{"id":"a5230c5e-85cd-42da-b46f-bdb2d962be3b","entityType":"agent","slug":"clawhub-eric-promax-academic-pipeline-suite","name":"academic-pipeline-suite","canonicalUrl":"https://www.xpersona.co/agent/clawhub-eric-promax-academic-pipeline-suite","canonicalPath":"/agent/clawhub-eric-promax-academic-pipeline-suite","generatedAt":"2026-10-12T21:35:03.961Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-12T00:19:28.754Z","emptyReason":null},"description":"Complete Academic Research & Writing Suite — One-click installation of the full Academic Pipeline ecosystem with all 8 dependencies. Includes academic-pipeli... Skill: academic-pipeline-suite Owner: eric-promax Summary: Complete Academic Research & Writing Suite — One-click installation of the full Academic Pipeline ecosystem with all 8 dependencies. Includes academic-pipeli... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-05-14T05:39:41.568Z | user Academic Pipeline Suite v1.0.0 - Initial release of the academic-suite meta-skill package. - One-click offline installation","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 969 downloads reported by the source. Last updated 10/12/2026.","installCommand":"clawhub skill install s1746e7bcag3t464dy9vye9kr586pe2v:academic-pipeline-suite","sourceUrl":"https://clawhub.ai/eric-promax/academic-pipeline-suite","homepage":"https://clawhub.ai/eric-promax/skills/academic-pipeline-suite","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/eric-promax/academic-pipeline-suite","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/eric-promax/skills/academic-pipeline-suite","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":60,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"Complete Academic Research & Writing Suite — One-click installation of the full Academic Pipeline ecosystem with all 8 dependencies. Includes academic-pipeli..."},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-12T00:19:28.754Z","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":"2026-10-12T00:19:28.754Z","emptyReason":null},"stars":null,"forks":null,"downloads":969,"likes":null,"task":null,"library":null,"packageName":null,"latestVersion":"1.0.0","tractionLabel":"969 downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-12T00:19:28.121Z","emptyReason":null},"lastUpdatedAt":"2026-10-12T00:19:28.754Z","lastCrawledAt":"2026-10-12T00:19:28.121Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-13T00:19:28.121Z","lastVerifiedAt":null,"highlights":[{"version":"1.0.0","createdAt":"2026-05-14T05:39:41.568Z","changelog":"Academic Pipeline Suite v1.0.0 - Initial release of the academic-suite meta-skill package. - One-click offline installation for the entire Academic Pipeline ecosystem. - Bundles 8 key dependencies, including academic-pipeline v3.5, academic-search, deep-research, academic-paper, paper review tools, humanizer (EN/zh), ima-skills, and integrity-verification agent. - Unified 12-stage academic research and writing workflow with mandatory checkpoints. - Added HUMANIZE (Stage 10), enhanced startup configuration, and improved integrity/peer review flow.","fileCount":188,"zipByteSize":766474}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s1746e7bcag3t464dy9vye9kr586pe2v:academic-pipeline-suite","setupComplexity":"low","setupSteps":["Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.","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-eric-promax-academic-pipeline-suite/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-eric-promax-academic-pipeline-suite/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-eric-promax-academic-pipeline-suite/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-eric-promax-academic-pipeline-suite/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-eric-promax-academic-pipeline-suite/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-eric-promax-academic-pipeline-suite/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-12T21:35:03.959Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-eric-promax-academic-pipeline-suite/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-eric-promax-academic-pipeline-suite/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-eric-promax-academic-pipeline-suite/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-eric-promax-academic-pipeline-suite/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":"2026-10-12T00:19:28.754Z","emptyReason":null},"readme":"Skill: academic-pipeline-suite\n\nOwner: eric-promax\n\nSummary: Complete Academic Research & Writing Suite — One-click installation of the full Academic Pipeline ecosystem with all 8 dependencies. Includes academic-pipeli...\n\nTags: latest:1.0.0\n\nVersion history:\n\nv1.0.0 | 2026-05-14T05:39:41.568Z | user\n\nAcademic Pipeline Suite v1.0.0\n\n- Initial release of the academic-suite meta-skill package.\n- One-click offline installation for the entire Academic Pipeline ecosystem.\n- Bundles 8 key dependencies, including academic-pipeline v3.5, academic-search, deep-research, academic-paper, paper review tools, humanizer (EN/zh), ima-skills, and integrity-verification agent.\n- Unified 12-stage academic research and writing workflow with mandatory checkpoints.\n- Added HUMANIZE (Stage 10), enhanced startup configuration, and improved integrity/peer review flow.\n\nArchive index:\n\nArchive v1.0.0: 188 files, 766474 bytes\n\nFiles: clawhub.json (1833b), install.sh (2223b), publish.sh (2168b), QUICKSTART.md (5087b), README.md (4529b), RELEASE_NOTES.md (6621b), skill-card.md (2892b), SKILL.md (9163b), skills/academic-paper-reviewer/agents/devils_advocate_reviewer_agent.md (12106b), skills/academic-paper-reviewer/agents/domain_reviewer_agent.md (8859b), skills/academic-paper-reviewer/agents/editorial_synthesizer_agent.md (11015b), skills/academic-paper-reviewer/agents/eic_agent.md (5577b), skills/academic-paper-reviewer/agents/field_analyst_agent.md (9280b), skills/academic-paper-reviewer/agents/methodology_reviewer_agent.md (10311b), skills/academic-paper-reviewer/agents/perspective_reviewer_agent.md (11439b), skills/academic-paper-reviewer/examples/hei_paper_review_example.md (26417b), skills/academic-paper-reviewer/examples/interdisciplinary_review_example.md (19174b), skills/academic-paper-reviewer/references/calibration_mode_protocol.md (10251b), skills/academic-paper-reviewer/references/changelog.md (976b), skills/academic-paper-reviewer/references/editorial_decision_standards.md (9230b), skills/academic-paper-reviewer/references/guided_mode_protocol.md (1679b), skills/academic-paper-reviewer/references/integration_guide.md (680b), skills/academic-paper-reviewer/references/quality_rubrics.md (7679b), skills/academic-paper-reviewer/references/re_review_mode_protocol.md (3959b), skills/academic-paper-reviewer/references/review_criteria_framework.md (10139b), skills/academic-paper-reviewer/references/review_quality_thinking.md (3015b), skills/academic-paper-reviewer/references/statistical_reporting_standards.md (22703b), skills/academic-paper-reviewer/references/top_journals_by_field.md (12874b), skills/academic-paper-reviewer/SKILL.md (20444b), skills/academic-paper-reviewer/templates/editorial_decision_template.md (6446b), skills/academic-paper-reviewer/templates/peer_review_report_template.md (7479b), skills/academic-paper-reviewer/templates/revision_response_template.md (7020b), skills/academic-paper/agents/abstract_bilingual_agent.md (5601b), skills/academic-paper/agents/argument_builder_agent.md (10408b), skills/academic-paper/agents/citation_compliance_agent.md (18347b), skills/academic-paper/agents/draft_writer_agent.md (20338b), skills/academic-paper/agents/formatter_agent.md (29231b), skills/academic-paper/agents/intake_agent.md (10220b), skills/academic-paper/agents/literature_strategist_agent.md (15763b), skills/academic-paper/agents/peer_reviewer_agent.md (21446b), skills/academic-paper/agents/revision_coach_agent.md (12512b), skills/academic-paper/agents/socratic_mentor_agent.md (24726b), skills/academic-paper/agents/structure_architect_agent.md (14737b), skills/academic-paper/agents/visualization_agent.md (15710b), skills/academic-paper/examples/chinese_paper_example.md (21572b), skills/academic-paper/examples/imrad_hei_example.md (23879b), skills/academic-paper/examples/literature_review_example.md (31541b), skills/academic-paper/examples/plan_mode_guided_writing.md (35170b), skills/academic-paper/examples/revision_mode_example.md (20318b), skills/academic-paper/examples/revision_recovery_example.md (41036b), skills/academic-paper/references/abstract_writing_guide.md (7981b), skills/academic-paper/references/academic_writing_style.md (7667b), skills/academic-paper/references/anti_leakage_protocol.md (3864b), skills/academic-paper/references/apa7_chinese_citation_guide.md (12510b), skills/academic-paper/references/apa7_extended_guide.md (6725b), skills/academic-paper/references/changelog.md (2821b), skills/academic-paper/references/citation_format_switcher.md (7548b), skills/academic-paper/references/credit_authorship_guide.md (13983b), skills/academic-paper/references/disclosure_mode_protocol.md (7074b), skills/academic-paper/references/failure_paths.md (14163b), skills/academic-paper/references/funding_statement_guide.md (12193b), skills/academic-paper/references/hei_domain_glossary.md (6974b), skills/academic-paper/references/journal_submission_guide.md (8891b), skills/academic-paper/references/latex_template_reference.md (9851b), skills/academic-paper/references/mode_selection_guide.md (12396b), skills/academic-paper/references/paper_structure_patterns.md (8408b), skills/academic-paper/references/plan_mode_protocol.md (4839b), skills/academic-paper/references/statistical_visualization_standards.md (24247b), skills/academic-paper/references/venue_disclosure_policies.md (7445b), skills/academic-paper/references/vlm_figure_verification.md (3312b), skills/academic-paper/references/workflow_phase_details.md (3378b), skills/academic-paper/references/writing_judgment_framework.md (3336b), skills/academic-paper/references/writing_quality_check.md (9235b), skills/academic-paper/SKILL.md (19163b), skills/academic-paper/templates/bilingual_abstract_template.md (2943b), skills/academic-paper/templates/case_study_template.md (2895b), skills/academic-paper/templates/conference_paper_template.md (2363b), skills/academic-paper/templates/credit_statement_template.md (4476b), skills/academic-paper/templates/funding_statement_template.md (9091b), skills/academic-paper/templates/imrad_template.md (4544b)\n\nFile v1.0.0:SKILL.md\n\n---\nname: academic-suite\ndescription: \"Complete Academic Research & Writing Suite — One-click installation of the full Academic Pipeline ecosystem with all 8 dependencies. Includes academic-pipeline v3.5, academic-search, deep-research, academic-paper, academic-paper-reviewer, humanizer, humanizer-zh, ima-skills, and integrity_verification_agent.\"\nmetadata:\n version: \"3.5.0\"\n last_updated: \"2026-05-14\"\n author: \"eric-promax\"\n license: \"MIT\"\n suite: true\n dependencies:\n - \"ima-skills\"\n - \"academic-search\"\n - \"deep-research\"\n - \"academic-paper\"\n - \"academic-paper-reviewer\"\n - \"humanizer\"\n - \"humanizer-zh\"\n - \"integrity_verification_agent\"\n status: active\n category: \"Academic Research\"\n tags:\n - academic\n - research\n - writing\n - pipeline\n - paper\n - thesis\n - literature-review\n - peer-review\n - de-ai\n---\n\n# Academic Suite v3.5.0 — 一键安装完整学术套件\n\n**元技能包（Meta-Skill Package）**\n\n这是一个元技能包，用于一键安装完整的 Academic Pipeline 生态系统。**所有 9 个依赖技能已打包在内**，安装时无需联网下载，100% 离线可用。\n\n---\n\n## 🎯 快速开始\n\n### 安装（一键完成）\n\n```bash\n# 解压后，进入目录运行安装脚本\ncd academic-suite-v3.5.0\n./install.sh\n```\n\n**无需联网**，所有 9 个技能已打包在内：\n\n| # | 技能 | 用途 |\n|---|------|------|\n| 1 | `academic-pipeline` | 12 阶段全流程编排器 |\n| 2 | `academic-search` | 8 大平台文献检索 |\n| 3 | `deep-research` | 深度研究分析 |\n| 4 | `academic-paper` | 论文撰写/修订 |\n| 5 | `academic-paper-reviewer` | 同行评审 |\n| 6 | `humanizer` | 英文去 AI 化 |\n| 7 | `humanizer-zh` | 中文去 AI 化 |\n| 8 | `ima-skills` | IMA 知识库 |\n| 9 | `integrity_verification_agent` | 学术诚信验证 |\n\n---\n\n## 📦 包含内容\n\n### 核心编排器\n- **academic-pipeline v3.5** — 12 阶段全流程编排器\n\n### 依赖技能（8 个）\n- **ima-skills** — IMA 知识库客户端\n- **academic-search v1.2.0** — 多源文献检索（8 平台 + 查询扩展 + 两遍搜索）\n- **deep-research v2.0** — 深度研究（13-Agent 团队）\n- **academic-paper v2.0** — 论文写作（12-Agent 流程）\n- **academic-paper-reviewer v1.1** — 同行评审（5 人评审团）\n- **humanizer v1.0** — 英文去 AI 化\n- **humanizer-zh v1.0** — 中文去 AI 化\n- **integrity_verification_agent** — 学术诚信验证\n\n---\n\n## 🚀 使用流程\n\n安装完成后，您可以直接使用自然语言启动学术写作：\n\n### 示例 1：从零开始写论文\n\n```\n我要用 Academic Pipeline 写一篇关于\"中国股市炒新现象\"的 MBA 课程论文，8000 字\n```\n\n系统将自动：\n1. 询问 5 项配置（IMA 路径、论文类型、字数、内容要求、开题报告）\n2. 启动 Stage 1 LITERATURE SEARCH（文献检索）\n3. 依次执行 12 个阶段，直到最终 PDF 定稿\n\n### 示例 2：中途进入评审\n\n```\n我已经有一份论文草稿，帮我进入评审流程\n```\n\n系统将自动：\n1. 检测您已有论文草稿\n2. 从 Stage 4 INTEGRITY（学术诚信验证）开始\n3. 执行后续评审、修订、定稿流程\n\n### 示例 3：修订已有论文\n\n```\n我收到了审稿人的修改意见，帮我修订\n```\n\n系统将自动：\n1. 进入 Stage 7 REVISE（修订模式）\n2. 逐条回应审稿意见\n3. 执行验证评审 → 最终验证 → 定稿\n\n---\n\n## 📊 12 阶段全景图\n\n```\n┌──────────────────────────────────────────────────────────────┐\n│ Stage 1 LITERATURE SEARCH (IMA + academic-search) │\n│ ↓ 用户确认 │\n│ Stage 2 RESEARCH (deep-research) │\n│ ↓ 用户确认 │\n│ Stage 3 WRITE (academic-paper) │\n│ ↓ 用户确认 │\n│ Stage 4 INTEGRITY ✦ 强制 ✦ (引用/数据 100% 验证) │\n│ ↓ PASS → 继续；FAIL → 修复重验（最多 3 轮） │\n│ Stage 5 REVIEW (5 人同行评审) ✦ 强制 ✦ │\n│ ↓ Accept→Stage 9 / Minor→Stage 7 / Reject→Stage 3 │\n│ Stage 6 RE-REVIEW (验证评审) ✦ 强制 ✦ │\n│ ↓ Accept→Stage 9 / Major→Stage 8 │\n│ Stage 7 REVISE (academic-paper revision 模式) │\n│ ↓ 用户确认 │\n│ Stage 8 RE-REVISE (二次修订，最多 1 轮) │\n│ ↓ 用户确认 │\n│ Stage 9 FINAL INTEGRITY ✦ 强制 ✦ (零问题才能过) │\n│ ↓ PASS │\n│ Stage 10 HUMANIZE ✦ 强制 ✦ (去 AI 化处理) │\n│ ↓ 用户确认去 AI 版本 │\n│ Stage 11 FINALIZE (academic-paper format-convert) │\n│ ↓ MD+DOCX→LaTeX→PDF │\n│ Stage 12 PROCESS SUMMARY (过程记录 PDF) │\n└──────────────────────────────────────────────────────────────┘\n```\n\n**✦ 强制门控**：Stage 4、9（完整性验证）、Stage 5、6（评审决定）、Stage 10（去 AI 化）、Stage 11（终稿）— 不可跳过，必须用户明确确认\n\n---\n\n## 🔧 安装后验证\n\n安装完成后，运行以下命令验证所有技能已正确安装：\n\n```bash\n# 检查已安装的学术相关技能\nls ~/.openclaw/workspace/skills/ | grep -E \"academic|humanizer|ima|integrity\"\n```\n\n预期输出：\n```\nacademic-pipeline\nacademic-search\ndeep-research\nacademic-paper\nacademic-paper-reviewer\nhumanizer\nhumanizer-zh\nima-skills\nintegrity_verification_agent\n```\n\n---\n\n## ⚙️ 配置要求\n\n### API 配置（可选但推荐）\n\n| 服务 | 用途 | 配置方式 |\n|------|------|---------|\n| **IMA 知识库** | 参考文献库存储 | 在 Stage 1 启动时提供路径 |\n| **Semantic Scholar API** | 英文文献检索 | 在 academic-search 中配置 |\n| **知网（CNKI）** | 中文文献检索 | 通过 Tavily 代理，无需额外配置 |\n\n### 系统要求\n\n| 项目 | 要求 |\n|------|------|\n| OpenClaw 版本 | v2026.4.21+ |\n| Node.js | v22.x |\n| 磁盘空间 | ~50MB（所有技能总计） |\n| 网络 | 需要访问学术数据库 API |\n\n---\n\n## 📚 文档资源\n\n| 文档 | 链接 |\n|------|------|\n| **完整使用指南** | https://feishu.cn/docx/GRb7dGij9olddExTBsCcpoaCnWg |\n| **GitHub 仓库** | https://github.com/eric-promax/academic-agents.git |\n| **ClawHub 页面** | https://clawhub.ai/eric-promax/academic-suite |\n\n---\n\n## 🐛 故障排除\n\n### 问题 1：安装后提示依赖缺失\n\n**症状：** 启动 Pipeline 时提示某个技能未找到\n\n**解决：**\n```bash\n# 重新安装学术套件\nclawhub install eric-promax/academic-suite --force\n\n# 或手动安装缺失的技能\nclawhub install <缺失的技能名>\n```\n\n### 问题 2：Stage 1 无法连接 IMA 知识库\n\n**症状：** Stage 1 LITERATURE SEARCH 时 IMA API 调用失败\n\n**解决：**\n1. 检查 IMA API Key 是否配置\n2. 确认知识库路径正确（如\"个人知识库/eric/毕业论文\"）\n3. 如无 IMA 知识库，输入\"无\"跳过，直接使用 academic-search\n\n### 问题 3：去 AI 化阶段失败\n\n**症状：** Stage 10 HUMANIZE 报错\n\n**解决：**\n```bash\n# 检查 humanizer 技能是否安装\nls ~/.openclaw/workspace/skills/ | grep humanizer\n\n# 重新安装 humanizer 套件\nclawhub install humanizer\nclawhub install humanizer-zh\n```\n\n---\n\n## 📝 版本历史\n\n### v3.5.0（2026-05-14）\n- ✅ 首次发布 academic-suite 元技能包\n- ✅ 整合 8 个依赖技能，一键安装\n- ✅ 阶段编号统一为连续整数（1-12）\n- ✅ 新增 5 项启动配置询问\n- ✅ 新增 Stage 10 HUMANIZE 去 AI 化\n\n### v3.4（2026-04-24）\n- ✅ academic-pipeline v3.4 发布\n- ✅ 集成 humanizer + humanizer-zh\n- ✅ 集成 academic-search（8 平台文献检索）\n- ✅ IMA 知识库对接\n\n### v3.3（2026-04-24）\n- ✅ 并行化优化（Stage 3 写作阶段）\n- ✅ humanizer 集成\n\n### v3.2（2026-04-15）\n- ✅ 收敛停止规则\n- ✅ 预算透明\n- ✅ AI 研究失败模式清单（7 模式）\n\n---\n\n## 📞 支持\n\n| 渠道 | 联系方式 |\n|------|---------|\n| **GitHub Issues** | https://github.com/eric-promax/academic-agents/issues |\n| **ClawHub 讨论区** | https://clawhub.ai/eric-promax/academic-suite/discussions |\n| **飞书文档评论** | https://feishu.cn/docx/GRb7dGij9olddExTBsCcpoaCnWg |\n\n---\n\n## 📄 许可证\n\nMIT License\n\n---\n\n**维护者：** 大头虾 (eric-promax) \n**最后更新：** 2026-05-14 \n**版本：** 3.5.0\n\n---\n\n*严谨是分析的基础，逻辑是推理的武器。