \"β受体阻滞剂\",\r\n \"calcium channel blocker\": \"钙通道阻滞剂\",\r\n \"ccb\": \"钙通道阻滞剂\",\r\n \"diuretic\": \"利尿剂\",\r\n \"nsaid\": \"非甾体抗炎药\",\r\n \"nonsteroidal anti-inflammatory drug\": \"非甾体抗炎药\",\r\n \"ppi\": \"质子泵抑制剂\",\r\n \"proton pump inhibitor\": \"质子泵抑制剂\",\r\n \"mab\": \"单抗\",\r\n \"nib\": \"替尼\",\r\n \"cept\": \"融合蛋白\",\r\n \"gliptin\": \"列汀\",\r\n \"gliflozin\": \"格列净\",\r\n \"glinide\": \"格列奈\",\r\n \"glitazone\": \"格列酮\",\r\n \"insulin\": \"胰岛素\",\r\n \"sulfonylurea\": \"磺脲\",\r\n \"agis\": \"糖苷酶抑制\"\r\n },\r\n \"class_members\": {\r\n \"sartan\": [\r\n \"valsartan\",\r\n \"losartan\",\r\n \"irbesartan\",\r\n \"telmisartan\",\r\n \"olmesartan\",\r\n \"candesartan\",\r\n \"azilsartan\",\r\n \"eprosartan\",\r\n \"fimasartan\"\r\n ],\r\n \"statin\": [\r\n \"atorvastatin\",\r\n \"rosuvastatin\",\r\n \"simvastatin\",\r\n \"pravastatin\",\r\n \"fluvastatin\",\r\n \"pitavastatin\",\r\n \"lovastatin\"\r\n ],\r\n \"gliptin\": [\r\n \"sitagliptin\",\r\n \"saxagliptin\",\r\n \"vildagliptin\",\r\n \"linagliptin\",\r\n \"alogliptin\",\r\n \"teneligliptin\",\r\n \"trelagliptin\",\r\n \"dutogliptin\",\r\n \"gemigliptin\",\r\n \"anagliptin\",\r\n \"evogliptin\",\r\n \"omegliptin\"\r\n ],\r\n \"gliflozin\": [\r\n \"dapagliflozin\",\r\n \"empagliflozin\",\r\n \"canagliflozin\",\r\n \"ertugliflozin\",\r\n \"ipragliflozin\",\r\n \"luseogliflozin\",\r\n \"tofogliflozin\"\r\n ],\r\n \"glinide\": [\r\n \"repaglinide\",\r\n \"nateglinide\",\r\n \"mitiglinide\"\r\n ],\r\n \"glitazone\": [\r\n \"pioglitazone\",\r\n \"rosiglitazone\",\r\n \"lobeglitazone\"\r\n ],\r\n \"sulfonylurea\": [\r\n \"glimepiride\",\r\n \"gliclazide\",\r\n \"glibenclamide\",\r\n \"glipizide\",\r\n \"glyburide\",\r\n \"gliquidone\",\r\n \"glimepiride\",\r\n \"glimiperide\"\r\n ],\r\n \"nib\": [\r\n \"osimertinib\",\r\n \"gefitinib\",\r\n \"erlotinib\",\r\n \"afatinib\",\r\n \"lapatinib\",\r\n \"sorafenib\",\r\n \"sunitinib\",\r\n \"imatinib\",\r\n \"dasatinib\",\r\n \"nilotinib\",\r\n \"pazopanib\",\r\n \"cabozantinib\",\r\n \"lenvatinib\",\r\n \"regorafenib\",\r\n \"rucaparib\",\r\n \"olaparib\",\r\n \"crizotinib\",\r\n \"alectinib\",\r\n \"ibrutinib\",\r\n \"acalabrutinib\",\r\n \"ponatinib\",\r\n \"bosutinib\",\r\n \"vandetanib\",\r\n \"vemurafenib\",\r\n \"dabrafenib\",\r\n \"trametinib\",\r\n \"larotrectinib\",\r\n \"entrectinib\",\r\n \"lorlatinib\",\r\n \"abemaciclib\",\r\n \"palbociclib\",\r\n \"ribociclib\",\r\n \"ruxolitinib\",\r\n \"tofacitinib\",\r\n \"baricitinib\",\r\n \"upadacitinib\",\r\n \"fedratinib\",\r\n \"pacritinib\"\r\n ],\r\n \"ace inhibitor\": [\r\n \"enalapril\",\r\n \"lisinopril\",\r\n \"ramipril\",\r\n \"benazepril\",\r\n \"captopril\",\r\n \"perindopril\",\r\n \"quinapril\",\r\n \"moexipril\",\r\n \"fosinopril\"\r\n ],\r\n \"beta blocker\": [\r\n \"metoprolol\",\r\n \"bisoprolol\",\r\n \"carvedilol\",\r\n \"atenolol\",\r\n \"propranolol\",\r\n \"nebivolol\",\r\n \"labetalol\"\r\n ],\r\n \"ccb\": [\r\n \"amlodipine\",\r\n \"nifedipine\",\r\n \"felodipine\",\r\n \"diltiazem\",\r\n \"verapamil\",\r\n \"lercanidipine\"\r\n ],\r\n \"fibrate\": [\r\n \"fenofibrate\",\r\n \"bezafibrate\",\r\n \"ciprofibrate\",\r\n \"gemfibrozil\"\r\n ],\r\n \"diuretic\": [\r\n \"furosemide\",\r\n \"hydrochlorothiazide\",\r\n \"indapamide\",\r\n \"spironolactone\",\r\n \"torasemide\",\r\n \"bumetanide\"\r\n ],\r\n \"nsaid\": [\r\n \"ibuprofen\",\r\n \"naproxen\",\r\n \"diclofenac\",\r\n \"celecoxib\",\r\n \"meloxicam\",\r\n \"etoricoxib\",\r\n \"indomethacin\"\r\n ],\r\n \"ppi\": [\r\n \"omeprazole\",\r\n \"esomeprazole\",\r\n \"pantoprazole\",\r\n \"lansoprazole\",\r\n \"rabeprazole\",\r\n \"dexrabeprazole\"\r\n ],\r\n \"insulin\": [\r\n \"insulin glargine\",\r\n \"insulin aspart\",\r\n \"insulin lispro\",\r\n \"insulin detemir\",\r\n \"insulin degludec\",\r\n \"insulin glulisine\"\r\n ],\r\n \"agis\": [\r\n \"acarbose\",\r\n \"miglitol\",\r\n \"voglibose\"\r\n ]\r\n },\r\n \"mab_families\": {\r\n \"anti-PD-1\": [\r\n \"pembrolizumab\",\r\n \"nivolumab\",\r\n \"cemiplimab\"\r\n ],\r\n \"anti-PD-L1\": [\r\n \"atezolizumab\",\r\n \"avelumab\",\r\n \"durvalumab\"\r\n ],\r\n \"anti-CTLA-4\": [\r\n \"ipilimumab\",\r\n \"tremelimumab\"\r\n ],\r\n \"anti-HER2\": [\r\n \"trastuzumab\",\r\n \"pertuzumab\",\r\n \"ado-trastuzumab emtansine\",\r\n \"trastuzumab deruxtecan\",\r\n \"margetuximab\"\r\n ],\r\n \"anti-EGFR\": [\r\n \"cetuximab\",\r\n \"panitumumab\",\r\n \"nimotuzumab\"\r\n ],\r\n \"anti-VEGF\n\nArchive v1.2.2: 51 files, 395815 bytes\n\nFiles: adapters/__init__.py (2602b), adapters/bug_report.py (20209b), adapters/coze_token_embedded.py (10126b), adapters/http_probe.py (1605b), adapters/install_sibling.py (12409b), adapters/probe_publication.py (15803b), adapters/refiner.py (46474b), adapters/sanitize.py (2233b), AGENTS.md (7529b), assets/icon.svg (2980b), CHANGELOG.md (233719b), config.json (801b), config/dedup_store.json (3126b), docs/2026-09-23-docarchive-table-spec.md (10810b), docs/2026-09-23-feishu-doc-archive-single-table-plan.md (35199b), docs/2026-09-23-feishu-document-archive-plan.md (20378b), docs/2026-09-23-local-guards-improvement.md (7483b), docs/2026-09-23-upload-limits-and-compression.md (10095b), LICENSE (1091b), README_zh-CN.md (35695b), README.md (38814b), scripts/_perf_deploy.py (2900b), scripts/check_coze.py (5129b), scripts/check_ooxml_sync.py (4401b), scripts/check_route_drift.py (6464b), scripts/clarify_loop.py (20324b), scripts/context_stitch.py (9968b), scripts/dedup_guard.py (5700b), scripts/doc_memory.py (46040b), scripts/entry.py (15384b), scripts/forward_guards.py (5601b), scripts/handle_need_tool.py (43968b), scripts/hardware_id.py (4142b), scripts/i18n_messages.json (31651b), scripts/i18n_skill_messages.json (10095b), scripts/i18n.py (15685b), scripts/kw_lexicon.json (25723b), scripts/office_to_md.py (18121b), scripts/orchestrate.py (33099b), scripts/refine_answer.py (57500b), scripts/route_tool.py (33949b), scripts/route.py (14919b), scripts/run_refined.py (4416b), scripts/scope_guard.py (4483b), scripts/serve.py (5340b), scripts/switch_lang.py (2155b), scripts/sync_i18n_from_ctbase.py (1562b), scripts/tool_mapping.json (17523b), skill-card.md (2190b), SKILL.md (15394b), _meta.json (129b)\n\nArchive v0.9.104: 86 files, 592361 bytes\n\nFiles: adapters/__init__.py (4575b), adapters/backend.py (3707b), adapters/bug_report.py (20209b), adapters/coze_token_embedded.py (10126b), adapters/data_context.py (2611b), adapters/http_probe.py (1605b), adapters/install_sibling.py (8973b), adapters/probe_publication.py (15865b), adapters/qa_store.py (2494b), adapters/refiner.py (42573b), adapters/sanitize.py (2233b), AGENTS.md (9039b), assets/icon.svg (2980b), CHANGELOG.md (210157b), config.json (801b), knowledge/methodology_core.md (20940b), knowledge/prompts.md (19654b), knowledge/ref-gcp-13-principles.md (4786b), knowledge/ref-icae-safety.md (11162b), knowledge/ref-interaction-style.md (10544b), knowledge/ref-ops-compliance-practical.md (9866b), knowledge/ref-ops-data.md (37204b), knowledge/ref-ops-design.md (24187b), knowledge/ref-ops-execution.md (21047b), knowledge/ref-ops-gcp-site.md (43178b), knowledge/ref-ops-safety.md (22568b), knowledge/ref-reg-cn.md (25428b), knowledge/ref-reg-gcp-version.md (2096b), knowledge/ref-reg-safety.md (14634b), knowledge/ref-reg-stats.md (17454b), knowledge/ref-reg-submission.md (38101b), knowledge/ref-regulatory-versions.md (7845b), knowledge/ref-safety-practical.md (7210b), knowledge/reference-index.md (10683b), knowledge/system_prompt.md (45391b), knowledge/term_aliases.json (18336b), LICENSE (1091b), README_zh-CN.md (35353b), README.md (38496b), references/ADVANCED.md (10017b), references/drug_name_map.json (23396b), references/search-sites.md (9543b), references/steps.md (27984b), references/term_map.json (9096b), references/tier_gate.md (10607b), references/tone_writing.md (4460b), references/units.md (8683b), references/visual-appendix.md (6855b), scripts/check_coze.py (5129b), scripts/check_deps.py (10105b), scripts/clarify_loop.py (20324b), scripts/context_stitch.py (9968b), scripts/drug_name_resolver.py (5168b), scripts/excel_style.py (24154b), scripts/gcp_audit.py (10933b), scripts/generate_term_aliases.py (11632b), scripts/handle_need_tool.py (43968b), scripts/hardware_id.py (4142b), scripts/i18n_messages.json (31651b), scripts/i18n_skill_messages.json (10095b), scripts/i18n.py (15685b), scripts/keyword_breadth.py (9756b), scripts/kw_lexicon.json (25723b), scripts/kw_localize.py (34167b), scripts/landscape_scorer.py (14254b), scripts/memory_manager.py (10143b), scripts/menu.json (8514b), scripts/menu.py (9593b), scripts/office_to_md.py (7571b), scripts/orchestrate.py (29575b), scripts/r_libs.py (5411b), scripts/refine_answer.py (54766b), scripts/route_tool.py (33633b), scripts/route.py (18409b), scripts/run_refined.py (4416b), scripts/search_refs.py (5823b), scripts/source_guard.py (5915b), scripts/switch_lang.py (2155b), scripts/sync_i18n_from_ctbase.py (1562b), scripts/tone_matcher.py (15722b)\n\nArchive v0.9.103: 81 files, 454248 bytes\n\nFiles: adapters/__init__.py (4575b), adapters/backend.py (3617b), adapters/bug_report.py (21992b), adapters/coze_token_embedded.py (6584b), adapters/data_context.py (2538b), adapters/http_probe.py (1432b), adapters/qa_store.py (2425b), adapters/refiner.py (37837b), adapters/sanitize.py (2177b), AGENTS.md (9040b), assets/icon.svg (2980b), CHANGELOG.md (74394b), config.json (801b), docs/clawhub_audit_trace_20260815.md (7033b), knowledge/methodology_core.md (17503b), knowledge/prompts.md (19756b), knowledge/ref-gcp-13-principles.md (4556b), knowledge/ref-interaction-style.md (10544b), knowledge/ref-ops-contract.md (158b), knowledge/ref-ops-data.md (37204b), knowledge/ref-ops-design.md (24187b), knowledge/ref-ops-execution.md (21047b), knowledge/ref-ops-gcp-site.md (43178b), knowledge/ref-ops-safety.md (22568b), knowledge/ref-reg-cn.md (25428b), knowledge/ref-reg-contract.md (158b), knowledge/ref-reg-gcp-version.md (2096b), knowledge/ref-reg-retrieval.md (67b), knowledge/ref-reg-safety.md (14634b), knowledge/ref-reg-stats.md (17454b), knowledge/ref-reg-submission.md (38101b), knowledge/ref-regulatory-versions.md (7845b), knowledge/reference-index.md (8778b), knowledge/system_prompt.md (37443b), knowledge/term_aliases.json (18336b), LICENSE (1091b), README_zh-CN.md (22543b), README.md (25276b), references/ADVANCED.md (9175b), references/drug_name_map.json (22340b), references/search-sites.md (9356b), references/steps.md (25462b), references/term_map.json (8934b), references/tone_writing.md (4383b), references/units.md (8543b), scripts/check_coze.py (4904b), scripts/check_deps.py (6588b), scripts/clarify_loop.py (19887b), scripts/context_stitch.py (9743b), scripts/drug_name_resolver.py (5018b), scripts/excel_style.py (23740b), scripts/gcp_audit.py (10607b), scripts/generate_term_aliases.py (11347b), scripts/handle_need_tool.py (15994b), scripts/i18n_messages.json (44189b), scripts/i18n.py (6465b), scripts/keyword_breadth.py (9543b), scripts/kw_lexicon.json (25723b), scripts/kw_localize.py (29986b), scripts/landscape_scorer.py (13850b), scripts/memory_manager.py (9878b), scripts/menu.json (8514b), scripts/menu.py (9354b), scripts/office_to_md.py (7354b), scripts/orchestrate.py (23012b), scripts/r_libs.py (5282b), scripts/refine_answer.py (37006b), scripts/route_tool.py (20526b), scripts/route.py (18063b), scripts/run_refined.py (4287b), scripts/search_refs.py (5683b), scripts/source_guard.py (5779b), scripts/switch_lang.py (2095b), scripts/sync_i18n_from_ctbase.py (1516b), scripts/tone_matcher.py (15358b), scripts/tool_mapping.json (8254b), scripts/update_reference_index.py (3523b), scripts/workflows.json (8751b), skill-card.md (2973b), SKILL.md (28607b)\n\nArchive v0.9.100: 80 files, 436366 bytes\n\nFiles: adapters/__init__.py (4407b), adapters/backend.py (3608b), adapters/bug_report.py (21992b), adapters/coze_token_embedded.py (6584b), adapters/data_context.py (2538b), adapters/http_probe.py (1411b), adapters/qa_store.py (2425b), adapters/refiner.py (33962b), adapters/sanitize.py (2177b), AGENTS.md (8905b), assets/icon.svg (2980b), CHANGELOG.md (68001b), config.json (801b), docs/clawhub_audit_trace_20260815.md (7033b), knowledge/methodology_core.md (17503b), knowledge/prompts.md (19756b), knowledge/ref-gcp-13-principles.md (4556b), knowledge/ref-interaction-style.md (10544b), knowledge/ref-ops-contract.md (158b), knowledge/ref-ops-data.md (37204b), knowledge/ref-ops-design.md (24187b), knowledge/ref-ops-execution.md (21047b), knowledge/ref-ops-gcp-site.md (43178b), knowledge/ref-ops-safety.md (22568b), knowledge/ref-reg-cn.md (25428b), knowledge/ref-reg-contract.md (158b), knowledge/ref-reg-gcp-version.md (2096b), knowledge/ref-reg-retrieval.md (67b), knowledge/ref-reg-safety.md (14634b), knowledge/ref-reg-stats.md (17454b), knowledge/ref-reg-submission.md (38101b), knowledge/ref-regulatory-versions.md (7845b), knowledge/reference-index.md (8778b), knowledge/system_prompt.md (37439b), knowledge/term_aliases.json (18336b), LICENSE (1091b), README_zh-CN.md (24425b), README.md (27074b), references/drug_name_map.json (22340b), references/search-sites.md (9356b), references/steps.md (23800b), references/term_map.json (8934b), references/tone_writing.md (4381b), references/units.md (8543b), scripts/check_coze.py (4904b), scripts/check_deps.py (6588b), scripts/clarify_loop.py (19885b), scripts/context_stitch.py (6728b), scripts/drug_name_resolver.py (5018b), scripts/excel_style.py (23740b), scripts/gcp_audit.py (10607b), scripts/generate_term_aliases.py (11347b), scripts/handle_need_tool.py (8537b), scripts/i18n_messages.json (44189b), scripts/i18n.py (6465b), scripts/keyword_breadth.py (9543b), scripts/kw_lexicon.json (25562b), scripts/kw_localize.py (29986b), scripts/landscape_scorer.py (13850b), scripts/memory_manager.py (9878b), scripts/menu.json (8514b), scripts/menu.py (9354b), scripts/office_to_md.py (7354b), scripts/orchestrate.py (21142b), scripts/r_libs.py (5282b), scripts/refine_answer.py (30625b), scripts/route_tool.py (20526b), scripts/route.py (18063b), scripts/run_refined.py (4287b), scripts/search_refs.py (5683b), scripts/source_guard.py (5779b), scripts/switch_lang.py (2095b), scripts/sync_i18n_from_ctbase.py (1516b), scripts/tone_matcher.py (15358b), scripts/tool_mapping.json (5614b), scripts/update_reference_index.py (3523b), scripts/workflows.json (8751b), skill-card.md (2873b), SKILL.md (27542b), _meta.json (131b)\n\nArchive v0.9.70: 80 files, 436492 bytes\n\nFiles: adapters/__init__.py (4407b), adapters/backend.py (3608b), adapters/bug_report.py (21992b), adapters/coze_token_embedded.py (6584b), adapters/data_context.py (2538b), adapters/http_probe.py (1411b), adapters/qa_store.py (2425b), adapters/refiner.py (33962b), adapters/sanitize.py (2177b), AGENTS.md (8905b), assets/icon.svg (2980b), CHANGELOG.md (68001b), config.json (801b), docs/clawhub_audit_trace_20260815.md (7033b), knowledge/methodology_core.md (17503b), knowledge/prompts.md (19756b), knowledge/ref-gcp-13-principles.md (4556b), knowledge/ref-interaction-style.md (10544b), knowledge/ref-ops-contract.md (158b), knowledge/ref-ops-data.md (37204b), knowledge/ref-ops-design.md (24187b), knowledge/ref-ops-execution.md (21047b), knowledge/ref-ops-gcp-site.md (43178b), knowledge/ref-ops-safety.md (22568b), knowledge/ref-reg-cn.md (25428b), knowledge/ref-reg-contract.md (158b), knowledge/ref-reg-gcp-version.md (2096b), knowledge/ref-reg-retrieval.md (67b), knowledge/ref-reg-safety.md (14634b), knowledge/ref-reg-stats.md (17454b), knowledge/ref-reg-submission.md (38101b), knowledg...","readmeExcerpt":"Skill: Clinical Trial Chief Advisor / 临床试验总顾问 Owner: medstatstar Summary: The single entry point for the ct-series across the full clinical-development lifecycle — a cloud-assisted clinical trial advisor. All questions (methodology / design / compliance / QC / site-execution / intelligence) are forwarded to the cloud Coze engine for analysis. The local side only performs a deterministic binary vague-gate (vague | for","codeSnippets":[],"executableExamples":[],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\r\nslug: ct-advisor\r\nname: ct-advisor\r\ndisplayName: Clinical Trial Chief Advisor / 临床试验总顾问\r\ncn_name: 临床试验总顾问\r\nversion: 1.3.0\r\ninvocable: true\r\nrequired_commands: [python]\r\nsummary: \"面向临床研发全生命周期的 ct 系列「总入口」，云端辅助的临床试验总顾问。所有问题（方法学/设计/合规/QC/现场执行/情报）统一提交云端 Coze 引擎分析处理。本地仅做确定性二值闸门（是否 vague）与附件解码，不保留知识库，不进行本地网络检索。外部参考：teal 临床数据交互探索框架。