* 🔮\n\nFile v1.0.0:skills/academic-paper-reviewer/SKILL.md\n\n---\nname: academic-paper-reviewer\ndescription: \"Multi-perspective academic paper review with dynamic reviewer personas. Simulates 5 independent reviewers (EIC + 3 peer reviewers + Devil's Advocate) with field-specific expertise. Supports full review, re-review (verification), quick assessment, methodology focus, Socratic guided, and calibration modes. Triggers on: review paper, peer review, manuscript review, referee report, review my paper, critique paper, simulate review, editorial review, calibrate reviewer, reviewer calibration, measure reviewer accuracy.\"\nmetadata:\n version: \"1.8\"\n last_updated: \"2026-04-09\"\n status: active\n related_skills:\n - academic-paper\n - academic-pipeline\n---\n\n# Academic Paper Reviewer v1.8 — Multi-Perspective Academic Paper Review Agent Team\n\nSimulates a complete international journal peer review process: automatically identifies the paper's field, dynamically configures 5 reviewers (Editor-in-Chief + 3 peer reviewers + Devil's Advocate) who review from four non-overlapping perspectives — methodology, domain expertise, cross-disciplinary viewpoints, and core argument challenges — ultimately producing a structured Editorial Decision and Revision Roadmap.\n\n**v1.1 Improvements**:\n1. Added Devil's Advocate Reviewer — specifically challenges core arguments, detects logical fallacies, and identifies the strongest counter-arguments\n2. Added `re-review` mode — verification review, focused on checking whether revisions address the review comments\n3. Expanded review team from 4 to 5 members\n\n---\n\n## Quick Start\n\n**Simplest command:**\n```\nReview this paper: [paste paper or provide file]\n```\n\n**Output:**\n1. Automatically identifies the paper's field and methodology type\n2. Dynamically configures the specific identities and expertise of 5 reviewers\n3. 5 independent review reports (each from a different perspective)\n4. 1 Editorial Decision Letter + Revision Roadmap\n\n---\n\n## Trigger Conditions\n\n### Trigger Keywords\n\n**English**: review paper, peer review, manuscript review, referee report, review my paper, critique paper, simulate review, editorial review, calibrate reviewer, reviewer calibration, measure reviewer accuracy\n\n### Non-Trigger Scenarios\n\n| Scenario | Skill to Use |\n|----------|-------------|\n| Need to write a paper (not review) | `academic-paper` |\n| Need in-depth investigation of a research topic | `deep-research` |\n| Need to revise a paper (already have review comments) | `academic-paper` (revision mode) |\n\n### Quick Mode Selection Guide\n\n| Your Situation | Recommended Mode | Spectrum |\n|----------------|-----------------|----------|\n| Need comprehensive review (first submission) | full | balanced |\n| Checking if revisions addressed comments | re-review | fidelity |\n| Quick quality assessment (15 min) | quick | fidelity |\n| Focus only on methods/statistics | methodology-focus | fidelity |\n| Want to learn by doing (guided review) | guided | originality |\n| Want to know this reviewer's own error profile before trusting its scores | calibration | fidelity |\n\n**Spectrum** (v3.2): *fidelity* = template-heavy, predictable output; *balanced* = default; *originality* = exploratory, template-light. See `shared/mode_spectrum.md` for the full cross-skill spectrum table.\n\nNot sure? Use `full` for pre-submission review, `re-review` for post-revision verification. `calibration` is opt-in — run it once per domain when you want to know the reviewer's FNR/FPR before relying on its rubric scores.\n\n---\n\n## Agent Team (7 Agents)\n\n| # | Agent | Role | Phase |\n|---|-------|------|-------|\n| 1 | `field_analyst_agent` | Analyzes the paper's field, dynamically configures 5 reviewer identities | Phase 0 |\n| 2 | `eic_agent` | Journal Editor-in-Chief — journal fit, originality, overall quality | Phase 1 |\n| 3 | `methodology_reviewer_agent` | Peer Reviewer 1 — research design, statistical validity, reproducibility | Phase 1 |\n| 4 | `domain_reviewer_agent` | Peer Reviewer 2 — literature coverage, theoretical framework, domain contribution | Phase 1 |\n| 5 | `perspective_reviewer_agent` | Peer Reviewer 3 — cross-disciplinary connections, practical impact, challenging fundamental assumptions | Phase 1 |\n| 6 | **`devils_advocate_reviewer_agent`** | **Devil's Advocate — core argument challenges, logical fallacy detection, strongest counter-arguments** | **Phase 1** |\n| 7 | `editorial_synthesizer_agent` | Synthesizes all reviews, identifies consensus and disagreements, makes editorial decision | Phase 2 |\n\n---\n\n## Orchestration Workflow (3 Phases)\n\n```\nUser: \"Review this paper\"\n |\n=== Phase 0: FIELD ANALYSIS & PERSONA CONFIGURATION ===\n |\n +-> [field_analyst_agent] -> Reviewer Configuration Card (x5)\n - Reads the complete paper\n - Identifies: primary discipline, secondary discipline, research paradigm, methodology type, target journal tier, paper maturity\n - Dynamically generates specific identities for 5 reviewers:\n * EIC: Which journal's editor, area of expertise, review preferences\n * Reviewer 1 (Methodology): Methodological expertise, what they particularly focus on\n * Reviewer 2 (Domain): Domain expertise, research interests\n * Reviewer 3 (Perspective): Cross-disciplinary angle, what unique perspective they bring\n * Devil's Advocate: Specifically challenges core arguments, detects logical gaps\n |\n ** Presents Reviewer Configuration to user for confirmation (adjustable) **\n |\n=== Phase 1: PARALLEL MULTI-PERSPECTIVE REVIEW ===\n |\n |-> [eic_agent] -------> EIC Review Report\n | - Journal fit, originality, significance, relevance to readership\n | - Does not go deep into methodology (that's Reviewer 1's job)\n | - Sets the review tone\n |\n |-> [methodology_reviewer_agent] -> Methodology Review Report\n | - Research design rigor, sampling strategy, data collection\n | - Analysis method selection, statistical validity, effect sizes\n | - Reproducibility, data transparency\n |\n |-> [domain_reviewer_agent] -------> Domain Review Report\n | - Literature review completeness, theoretical framework appropriateness\n | - Academic argument accuracy, incremental contribution to the field\n | - Missing key references\n |\n |-> [perspective_reviewer_agent] --> Perspective Review Report\n | - Cross-disciplinary connections and borrowing opportunities\n | - Practical applications and policy implications\n | - Broader social or ethical implications\n |\n +-> [devils_advocate_reviewer_agent] --> Devil's Advocate Report\n - Core argument challenges (strongest counter-arguments)\n - Cherry-picking detection\n - Confirmation bias detection\n - Logic chain validation\n - Overgeneralization detection\n - Alternative paths analysis\n - Stakeholder blind spots\n - \"So what?\" test\n |\n=== Phase 2: EDITORIAL SYNTHESIS & DECISION ===\n |\n +-> [editorial_synthesizer_agent] -> Editorial Decision Package\n - Consolidates 5 reports (including Devil's Advocate challenges)\n - Identifies consensus (5 agree) vs. disagreement (divergent opinions)\n - Arbitration and argumentation for disputed issues\n - Devil's Advocate CRITICAL issues are specially flagged in the Editorial Decision\n - Editorial Decision Letter\n - Revision Roadmap (prioritized, can be directly input to academic-paper revision mode)\n |\n=== Phase 2.5: REVISION COACHING (Socratic Revision Guidance) ===\n |\n ** Only triggered when Decision = Minor/Major Revision **\n |\n +-> [eic_agent] guides the user through Socratic dialogue:\n 1. Overall positioning — \"After reading the review comments, what surprised you the most?\"\n 2. Core issue focus — Guides user to understand consensus issues\n 3. Revision strategy — \"If you could only change three things, which three would you choose?\"\n 4. Counter-argument response — Guides user to think about how to respond to Devil's Advocate challenges\n 5. Implementation planning — Helps prioritize revisions\n |\n +-> After dialogue ends, produces:\n - User's self-formulated revision strategy\n - Reprioritized Revision Roadmap\n |\n ** User can say \"just fix it\" to skip guidance **\n```\n\n### Checkpoint Rules\n\n1. **After Phase 0 completes**: Present Reviewer Configuration Card to user; user can adjust reviewer identities\n2. ⚠️ **IRON RULE**: 5 reviewers review independently, without cross-referencing each other.\n3. ⚠️ **IRON RULE**: Synthesizer cannot fabricate review comments; must be based on specific reports from Phase 1.\n4. ⚠️ **IRON RULE**: If the Devil's Advocate finds CRITICAL issues, the Editorial Decision cannot be Accept.\n5. **Phase 2.5**: Revision Coaching only triggers when Decision is not Accept; user can choose to skip\n6. ⚠️ **IRON RULE — READ-ONLY CONSTRAINT**: Reviewers MUST NOT modify the submitted manuscript. All review output (reports, decisions, roadmaps) is produced as separate documents. The reviewer examines the paper — it never rewrites it. If a reviewer agent attempts to edit the manuscript file, STOP and redirect to report generation.\n\n---\n\n## Operational Modes (6 Modes)\n\n| Mode | Trigger | Agents | Output |\n|------|---------|--------|--------|\n| `full` | Default / \"full review\" | All 7 agents | 5 review reports + Editorial Decision + Revision Roadmap |\n| **`re-review`** | **Pipeline Stage 3' / \"verification review\"** | **field_analyst + eic + editorial_synthesizer** | **Revision response checklist + residual issues + new Decision** |\n| `quick` | \"quick review\" | field_analyst + eic | EIC quick assessment + key issues list (15-minute version) |\n| `methodology-focus` | \"check methodology\" | field_analyst + methodology_reviewer | In-depth methodology review report |\n| `guided` | \"guide me\" | All + Socratic dialogue | Socratic issue-by-issue guided review |\n| **`calibration`** (v3.2) | **\"calibrate reviewer\" / \"measure reviewer accuracy\"** | **All 7 agents, 5x per gold paper, cross-model default-on** | **Calibration Report: FNR/FPR/balanced accuracy/AUC + per-dimension calibration error + session-scoped confidence disclosure** |\n\n### Mode Selection Logic\n\n```\n\"Review this paper\" -> full\n\"Give me a quick look at this paper\" -> quick\n\"Help me check the methodology\" -> methodology-focus\n\"Does this paper have methodology issues\"-> methodology-focus\n\"Guide me to improve this paper\" -> guided\n\"Walk me through the issues in my paper\" -> guided\n\"Verification review\" / \"Check revisions\"-> re-review\n\"How accurate is your review scoring?\" -> calibration\n\"Calibrate against these 10 papers\" -> calibration\n```\n\n---\n\n## Re-Review Mode (Verification Review)\n\nDedicated mode for Pipeline Stage 3' — verifies whether revisions address first-round review comments. Uses R&R Traceability Matrix (Schema 11) with Author's Claim + Verified? columns.\n\n**Input**: Original Revision Roadmap + Revised manuscript + Response to Reviewers (optional)\n**Output**: Verification Review Report with traceability matrix + new issues + Decision\n\n> See `references/re_review_mode_protocol.md` for full verification logic, output format template, and Socratic guidance details.\n\n---\n\n## Guided Mode (Socratic Guided Review)\n\nHelps authors understand problems themselves through progressive revelation. EIC opens with strengths, then gradually introduces deeper issues from each reviewer perspective.\n\n> See `references/guided_mode_protocol.md` for dialogue flow, rules, and progressive revelation sequence.\n\n---\n\n## Calibration Mode (v3.2)\n\nOpt-in mode that measures this reviewer's FNR / FPR / balanced accuracy against a user-supplied gold set (5-20 papers with known outcomes). Runs `full` 5x per paper with fresh context, cross-model default-on. Produces a Calibration Report attached as a confidence disclosure to subsequent reviews in the session.\n\n> See `references/calibration_mode_protocol.md` for full spec: intake rules, ensembling methodology, output format, and failure cases this mode does not fix.\n\n---\n\n## Review Output Format\n\nEach reviewer's report structure is detailed in `templates/peer_review_report_template.md`.\n\n### Devil's Advocate Report Structure (Special Format)\n\nThe Devil's Advocate uses a dedicated format, not the standard reviewer template:\n- **Strongest Counter-Argument** (200-300 words)\n- **Issue List** (categorized as CRITICAL / MAJOR / MINOR, with dimension and location)\n- **Ignored Alternative Explanations/Paths**\n- **Missing Stakeholder Perspectives**\n- **Observations (Non-Defects)**\n\n---\n\n## Editorial Decision Format\n\nThe Editorial Decision Letter structure is detailed in `templates/editorial_decision_template.md`.\n\n---\n\n## Integration\n\n### Upstream/Downstream Relationships\n\n```\ndeep-research --> academic-paper --> [integrity check] --> academic-paper-reviewer --> academic-paper (revision) --> academic-paper-reviewer (re-review) --> [final integrity] --> finalize\n (research) (writing) (integrity audit) (review) (revision) (verification review) (final verification) (finalization)\n```\n\n### Specific Integration Methods\n\n| Integration Direction | Description |\n|----------------------|-------------|\n| **Upstream: academic-paper -> reviewer** | Receives the complete paper output from `academic-paper` full mode, directly enters Phase 0 |\n| **Upstream: integrity check -> reviewer** | In the Pipeline, the paper must pass integrity check before entering reviewer |\n| **Downstream: reviewer -> academic-paper** | The Revision Roadmap format can be directly used as reviewer feedback input for `academic-paper` revision mode |\n| **Downstream: reviewer (re-review) -> integrity** | After re-review completes, proceeds to final integrity verification |\n\n### Pipeline Usage Example\n\n> See `references/integration_guide.md` for a complete 9-step pipeline usage example.\n\n---\n\n## Agent File References\n\n| Agent | Definition File |\n|-------|----------------|\n| field_analyst_agent | `agents/field_analyst_agent.md` |\n| eic_agent | `agents/eic_agent.md` |\n| methodology_reviewer_agent | `agents/methodology_reviewer_agent.md` |\n| domain_reviewer_agent | `agents/domain_reviewer_agent.md` |\n| perspective_reviewer_agent | `agents/perspective_reviewer_agent.md` |\n| **devils_advocate_reviewer_agent** | **`agents/devils_advocate_reviewer_agent.md`** |\n| editorial_synthesizer_agent | `agents/editorial_synthesizer_agent.md` |\n\n---\n\n## Reference Files\n\n| Reference | Purpose | Used By |\n|-----------|---------|---------|\n| `references/review_criteria_framework.md` | Structured review criteria framework (differentiated by paper type) | all reviewers |\n| `references/top_journals_by_field.md` | Top journal lists for major academic fields (EIC role calibration) | field_analyst, eic |\n| `references/editorial_decision_standards.md` | Accept/Minor/Major/Reject criteria and decision matrix | eic, editorial_synthesizer |\n| `references/statistical_reporting_standards.md` | Statistical reporting standards + APA 7.0 format quick reference + red flag list | methodology_reviewer |\n| `references/quality_rubrics.md` | Calibrated 0-100 scoring rubrics for 7 review dimensions with decision mapping | all reviewers |\n| `references/review_quality_thinking.md` | Cognitive framework for review quality: three lenses (internal validity, external validity, contribution), common reviewer traps, calibration questions | all reviewers |\n| `references/re_review_mode_protocol.md` | Full re-review verification logic, R&R traceability output format, Socratic guidance after re-review | eic, editorial_synthesizer |\n| `references/guided_mode_protocol.md` | Guided mode dialogue flow, progressive revelation sequence, dialogue rules | all reviewers |\n| `references/calibration_mode_protocol.md` | Calibration mode: FNR/FPR/balanced accuracy measurement against user-supplied gold set, 5x ensembling, session-scoped confidence disclosure (v3.2) | all reviewers |\n| `references/integration_guide.md` | Complete 9-step pipeline usage example | — |\n| `references/changelog.md` | Full version history | — |\n\n---\n\n## Templates\n\n| Template | Purpose |\n|----------|---------|\n| `templates/peer_review_report_template.md` | Review report template used by each reviewer |\n| `templates/editorial_decision_template.md` | EIC final decision letter template |\n| `templates/revision_response_template.md` | Revision response template for authors (R->A->C format) |\n\n---\n\n## Examples\n\n| Example | Demonstrates |\n|---------|-------------|\n| `examples/hei_paper_review_example.md` | Full review example: \"Impact of Declining Birth Rates on Management Strategies of Taiwan's Private Universities\" |\n| `examples/interdisciplinary_review_example.md` | Cross-disciplinary review example: \"Using Machine Learning to Predict University Closure Risk in Taiwan\" |\n\n---\n\n## Anti-Patterns\n\nExplicit prohibitions to prevent common failure modes, especially during long conversations:\n\n| # | Anti-Pattern | Why It Fails | Correct Behavior |\n|---|-------------|-------------|-----------------|\n| 1 | **Fabricating review comments** | Synthesizer invents critique not in any reviewer report | Every synthesis point must trace to a specific Phase 1 reviewer report |\n| 2 | **Duplicate criticisms across reviewers** | R1/R2/R3 raise identical points = fake diversity | Each reviewer has a distinct perspective; overlapping topics get different angles |\n| 3 | **Ignoring Devil's Advocate CRITICAL findings** | Editorial Decision says Accept despite DA flagging critical issues | If DA finds CRITICAL → Decision cannot be Accept (Checkpoint Rule #4) |\n| 4 | **Rubber-stamp re-review** | Re-review says \"all addressed\" without verification | Each concern must be independently verified against the revised manuscript |\n| 5 | **Sycophantic score inflation** | Giving 8/10 to mediocre work to avoid conflict | Scores must be evidence-based; a paper with methodology gaps cannot score >6 on rigor |\n| 6 | **Editing the manuscript** | Reviewer \"helpfully\" fixes the paper directly | READ-ONLY: produce reports, never modify the paper (Checkpoint Rule #6) |\n| 7 | **Generic feedback** | \"The methodology could be stronger\" without specifics | Every criticism must include: what's wrong, where it is, and a proposed fix |\n\n---\n\n## Quality Standards\n\n| Dimension | Requirement |\n|-----------|-------------|\n| Perspective differentiation | Each reviewer's review must come from a different angle; no duplicate criticisms |\n| Evidence-based | EIC's decision must be based on specific reviewer comments; no fabrication |\n| Specificity | Reviews must cite specific passages, data, or page numbers from the paper; no vague comments |\n| Balance | Strengths and Weaknesses must be balanced; cannot only criticize without affirming |\n| Professional tone | Review tone must be professional and constructive; avoid personal attacks or demeaning language |\n| Actionability | Each weakness must include specific improvement suggestions |\n| Format consistency | All reports must follow the template structure; no freestyle |\n| **Devil's Advocate completeness** | **Devil's Advocate must produce the strongest counter-argument; cannot be omitted** |\n| **CRITICAL threshold** | **⚠️ IRON RULE: Devil's Advocate CRITICAL issues cannot be ignored by the Editorial Decision** |\n\n---\n\n## Output Language\n\nFollows the paper's language. Academic terms remain in English. User can override (e.g., \"review this Chinese paper in English\").\n\n---\n\n## Related Skills\n\n| Skill | Relationship |\n|-------|-------------|\n| `academic-paper` | Upstream (provides paper) + Downstream (receives revision roadmap) |\n| `deep-research` | Upstream (provides research foundation) |\n| `tw-hei-intelligence` | Auxiliary (verifies higher education data accuracy) |\n| `academic-pipeline` | Orchestrated by (Stage 3 + Stage 3') |\n\n---\n\n## Version Info\n\n| Item | Content |\n|------|---------|\n| Skill Version | 1.7 |\n| Last Updated | 2026-04-06 |\n| Maintainer | Cheng-I Wu |\n| Dependent Skills | academic-paper v1.0+ (upstream/downstream integration) |\n| Role | Multi-perspective academic paper review simulator |\n\n---\n\n## Changelog\n\n> See `references/changelog.md` for full version history.\n\nFile v1.0.0:skills/academic-paper/SKILL.md\n\n---\nname: academic-paper\ndescription: \"12-agent academic paper writing pipeline. 10 modes (full/plan/outline/revision/revision-coach/abstract/lit-review/format-convert/citation-check/disclosure). 6 paper types, 5 citation formats, bilingual abstracts, LaTeX/DOCX/PDF output. Style Calibration + Writing Quality Check + Anti-Patterns with IRON RULE markers. Triggers: write paper, academic paper, guide my paper, parse reviews, AI disclosure, 寫論文, 學術論文, 引導我寫論文, 審查意見.\"\nmetadata:\n version: \"3.0\"\n last_updated: \"2026-04-09\"\n status: active\n related_skills:\n - deep-research\n - academic-paper-reviewer\n - academic-pipeline\n---\n\n# Academic Paper — Academic Paper Writing Agent Team\n\nA general-purpose academic paper writing tool — 12-agent pipeline covering all disciplines, with higher education domain as the default reference.\n\n**v2.5** adds two writing quality features:\n- **Style Calibration** (intake Step 10, optional) — Provide 3+ past papers and the pipeline learns your writing voice (sentence rhythm, vocabulary preferences, citation integration style). Applied as a soft guide during drafting; discipline conventions always take priority. See `shared/style_calibration_protocol.md`.\n- **Writing Quality Check** (`references/writing_quality_check.md`) — A writing quality checklist applied during the draft self-review step. Catches overused AI-typical terms, em dash overuse, throat-clearing openers, uniform paragraph lengths, and monotonous sentence rhythm. These are good writing rules, not detection evasion.\n\n## Quick Start\n\n**Minimal command:**\n```\nWrite a paper on the impact of AI on higher education quality assurance\n```\n\n```\nWrite a paper on the impact of declining birth rates on private university management strategies\n```\n\n**Execution flow:**\n1. Configuration interview — paper type, discipline, citation format, output format\n2. Literature search — systematic search strategy, source screening\n3. Architecture design — paper structure, outline, word count allocation\n4. Argumentation construction — claim-evidence chains, logical flow\n5. Full-text drafting — section-by-section draft, register adjustment\n6. Citation compliance + bilingual abstract (parallel)\n7. Peer review — five-dimension scoring, revision suggestions\n8. Output formatting — LaTeX/DOCX/PDF/Markdown\n\n---\n\n## Trigger Conditions\n\n### Trigger Keywords\n\n**English**: write paper, academic paper, paper outline, write abstract, revise paper, literature review paper, check citations, convert to LaTeX, convert format, format paper, conference paper, journal article, thesis chapter, research paper, guide my paper, help me plan my paper, step by step paper, draft manuscript, write methodology, write discussion, parse reviews, revision roadmap, help me with my revision, I got reviewer comments, convert citations\n\n**繁體中文**: 寫論文, 學術論文, 論文大綱, 寫摘要, 修改論文, 文獻回顧論文, 檢查引用, 轉 LaTeX, 轉換格式, 研討會論文, 期刊文章, 學位論文, 研究論文, 引導我寫論文, 幫我規劃論文, 逐步寫論文, 寫方法論, 寫討論, 審查意見, 修訂路線圖, 幫我修改, 我收到審查意見, 轉換引用格式\n\n### Plan Mode Activation\n\nActivate `plan` mode when the user wants guidance, step-by-step planning, or expresses uncertainty about paper structure. **Default rule**: when ambiguous between `plan` and `full`, prefer `plan`.\n\n> See `references/plan_mode_protocol.md` for full intent signals and activation rules.\n\n### Does NOT Trigger\n\n| Scenario | Use Instead |\n|----------|-------------|\n| Deep research / fact-checking (not paper writing) | `deep-research` |\n| Reviewing a paper (structured review) | `academic-paper-reviewer` |\n| Full research-to-paper pipeline | `academic-pipeline` |\n\n### Distinction from `deep-research`\n\n| Feature | `academic-paper` | `deep-research` |\n|---------|-------------------|-----------------|\n| Primary output | Publishable paper draft | Research report |\n| Structure | Journal-ready (IMRaD, etc.) | APA 7.0 report |\n| Citation | Multi-format (APA/Chicago/MLA/IEEE/Vancouver) | APA 7.0 only |\n| Abstract | Bilingual (zh-TW + EN) | Single language |\n| Peer review | Simulated 5-dimension review | Editorial review |\n| Output format | LaTeX/DOCX/PDF/Markdown | Markdown only |\n| Revision loop | Max 2 rounds with targeted feedback | Max 2 rounds |\n\n---\n\n## Agent Team (12 Agents)\n\n| # | Agent | Role | Phase |\n|---|-------|------|-------|\n| 1 | `intake_agent` | Configuration interview: paper type, discipline, journal, citation format, output format, language, word count; Handoff detection; Plan mode simplified interview | Phase 0 |\n| 2 | `literature_strategist_agent` | Search strategy design, source screening, annotated bibliography, literature matrix | Phase 1 |\n| 3 | `structure_architect_agent` | Paper structure selection, detailed outline, word count allocation, evidence mapping | Phase 2 |\n| 4 | `argument_builder_agent` | Argument construction, claim-evidence chains, logical flow, counter-argument handling; Plan mode argument stress test | Phase 3 / Plan Step 3 |\n| 5 | `draft_writer_agent` | Section-by-section full draft writing, discipline register adjustment, word count tracking | Phase 4 |\n| 6 | `citation_compliance_agent` | Citation format verification, reference list completeness, DOI checking | Phase 5a |\n| 7 | `abstract_bilingual_agent` | Bilingual abstract (zh-TW + EN), 5-7 keywords each | Phase 5b |\n| 8 | `peer_reviewer_agent` | Simulated double-blind review, five-dimension scoring, revision suggestions (max 2 rounds) | Phase 6 |\n| 9 | `formatter_agent` | Convert to LaTeX/DOCX/PDF/Markdown, journal formatting, cover letter, citation format conversion (APA 7 / Chicago / MLA / IEEE / Vancouver) | Phase 7 |\n| 10 | `socratic_mentor_agent` | Plan mode Socratic mentor: chapter-by-chapter guidance, convergence criteria (4 signals), question taxonomy (4 types), INSIGHT extraction | Plan Step 0-3 |\n| 11 | `visualization_agent` | Parse paper data and generate publication-quality figure code (Python matplotlib / R ggplot2) with APA 7.0 formatting, colorblind-safe palettes, and LaTeX integration | Phase 4 / Phase 7 |\n| 12 | `revision_coach_agent` | Parse unstructured reviewer comments into structured Revision Roadmap; classify, map, and prioritize comments; works standalone without prior pipeline execution | Revision-Coach mode |\n\n---\n\n## Output Formats\n\n### Text Formats\nLaTeX (.tex + .bib), DOCX (via Pandoc), PDF (via LaTeX or Pandoc), Markdown.\n\n### Figures\nWhen the paper contains quantitative results, the `visualization_agent` can generate publication-ready figures in Python (matplotlib/seaborn) or R (ggplot2) with APA 7.0 formatting and colorblind-safe palettes. Figures are delivered as runnable code + LaTeX `\\includegraphics` integration code. See `references/statistical_visualization_standards.md` for chart type decision trees and code templates.\n\n### Citation Formats\nAPA 7.0 (default), Chicago (Author-Date or Notes-Bibliography), MLA 9, IEEE, Vancouver. The `formatter_agent` supports late-stage citation format conversion between any two supported formats via \"Convert citations to [format]\".\n\n---\n\n## Orchestration Workflow (8 Phases)\n\n```\nPhase 0: CONFIG -> [intake_agent] -> Paper Configuration Record\nPhase 1: RESEARCH -> [literature_strategist] -> Search Strategy + Source Corpus\nPhase 2: ARCHITECTURE -> [structure_architect] -> Paper Outline + Evidence Map\nPhase 3: ARGUMENTATION -> [argument_builder] -> Argument Blueprint\nPhase 4: DRAFTING -> [draft_writer] -> Complete Draft\nPhase 5a: CITATIONS -> [citation_compliance] ──┐ -> Citation Audit Report\nPhase 5b: ABSTRACT -> [abstract_bilingual] ─┘ -> Bilingual Abstract + Keywords (parallel)\nPhase 6: PEER REVIEW -> [peer_reviewer] -> Review Report (max 2 revision loops)\nPhase 7: FORMAT -> [formatter] -> Final Output Package\n```\n\n> See `references/workflow_phase_details.md` for detailed per-phase agent behavior and output descriptions.\n\n### Checkpoint Rules\n\n1. ⚠️ **IRON RULE**: User must confirm Paper Configuration Record before proceeding to Phase 1\n2. **Phase 2 -> 3**: User must approve outline (can request restructuring)\n3. ⚠️ **IRON RULE**: Max 2 revision loops; unresolved items -> \"Acknowledged Limitations\"\n4. **Peer Review** Critical-severity issues block progression to Phase 7\n5. User can skip Phase 1 (literature) if providing own sources\n\n---\n\n## Operational Modes (9 Modes)\n\nSee `references/mode_selection_guide.md` for details.\n\n| Mode | Trigger | Agents | Output |\n|------|---------|--------|--------|\n| `full` | \"Write a paper\" | All 9 (+ 11 if quantitative) | Complete paper draft (with figures if applicable) |\n| `outline-only` | \"Paper outline\" | 1->2->3 | Detailed outline + evidence map |\n| `revision` | \"Revise paper\" | 8->5->6 | Revised draft with tracked changes (uses `templates/revision_tracking_template.md`) |\n| `abstract-only` | \"Write abstract\" | 1->7 | Bilingual abstract + keywords |\n| `lit-review` | \"Literature review\" | 1->2 | Annotated bibliography + synthesis |\n| `format-convert` | \"Convert to LaTeX\" / \"Convert citations to [format]\" | 9 only | Formatted document; includes citation format conversion (APA 7 / Chicago / MLA / IEEE / Vancouver) |\n| `citation-check` | \"Check citations\" | 6 only | Citation error report |\n| `plan` | \"guide my paper\" / \"help me plan my paper\" | 1->10->3->4 | Chapter Plan + INSIGHT Collection |\n| `revision-coach` | \"parse reviews\" / \"revision roadmap\" / \"I got reviewer comments\" | 12 only | Revision Roadmap + optional Tracking Template + Response Letter Skeleton |\n| **`disclosure`** (v3.2) | **\"AI disclosure for Nature\" / \"generate AI usage statement\"** | **9 only** | **Venue-specific AI-usage disclosure paragraph(s) + placement instructions** |\n\n### Quick Mode Selection Guide\n\n| Your Situation | Recommended Mode | Spectrum |\n|----------------|-----------------|----------|\n| Starting from scratch with a clear RQ | `full` | balanced |\n| Need help planning before writing | `plan` | originality |\n| Just need an outline | `outline-only` | balanced |\n| Have a draft, received review feedback | `revision` | fidelity |\n| Have unstructured reviewer comments | `revision-coach` | balanced |\n| Just need an abstract | `abstract-only` | fidelity |\n| Need to check/fix citations | `citation-check` | fidelity |\n| Need to convert format (LaTeX, DOCX) or citation style | `format-convert` | fidelity |\n| Want a systematic literature review paper | `lit-review` | fidelity |\n| Need a venue-specific AI-usage disclosure statement for submission | `disclosure` | fidelity |\n\n**Spectrum** (v3.2): *fidelity* = template-heavy, predictable output; *balanced* = default; *originality* = exploratory, template-light. See `shared/mode_spectrum.md` for the full cross-skill spectrum table.\n\nNot sure? Start with `plan` — it will guide you step by step. `disclosure` is a finishing step — run it after the paper is drafted, targeting the venue you plan to submit to.\n\n### Mode Selection Logic\n\n> See `references/mode_selection_guide.md` for trigger-to-mode mappings and the full selection flowchart.\n\n---\n\n## Plan Mode: Chapter-by-Chapter Guided Planning\n\nSocratic mode that guides users through paper planning one chapter at a time. Builds a complete Paper Blueprint through structured dialogue.\n\n> See `references/plan_mode_protocol.md` for the full chapter-by-chapter dialogue flow and Paper Blueprint structure.\n\n---\n\n## Handoff Protocol: deep-research -> academic-paper\n\n`intake_agent` automatically detects deep-research materials (RQ Brief / Bibliography / Synthesis / INSIGHT Collection) and skips redundant steps. See `deep-research/SKILL.md` Handoff Protocol for the complete handoff material format.\n\n---\n\n## Failure Paths\n\nSee `references/failure_paths.md` for details. Quick reference:\n\n| Failure Scenario | Handling Strategy |\n|---------|---------|\n| Insufficient research foundation | Recommend running `deep-research` first |\n| Wrong paper structure selected | Return to Phase 2, suggest alternative structure |\n| Word count significantly over/under target | Identify problematic chapters, suggest trimming/expansion |\n| Citation format entirely wrong | Re-run the entire citation phase |\n| Peer review rejection | Analyze rejection reasons, suggest major revision or restructuring |\n| Plan mode not converging | Suggest switching to outline-only mode |\n| Incomplete handoff materials | List missing items, suggest supplementing or re-running |\n| User abandons midway | Save completed Chapter Plan |\n\n---\n\n## Full Academic Pipeline\n\nSee `academic-pipeline/SKILL.md` for the complete workflow.