\"\r\ndescription: \"The single entry point for the ct-series across the full clinical-development lifecycle — a cloud-assisted clinical trial advisor. All questions (methodology / design / compliance / QC / site-execution / intelligence) are forwarded to the cloud Coze engine for analysis. The local side only performs a deterministic binary vague-gate (vague | forwarded) and attachment decoding; no knowledge base is retained locally, and no local network retrieval occurs. External reference: the teal clinical-data interactive exploration framework. / 面向临床研发全生命周期的 ct 系列「总入口」，云端辅助的临床试验总顾问。所有问题（方法学/设计/合规/QC/现场执行/情报）统一提交云端 Coze 引擎分析处理。本地仅做确定性二值闸门（是否 vague）与附件解码，不保留知识库，不进行本地网络检索。外部参考：teal 临床数据交互探索框架。\"\r\nlicense: MIT\r\ntriggers:\r\n - \"ct-advisor\"\r\n - \"clinical trial advisor\"\r\n - \"ct advisor\"\r\n - \"trial methodology\"\r\n - \"clinical trial methodology\"\r\n - \"clinical research advisor\"\r\n - \"trial design\"\r\n - \"GCP question\"\r\n - \"临床试验顾问\"\r\n - \"临床试验总顾问\"\r\ntrigger_scope: \"触发词仅限临床试验方法学/法规/设计/合规/QC/情报类问题；不主动匹配非临床类通用问答；不含文件系统写入与系统级 API 调用。\"\r\nmetadata:\r\n openclaw: { emoji: \"🛠️\", icon: \"assets/icon.svg\" }\r\n authors: [\"medstatstar\", \"phoe-zip\"]\r\n family: ct-series\r\n homepage: \"https://github.com/medstatstar/ct-advisor\"\r\npermissions:\r\n scope: \"user-space-only\"\r\n network: \"controlled-coze-opt-in\"\r\n network_note: \"All questions are forwarded to Coze (single call, internal `scripts/orchestrate.py`). Local side performs NO knowledge base lookup, NO local network retrieval, NO web search. Attachments under 5 MB are uploaded as original bytes to Coze `/upload_file` and shipped as the top-level `doc_context` field (Coze decodes natively); attachments over 5 MB are converted to Markdown locally via `scripts/office_to_md.py` (stdlib-only) and the resulting .md is uploaded through the SAME doc_context channel. The Coze-side knowledge base is the single source of truth.\"\r\n filesystem: \"Read-only to own files; no confidential data leaves locally — Coze payloads sanitized, query_origin is a stable per-machine sha256 hash (non-PII).\"\r\nadapted_from: \"https://github.com/A-xin946/clinical-trial-advisor\"\r\ndependencies:\r\n - {slug: ct-registry, tier: A}\r\n - {slug: ct-safety, tier: A}\r\n - {slug: ct-literature, tier: A}\r\n - {slug: ct-samplesize, tier: A}\r\ntier: A\r\n---\r\n\r\n# Clinical Trial Chief Advisor\r\n\r\n## Published Application\r\n\r\n| Item | Value |\r\n|---|---|\r\n| Share link | `https://ct-advisor.app.workbuddy.host/` |\r\n| appId | `wbapp_FBxILYuXi6yMolY8CsYzA7` |\r\n| Payload | `workbench/publish/` — in-skill, workspace-independent; deploy metadata in `workbench/app.config.json` (Python HTTP service) |\r\n\r\n> **Re-publish rule**: always overwrite with t"},{"path":"README.md","content":"# Clinical Trial Chief Advisor (ct-advisor)\r\n\r\n- **English guide** → [README.md](https://github.com/medstatstar/ct-advisor/blob/main/README.md) · **中文指南** → [README\\_zh-CN.md](https://github.com/medstatstar/ct-advisor/blob/main/README_zh-CN.md)\r\n\r\n
\r\n\"ct-advisor\r\n
\r\n\r\n> **Works without installation:** If you'd rather not install and just want to quickly use this skill's basic features, you can also visit the ct-series unified web portal **https://ct.medstatstar.com** directly.\r\n\r\n> **The single front door for the whole `ct-*` clinical-trial skill family — a methodology & regulatory-evidence advisor that also routes real-data / competitive-intel needs to the sibling data skills through a local, code-only orchestrator (`orchestrate.py`) and stitches their results back in code.**\r\n>\r\n> No commands or manual needed. Just describe your trial question **in plain language inside a chat** — the advisor passes every **non-vague** question to the local orchestrator (`orchestrate.py`), which calls the Coze cloud workflow for methodology / design / statistics / GCP / safety / regulatory / QC / tone answers, and when needed runs the right sibling skill (`ct-registry` / `ct-safety` / `ct-literature` / `ct-samplesize`) **locally** and stitches the result **in code**. It **re-implements no** retrieval or computation logic.\r\n\r\n---\r\n\r\n> **Scope reality check (read this first).