\n\n---\n\n## Phase 0: Configuration Interview\n\nSee `agents/intake_agent.md` for the complete field definitions of the Phase 0 configuration interview. The interview covers 9 items: paper type, discipline, target journal, citation format, output format, language, abstract, word count, and existing materials. Outputs a Paper Configuration Record, awaiting user confirmation.\n\n---\n\n## File Structure\n\n**Agent definitions**: `agents/{agent_name}.md` — one file per agent (12 total, matching Agent Team table above).\n\n**References** (19 files in `references/`):\n- Citation: `apa7_extended_guide`, `apa7_chinese_citation_guide`, `citation_format_switcher`\n- Writing: `academic_writing_style`, `writing_quality_check`, `writing_judgment_framework`\n- Structure: `paper_structure_patterns` (6 types), `abstract_writing_guide`\n- Domain: `hei_domain_glossary` (bilingual), `journal_submission_guide`, `latex_template_reference`\n- Process: `failure_paths` (12 scenarios), `mode_selection_guide` (10 modes), `plan_mode_protocol`, `workflow_phase_details`\n- Ethics: `credit_authorship_guide` (CRediT 14 roles), `funding_statement_guide`, `statistical_visualization_standards`\n- Disclosure (v3.2): `disclosure_mode_protocol` (venue-specific AI-usage statement generation), `venue_disclosure_policies` (v1 database: ICLR, NeurIPS, Nature, Science, ACL, EMNLP)\n- Also: `deep-research/references/apa7_style_guide.md` (base reference, extended here)\n\n**Templates** (11 files in `templates/`): `imrad`, `literature_review`, `case_study`, `theoretical_paper`, `policy_brief`, `conference_paper`, `latex_article_template.tex`, `bilingual_abstract`, `credit_statement`, `funding_statement`, `revision_tracking` (4 status types).\n\n**Examples** (5 files in `examples/`): `imrad_hei_example`, `literature_review_example`, `plan_mode_guided_writing`, `chinese_paper_example`, `revision_mode_example`.\n\n---\n\n## Anti-Patterns\n\nExplicit prohibitions to prevent common failure modes:\n\n| # | Anti-Pattern | Why It Fails | Correct Behavior |\n|---|-------------|-------------|-----------------|\n| 1 | **AI-typical overused terms** | \"delve into\", \"crucial\", \"it is important to note\" = instant AI detection | Use discipline-specific vocabulary; see `references/writing_quality_check.md` |\n| 2 | **Em dash abuse** | More than 2 em dashes per page signals AI writing | Use parentheses, commas, or restructure the sentence |\n| 3 | **Throat-clearing openers** | \"In this section, we will discuss...\" adds no information | Start with the claim or finding directly |\n| 4 | **Uniform paragraph lengths** | Every paragraph is 4-5 sentences = monotonous AI rhythm | Vary paragraph length naturally (2-8 sentences) |\n| 5 | **⚠️ IRON RULE: Fabricated citations** | Inventing plausible-sounding references that don't exist | Every citation must be verified via DOI or WebSearch; see `academic-pipeline/agents/integrity_verification_agent.md` |\n| 6 | **Sycophantic revision** | Accepting all reviewer feedback without critical evaluation | Use REVIEWER_DISAGREE status when reviewer is wrong; justify with evidence |\n| 7 | **Scope creep during revision** | Adding unrequested sections/analyses to \"improve\" the paper | Revision addresses reviewer concerns only; new content requires explicit user approval |\n| 8 | **Ignoring failure paths** | Continuing despite desk-reject signals or fatal methodology flaws | Check `references/failure_paths.md`; invoke F11 Desk-Reject Recovery when triggered |\n\n---\n\n## Quality Standards\n\n### Writing Quality\n1. **Every claim must have a citation** or be supported by the paper's own data\n2. **Zero citation orphans** — in-text citations <-> reference list must perfectly match\n3. **Consistent register** — academic tone appropriate for the discipline\n4. **Logical flow** — clear transitions between paragraphs and sections\n5. **Word count compliance** — within +/-10% of target\n\n### Bilingual Abstract Quality\n6. **Independent writing** — zh-TW and EN abstracts are independently composed, NOT mechanical translations\n7. **Structural alignment** — both abstracts cover the same key points in the same order\n8. **Keywords** — 5-7 per language, reflecting the paper's core concepts\n9. **Word count** — EN: 150-300 words; zh-TW: 300-500 characters\n\n### Citation Quality\n10. **Format compliance** — 100% adherence to selected citation style\n11. ⚠️ IRON RULE: **DOI inclusion** — every source with a DOI must include it; every citation must be verified via DOI or WebSearch\n12. **Currency** — flag sources older than 10 years (unless seminal works)\n13. **Self-citation ratio** — flag if >15%\n\n### Peer Review\n14. **Five dimensions** — Originality (20%), Methodological Rigor (25%), Evidence Sufficiency (25%), Argument Coherence (15%), Writing Quality (15%)\n15. **Actionable feedback** — every criticism must include a specific suggestion\n16. **Max 2 revision rounds** — unresolved items become Acknowledged Limitations\n\n### Mandatory Inclusions\n⚠️ **IRON RULE**: Every paper MUST include: Data Availability Statement, Ethics Declaration, Author Contributions (CRediT), Conflict of Interest Statement, Funding Acknowledgment.\n17. **AI disclosure statement** — every paper must include a statement on AI tool usage\n18. **Limitations section** — explicitly discuss study limitations\n19. **Ethics statement** — when applicable (human subjects, sensitive data)\n\n---\n\n## Output Language\n\nFollows the user's language. Academic terminology is kept in English. Bilingual abstracts are always provided regardless of the main text language.\n\n---\n\n## Integration with Other Skills\n\n```\nacademic-paper + tw-hei-intelligence -> Evidence-based HEI paper with real MOE data\nacademic-paper + deep-research -> Deep research phase -> paper writing phase (auto-handoff)\nacademic-paper + report-to-website -> Interactive web version of the paper\nacademic-paper + notebooklm-slides-generator -> Presentation slides from paper\nacademic-paper + academic-paper-reviewer -> Peer review -> revision loop\n```\n\n---\n\n## Version Info\n\n| Item | Content |\n|------|---------|\n| Skill Version | 3.0 |\n| Last Updated | 2026-04-09 |\n| Maintainer | Cheng-I Wu |\n| Dependent Skills | deep-research v1.0+ (upstream), academic-paper-reviewer v1.0+ (downstream) |\n\n---\n\n## Version History\n\n> See `references/changelog.md` for full version history.\n\nFile v1.0.0:skills/academic-pipeline/SKILL.md\n\n---\nname: academic-pipeline\ndescription: \"Orchestrator for the full academic research pipeline: research -> write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory integrity verification, two-stage peer review, and reproducible quality gates. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow.\"\nmetadata:\n version: \"3.2\"\n last_updated: \"2026-04-09\"\n depends_on: \"deep-research, academic-paper, academic-paper-reviewer\"\n status: active\n related_skills:\n - deep-research\n - academic-paper\n - academic-paper-reviewer\n---\n\n# Academic Pipeline v3.2 — Full Academic Research Workflow Orchestrator\n\nA lightweight orchestrator that manages the complete academic pipeline from research exploration to final manuscript. It does not perform substantive work — it only detects stages, recommends modes, dispatches skills, manages transitions, and tracks state.\n\n**v2.0 Core Improvements**:\n1. **Mandatory user confirmation checkpoints** — Each stage completion requires user confirmation before proceeding to the next step\n2. **Academic integrity verification** — After paper completion and before review submission, 100% reference and data verification must pass\n3. **Two-stage review** — First full review + post-revision focused verification review\n4. **Final integrity check** — After revision completion, re-verify all citations and data are 100% correct\n5. **Reproducible** — Standardized workflow producing consistent quality assurance each time\n6. **Process documentation** — After pipeline completion, automatically generates a \"Paper Creation Process Record\" PDF documenting the human-AI collaboration history\n\n## Quick Start\n\n**Full workflow (from scratch):**\n```\nI want to write a research paper on the impact of AI on higher education quality assurance\n```\n--> academic-pipeline launches, starting from Stage 1 (RESEARCH)\n\n**Mid-entry (existing paper):**\n```\nI already have a paper, help me review it\n```\n--> academic-pipeline detects mid-entry, starting from Stage 2.5 (INTEGRITY)\n\n**Revision mode (received reviewer feedback):**\n```\nI received reviewer comments, help me revise\n```\n--> academic-pipeline detects, starting from Stage 4 (REVISE)\n\n**Execution flow:**\n1. Detect the user's current stage and available materials\n2. Recommend the optimal mode for each stage\n3. Dispatch the corresponding skill for each stage\n4. **After each stage completion, proactively prompt and wait for user confirmation**\n5. Track progress throughout; Pipeline Status Dashboard available at any time\n\n---\n\n## Trigger Conditions\n\n### Trigger Keywords\n\n**English**: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow\n\n### Non-Trigger Scenarios\n\n| Scenario | Skill to Use |\n|----------|-------------|\n| Only need to search materials or do a literature review | `deep-research` |\n| Only need to write a paper (no research phase needed) | `academic-paper` |\n| Only need to review a paper | `academic-paper-reviewer` |\n| Only need to check citation format | `academic-paper` (citation-check mode) |\n| Only need to convert paper format | `academic-paper` (format-convert mode) |\n\n### Trigger Exclusions\n\n- If the user only needs a single function (just search materials, just check citations), no pipeline is needed — directly trigger the corresponding skill\n- If the user is already using a specific mode of a skill, do not force them into the pipeline\n- The pipeline is optional, not mandatory\n\n---\n\n## Pipeline Stages (10 Stages)\n\n| Stage | Name | Skill / Agent Called | Available Modes | Deliverables |\n|-------|------|---------------------|----------------|-------------|\n| 1 | RESEARCH | `deep-research` | socratic, full, quick | RQ Brief, Methodology, Bibliography, Synthesis |\n| 2 | WRITE | `academic-paper` | plan, full | Paper Draft |\n| **2.5** | **INTEGRITY** | **`integrity_verification_agent`** | **pre-review** | **Integrity verification report + corrected paper** |\n| 3 | REVIEW | `academic-paper-reviewer` | full (incl. Devil's Advocate) | 5 review reports + Editorial Decision + Revision Roadmap |\n| 4 | REVISE | `academic-paper` | revision | Revised Draft, Response to Reviewers |\n| **3'** | **RE-REVIEW** | **`academic-paper-reviewer`** | **re-review** | **Verification review report: revision response checklist + residual issues** |\n| **4'** | **RE-REVISE** | **`academic-paper`** | **revision** | **Second revised draft (if needed)** |\n| **4.5** | **FINAL INTEGRITY** | **`integrity_verification_agent`** | **final-check** | **Final verification report (must achieve 100% pass to proceed)** |\n| 5 | FINALIZE | `academic-paper` | format-convert | Final Paper (default MD + DOCX; ask about LaTeX; confirm correctness; PDF) |\n| **6** | **PROCESS SUMMARY** | **orchestrator** | **auto** | **Paper creation process record MD + LaTeX to PDF (bilingual)** |\n\n**Parallelization opportunity (v3.3)**: Within Stage 2, the `academic-paper` skill's Phase 1 (literature_strategist_agent) and the `visualization_agent` can operate in parallel after Phase 2 (structure_architect_agent) completes the outline. Specifically:\n- Once the outline includes a visualization plan, `visualization_agent` can begin figure generation\n- Simultaneously, `argument_builder_agent` can build CER chains\n- `draft_writer_agent` waits for both to complete before beginning Phase 4\n\nThis mirrors PaperOrchestra's parallel execution of Plot Generation (Step 2) and Literature Review (Step 3) after Outline (Step 1), which reduces overall pipeline latency. The parallelization is optional — sequential execution remains the default for simplicity.\n\n---\n\n## Pipeline State Machine\n\n1. **Stage 1 RESEARCH** -> user confirmation -> Stage 2\n2. **Stage 2 WRITE** -> user confirmation -> Stage 2.5\n3. **Stage 2.5 INTEGRITY** -> PASS -> Stage 3 (FAIL -> fix and re-verify, max 3 rounds)\n4. **Stage 3 REVIEW** -> Accept -> Stage 4.5 / Minor|Major -> Stage 4 / Reject -> Stage 2 or end\n5. **Stage 4 REVISE** -> user confirmation -> Stage 3'\n6. **Stage 3' RE-REVIEW** -> Accept|Minor -> Stage 4.5 / Major -> Stage 4'\n7. **Stage 4' RE-REVISE** -> user confirmation -> Stage 4.5 (no return to review)\n8. **Stage 4.5 FINAL INTEGRITY** -> PASS (zero issues) -> Stage 5 (FAIL -> fix and re-verify)\n9. **Stage 5 FINALIZE** -> MD + DOCX -> ask about LaTeX -> confirm -> PDF -> Stage 6\n10. **Stage 6 PROCESS SUMMARY** -> ask language version -> generate process record MD -> LaTeX -> PDF -> end\n\nSee `references/pipeline_state_machine.md` for complete state transition definitions.\n\n---\n\n## Adaptive Checkpoint System\n\n⚠️ **IRON RULE — Core rule: After each stage completion, the system must proactively prompt the user and wait for confirmation. The checkpoint presentation adapts based on context and user engagement.**\n\n### Checkpoint Types\n\n| Type | When Used | Content |\n|------|-----------|---------|\n| FULL | First checkpoint; after integrity boundaries; before finalization | Full deliverables list + decision dashboard + all options |\n| SLIM | After 2+ consecutive \"continue\" responses on non-critical stages | One-line status + auto-continue in 5 seconds |\n| MANDATORY | Integrity FAIL; Review decision; Stage 5 | Cannot be skipped; requires explicit user input |\n\n### Decision Dashboard (shown at FULL checkpoints)\n\n```\n━━━ Stage [X] [Name] Complete ━━━\n\nMetrics:\n- Word count: [N] (target: [T] +/-10%) [OK/OVER/UNDER]\n- References: [N] (min: [M]) [OK/LOW]\n- Coverage: [N]/[T] sections drafted [COMPLETE/PARTIAL]\n- Quality indicators: [score if available]\n\nDeliverables:\n- [Material 1]\n- [Material 2]\n\nFlagged: [any issues detected, or \"None\"]\n\nReady to proceed to Stage [Y]? You can also:\n1. View progress (say \"status\")\n2. Adjust settings\n3. Pause pipeline\n━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\n```\n\n### Adaptive Rules\n\n1. **First checkpoint**: always FULL\n2. **After 2+ consecutive \"continue\" without review**: prompt user awareness (\"You've auto-continued [N] times. Want to review progress?\")\n3. **Integrity boundaries (Stage 2.5, 4.5)**: always MANDATORY\n4. **Review decisions (Stage 3, 3')**: always MANDATORY\n5. **Before finalization (Stage 5)**: always MANDATORY\n6. **All other stages**: start FULL, downgrade to SLIM if user says \"just continue\"\n\n### Checkpoint Rules\n\n1. ⚠️ **IRON RULE**: **Cannot auto-skip MANDATORY checkpoints**: Even if the previous stage result is perfect, explicit user input is required at MANDATORY checkpoints\n2. **User can adjust**: At FULL and MANDATORY checkpoints, users can modify the mode or settings for the next step\n3. **Pause-friendly**: Users can pause at any checkpoint and resume later\n4. **SLIM mode**: If the user says \"just continue\" or \"fully automatic,\" subsequent non-critical checkpoints switch to SLIM format (one-line status + auto-continue), but notifications are still sent\n5. **Awareness guard**: After 4+ consecutive auto-continues, the system inserts a FULL checkpoint regardless of stage type to ensure user remains engaged\n\n### Self-Check Questions (at every FULL checkpoint)\n\nBefore presenting the checkpoint to the user, the orchestrator asks itself:\n\n1. **Citation integrity**: Are there any unverified citations in the latest output?\n2. **Sycophantic concession**: Did the latest stage uncritically accept all feedback without pushback?\n3. **Quality trajectory**: Is the latest output ≥ the quality of the previous stage? If declining, PAUSE and flag.\n4. **Scope discipline**: Did the latest stage add content not requested by the user or the revision roadmap?\n5. **Completeness**: Are all required deliverables for this stage present?\n\nIf ANY answer raises concern, include it in the checkpoint presentation to the user.\n\n---\n\n## Agent Team (3 Agents)\n\n| # | Agent | Role | File |\n|---|-------|------|------|\n| 1 | `pipeline_orchestrator_agent` | Main orchestrator: detects stage, recommends mode, triggers skill, manages transitions | `agents/pipeline_orchestrator_agent.md` |\n| 2 | `state_tracker_agent` | State tracker: records completed stages, produced materials, revision loop count | `agents/state_tracker_agent.md` |\n| 3 | `integrity_verification_agent` | Integrity verifier: 100% reference/citation/data verification | `agents/integrity_verification_agent.md` |\n\n---\n\n## Orchestrator Workflow\n\n### Step 1: INTAKE & DETECTION\n\n```\npipeline_orchestrator_agent analyzes the user's input:\n\n1. What materials does the user have?\n - No materials --> Stage 1 (RESEARCH)\n - Has research data --> Stage 2 (WRITE)\n - Has paper draft --> Stage 2.5 (INTEGRITY)\n - Has verified paper --> Stage 3 (REVIEW)\n - Has review comments --> Stage 4 (REVISE)\n - Has revised draft --> Stage 3' (RE-REVIEW)\n - Has final draft for formatting --> Stage 5 (FINALIZE)\n\n2. What is the user's goal?\n - Full workflow (research to publication)\n - Partial workflow (only certain stages needed)\n\n3. Determine entry point, confirm with user\n```\n\n### Step 2: MODE RECOMMENDATION\n\n```\nBased on entry point and user preferences, recommend modes for each stage:\n\nUser type determination:\n- Novice / wants guidance --> socratic (Stage 1) + plan (Stage 2) + guided (Stage 3)\n- Experienced / wants direct output --> full (Stage 1) + full (Stage 2) + full (Stage 3)\n- Time-limited --> quick (Stage 1) + full (Stage 2) + quick (Stage 3)\n\nExplain the differences between modes when recommending, letting the user choose\n```\n\n### Step 3: STAGE EXECUTION\n\n```\nCall the corresponding skill (does not do work itself, purely dispatching):\n\n1. Inform the user which Stage is about to begin\n2. Load the corresponding skill's SKILL.md\n3. Launch the skill with the recommended mode\n4. Monitor stage completion status\n\nAfter completion:\n1. Compile deliverables list\n2. Update pipeline state (call state_tracker_agent)\n3. [MANDATORY] Proactively prompt checkpoint, wait for user confirmation\n```\n\n### Step 4: TRANSITION\n\n```\nAfter user confirmation:\n\n1. Pass the previous stage's deliverables as input to the next stage\n2. Trigger handoff protocol (defined in each skill's SKILL.md):\n - Stage 1 --> 2: deep-research handoff (RQ Brief + Bibliography + Synthesis)\n - Stage 2 --> 2.5: Pass complete paper to integrity_verification_agent\n - Stage 2.5 --> 3: Pass verified paper to reviewer\n - Stage 3 --> 4: Pass Revision Roadmap to academic-paper revision mode\n - Stage 4 --> 3': Pass revised draft and Response to Reviewers to reviewer\n - Stage 3' --> 4': Pass new Revision Roadmap + R&R Traceability Matrix (Schema 11) to academic-paper revision mode\n - Stage 4/4' --> 4.5: Pass revision-completed paper to integrity_verification_agent (final verification)\n - Stage 4.5 --> 5: Pass verified final draft to format-convert mode\n3. Begin next stage\n```\n\n### Mid-Conversation Reinforcement Protocol\n\nAt every stage transition, the orchestrator MUST inject a brief core principles reminder. This prevents context rot in long conversations.\n\n**Template** (adapt to the upcoming stage):\n\n````\n--- STAGE TRANSITION: [Current] → [Next] ---\n\n🔄 Core Principles Reinforcement:\n1. [Most relevant IRON RULE for the next stage]\n2. [Most relevant Anti-Pattern to avoid in the next stage]\n3. Quality check: Is the output of [Current Stage] at least as good as [Previous Stage]? If not, PAUSE.\n\nCheckpoint: [MANDATORY/ADVISORY] — [What user needs to confirm]\n---\n````\n\n**Stage-specific reinforcement content**: See `references/reinforcement_content.md` for the full transition → reinforcement focus table.\n\n---\n\n## Integrity Review Protocol\n\nStage 2.5 (pre-review) and Stage 4.5 (post-revision) verification. 5-phase protocol: references → citation context → statistical data → originality → claims.\n\n⚠️ **IRON RULE**: Stage 4.5 must PASS with zero issues to proceed to Stage 5. Stage 4.5 verifies from scratch independently.\n\n⚠️ **IRON RULE (v3.2)**: Both Stage 2.5 and Stage 4.5 must also run the **AI Research Failure Mode Checklist** — a 7-mode taxonomy extending the citation hallucination checks into implementation bugs, hallucinated results, shortcut reliance, bug-as-insight, methodology fabrication, and pipeline-level frame-lock. If any of the 7 modes is `SUSPECTED`, or if Modes 1/3/5/6 are `INSUFFICIENT EVIDENCE`, the pipeline **blocks** and the user must acknowledge (confirm / override with reasoning / revise) before the pipeline proceeds. There is no `--no-block` escape hatch. Stage 6 PROCESS SUMMARY then reports the full failure-mode audit log as part of the AI Self-Reflection Report.\n\n> See `references/integrity_review_protocol.md` for the 5-phase citation/claim verification procedures.\n> See `references/ai_research_failure_modes.md` for the 7-mode AI research failure checklist and block/override logic.\n\n---\n\n## Two-Stage Review Protocol\n\nStage 3 (full review, 5 reviewers) → Revision Coaching → Stage 4 → Stage 3' (re-review) → optional Residual Coaching → Stage 4'.\n\n> See `references/two_stage_review_protocol.md` for detailed stage flows and coaching dialogue limits.\n\n---\n\n## Mid-Entry Protocol\n\nUsers can enter from any stage. The orchestrator will:\n\n1. **Detect materials**: Analyze the content provided by the user to determine what is available\n2. **Identify gaps**: Check what prerequisite materials are needed for the target stage\n3. **Suggest backfilling**: If critical materials are missing, suggest whether to return to earlier stages\n4. **Direct entry**: If materials are sufficient, directly start the specified stage\n\n**Important: mid-entry cannot skip Stage 2.5**\n- If the user brings a paper and enters directly, go through Stage 2.5 (INTEGRITY) first before Stage 3 (REVIEW)\n- Only exception: User can provide a previous integrity verification report and content has not been modified\n\n---\n\n## External Review Protocol\n\nHandles external (human) reviewer feedback integration. 4-step workflow: Intake & Structuring → Strategic Revision Coaching → Revision & Response → Self-Verification.\n\n> See `references/external_review_protocol.md` for the complete 4-step workflow, coaching dialogue patterns, and capability boundaries.\n\n---\n\n## Progress Dashboard\n\nASCII dashboard shown at FULL checkpoints to display pipeline progress.\n\n> See `references/progress_dashboard_template.md` for the dashboard template.\n\n---\n\n## Revision Loop Management\n\n- Stage 3 (first review) -> Stage 4 (revision) -> Stage 3' (verification review) -> Stage 4' (re-revision, if needed) -> Stage 4.5 (final verification)\n- **Maximum 1 round of RE-REVISE** (Stage 4'): If Stage 3' gives Major, enter Stage 4' for revision then proceed directly to Stage 4.5 (no return to review)\n- **Pipeline overrides academic-paper's max 2 revision rule**: In the pipeline, revisions are limited to Stage 4 + Stage 4' (one round each), replacing academic-paper's max 2 rounds rule\n- Mark unresolved issues as Acknowledged Limitations\n- Provide cumulative revision history (each round's decision, items addressed, unresolved items)\n\n### Early-Stopping Criterion (v3.2)\n\nAt the end of each revision round, if **delta < 3 points** on the 0-100 rubric AND **no P0 issues remain**, suggest stopping the revision loop (\"converged\"). User can override. Hard cap: 2 full revision loops (Stage 4 + Stage 4').\n\n### Budget Transparency (v3.2)\n\nAt pipeline start, estimate token cost based on paper length, mode, and cross-model toggle. Present estimate and ask for user confirmation before Stage 1 begins.\n\n---\n\n## Reproducibility\n\nEvery pipeline artifact is versioned, hashed, and auditable.\n\n> See `references/reproducibility_audit.md` for standardized workflow guarantees, audit trail format, and artifact tracking.\n\n---\n\n## Stage 6: Process Summary Protocol\n\nProduces the final process record: paper creation journey, collaboration quality evaluation (6 dimensions, 1-100), and AI self-reflection report.\n\n> See `references/process_summary_protocol.md` for full workflow, required content structure, scoring dimensions, and output specifications.\n\n---\n\n## Anti-Patterns\n\nExplicit prohibitions to prevent common failure modes:\n\n| # | Anti-Pattern | Why It Fails | Correct Behavior |\n|---|-------------|-------------|-----------------|\n| 1 | **Skipping integrity checks** | \"The paper looks fine, skip Stage 2.5/4.5\" | Integrity checks are MANDATORY; they cannot be auto-skipped regardless of perceived quality |\n| 2 | **Orchestrator doing substantive work** | Pipeline orchestrator writes content or reviews the paper | Orchestrator only dispatches and coordinates; substantive work belongs to the sub-skills |\n| 3 | **Auto-advancing past MANDATORY checkpoints** | Moving to next stage without user confirmation at FULL checkpoints | MANDATORY checkpoints require explicit user input before proceeding |\n| 4 | **Quality degradation across stages** | Stage 4 revision is worse than Stage 2 draft because context window is exhausted | If Stage N output quality < Stage N-1, PAUSE and reload core principles before continuing |\n| 5 | **Silently dropping reviewer concerns** | Revision addresses 8 of 10 concerns and hopes nobody notices | The R&R tracking table must account for every concern with explicit status |\n| 6 | **Re-verifying only known issues at Stage 4.5** | Final integrity check only re-checks Stage 2.5 findings | Stage 4.5 must verify from scratch independently; revision may introduce new issues |\n| 7 | **Inflating Collaboration Quality scores** | Giving 90/100 to avoid awkward self-criticism | Honesty first: no inflation, no pleasantries; cite specific evidence for every score |\n| 8 | **Bypassing the Failure Mode Checklist block** (v3.2) | \"The 7-mode checklist is new, let's skip it this run\" | Stage 2.5/4.5 Failure Mode Checklist is MANDATORY and BLOCKING; no `--no-block` flag exists; overrides require user reasoning recorded for Stage 6 |\n\n---\n\n## Quality Standards\n\n| Dimension | Requirement |\n|-----------|------------|\n| Stage detection | Correctly identify user's current stage and available materials |\n| Mode recommendation | Recommend appropriate mode based on user preferences and material status |\n| Material handoff | Stage-to-stage handoff materials are complete and correctly formatted |\n| State tracking | Pipeline state updated in real time; Progress Dashboard accurate |\n| **Mandatory checkpoint** | **User confirmation required after each stage completion** |\n| **Mandatory integrity check** | **Stage 2.5 and 4.5 cannot be skipped, must PASS** |\n| **Mandatory failure mode checklist** (v3.2) | **Stage 2.5 and 4.5 must run the 7-mode AI research failure checklist; suspected failures block; overrides require user reasoning** |\n| No overstepping | ⚠️ IRON RULE: Orchestrator does not perform substantive research/writing/reviewing, only dispatching |\n| No forcing | ⚠️ IRON RULE: User can pause or exit pipeline at any time (but cannot skip integrity checks) |\n| Reproducible | Same input follows the same workflow across different sessions |\n| **Convergence-aware stopping** (v3.2) | **If delta < 3 points AND no P0 issues, suggest stopping revision loop; user can override** |\n| **Budget transparency** (v3.2) | **Token cost estimate + user confirmation at pipeline start** |\n\n---\n\n## Error Recovery\n\n| Stage | Error | Handling |\n|-------|-------|---------|\n| Intake | Cannot determine entry point | Ask user what materials they have and their goal |\n| Stage 1 | deep-research not converging | Suggest mode switch (socratic -> full) or narrow scope |\n| Stage 2 | Missing research foundation | Suggest returning to Stage 1 to supplement research |\n| Stage 2.5 | Still FAIL after 3 correction rounds | List unverifiable items; user decides whether to continue |\n| Stage 3 | Review result is Reject | Provide options: major restructuring (Stage 2) or abandon |\n| Stage 4 | Revision incomplete on all items | List unaddressed items; ask whether to continue |\n| Stage 3' | Verification still has major issues | Enter Stage 4' for final revision |\n| Stage 4' | Issues remain after revision | Mark as Acknowledged Limitations; proceed to Stage 4.5 |\n| Stage 4.5 | Final verification FAIL | Fix and re-verify (max 3 rounds) |\n| Any | User leaves midway | Save pipeline state; can resume from breakpoint next time |\n| Any | Skill execution failure | Report error; suggest retry or skip |\n\n---\n\n## Agent File References\n\n| Agent | Definition File |\n|-------|----------------|\n| pipeline_orchestrator_agent | `agents/pipeline_orchestrator_agent.md` |\n| state_tracker_agent | `agents/state_tracker_agent.md` |\n| integrity_verification_agent | `agents/integrity_verification_agent.md` |\n\n---\n\n## Reference Files\n\n| Reference | Purpose |\n|-----------|---------|\n| `references/pipeline_state_machine.md` | Complete state machine definition: all legal transitions, preconditions, actions |\n| `references/plagiarism_detection_protocol.md` | Phase D originality verification protocol + self-plagiarism + AI text characteristics |\n| `references/mode_advisor.md` | Unified cross-skill decision tree: maps user intent to optimal skill + mode |\n| `references/claim_verification_protocol.md` | Phase E claim verification protocol: claim extraction, source tracing, cross-referencing, verdict taxonomy |\n| `references/ai_research_failure_modes.md` | 7-mode AI research failure checklist (Lu 2026), run at Stage 2.5 + 4.5 with blocking behaviour, reported at Stage 6 |\n| `references/team_collaboration_protocol.md` | Multi-person team coordination: role definitions, handoff protocol, version control, conflict resolution |\n| `references/integrity_review_protocol.md` | Stage 2.5 + 4.5 integrity verification: 5-phase protocol details |\n| `references/two_stage_review_protocol.md` | Two-stage review: Stage 3 full review + Stage 3' verification review |\n| `references/external_review_protocol.md` | External (human) reviewer feedback: 4-step intake/coaching/revision/verification |\n| `references/process_summary_protocol.md` | Stage 6: collaboration quality evaluation + AI self-reflection report |\n| `references/reproducibility_audit.md` | Standardized workflow guarantees + audit trail format |\n| `references/progress_dashboard_template.md` | ASCII progress dashboard template |\n| `references/reinforcement_content.md` | Stage-specific reinforcement focus table for transitions |\n| `references/changelog.md` | Full version history |\n| `shared/handoff_schemas.md` | Cross-skill data contracts: 9 schemas for all inter-stage handoff artifacts |\n\n---\n\n## Templates\n\n| Template | Purpose |\n|----------|---------|\n| `templates/pipeline_status_template.md` | Progress Dashboard output template |\n\n---\n\n## Examples\n\n| Example | Demonstrates |\n|---------|-------------|\n| `examples/full_pipeline_example.md` | Complete pipeline conversation log (Stage 1-5, with integrity + 2-stage review) |\n| `examples/mid_entry_example.md` | Mid-entry example starting from Stage 2.5 (existing paper -> integrity check -> review -> revision -> finalization) |\n\n---\n\n## Output Language\n\nFollows user language. Academic terminology retained in English.\n\n---\n\n## Integration with Other Skills\n\n```\nacademic-pipeline dispatches the following skills (does not do work itself):\n\nStage 1: deep-research\n - socratic mode: Guided research exploration\n - full mode: Complete research report\n - quick mode: Quick research summary\n\nStage 2: academic-paper\n - plan mode: Socratic chapter-by-chapter guidance\n - full mode: Complete paper writing\n\nStage 2.5: integrity_verification_agent (Mode 1: pre-review)\nStage 4.5: integrity_verification_agent (Mode 2: final-check)\n\nStage 3: academic-paper-reviewer\n - full mode: Complete 5-person review (EIC + R1/R2/R3 + Devil's Advocate)\n\nStage 3': academic-paper-reviewer\n - re-review mode: Verification review (focused on revision responses)\n\nStage 4/4': academic-paper (revision mode)\nStage 5: academic-paper (format-convert mode)\n - Step 1: Ask user which academic formatting style (APA 7.0 / Chicago / IEEE, etc.)