** ct-advisor is a **cloud-assisted** advisor, not a pure-local tool. In operation it forwards your **question to the remote Coze engine**; runs sibling `ct-*` skills **locally on your machine** (these skills themselves may query public registries/APIs such as ClinicalTrials.gov, China CDE, FDA FAERS/openFDA, OpenAlex, PubChem); submits an **optional** bug report; keeps a language preference / context cache / memory notes on your device; and runs local connectivity diagnostics. All of this is spelled out honestly in [§5 Data & Privacy](#5-data--privacy).\r\n\r\n> **⚠️ Attachments are part of your question.** If you attach a document (≤5 MB, any Word/Excel/PPT/PDF/TXT), the **original file itself is uploaded to the remote Coze engine** (via the `doc_context` file-id channel) and parsed there — nothing stays local. For files >5 MB the skill converts them to Markdown locally and uploads the converted `.md` the same way. Anything inside an attached file — protocol drafts, sponsor names, subject-level details — should be treated as **leaving your machine**. Remove sensitive content before attaching.\r\n\r\n## Who This Is For\r\n\r\nThe `ct-*` clinical-trial skill family is built to address needs across the entire clinical-trial lifecycle, mainly for three groups:\r\n\r\n- **Clinical-trial practitioners at pharmaceutical companies** — sponsors, CROs, and medical / statistical / regulatory roles;\r\n- **Clinicians and nurses who design, manage clinical-trial projects, or take part in hands-on trial conduct in medical institutions*"},{"path":"_meta.json","content":"{\n \"ownerId\": \"kn7amqq1jv28skb63wavr6shah89jsm5\",\n \"slug\": \"ct-advisor\",\n \"version\": \"1.3.0\",\n \"publishedAt\": 1791546960277\n}"},{"path":"references/drug_name_map.json","content":"{\r\n \"_meta\": {\r\n \"description\": \"中文药物名 → 标准英文 INN/通用名 映射表（用于 openFDA FAERS 检索预处理）\",\r\n \"version\": \"1.1\",\r\n \"updated\": \"2026-09-06\",\r\n \"note\": \"一个中文名可对应多个英文名（如复方制剂、不同盐基）；检索时多候选列出让用户确认。仅覆盖常见药，不在表中时提示用户手动输入英文名。\"\r\n },\r\n \"阿司匹林\": [\r\n \"aspirin\"\r\n ],\r\n \"布洛芬\": [\r\n \"ibuprofen\"\r\n ],\r\n \"对乙酰氨基酚\": [\r\n \"acetaminophen\",\r\n \"paracetamol\"\r\n ],\r\n \"阿莫西林\": [\r\n \"amoxicillin\"\r\n ],\r\n \"头孢氨苄\": [\r\n \"cefalexin\",\r\n \"cephalexin\"\r\n ],\r\n \"头孢呋辛\": [\r\n \"cefuroxime\"\r\n ],\r\n \"头孢曲松\": [\r\n \"ceftriaxone\"\r\n ],\r\n \"阿奇霉素\": [\r\n \"azithromycin\"\r\n ],\r\n \"克拉霉素\": [\r\n \"clarithromycin\"\r\n ],\r\n \"左氧氟沙星\": [\r\n \"levofloxacin\"\r\n ],\r\n \"莫西沙星\": [\r\n \"moxifloxacin\"\r\n ],\r\n \"甲硝唑\": [\r\n \"metronidazole\"\r\n ],\r\n \"奥美拉唑\": [\r\n \"omeprazole\"\r\n ],\r\n \"兰索拉唑\": [\r\n \"lansoprazole\"\r\n ],\r\n \"泮托拉唑\": [\r\n \"pantoprazole\"\r\n ],\r\n \"雷贝拉唑\": [\r\n \"rabeprazole\"\r\n ],\r\n \"艾司奥美拉唑\": [\r\n \"esomeprazole\"\r\n ],\r\n \"法莫替丁\": [\r\n \"famotidine\"\r\n ],\r\n \"雷尼替丁\": [\r\n \"ranitidine\"\r\n ],\r\n \"西咪替丁\": [\r\n \"cimetidine\"\r\n ],\r\n \"二甲双胍\": [\r\n \"metformin\"\r\n ],\r\n \"格列美脲\": [\r\n \"glimepiride\"\r\n ],\r\n \"格列齐特\": [\r\n \"gliclazide\"\r\n ],\r\n \"格列吡嗪\": [\r\n \"glipizide\"\r\n ],\r\n \"格列本脲\": [\r\n \"glibenclamide\",\r\n \"glyburide\"\r\n ],\r\n \"阿卡波糖\": [\r\n \"acarbose\"\r\n ],\r\n \"伏格列波糖\": [\r\n \"voglibose\"\r\n ],\r\n \"瑞格列奈\": [\r\n \"repaglinide\"\r\n ],\r\n \"那格列奈\": [\r\n \"nateglinide\"\r\n ],\r\n \"西格列汀\": [\r\n \"sitagliptin\"\r\n ],\r\n \"沙格列汀\": [\r\n \"saxagliptin\"\r\n ],\r\n \"利格列汀\": [\r\n \"linagliptin\"\r\n ],\r\n \"维格列汀\": [\r\n \"vildagliptin\"\r\n ],\r\n \"恩格列净\": [\r\n \"empagliflozin\"\r\n ],\r\n \"达格列净\": [\r\n \"dapagliflozin\"\r\n ],\r\n \"卡格列净\": [\r\n \"canagliflozin\"\r\n ],\r\n \"吡格列酮\": [\r\n \"pioglitazone\"\r\n ],\r\n \"罗格列酮\": [\r\n \"rosiglitazone\"\r\n ],\r\n \"胰岛素\": [\r\n \"insulin\"\r\n ],\r\n \"甘精胰岛素\": [\r\n \"insulin glargine\"\r\n ],\r\n \"门冬胰岛素\": [\r\n \"insulin aspart\"\r\n ],\r\n \"赖脯胰岛素\": [\r\n \"insulin lispro\"\r\n ],\r\n \"地特胰岛素\": [\r\n \"insulin detemir\"\r\n ],\r\n \"格列喹酮\": [\r\n \"gliquidone\"\r\n ],\r\n \"阿托伐他汀\": [\r\n \"atorvastatin\"\r\n ],\r\n \"瑞舒伐他汀\": [\r\n \"rosuvastatin\"\r\n ],\r\n \"辛伐他汀\": [\r\n \"simvastatin\"\r\n ],\r\n \"普伐他汀\": [\r\n \"pravastatin\"\r\n ],\r\n \"氟伐他汀\": [\r\n \"fluvastatin\"\r\n ],\r\n \"匹伐他汀\": [\r\n \"pitavastatin\"\r\n ],\r\n \"洛伐他汀\": [\r\n \"lovastatin\"\r\n ],\r\n \"依折麦布\": [\r\n \"ezetimibe\"\r\n ],\r\n \"非诺贝特\": [\r\n \"fenofibrate\"\r\n ],\r\n \"吉非贝齐\": [\r\n \"gemfibrozil\"\r\n ],\r\n \"苯扎贝特\": [\r\n \"bezafibrate\"\r\n ],\r\n \"考来烯胺\": [\r\n \"cholestyramine\"\r\n ],\r\n \"阿昔单抗\": [\r\n \"abciximab\"\r\n ],\r\n \"氯吡格雷\": [\r\n \"clopidogrel\"\r\n ],\r\n \"替格瑞洛\": [\r\n \"ticagrelor\"\r\n ],\r\n \"普拉格雷\": [\r\n \"prasugrel\"\r\n ],\r\n \"华法林\": [\r\n \"warfarin\"\r\n ],\r\n \"利伐沙班\": [\r\n \"rivaroxaban\"\r\n ],\r\n \"阿哌沙班\": [\r\n \"apixaban\"\r\n ],\r\n \"达比加群\": [\r\n \"dabigatran\"\r\n ],\r\n \"依度沙班\": [\r\n \"edoxaban\"\r\n ],\r\n \"肝素\": [\r\n \"heparin\"\r\n ],\r\n \"低分子肝素\": [\r\n \"enoxaparin\",\r\n \"low molecular weight heparin\"\r\n ],\r\n \"达肝素\": [\r\n \"dalteparin\"\r\n ],\r\n \"那屈肝素\": [\r\n \"nadroparin\"\r\n ],\r\n \"磺达肝癸钠\": [\r\n \"fondaparinux\"\r\n ],\r\n \"阿替普酶\": [\r\n "},{"path":"references/term_map.json","content":"{\r\n \"1型糖尿病\": \"type 1 diabetes\",\r\n \"2型糖尿病\": \"type 2 diabetes\",\r\n \"ALK\": \"ALK\",\r\n \"BRAF\": \"BRAF\",\r\n \"BRCA\": \"BRCA\",\r\n \"CAR-T\": \"CAR-T\",\r\n \"CDK4/6\": \"CDK4/6\",\r\n \"CTLA-4\": \"CTLA-4\",\r\n \"EGFR\": \"EGFR\",\r\n \"Graves病\": \"Graves disease\",\r\n \"HER2\": \"HER2\",\r\n \"III期临床试验\": \"phase III clinical trial\",\r\n \"IgA肾病\": \"IgA nephropathy\",\r\n \"KRAS\": \"KRAS\",\r\n \"MET\": \"MET\",\r\n \"NTRK\": \"NTRK\",\r\n \"PD-1\": \"PD-1\",\r\n \"PD-L1\": \"PD-L1\",\r\n \"PI3K\": \"PI3K\",\r\n \"RET\": \"RET\",\r\n \"ROS1\": \"ROS1\",\r\n \"一线\": \"first-line\",\r\n \"一线治疗\": \"first-line therapy\",\r\n \"三叉神经痛\": \"trigeminal neuralgia\",\r\n \"三线\": \"third-line\",\r\n \"三线治疗\": \"third-line therapy\",\r\n \"上市后监测\": \"post-marketing surveillance\",\r\n \"不良事件\": \"adverse events\",\r\n \"不良反应\": \"adverse events\",\r\n \"丙卡特罗\": \"procaterol\",\r\n \"丙肝\": \"hepatitis C\",\r\n \"丛集性头痛\": \"cluster headache\",\r\n \"中位总生存期\": \"median overall survival\",\r\n \"中位无进展生存期\": \"median progression-free survival\",\r\n \"临床试验\": \"clinical trial\",\r\n \"主动脉夹层\": \"aortic dissection\",\r\n \"乌司奴单抗\": \"ustekinumab\",\r\n \"乌美溴铵\": \"umeclidinium bromide\",\r\n \"乐卡地平\": \"lercanidipine\",\r\n \"乙肝\": \"hepatitis B\",\r\n \"乳腺癌\": \"breast cancer\",\r\n \"二线\": \"second-line\",\r\n \"二线治疗\": \"second-line therapy\",\r\n \"二羟丙茶碱\": \"diprophylline\",\r\n \"亚急性甲状腺炎\": \"subacute thyroiditis\",\r\n \"亨廷顿病\": \"Huntington disease\",\r\n \"仑伐替尼\": \"lenvatinib\",\r\n \"他克莫司\": \"tacrolimus\",\r\n \"他拉唑帕利\": \"talazoparib\",\r\n \"他法替他单抗\": \"tafasitamab\",\r\n \"他莫昔芬\": \"tamoxifen\",\r\n \"代谢综合征\": \"metabolic syndrome\",\r\n \"伊伐布雷定\": \"ivabradine\",\r\n \"伊匹木单抗\": \"ipilimumab\",\r\n \"伊布替尼\": \"ibrutinib\",\r\n \"伊沙佐米\": \"ixazomib\",\r\n \"伊班膦酸钠\": \"ibandronate\",\r\n \"伊立替康\": \"irinotecan\",\r\n \"伊马替尼\": \"imatinib\",\r\n \"伏美替尼\": \"furmonertinib\",\r\n \"伯西塔单抗\": \"brolucizumab\",\r\n \"低分子肝素\": \"low molecular weight heparin (LMWH)\",\r\n \"低强度激光治疗\": \"low-level laser therapy (LLLT)\",\r\n \"依奇珠单抗\": \"ixekizumab\",\r\n \"依库珠单抗\": \"eculizumab\",\r\n \"依度沙班\": \"edoxaban\",\r\n \"依折麦布\": \"ezetimibe\",\r\n \"依普利酮\": \"eplerenone\",\r\n \"依替巴肽\": \"eptifibatide\",\r\n \"依洛尤单抗\": \"evolocumab\",\r\n \"依维莫司\": \"everolimus\",\r\n \"依降钙素\": \"elcatonin\",\r\n \"促皮质素\": \"corticotropin\",\r\n \"信迪利单抗\": \"sintilimab\",\r\n \"倍他米松\": \"betamethasone\",\r\n \"倍氯米松\": \"beclomethasone\",\r\n \"假性痛风\": \"pseudogout\",\r\n \"偏头痛\": \"migraine\",\r\n \"儿童\": \"pediatric\",\r\n \"光生物调节\": \"photobiomodulation (PBM)\",\r\n \"克唑替尼\": \"crizotinib\",\r\n \"克罗恩病\": \"Crohn disease\",\r\n \"免疫检查点抑制剂\": \"immune checkpoint inhibitor\",\r\n \"免疫治疗\": \"immunotherapy\",\r\n \"免疫相关不良事件\": \"immune-related adverse events (irAE)\",\r\n \"兰瑞肽\": \"lanreotide\",\r\n \"内分泌治疗\": \"endocrine therapy\",\r\n \"再生障碍性贫血\": \"aplastic anemia\",\r\n \"冠心病\": \"coronary artery disease (CAD)\",\r\n \"凡德他尼\": \"vandetanib\",\r\n \"出血性卒中\": \"hemorrhagic stroke\",\r\n \"利伐沙班\": \"rivaroxaban\",\r\n \"利塞膦酸钠\": \"risedronate\",\r\n \"利妥昔单抗\": \"rituximab\",\r\n \"利拉鲁肽\": \"liraglutide\",\r\n \"利生奇珠单抗\": \"risankizumab\",\r\n \"利纳西珠单抗\": \"rilonacept\",\r\n \"利血平\": \"reserpine\",\r\n \"剂量\": \"dose\",\r\n \"剂量爬坡\": \"dose escalation\",\r\n \"前列腺癌\": \"prostate cancer\",\r\n \"前瞻性研究\": \"prospective study\",\r\n \"动脉瘤\": \"aneurysm\",\r\n \"动脉粥样硬化\": \"atherosclerosis\",\r\n \"化疗\": \"chemotherapy\",\r\n \"卒中\": \"stroke\",\r\n \"单硝酸异山梨酯\": \"isosorbide mononitra"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"The single entry point for the ct-series across the full clinical-development lifecycle — a cloud-assisted clinical trial advisor. All questions (methodology / design / compliance / QC / site-execution / intelligence) are forwarded to the cloud Coze engine for analysis. The local side only performs a deterministic binary vague-gate (vague | forwarded) and attachment decoding; no knowledge base is retained locally, and no local network retrieval occurs. External reference: the teal clinical-data interactive exploration framework. / 面向临床研发全生命周期的 ct 系列「总入口」，云端辅助的临床试验总顾问。所有问题（方法学/设计/合规/QC/现场执行/情报）统一提交云端 Coze 引擎分析处理。本地仅做确定性二值闸门（是否 vague）与附件解码，不保留知识库，不进行本地网络检索。外部参考：teal 临床数据交互探索框架。 Skill: Clinical Trial Chief Advisor / 临床试验总顾问 Owner: medstatstar Summary: The single entry point for the ct-series across the full clinical-development lifecycle — a cloud-assisted clinical trial advisor. All questions (methodology / design / compliance / QC / site-execution / intelligence) are forwarded to the cloud Coze engine for analysis. The local side only performs a deterministic binary vague-gate (vague | for","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":1798,"uniquenessScore":56,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-10T05:18:56.414Z","emptyReason":"No screenshots, media assets, or demo links are available."},"primaryImageUrl":null,"mediaAssetCount":0,"assets":[],"demoUrl":null},"ownerResources":{"evidence":{"source":"unclaimed","verified":false,"confidence":"low","updatedAt":"2026-10-10T05:18:56.414Z","emptyReason":"This page has not been claimed by the agent owner."},"hasCustomPage":false,"customPageUpdatedAt":null,"customLinks":[],"structuredLinks":{"docsUrl":null,"demoUrl":null,"supportUrl":null,"pricingUrl":null,"statusUrl":null},"customPage":null},"relatedAgents":{"evidence":{"source":"protocol-neighbors","verified":false,"confidence":"medium","updatedAt":"2026-10-10T10:43:12.000Z","emptyReason":null},"items":[{"id":"8ebccd8e-3863-4187-8355-c3f14e1f9edf","entityType":"agent","canonicalPath":"/agent/iofficeai-aionui","slug":"iofficeai-aionui","name":"AionUi","description":"Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!","url":"https://github.com/iOfficeAI/AionUi","homepage":"https://www.aionui.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-10-09T19:11:12.944Z","createdAt":"2026-02-25T03:38:16.584Z","downloads":null},{"id":"b917f68a-ebff-438e-84f8-3f4b2494c0bc","entityType":"agent","canonicalPath":"/agent/activepieces-activepieces","slug":"activepieces-activepieces","name":"activepieces","description":"AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents","url":"https://github.com/activepieces/activepieces","homepage":"https://www.activepieces.com","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-15T02:22:12.426Z","createdAt":"2026-02-25T03:38:12.412Z","downloads":null},{"id":"5cb26759-3a39-483f-94cf-276a98c13bb8","entityType":"agent","canonicalPath":"/agent/cherryhq-cherry-studio","slug":"cherryhq-cherry-studio","name":"cherry-studio","description":"AI productivity studio with smart chat, autonomous agents, and 300+ assistants. Unified access to frontier LLMs","url":"https://github.com/CherryHQ/cherry-studio","homepage":"https://cherry-ai.com","source":"GITHUB_REPOS","protocols":["MCP","OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-04-11T14:38:40.986Z","createdAt":"2026-02-25T03:38:19.379Z","downloads":null},{"id":"6f6582d0-5d76-4f0f-b81d-86520247950b","entityType":"agent","canonicalPath":"/agent/copilotkit-copilotkit","slug":"copilotkit-copilotkit","name":"CopilotKit","description":"The Frontend for Agents & Generative UI. React + Angular","url":"https://github.com/CopilotKit/CopilotKit","homepage":"https://docs.copilotkit.ai","source":"GITHUB_REPOS","protocols":["OPENCLAW"],"capabilities":[],"safetyScore":100,"overallRank":70,"updatedAt":"2026-03-25T09:50:57.846Z","createdAt":"2026-02-25T03:39:14.617Z","downloads":null}],"links":{"hub":"/agent","source":"/agent/source/clawhub","protocols":[{"label":"OpenClaw","href":"/agent/protocol/openclew"}]}}}