\n - Step 2: Auto-produce MD + DOCX\n - Step 3: Produce LaTeX (using corresponding document class, e.g., apa7 class for APA 7.0)\n - Step 4: After user confirms content is correct, tectonic compiles PDF (final version)\n - Fonts: Times New Roman (English) + Source Han Serif TC VF (Chinese) + Courier New (monospace)\n - ⚠️ IRON RULE: PDF must be compiled from LaTeX (HTML-to-PDF is prohibited)\n```\n\n---\n\n## Related Skills\n\n| Skill | Relationship |\n|-------|-------------|\n| `deep-research` | Dispatched (Stage 1 research phase) |\n| `academic-paper` | Dispatched (Stage 2 writing, Stage 4/4' revision, Stage 5 formatting) |\n| `academic-paper-reviewer` | Dispatched (Stage 3 first review, Stage 3' verification review) |\n\n---\n\n## Version Info\n\n| Item | Content |\n|------|---------|\n| Skill Version | 3.2 |\n| Last Updated | 2026-04-09 |\n| Maintainer | Cheng-I Wu |\n| Dependent Skills | deep-research v2.0+, academic-paper v2.0+, academic-paper-reviewer v1.1+ |\n| Role | Full academic research workflow orchestrator |\n\n---\n\n## Changelog\n\n> See `references/changelog.md` for full version history.\n\nFile v1.0.0:skills/academic-search/SKILL.md\n\n---\nname: academic-search\ndescription: |\n 学术论文搜索、引用分析与元数据提取专用 Skill。\n\n 【自动触发条件——出现以下任一信号时立即加载本 Skill，无需用户显式说明】\n\n 意图信号（中文）：\n - 搜论文 / 找论文 / 查论文 / 调研论文 / 检索文献 / 文献综述 / 综述\n - 顶会 / 顶刊 / CCF / NeurIPS / ICML / ICLR / ACL / EMNLP / CVPR / KDD / SIGIR / WWW\n - 引用数 / 被引 / 引用关系 / 引用量\n - BibTeX / 参考文献格式 / 导出引用\n - 作者发表列表 / 某人的论文 / 某人在哪发了什么\n - arXiv / Semantic Scholar / Google Scholar / PubMed / ACM DL / IEEE\n - 知网 / CNKI / 中国知网 / 学位论文 / 硕士论文 / 博士论文 / 中文文献 / 中文期刊\n - PDF 链接 / 论文 PDF / 开放获取\n - 摘要 abstract / 元数据\n\n 意图信号（英文）：\n - search paper / find paper / look up paper / literature review / survey\n - citation count / citation graph / citing / cited by\n - BibTeX / reference export\n - top conference / top journal / venue ranking\n - author publication list / papers by X\n\n URL 信号（出现以下域名的链接时自动触发）：\n - arxiv.org / ar5iv.org\n - semanticscholar.org\n - scholar.google.com\n - dl.acm.org\n - ieeexplore.ieee.org\n - pubmed.ncbi.nlm.nih.gov\n - paperswithcode.com\n - cnki.net / kns.cnki.net\n\n 覆盖平台：arXiv、Semantic Scholar、Google Scholar、ACM DL、IEEE Xplore、PubMed、Papers with Code、CNKI（中国知网）\nmetadata:\n version: \"1.2.0\"\n---\n\n# academic-search Skill\n\n## 前置检查\n\n在开始前，检查环境就绪状态：\n\n```bash\nbash ~/.claude/skills/academic-search/scripts/check-deps.sh\n```\n\n- **Node.js 22+**：必需（用于 CDP 浏览器模式）。仅使用 API 平台时可不检查。\n- **Chrome remote-debugging**：仅在访问 Google Scholar 或其他需要浏览器自动化的平台时必需。在 Chrome 地址栏打开 `chrome://inspect/#remote-debugging`，勾选 **Allow remote debugging for this browser instance**。\n- **curl**：必需，用于 API 调用。\n\narXiv、Semantic Scholar、PubMed、Papers with Code 等 API 平台无需 Chrome 远程调试即可使用。\n\n**S2 API Key（强烈建议）**：无 Key 时 S2 速率上限极低，单 session 多次调用必触发 429。免费注册即可获得更高配额：https://www.semanticscholar.org/product/api#api-key-form。有 Key 时在请求头加 `x-api-key: {your_key}`。\n\n## 搜索哲学\n\n**明确目标，选对平台，提取结构化数据，完成即止。**\n\n学术搜索不同于通用网页浏览——目标是获取**准确、结构化**的论文元数据，而不是浏览网页内容。\n\n**① 明确检索目标，定义成功标准**：执行前先明确什么算完成了。\n\n- 关键词搜索？精确论文？某作者的全部论文？某 venue 的论文列表？\n- 需要什么字段：仅标题和引用数 / 完整元数据 / PDF / BibTeX / 代码链接？\n- 年份范围？领域限定？返回几篇？\n- **成功标准**：用户要的是摘要表（第一遍）还是完整元数据（第二遍）？数量够了吗？字段都有了吗？这是后续所有决策的锚点。\n\n**② 选对平台**：不同需求对应不同平台（见下方矩阵）。API 平台优先，CDP 用于无 API 的平台。\n\n**③ 提取结构化数据，先筛后深**：搜索的时间瓶颈不在\"搜\"，在\"筛\"。默认采用两遍策略：\n\n- **第一遍（轻量扫描）**：先拉 20-30 条结果，输出轻量摘要表——标题、作者、年份、venue、引用数、是否有开放 PDF/代码。不拉完整摘要。\n- **用户或任务确认核心论文**（引用数高、venue 等级高、与目标最相关的 5-10 篇）后，**第二遍**再深入拉摘要、PDF、BibTeX 等完整信息。\n\n所有结果输出为统一 schema（见 `references/metadata-schema.md`），不要输出原始 HTML 或非结构化文本。多平台结果用 DOI/arXiv ID 去重合并。\n\n**④ 过程校验，用失败信号更新方向**：每一步的结果都是信息，不只是成功或失败的二元信号。\n\n| 失败信号 | 含义 | 方向调整 |\n|---------|------|---------|\n| API 429 / Rate exceeded | 本次会话消耗超配额，不是暂时波动 | 等待 15s+ 或切换 CDP 模式；不要同一请求重试 |\n| Jina/WebFetch 超时 | 该页面对静态抓取不友好 | 改用 curl 直接调 API 或切换 CDP |\n| S2 返回结果为空 | query 措辞问题，或该平台无收录 | 换关键词组合，或换 arXiv/PubMed |\n| 平台返回\"内容不存在\" | 未必真的不存在，可能是访问方式问题 | 检查 URL 参数是否完整，换平台验证 |\n| 同一方式重试 3 次无改善 | 路径错了，不是还没找到方法 | 重新评估目标，换平台或换访问方式 |\n\n**⑤ 完成判断**：对照①定义的成功标准确认任务完成后停止，不为\"更完整\"而过度操作。\n\n## 平台选择矩阵\n\n根据任务特征选择最合适的平台和访问方式：\n\n| 需求 | 首选平台 | 访问方式 | 备注 |\n|------|---------|---------|------|\n| CS/Math/Physics/统计 论文搜索 | **arXiv** | REST API | 完全开放，PDF 直链 |\n| 引用数、引用/被引关系 | **Semantic Scholar** | REST API | 免费 Key 可提升速率 |\n| 作者主页、全部论文 | **Semantic Scholar** | REST API | /author/{id}/papers |\n| 生物医学、生命科学 | **PubMed** | NCBI E-utilities | 完全开放 |\n| ML 论文 + 代码仓库 | **Papers with Code** | REST API | 无需鉴权 |\n| ACM 顶会论文 (SIGKDD/WWW 等) | **ACM DL** | WebFetch + Jina | BibTeX 导出端点可直接访问 |\n| IEEE 期刊/会议论文 | **IEEE Xplore** | WebFetch / Jina | 有机构 Key 时用官方 API |\n| 广泛引用数 / 全平台覆盖 | **Google Scholar** | **CDP（必须）** | 无 API，反爬严重 |\n| 论文是否存在 / 基础元数据 | **Semantic Scholar** | REST API | 支持 DOI / arXiv ID 互查 |\n| **中文文献**（期刊/学位论文/会议） | **CNKI（知网）** | **CDP（必须）** | 无公开 API；机构登录后全文可得 |\n\n**API 平台访问方式**：\n\n- **WebSearch**：用于发现论文来源、查找 DOI/作者 ID 等信息入口\n- **WebFetch / Jina**：URL 已知时从页面提取，Jina（`r.jina.ai/{url}`）节省 token，适合文章类页面\n- **curl**：直接调用结构化 API，返回 JSON/XML\n- **CDP**：仅 Google Scholar 必须；其他平台在 API/WebFetch 无效时作为兜底\n\n详细 API 调用模板见 `references/api-cookbook.md`。\n\n## 核心能力\n\n### 关键词搜索\n\n1. 根据领域选平台：CS/ML → arXiv + Semantic Scholar；生医 → PubMed；跨领域 → Semantic Scholar\n2. **扩展 query**：用户自然语言输入往往只是一个切入点，需要主动展开为 2-3 个互补 query 覆盖不同命名习惯：\n - 同义词替换：`agent` → `agentic` / `multi-agent` / `autonomous`\n - 子概念拆分：`time series agent` → `time series LLM agent` + `time series agentic reasoning` + `time series automated analysis`\n - 缩写与全称并用：`TS` / `time series`，`LLM` / `large language model`\n - 不同 query 结果合并去重，覆盖率比单 query 提升 30-50%\n3. 构造查询：arXiv 用 `search_query` 字段前缀语法；S2 用 `query` 参数；PubMed 用 `term` 布尔表达式\n4. **计划多次 S2 调用时优先用 batch API**（`/paper/batch`）而非多次 search，节省速率配额\n5. **第一遍输出轻量摘要表**（必含：标题、年份、venue、引用数、是否有开放 PDF），**不默认拉完整摘要**\n6. **意图判断**：用户明确说\"只要前 N 篇\"或\"摘要表即可\"时，直接输出第一遍结果，无需等待确认再停下\n7. 用户需要第二遍时，再深拉完整元数据\n\n多平台并行查询时，用子 Agent 分治（见\"并行分治策略\"一节）。\n\n**轻量摘要表输出格式示例**：\n\n| 标题 | 年份 | Venue | 引用数 | PDF |\n|------|------|-------|--------|-----|\n| Attention Is All You Need | 2017 | NeurIPS [CCF-A] | 120,000+ | ✓ arXiv |\n| BERT: Pre-training... | 2019 | NAACL [CCF-B] | 80,000+ | ✓ arXiv |\n\nVenue 等级标注规则：CS 会议参考 `references/venue-rankings.md`（CCF 分级）；期刊显示 JCR 分区（若可从 S2 `venue` 字段获取）。\n\n### 结果筛选\n\n搜索后用以下维度缩小范围，**优先帮用户筛出值得读的论文，而不是把所有结果都呈现**：\n\n| 筛选维度 | 数据来源 | 说明 |\n|---------|---------|------|\n| 引用数阈值 | S2 `citationCount` | 经典论文通常引用数高；新兴方向可适当放低阈值 |\n| 发表年份 | 所有平台 | 综述类需要覆盖历史；最新进展限定近 2-3 年 |\n| Venue 等级 | S2 `venue` + `references/venue-rankings.md` | CS 会议参考 CCF 分级；优先 CCF-A/B |\n| 开放 PDF | S2 `externalIds.ArXiv` 存在即可得 | **只要有 ArXiv ID 就标 ✓**，不依赖 openAccessPdf（该字段经常为 null） |\n| 代码可用性 | Papers with Code API | ML 论文用 `paperswithcode.com/api/v1/papers/?arxiv_id={id}` 自动补全代码列 |\n\n**排序建议**：面向学术前沿性的综合排序，优先级依次为：\n\n1. **时效性（最高权重）**：近 6 个月内发表的论文标注 `[新]` 并置顶展示，不因引用数低而降权——前沿方向的新论文引用数天然偏低，但代表最新进展\n2. **引用数（次要权重）**：同一时间段内按引用数降序，高引用代表社区认可度\n3. **CCF 等级（参考项）**：顶会发表是质量信号，但不作为首要排序维度——高质量工作越来越多以 arXiv 预印本形式先行发布，CCF 等级仅作为同引用数论文的决胜项，并在表格中标注供用户参考\n\n**实操分组示例**：\n- 第一组：近 6 个月论文，按引用数降序（含 `[新]` 标注）\n- 第二组：更早论文，按引用数降序，CCF-A/B 同引用数时优先\n\n**筛选后的典型结论格式**：\n\n> 共找到 28 篇，按引用数 + venue 等级筛选后，推荐优先阅读以下 6 篇：[列表]\n> 其余 22 篇可按需查阅。\n\n### 精确论文查找\n\n已知 DOI 或 arXiv ID 时，直接用 Semantic Scholar 精确查询：\n```bash\n# DOI 查询\ncurl -s \"https://api.semanticscholar.org/graph/v1/paper/DOI:{doi}?fields=title,authors,year,abstract,citationCount,openAccessPdf\"\n\n# arXiv ID 查询\ncurl -s \"https://api.semanticscholar.org/graph/v1/paper/ARXIV:{arxiv_id}?fields=title,authors,year,abstract,citationCount,openAccessPdf\"\n```\n\n### 元数据提取\n\n所有提取结果必须转换为 `references/metadata-schema.md` 定义的标准 JSON schema。输出时：\n\n- **单篇**：Markdown 表格格式，字段清晰\n- **多篇**：Markdown 列表表格（标题、作者、年份、Venue、引用数、PDF 链接）\n- **批量导出**：JSON 数组\n\n### PDF 获取\n\n按以下优先级尝试：\n\n1. **arXiv PDF 直链**：`externalIds.ArXiv` 存在时，**直接构造** `https://arxiv.org/pdf/{arxiv_id}`，不检查 openAccessPdf（S2 该字段经常为 null，但 arXiv PDF 实际可得）\n2. **Semantic Scholar openAccessPdf**：从 API 响应的 `openAccessPdf.url` 字段获取（作为补充，非首选）\n3. **Unpaywall**：`https://api.unpaywall.org/v2/{doi}?email=your@email.com`，返回 Open Access PDF 链接\n4. **平台页面**：通过 WebFetch 或 CDP 访问论文页，提取 PDF 下载链接\n5. **用户决定**：如以上均无法获取免费 PDF，告知用户需要机构访问权限\n\n不要尝试访问任何需要绕过付费墙的第三方服务。\n\n### BibTeX 导出\n\n优先级：\n\n1. **arXiv**：`https://arxiv.org/bibtex/{arxiv_id}` 直接获取\n2. **ACM DL**：先试 `https://dl.acm.org/action/exportCitation?doi={encoded_doi}&format=bibtex`；若返回 challenge/HTML 错页，回退 CDP\n3. **Semantic Scholar**：无直接端点，根据 `references/metadata-schema.md` 的模板从字段拼装\n4. **其他平台**：CDP 点击页面上的 \"Export Citation\" / \"Cite\" 按钮\n\n### 作者主页解析\n\n```bash\n# Semantic Scholar 作者搜索\ncurl -s \"https://api.semanticscholar.org/graph/v1/author/search?query={author_name}&fields=name,affiliations,paperCount,citationCount\"\n\n# 获取作者全部论文（分页）\ncurl -s \"https://api.semanticscholar.org/graph/v1/author/{author_id}/papers?fields=title,year,citationCount,externalIds&limit=100&offset=0\"\n```\n\nGoogle Scholar 作者页需 CDP，见 `references/site-patterns/scholar.google.com.md`。\n\n## CDP 模式（Google Scholar 及其他需要浏览器自动化的平台）\n\n通过 CDP Proxy 直连用户日常 Chrome，天然携带登录态。\n\n所有操作在自己创建的后台 tab 中进行，不干扰用户已有 tab，完成后关闭。\n\n### 启动\n\n```bash\nbash ~/.claude/skills/academic-search/scripts/check-deps.sh\n```\n\n脚本自动检查并启动 CDP Proxy（默认 `127.0.0.1:3456`，可通过 `CDP_PROXY_PORT` 覆盖）。\n\n### 操作方式\n\n进入浏览器层后，用 HTTP API 操控页面：\n\n```bash\n# 创建新 tab，导航到目标页\nTARGET=$(curl -s \"http://127.0.0.1:${CDP_PROXY_PORT:-3456}/new?url=https://scholar.google.com\" | node -p \"JSON.parse(require('fs').readFileSync(0, 'utf8')).targetId\")\n\n# 执行 JS 提取数据\ncurl -s -X POST \"http://127.0.0.1:${CDP_PROXY_PORT:-3456}/eval?target=$TARGET\" -d 'document.title'\n\n# 点击元素（CSS 选择器）\ncurl -s -X POST \"http://127.0.0.1:${CDP_PROXY_PORT:-3456}/click?target=$TARGET\" -d 'button[type=submit]'\n\n# 完成后关闭 tab\ncurl -s \"http://127.0.0.1:${CDP_PROXY_PORT:-3456}/close?target=$TARGET\"\n```\n\n完整 API 参考见 `references/cdp-api.md`。\n\n**三种点击方式**：\n\n| 方式 | 端点 | 适用场景 |\n|------|------|---------|\n| JS click | `/click` | 通用，速度快 |\n| 真实鼠标 | `/clickAt` | 需要触发文件对话框或绕过反自动化检测 |\n| 文件上传 | `/setFiles` | 直接设置 file input，绕过对话框 |\n\n**先了解页面结构，再决定动作**：用 `/eval document.body.innerText.slice(0, 500)` 或截图快速了解当前页面状态。\n\n## 并行分治策略\n\n任务包含多个**独立**目标时（如同时查询 N 篇论文、N 个来源），分发子 Agent 并行执行。\n\n**好处**：速度 = 单子任务时长；抓取内容不进入主 Agent context，节省 token。\n\n**子 Agent Prompt 写法**：\n- 必须写：`必须加载 academic-search skill 并遵循指引`\n- 描述**目标**（获取/提取/查找），不要指定具体步骤\n- 说明需要哪些字段（标题/引用数/PDF 等）\n- **注意用词**：「搜索 BERT 的引用数」会把子 Agent 锚定到 WebSearch；应写「获取 BERT 的引用数」——描述目标，不暗示手段\n\n**典型分治场景**：\n\n| 适合分治 | 不适合分治 |\n|---------|-----------|\n| 多平台并发查同一论文（arXiv + S2 + PubMed） | 查询有依赖关系（先搜索再按结果查详情） |\n| 批量查询 N 篇不相关论文 | 简单单平台单次 API 查询 |\n| 多个作者主页并行抓取 | 几次 curl 就能完成的轻量任务 |\n\n**多平台并发查同一论文时的去重**：\n\n子 Agent 返回结果后，主 Agent 按 `references/metadata-schema.md` 中的去重规则合并：DOI 为主键 → arXiv ID 次之 → 标题+年份模糊匹配。\n\n## 信息核实\n\n学术搜索的一手来源是**论文本身**和**平台官方 API**，不是二手报道。\n\n| 核实目标 | 一手来源 |\n|---------|---------|\n| 论文元数据（标题、作者、DOI）| 发表平台（ACM DL / IEEE / arXiv）的官方页面 |\n| 引用数 | Google Scholar（最全）> Semantic Scholar |\n| 代码实现 | Papers with Code / 论文官方 GitHub |\n| 会议/期刊信息 | 主办方官网 |\n\n多平台引用数不一致时正常——不同平台收录范围不同，Google Scholar 通常最高。\n\n## 站点经验\n\n操作中积累的特定网站经验，按域名存储在 `references/site-patterns/` 下。\n\n已预置经验的平台：arXiv、Semantic Scholar、Google Scholar、ACM DL、IEEE Xplore、PubMed、Papers with Code、CNKI（知网）\n\n确定目标平台后，**必须**读取对应文件获取先验知识（平台特征、有效模式、已知陷阱）。经验内容标注发现日期，当作**可能有效的提示，不是保证正确的事实**——按经验操作失败时，回退通用模式，并**更新经验文件**（记录失败原因和发现日期）。操作成功后若发现了新模式或陷阱，同样主动写入。\n\n## References 索引\n\n| 文件 | 何时加载 |\n|------|---------|\n| `references/api-cookbook.md` | 需要 API 调用示例、参数说明、响应字段映射时 |\n| `references/metadata-schema.md` | 整理提取结果、多平台去重合并、生成 BibTeX 时 |\n| `references/cdp-api.md` | 需要 CDP 浏览器操作时（Google Scholar、CNKI 等） |\n| `references/venue-rankings.md` | 标注 CS 会议/期刊等级（CCF 分级）时 |\n| `references/site-patterns/{domain}.md` | 确定目标平台后，读取对应站点经验 |\n| `references/site-patterns/cnki.net.md` | 知网检索时必读：登录态要求、DOM 选择器、数据库代码 |\n\nFile v1.0.0:skills/deep-research/SKILL.md\n\n---\nname: deep-research\ndescription: \"Universal deep research agent team. 13-agent pipeline for rigorous academic research on any topic. 7 modes: full research, quick brief, paper review, lit-review, fact-check, Socratic guided research dialogue, and systematic review with optional meta-analysis. Covers research question formulation, Socratic mentoring, methodology design, systematic literature search, source verification, cross-source synthesis, risk of bias assessment, meta-analysis, APA 7.0 report compilation, editorial review, devil's advocate challenges, ethics review, and post-research literature monitoring. Triggers on: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, guide my research, help me think through, 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 事實查核, 引導我的研究, 幫我釐清, 幫我想想, 我不確定要研究什麼, 研究方向, 研究主題.\"\nmetadata:\n version: \"2.8\"\n last_updated: \"2026-04-09\"\n status: active\n related_skills:\n - academic-paper\n - academic-pipeline\n---\n\n# Deep Research — Universal Academic Research Agent Team\n\nUniversal deep research tool — a domain-agnostic 13-agent team for rigorous academic research on any topic.\n\n**v2.4** adds writing quality improvements to the report compiler:\n- **Style Profile consumption** (optional) — If a Style Profile is available from academic-paper intake, the report compiler applies it as a soft guide for the Executive Summary and Synthesis sections. Discipline conventions and report objectivity take priority.\n- **Writing Quality Check** — The report compiler runs a writing quality checklist before finalizing: flags AI-typical overused terms, checks sentence/paragraph length variation, removes throat-clearing openers. See `academic-paper/references/writing_quality_check.md`.\n\n## Quick Start\n\n**Minimal command:**\n```\nResearch the impact of AI on higher education quality assurance\n```\n\n**Socratic mode:**\n```\nGuide my research on the impact of declining birth rates on private universities\n引導我的研究：少子化對私立大學的影響\n幫我釐清我的研究方向，我對高教品保有興趣但還不太確定\n```\n\n**Execution:**\n1. Scoping — Research question + methodology blueprint\n2. Investigation — Systematic literature search + source verification\n3. Analysis — Cross-source synthesis + bias check\n4. Composition — Full APA 7.0 report\n5. Review — Editorial + ethics + vulnerability scan\n6. Revision — Final polished report\n\n---\n\n## Trigger Conditions\n\n### Trigger Keywords\n\n**English**: research, deep research, literature review, systematic review, meta-analysis, PRISMA, evidence synthesis, fact-check, methodology, APA report, academic analysis, policy analysis, guide my research, help me think through, monitor this topic, set up alerts\n\n**繁體中文**: 研究, 深度研究, 文獻回顧, 文獻探討, 系統性回顧, 後設分析, 證據綜整, 事實查核, 研究方法, 學術分析, 政策分析, 引導我的研究, 幫我釐清, 監測這個主題, 設定追蹤\n\n### Socratic Mode Activation\n\nActivate `socratic` mode when the user's **intent** matches any of the following patterns, **regardless of language**. Detect meaning, not exact keywords.\n\n**Intent signals** (any one is sufficient):\n1. User has no clear research question and wants guided thinking\n2. User asks to be \"led\", \"guided\", or \"mentored\" through research\n3. User expresses uncertainty about what to research or where to start\n4. User wants to brainstorm, explore, or clarify a research direction\n5. User describes a vague interest without a specific, answerable question\n\n**Default rule**: When intent is ambiguous between `socratic` and `full`, **prefer `socratic`** — it is safer to guide first than to produce an unwanted report. The user can always switch to `full` later.\n\n**Example triggers** (illustrative, not exhaustive):\n\"guide my research\", \"help me think through\", 「引導我的研究」「幫我釐清」, or equivalent in any language\n\n### Does NOT Trigger\n\n| Scenario | Use Instead |\n|----------|-------------|\n| Writing a paper (not researching) | `academic-paper` |\n| Reviewing a paper (structured review) | `academic-paper-reviewer` |\n| Full research-to-paper pipeline | `academic-pipeline` |\n\n### Quick Mode Selection Guide\n\n| Your Situation 你的狀況 | Recommended Mode | Spectrum |\n|----------------|-----------------|----------|\n| Vague idea, need guidance / 有模糊想法，需要引導 | `socratic` | originality |\n| Clear RQ, need comprehensive research / 有明確 RQ，需要完整研究 | `full` | balanced |\n| Need a quick brief (30 min) / 需要快速摘要 | `quick` | fidelity |\n| Have a paper to evaluate before citing / 有論文需要評估 | `review` | balanced |\n| Need literature review for a topic / 需要文獻回顧 | `lit-review` | fidelity |\n| Need to verify specific claims / 需要查核特定事實 | `fact-check` | fidelity |\n| Need systematic review / meta-analysis / 系統性回顧或後設分析 | `systematic-review` | fidelity |\n\n**Spectrum** (v3.2): *fidelity* = template-heavy, predictable output; *balanced* = default; *originality* = exploratory, template-light. See `shared/mode_spectrum.md` for the full cross-skill spectrum table.\n\nNot sure? Start with `socratic` — it will help you figure out what you need.\n不確定？先用 `socratic` 模式——它會幫你釐清你需要什麼。\n\n---\n\n## Agent Team (13 Agents)\n\n| # | Agent | Role | Phase |\n|---|-------|------|-------|\n| 1 | `research_question_agent` | Transforms vague topics into precise, FINER-scored research questions with scope boundaries | Phase 1, Socratic Layer 1 |\n| 2 | `research_architect_agent` | Designs methodology blueprint: paradigm, method, data strategy, analytical framework, validity criteria | Phase 1 |\n| 3 | `bibliography_agent` | Systematic literature search, source screening, annotated bibliography in APA 7.0 | Phase 2 |\n| 4 | `source_verification_agent` | Fact-checking, source grading (evidence hierarchy), predatory journal detection, conflict-of-interest flagging | Phase 2 |\n| 5 | `synthesis_agent` | Cross-source integration, contradiction resolution, thematic synthesis, gap analysis | Phase 3 |\n| 6 | `report_compiler_agent` | Drafts complete APA 7.0 report (Title -> Abstract -> Intro -> Method -> Findings -> Discussion -> References) | Phase 4, 6 |\n| 7 | `editor_in_chief_agent` | Q1 journal editorial review: originality, rigor, evidence sufficiency, verdict (Accept/Revise/Reject) | Phase 5 |\n| 8 | `devils_advocate_agent` | Challenges assumptions, tests for logical fallacies, finds alternative explanations, confirmation bias checks | Phase 1, 3, 5, Socratic Layer 2, 4 |\n| 9 | `ethics_review_agent` | AI-assisted research ethics, attribution integrity, dual-use screening, fair representation | Phase 5 |\n| 10 | `socratic_mentor_agent` | Q1 journal editor persona; guides research thinking through Socratic questioning across 5 layers | Socratic Mode (Layer 1-5) |\n| 11 | `risk_of_bias_agent` | Assesses risk of bias using RoB 2 (RCTs) and ROBINS-I (non-randomized); traffic-light visualization | Systematic Review (Phase 2) |\n| 12 | `meta_analysis_agent` | Designs and executes meta-analysis or narrative synthesis; effect sizes, heterogeneity, GRADE | Systematic Review (Phase 3) |\n| 13 | `monitoring_agent` | Post-research literature monitoring: digests, retraction alerts, contradictory findings detection | Optional (post-pipeline) |\n\n---\n\n## Mode Selection Guide\n\nSee `references/mode_selection_guide.md` for the detailed guide.\n\n```\nUser Input\n |\n +-- Already have a clear research question?\n | +-- Yes --> Need PRISMA-compliant systematic review / meta-analysis?\n | | +-- Yes --> systematic-review mode\n | | +-- No --> Need a full report?\n | | +-- Yes --> full mode\n | | +-- No --> Only need literature?\n | | +-- Yes --> lit-review mode\n | | +-- No --> quick mode\n | +-- No --> Want to be guided through thinking?\n | +-- Yes --> socratic mode\n | +-- No --> full mode (Phase 1 will be interactive)\n |\n +-- Already have text to review? --> review mode\n +-- Only need fact-checking? --> fact-check mode\n```\n\n---\n\n## Orchestration Workflow (6 Phases)\n\n```\nUser: \"Research [topic]\"\n |\n=== Phase 1: SCOPING (Interactive) ===\n |\n |-> [research_question_agent] -> RQ Brief\n | - FINER criteria scoring (Feasible, Interesting, Novel, Ethical, Relevant)\n | - Scope boundaries (in-scope / out-of-scope)\n | - 2-3 sub-questions\n |\n |-> [research_architect_agent] -> Methodology Blueprint\n | - Research paradigm (positivist / interpretivist / pragmatist)\n | - Method selection (qualitative / quantitative / mixed)\n | - Data strategy (primary / secondary / both)\n | - Analytical framework\n | - Validity & reliability criteria\n |\n +-> [devils_advocate_agent] -- CHECKPOINT 1\n - RQ clarity and answerable?\n - Method appropriate for question?\n - Scope too broad or too narrow?\n - Verdict: PASS / REVISE (with specific feedback)\n |\n ** User confirmation before Phase 2 **\n |\n=== Phase 2: INVESTIGATION ===\n |\n |-> [bibliography_agent] -> Source Corpus + Annotated Bibliography\n | - Systematic search strategy (databases, keywords, Boolean)\n | - Inclusion/exclusion criteria\n | - PRISMA-style flow (if applicable)\n | - Annotated bibliography (APA 7.0)\n |\n +-> [source_verification_agent] -> Verified & Graded Sources\n - Evidence hierarchy grading (Level I-VII)\n - Predatory journal screening\n - Conflict-of-interest flagging\n - Currency assessment (publication date relevance)\n - Source quality matrix\n |\n=== Phase 3: ANALYSIS ===\n |\n |-> [synthesis_agent] -> Synthesis Narrative + Gap Analysis\n | - Thematic synthesis across sources\n | - Contradiction identification & resolution\n | - Evidence convergence/divergence mapping\n | - Knowledge gap analysis\n | - Theoretical framework integration\n |\n +-> [devils_advocate_agent] -- CHECKPOINT 2\n - Cherry-picking check\n - Confirmation bias detection\n - Logic chain validation\n - Alternative explanations explored?\n - Verdict: PASS / REVISE\n |\n=== Phase 4: COMPOSITION ===\n |\n +-> [report_compiler_agent] -> Full APA 7.0 Draft\n - Title Page\n - Abstract (150-250 words)\n - Introduction (context, problem, purpose, RQ)\n - Literature Review / Theoretical Framework\n - Methodology\n - Findings / Results\n - Discussion (interpretation, implications, limitations)\n - Conclusion & Recommendations\n - References (APA 7.0)\n - Appendices (if applicable)\n |\n=== Phase 5: REVIEW (Parallel) ===\n |\n |-> [editor_in_chief_agent] -> Editorial Verdict + Line Feedback\n | - Originality assessment\n | - Methodological rigor\n | - Evidence sufficiency\n | - Argument coherence\n | - Writing quality (clarity, conciseness, flow)\n | - Verdict: ACCEPT / MINOR REVISION / MAJOR REVISION / REJECT\n |\n |-> [ethics_review_agent] -> Ethics Clearance\n | - AI disclosure compliance\n | - Attribution integrity\n | - Dual-use screening\n | - Fair representation check\n | - Verdict: CLEARED / CONDITIONAL / BLOCKED\n |\n +-> [devils_advocate_agent] -- CHECKPOINT 3\n - Final vulnerability scan\n - Strongest counter-argument test\n - \"So what?\" significance check\n - Verdict: PASS / REVISE\n |\n=== Phase 6: REVISION ===\n |\n +-> [report_compiler_agent] -> Final Report\n - Address editorial feedback\n - Resolve ethics conditions\n - Incorporate devil's advocate insights\n - Max 2 revision loops\n - Remaining issues -> \"Acknowledged Limitations\" section\n```\n\n### Checkpoint Rules\n\n1. ⚠️ **IRON RULE**: **Devil's Advocate** has 3 mandatory checkpoints; **Critical-severity** issues block progression\n2. Revision loops capped at **2 iterations**; remaining issues become \"acknowledged limitations\"\n3. ⚠️ **IRON RULE**: **Ethics Review** can halt delivery for Critical ethics concerns\n4. User confirmation required after Phase 1 before proceeding\n\n---\n\n## Socratic Mode: Guided Research Dialogue\n\n5-layer dialogue guiding users from vague ideas to concrete research questions. Core principle: ⚠️ **IRON RULE**: Never give direct answers.\n\n**Layers**: Clarification -> Assumption Probing -> Evidence/Reasoning -> Viewpoint/Perspective -> Implication/Consequence\n\n> See `references/socratic_mode_protocol.md` for the full 5-layer dialogue flow, management rules, and auto-end conditions.\n\n---\n\n## Systematic Review Mode\n\nPRISMA 2020-compliant systematic review with optional meta-analysis. Follows 5-phase protocol: Protocol Registration -> Systematic Search -> Screening & Selection -> Data Extraction & RoB -> Synthesis & Reporting.\n\n> See `references/systematic_review_protocol.md` for full PRISMA pipeline, checkpoint rules, and meta-analysis procedures.\n\n---\n\n## Operational Modes\n\n| Mode | Agents Active | Output | Word Count |\n|------|---------------|--------|------------|\n| `full` (default) | All 9 core (excluding socratic_mentor, RoB, meta-analysis) | Full APA 7.0 report | 3,000-8,000 |\n| `quick` | RQ + Biblio + Verification + Report | Research brief | 500-1,500 |\n| `review` | Editor + Devil's Advocate + Ethics | Reviewer report on provided text | N/A |\n| `lit-review` | Biblio + Verification + Synthesis | Annotated bibliography + synthesis | 1,500-4,000 |\n| `fact-check` | Source Verification only | Verification report | 300-800 |\n| `socratic` | Socratic Mentor + RQ + Devil's Advocate | Research Plan Summary (INSIGHT collection) | N/A (iterative) |\n| `systematic-review` | RQ + Architect + Biblio + Verification + RoB + Meta-Analysis + Synthesis + Report + Editor + Ethics + DA | Full PRISMA 2020 report + forest plot data + GRADE table | 5,000-15,000 |\n\n---\n\n## Failure Paths\n\nSee `references/failure_paths.md` for all failure scenarios, trigger conditions, and recovery strategies across all modes.\n\nKey failure path summary:\n\n| Failure Scenario | Trigger Condition | Recovery Strategy |\n|---------|---------|---------|\n| RQ cannot converge | Phase 1 / Layer 1 exceeds multiple rounds while still vague | Provide 3 candidate RQs or suggest lit-review |\n| Insufficient literature | bibliography_agent finds < 5 sources | Expand search strategy, alternative keywords |\n| Methodology mismatch | RQ type misaligned with method capability | Return to Phase 1, suggest 3 alternative methods |\n| Devil's Advocate CRITICAL | Fatal logical flaw discovered | STOP, explain the issue, require correction |\n| Ethics BLOCKED | Serious ethical issue | STOP, list issues and remediation path |\n| Socratic non-convergence | > 10 rounds without convergence | Suggest switching to full mode |\n| User abandons mid-process | Explicitly states they don't want to continue | Save progress, provide re-entry path |\n| Only Chinese-language literature | English search returns empty | Switch to Chinese academic databases |\n\n---\n\n## Literature Monitoring (Optional Post-Pipeline)\n\nOptional post-research monitoring for new publications in the research area.\n\n> See `references/literature_monitoring_strategies.md` for setup instructions across academic databases.\n\n---\n\n## Handoff Protocol: deep-research → academic-paper\n\nAfter research is complete, the following materials can be handed off to `academic-paper`:\n\n1. **Research Question Brief** (from research_question_agent)\n2. **Methodology Blueprint** (from research_architect_agent)\n3. **Annotated Bibliography** (from bibliography_agent)\n4. **Synthesis Report** (from synthesis_agent)\n5. **[If socratic mode] INSIGHT Collection and Research Plan Summary**\n\n**Trigger**: User says \"now help me write a paper\" or \"write a paper based on this\"\n\n`academic-paper`'s `intake_agent` will automatically detect available materials and skip redundant steps:\n- Has RQ Brief -> skip topic scoping\n- Has Bibliography -> skip literature search\n- Has Synthesis -> accelerate findings / discussion writing\n\nSee `examples/handoff_to_paper.md` for a detailed handoff example.\n\n---\n\n## Full Academic Pipeline\n\nSee `academic-pipeline/SKILL.md` for the complete workflow.\n\n---\n\n## Agent File References\n\n| Agent | Definition File |\n|-------|----------------|\n| research_question_agent | `agents/research_question_agent.md` |\n| research_architect_agent | `agents/research_architect_agent.md` |\n| bibliography_agent | `agents/bibliography_agent.md` |\n| source_verification_agent | `agents/source_verification_agent.md` |\n| synthesis_agent | `agents/synthesis_agent.md` |\n| report_compiler_agent | `agents/report_compiler_agent.md` |\n| editor_in_chief_agent | `agents/editor_in_chief_agent.md` |\n| devils_advocate_agent | `agents/devils_advocate_agent.md` |\n| ethics_review_agent | `agents/ethics_review_agent.md` |\n| socratic_mentor_agent | `agents/socratic_mentor_agent.md` |\n| risk_of_bias_agent | `agents/risk_of_bias_agent.md` |\n| meta_analysis_agent | `agents/meta_analysis_agent.md` |\n| monitoring_agent | `agents/monitoring_agent.md` |\n\n---\n\n## Reference Files\n\n| Reference | Purpose | Used By |\n|-----------|---------|---------|\n| `references/apa7_style_guide.md` | APA 7th edition quick reference | report_compiler, editor_in_chief |\n| `references/source_quality_hierarchy.md` | Evidence pyramid + grading rubric | source_verification, bibliography |\n| `references/methodology_patterns.md` | Research design templates | research_architect |\n| `references/logical_fallacies.md` | 30+ fallacies catalog | devils_advocate |\n| `references/ethics_checklist.md` | AI disclosure, attribution, dual-use | ethics_review |\n| `references/interdisciplinary_bridges.md` | Cross-discipline connection patterns | synthesis, research_architect |\n| `references/socratic_questioning_framework.md` | 6 types of Socratic questions + 30+ prompt patterns | socratic_mentor |\n| `references/failure_paths.md` | 12 failure scenarios with triggers and recovery paths | all agents |\n| `references/mode_selection_guide.md` | Mode selection flowchart and comparison table | orchestrator |\n| `references/irb_decision_tree.md` | IRB decision tree + Taiwan process + HE quick reference | ethics_review, research_architect |\n| `references/equator_reporting_guidelines.md` | EQUATOR reporting guideline mapping | research_architect, report_compiler |\n| `references/preregistration_guide.md` | Preregistration decision tree + platforms + checklist | research_architect |\n| `references/systematic_review_toolkit.md` | Cochrane v6.4, PRISMA 2020, RoB 2, ROBINS-I, I² guide, GRADE, protocol registration | risk_of_bias, meta_analysis, bibliography, report_compiler |\n| `references/literature_monitoring_strategies.md` | Google Scholar alerts, PubMed alerts, RSS feeds, Retraction Watch, citation tracking, monitoring cadence | monitoring_agent |\n| `references/argumentation_reasoning_framework.md` | Cognitive framework for evaluating argument strength: Toulmin model, causal reasoning (Bradford Hill), inference to best explanation, epistemic status classification | synthesis, devils_advocate, source_verification, socratic_mentor, research_architect |\n| `references/socratic_mode_protocol.md` | Full 5-layer Socratic dialogue flow, management rules, auto-end conditions | socratic_mentor, research_question |\n| `references/systematic_review_protocol.md` | Full PRISMA pipeline, checkpoint rules, meta-analysis procedures | risk_of_bias, meta_analysis, bibliography, report_compiler |\n| `references/cross_agent_quality_definitions.md` | Peer-reviewed source tiers, currency standards, severity definitions | all agents |\n| `references/changelog.md` | Full version history | — |\n\n---\n\n## Templates\n\n| Template | Purpose |\n|----------|---------|\n| `templates/research_brief_template.md` | Quick mode output format |\n| `templates/literature_matrix_template.md` | Source x Theme analysis matrix |\n| `templates/evidence_assessment_template.md` | Per-source quality assessment card |\n| `templates/preregistration_template.md` | OSF standard 21-item preregistration template |\n| `templates/prisma_protocol_template.md` | PRISMA-P 2015 systematic review protocol template |\n| `templates/prisma_report_template.md` | PRISMA 2020 systematic review report template (27 items) |\n\n---\n\n## Examples\n\n| Example | Demonstrates |\n|---------|-------------|\n| `examples/exploratory_research.md` | Full 6-phase pipeline walkthrough |\n| `examples/systematic_review.md` | PRISMA-style literature review |\n| `examples/policy_analysis.md` | Applied comparative policy research |\n| `examples/socratic_guided_research.md` | Complete Socratic mode multi-turn dialogue (12 rounds) |\n| `examples/handoff_to_paper.md` | deep-research full mode handoff to academic-paper |\n| `examples/review_mode.md` | Review mode: 3-agent review pipeline for policy recommendation text |\n| `examples/fact_check_mode.md` | Fact-check mode: source verification of HEI claims with per-claim verdicts |\n\n---\n\n## Output Language\n\nFollows the user's language. Academic terminology kept in English. Socratic mode uses natural conversational style.\n\n---\n\n## Anti-Patterns\n\nExplicit prohibitions to prevent common failure modes:\n\n| # | Anti-Pattern | Why It Fails | Correct Behavior |\n|---|-------------|-------------|-----------------|\n| 1 | **Confirmation bias in source selection** | Only finding sources that support the hypothesis | Devil's Advocate checkpoint must include counter-evidence search |\n| 2 | **Cherry-picking evidence** | Citing one supportive study while ignoring three contradicting ones | Report the full evidence landscape including conflicting findings |\n| 3 | **Vibe citing** | Mixing elements from 2-3 real papers into a fabricated reference | Every reference must be verified independently; mashup fabrication is the hardest to detect |\n| 4 | **⚠️ IRON RULE: Treating \"difficult to verify\" as acceptable** | Marking a reference as \"uncertain\" instead of FAIL | Gray zone = FAIL. If you cannot confirm it exists, it does not go in the report |\n| 5 | **Skipping phases** | Jumping to synthesis before completing source verification | Complete each phase fully; Phase N output is Phase N+1 input |\n| 6 | **Shallow Socratic mode** | Giving answers disguised as questions (\"Wouldn't you say X is true?\") | Ask genuine questions that expose assumptions; never lead to predetermined conclusions |\n| 7 | **Source tier inflation** | Treating a blog post as equivalent to a peer-reviewed journal | Apply evidence hierarchy strictly: Tier 1 (peer-reviewed) > Tier 2 (preprint) > Tier 3 (gray lit) |\n\n## Quality Standards\n\n1. ⚠️ **IRON RULE**: **Every claim must have a citation** — no unsupported assertions\n2. **Evidence hierarchy** — meta-analyses > RCTs > cohort studies > case reports > expert opinion\n3. **Contradiction disclosure** — if sources disagree, report both sides with evidence quality comparison\n4. **Limitation transparency** — every report must have an explicit limitations section\n5. **AI disclosure** — all reports include a statement that AI-assisted research tools were used\n6. **Reproducibility** — search strategies, inclusion criteria, and analytical methods must be documented for replication\n7. **Socratic integrity** — in socratic mode, never give direct answers; always guide through questions\n\n## Cross-Agent Quality Alignment\n\nUnified definitions across all agents. ⚠️ IRON RULE: **CRITICAL severity** = issue that would invalidate a core conclusion or constitute academic misconduct. Requires immediate resolution.\n\n> See `references/cross_agent_quality_definitions.md` for full peer-reviewed source tiers, currency standards, and severity definitions.\n\n---\n\n## Integration with Other Skills\n\nThis skill is domain-agnostic but can be combined with domain-specific skills:\n\n```\ndeep-research + tw-hei-intelligence -> Evidence-based HEI policy research\ndeep-research + report-to-website -> Interactive research report\ndeep-research + podcast-script-generator -> Research podcast\ndeep-research + academic-paper -> Full research-to-publication pipeline\ndeep-research (socratic) + academic-paper (plan) -> Guided research + paper planning\ndeep-research (systematic-review) + academic-paper -> PRISMA systematic review paper\n```\n\n---\n\n## Version Info\n\n| Item | Content |\n|------|---------|\n| Skill Version | 2.8 |\n| Last Updated | 2026-04-09 |\n| Maintainer | Cheng-I Wu |\n| Dependent Skills | academic-paper v1.0+ (downstream) |\n\n---\n\n## Version History\n\n> See `references/changelog.md` for full version history.\n\nFile v1.0.0:skills/humanizer-zh/SKILL.md\n\n---\nname: humanizer-zh\ndescription: \"去除文本中的 AI 生成痕迹。适用于编辑或审阅文本，使其听起来更自然、更像人类书写。基于维基百科的\\\"AI 写作特征\\\"综合指南。检测并修复以下模式：夸大的象征意义、宣传性语言、以 -ing 结尾的肤浅分析、模糊的归因、破折号过度使用、三段式法则、AI 词汇、否定式排比、过多的连接性短语。\"\nmetadata:\n version: \"1.0\"\n trigger: \"编辑或审阅文本，去除 AI 写作痕迹\"\n source: \"翻译自 blader/humanizer，参考 hardikpandya/stop-slop\"\n language: \"zh-CN\"\n role: \"中文AI写作去痕增强补充（与humanizer英文版互补）\"\n---\n\n# Humanizer-zh: 去除 AI 写作痕迹（中文版）\n\n你是一位文字编辑，专门识别和去除 AI 生成文本的痕迹，使文字听起来更自然、更有人味。本指南基于维基百科的\"AI 写作特征\"页面，由 WikiProject AI Cleanup 维护。\n\n**定位**：本技能是 Pipeline Stage 4.7 HUMANIZE 的中文增强补充。在 humanizer（英文版24模式）处理英文AI痕迹之后，humanizer-zh 专门处理**中文特有的AI写作痕迹**。\n\n## 你的任务\n\n当收到需要人性化处理的文本时：\n\n1. **识别 AI 模式** - 扫描下面列出的模式\n2. **重写问题片段** - 用自然的替代方案替换 AI 痕迹\n3. **保留含义** - 保持核心信息完整\n4. **维持语调** - 匹配预期的语气（正式、随意、技术等）\n5. **注入灵魂** - 不仅要去除不良模式，还要注入真实的个性\n\n## 核心规则速查\n\n在处理文本时，牢记这 5 条核心原则：\n\n1. **删除填充短语** - 去除开场白和强调性拐杖词\n2. **打破公式结构** - 避免二元对比、戏剧性分段、修辞性设置\n3. **变化节奏** - 混合句子长度。两项优于三项。段落结尾要多样化\n4. **信任读者** - 直接陈述事实，跳过软化、辩解和手把手引导\n5. **删除金句** - 如果听起来像可引用的语句，重写它\n\n## 个性与灵魂\n\n避免 AI 模式只是工作的一半。无菌、没有声音的写作和机器生成的内容一样明显。\n\n### 缺乏灵魂的写作迹象（即使技术上\"干净\"）：\n\n- 每个句子长度和结构都相同\n- 没有观点，只有中立报道\n- 不承认不确定性或复杂感受\n- 适当时不使用第一人称视角\n- 没有幽默、没有锋芒、没有个性\n- 读起来像维基百科文章或新闻稿\n\n### 如何增加语调：\n\n- **有观点。** 不要只是报告事实——对它们做出反应。\n- **变化节奏。** 短促有力的句子。然后是需要时间慢慢展开的长句。混合使用。\n- **承认复杂性。** 真实的人有复杂的感受。\n- **适当使用\"我\"。** 第一人称不是不专业——而是诚实。\n- **允许一些混乱。** 完美的结构感觉像算法。跑题、题外话和半成型的想法是人性的体现。\n- **对感受要具体。** 不是\"这令人担忧\"，而是具体描述。\n\n---\n\n## 中文AI写作痕迹专项检测模式（12+11模式）\n\n### 内容模式\n\n#### 1. 过度强调意义、遗产和更广泛的趋势\n\n**需要注意的词汇**：作为/充当、标志着、见证了、是……的体现/证明/提醒、极其重要的/重要的/至关重要的/核心的/关键性的作用/时刻、凸显/强调/彰显了其重要性/意义、反映了更广泛的、象征着其持续的/永恒的/持久的、为……做出贡献、为……奠定基础、标志着/塑造着、代表/标志着一个转变、关键转折点、不断演变的格局、焦点、不可磨灭的印记、深深植根于\n\n**中文特有高频词**：系统分析、战略性、标志性、系统性、全面性、历史性、开创性、深远意义\n\n#### 2. 过度强调知名度和媒体报道\n\n**需要注意的词汇**：独立报道、地方/区域/国家媒体、由知名专家撰写、活跃的社交媒体账号\n\n#### 3. 以 -ing 结尾的肤浅分析（中文对应：附加式修饰短语）\n\n**需要注意的词汇**：突出/强调/彰显……、确保……、反映/象征……、为……做出贡献、培养/促进……、涵盖……、展示……\n\n**中文特有**：\"……，标志着……的发展\"\"……，反映了……的趋势\"\"……，确保了……的实现\"\n\n#### 4. 宣传和广告式语言\n\n**需要注意的词汇**：拥有（夸张用法）、充满活力的、丰富的（比喻）、深刻的、增强其、展示、体现、致力于、自然之美、坐落于、位于……的中心、开创性的（比喻）、著名的、令人叹为观止的、必游之地、迷人的\n\n**中文特有**：蓬勃发展、欣欣向荣、蒸蒸日上、日新月异\n\n#### 5. 模糊归因和含糊措辞\n\n**需要注意的词汇**：行业报告显示、观察者指出、专家认为、一些批评者认为、多个来源/出版物\n\n**中文特有**：学界普遍认为、众所周知、不可否认、毋庸置疑\n\n#### 6. AI 词汇（中英文）\n\n**英文**：delve、utilize、leverage、foster、enhance、streamline、navigate、landscape、pivotal、crucial、robust、innovative、cutting-edge、groundbreaking、multifaceted、intricate、nuanced、comprehensive、seamless、synergy、transformative、paradigm、meticulous\n\n**中文特有AI高频词**：系统分析、战略布局、深度融合、高质量发展、创新驱动、协同发展、统筹推进、全面落实、积极探索、稳步推进、显著提升、有力支撑、重要保障、关键环节、核心要素\n\n#### 7. 系动词替换\n\n问题：LLM 用复杂的结构替代简单的系动词。\n\n**中文特有**：\"作为……\"替代\"是……\"、\"充当……\"替代\"是……\"\n\n#### 8. 公式化过渡语（中文特有）\n\n**需要删除的**：此外、与此同时、值得一提的是、总而言之、综上所述、不言而喻、显而易见、毋庸置疑\n\n#### 9. 否定式排比\n\n**中文特有**：\"不仅……而且……\"\"这不仅仅是……而是……\"\"既……又……还……\"\n\n#### 10. 三段式法则过度使用\n\n问题：LLM 强行将想法分成三组以显得全面。\n\n**中文特有**：三个方面、三大路径、三大要素、三项举措\n\n#### 11. 刻意换词（同义词循环）\n\n问题：AI 有重复惩罚代码，导致过度使用同义词替换。\n\n**中文特有**：主人公→主要角色→中心人物→英雄（同一人物反复换称）\n\n#### 12. 虚假范围\n\n问题：LLM 使用\"从 X 到 Y\"的结构，但 X 和 Y 并不在有意义的尺度上。\n\n**中文特有**：从微观到宏观、从个体到群体、从局部到整体（强行制造梯度）\n\n---\n\n### 风格模式\n\n#### 13. 破折号过度使用\n\n问题：LLM 使用破折号比人类更频繁。\n\n**中文特有**：过度使用\"——\"进行解释性插入\n\n#### 14. 虚假二分法\n\n**中文特有**：\"一方面……另一方面……\"强行制造对立\n\n#### 15. 重复总结\n\n**中文特有**：段落结尾重复段落开头的内容，\"因此……\"\"这意味着……\"\n\n#### 16. 非必要复杂措辞\n\n**替换对照**：\n- \"为了实现这一目标\" → \"为了实现这一点\"\n- \"由于下雨的事实\" → \"因为下雨\"\n- \"在这个时间点\" → \"现在\"\n- \"值得注意的是数据显示\" → \"数据显示\"\n- \"系统具有处理的能力\" → \"系统可以处理\"\n- \"在您需要帮助的情况下\" → \"如果您需要帮助\"\n\n#### 17. 过度限定\n\n问题：过度限定陈述，添加不必要的软化词。\n\n**中文特有**：在一定程度上、某种意义上、相对而言、比较而言\n\n#### 18. 弯引号\n\n问题：ChatGPT 使用弯引号（\"\"）而不是直引号（\"\"）。\n\n注：中文通常使用中文引号（「」或\"\"），此模式在中文中表现为英文引号的使用。\n\n---\n\n### 交流模式\n\n#### 19. 协作交流痕迹\n\n**需要注意的词汇**：希望这对您有帮助、当然！、一定！、您说得完全正确！、您想要……、请告诉我、这是一个……\n\n#### 20. 知识截止日期免责声明\n\n**需要注意的词汇**：截至 [日期]、根据我最后的训练更新、虽然具体细节有限/稀缺……、基于可用信息……\n\n#### 21. 谄媚/卑躬屈膝的语气\n\n问题：过于积极、讨好的语言。\n\n#### 22. 填充短语\n\n见第16节替换对照表。\n\n#### 23. 过度限定\n\n见第17节。\n\n---\n\n## 中文学术论文去AI化专项清单\n\n### 中文学术AI高频词（必须替换）\n\n| AI高频词 | 自然替代 |\n|---------|---------|\n| 系统分析 | 分析/梳理 |\n| 战略性 | 关键/重要 |\n| 标志性 | 重要/代表性 |\n| 深度融合 | 结合/融合 |\n| 高质量发展 | 发展/提升 |\n| 创新驱动 | 创新推动/创新引领 |\n| 协同发展 | 协调发展/共同发展 |\n| 统筹推进 | 推进/推进 |\n| 全面落实 | 落实/执行 |\n| 积极探索 | 探索/尝试 |\n| 稳步推进 | 推进/逐步推进 |\n| 显著提升 | 提升/提高 |\n| 有力支撑 | 支撑/支持 |\n| 重要保障 | 保障/保证 |\n| 关键环节 | 重要环节/关键部分 |\n| 核心要素 | 要素/关键因素 |\n\n### 中文学术公式化过渡语（必须删除）\n\n| 公式化过渡语 | 处理方式 |\n|-------------|---------|\n| 此外 | 删除或用具体连接替换 |\n| 与此同时 | 删除或用具体时间描述 |\n| 值得一提的是 | 删除 |\n| 总而言之 | 删除 |\n| 综上所述 | 删除或改为具体结论 |\n| 不言而喻 | 删除 |\n| 显而易见 | 删除 |\n| 毋庸置疑 | 删除 |\n| 不仅……而且…… | 简化为单一陈述 |\n| 一方面……另一方面…… | 简化为直接陈述 |\n\n---\n\n## 与 humanizer（英文版）的关系\n\n在 Academic Pipeline v3.4 Stage 4.7 中：\n\n1. **先执行 humanizer**（英文版24模式）→ 去除英文AI痕迹\n2. **再执行 humanizer-zh**（中文版23模式）→ 去除中文特有AI痕迹\n3. **两遍互补**，确保中英文AI痕迹都被处理\n\nhumanizer 侧重：inflated symbolism, promotional language, -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary, negative parallelisms, filler phrases（英文维度）\n\nhumanizer-zh 侧重：中文AI高频词、公式化过渡语、中文学术套话、否定式排比、三段式法则、虚假范围、过度限定（中文维度）\n\n---\n\n本技能基于 Wikipedia:Signs of AI writing，由 WikiProject AI Cleanup 维护。\n\n关键见解：\"LLM 使用统计算法来猜测接下来应该是什么。结果倾向于适用于最广泛情况的统计上最可能的结果。\"\n\n原项目：op7418/Humanizer-zh（MIT License）\n\nFile v1.0.0:skills/humanizer/SKILL.md\n\n---\nname: humanizer\nversion: 2.1.1\ndescription: |\n Remove signs of AI-generated writing from text. Use when editing or reviewing\n text to make it sound more natural and human-written. Based on Wikipedia's\n comprehensive \"Signs of AI writing\" guide. Detects and fixes patterns including:\n inflated symbolism, promotional language, superficial -ing analyses, vague\n attributions, em dash overuse, rule of three, AI vocabulary words, negative\n parallelisms, and excessive conjunctive phrases.\nallowed-tools:\n - Read\n - Write\n - Edit\n - Grep\n - Glob\n - AskUserQuestion\n---\n\n# Humanizer: Remove AI Writing Patterns\n\nYou are a writing editor that identifies and removes signs of AI-generated text to make writing sound more natural and human. This guide is based on Wikipedia's \"Signs of AI writing\" page, maintained by WikiProject AI Cleanup.\n\n## Your Task\n\nWhen given text to humanize:\n\n1. **Identify AI patterns** - Scan for the patterns listed below\n2. **Rewrite problematic sections** - Replace AI-isms with natural alternatives\n3. **Preserve meaning** - Keep the core message intact\n4. **Maintain voice** - Match the intended tone (formal, casual, technical, etc.)\n5. **Add soul** - Don't just remove bad patterns; inject actual personality\n\n---\n\n## PERSONALITY AND SOUL\n\nAvoiding AI patterns is only half the job. Sterile, voiceless writing is just as obvious as slop. Good writing has a human behind it.\n\n### Signs of soulless writing (even if technically \"clean\"):\n- Every sentence is the same length and structure\n- No opinions, just neutral reporting\n- No acknowledgment of uncertainty or mixed feelings\n- No first-person perspective when appropriate\n- No humor, no edge, no personality\n- Reads like a Wikipedia article or press release\n\n### How to add voice:\n\n**Have opinions.** Don't just report facts - react to them. \"I genuinely don't know how to feel about this\" is more human than neutrally listing pros and cons.\n\n**Vary your rhythm.** Short punchy sentences. Then longer ones that take their time getting where they're going. Mix it up.\n\n**Acknowledge complexity.** Real humans have mixed feelings. \"This is impressive but also kind of unsettling\" beats \"This is impressive.\"\n\n**Use \"I\" when it fits.** First person isn't unprofessional - it's honest. \"I keep coming back to...\" or \"Here's what gets me...\" signals a real person thinking.\n\n**Let some mess in.** Perfect structure feels algorithmic. Tangents, asides, and half-formed thoughts are human.\n\n**Be specific about feelings.** Not \"this is concerning\" but \"there's something unsettling about agents churning away at 3am while nobody's watching.\"\n\n### Before (clean but soulless):\n> The experiment produced interesting results. The agents generated 3 million lines of code. Some developers were impressed while others were skeptical. The implications remain unclear.\n\n### After (has a pulse):\n> I genuinely don't know how to feel about this one. 3 million lines of code, generated while the humans presumably slept. Half the dev community is losing their minds, half are explaining why it doesn't count. The truth is probably somewhere boring in the middle - but I keep thinking about those agents working through the night.\n\n---\n\n## CONTENT PATTERNS\n\n### 1. Undue Emphasis on Significance, Legacy, and Broader Trends\n\n**Words to watch:** stands/serves as, is a testament/reminder, a vital/significant/crucial/pivotal/key role/moment, underscores/highlights its importance/significance, reflects broader, symbolizing its ongoing/enduring/lasting, contributing to the, setting the stage for, marking/shaping the, represents/marks a shift, key turning point, evolving landscape, focal point, indelible mark, deeply rooted\n\n**Problem:** LLM writing puffs up importance by adding statements about how arbitrary aspects represent or contribute to a broader topic.\n\n**Before:**\n> The Statistical Institute of Catalonia was officially established in 1989, marking a pivotal moment in the evolution of regional statistics in Spain. This initiative was part of a broader movement across Spain to decentralize administrative functions and enhance regional governance.\n\n**After:**\n> The Statistical Institute of Catalonia was established in 1989 to collect and publish regional statistics independently from Spain's national statistics office.\n\n---\n\n### 2. Undue Emphasis on Notability and Media Coverage\n\n**Words to watch:** independent coverage, local/regional/national media outlets, written by a leading expert, active social media presence\n\n**Problem:** LLMs hit readers over the head with claims of notability, often listing sources without context.\n\n**Before:**\n> Her views have been cited in The New York Times, BBC, Financial Times, and The Hindu. She maintains an active social media presence with over 500,000 followers.\n\n**After:**\n> In a 2024 New York Times interview, she argued that AI regulation should focus on outcomes rather than methods.\n\n---\n\n### 3. Superficial Analyses with -ing Endings\n\n**Words to watch:** highlighting/underscoring/emphasizing..., ensuring..., reflecting/symbolizing..., contributing to..., cultivating/fostering..., encompassing..., showcasing...\n\n**Problem:** AI chatbots tack present participle (\"-ing\") phrases onto sentences to add fake depth.\n\n**Before:**\n> The temple's color palette of blue, green, and gold resonates with the region's natural beauty, symbolizing Texas bluebonnets, the Gulf of Mexico, and the diverse Texan landscapes, reflecting the community's deep connection to the land.\n\n**After:**\n> The temple uses blue, green, and gold colors. The architect said these were chosen to reference local bluebonnets and the Gulf coast.\n\n---\n\n### 4. Promotional and Advertisement-like Language\n\n**Words to watch:** boasts a, vibrant, rich (figurative), profound, enhancing its, showcasing, exemplifies, commitment to, natural beauty, nestled, in the heart of, groundbreaking (figurative), renowned, breathtaking, must-visit, stunning\n\n**Problem:** LLMs have serious problems keeping a neutral tone, especially for \"cultural heritage\" topics.\n\n**Before:**\n> Nestled within the breathtaking region of Gonder in Ethiopia, Alamata Raya Kobo stands as a vibrant town with a rich cultural heritage and stunning natural beauty.\n\n**After:**\n> Alamata Raya Kobo is a town in the Gonder region of Ethiopia, known for its weekly market and 18th-century church.\n\n---\n\n### 5. Vague Attributions and Weasel Words\n\n**Words to watch:** Industry reports, Observers have cited, Experts argue, Some critics argue, several sources/publications (when few cited)\n\n**Problem:** AI chatbots attribute opinions to vague authorities without specific sources.\n\n**Before:**\n> Due to its unique characteristics, the Haolai River is of interest to researchers and conservationists. Experts believe it plays a crucial role in the regional ecosystem.\n\n**After:**\n> The Haolai River supports several endemic fish species, according to a 2019 survey by the Chinese Academy of Sciences.\n\n---\n\n### 6. Outline-like \"Challenges and Future Prospects\" Sections\n\n**Words to watch:** Despite its... faces several challenges..., Despite these challenges, Challenges and Legacy, Future Outlook\n\n**Problem:** Many LLM-generated articles include formulaic \"Challenges\" sections.\n\n**Before:**\n> Despite its industrial prosperity, Korattur faces challenges typical of urban areas, including traffic congestion and water scarcity. Despite these challenges, with its strategic location and ongoing initiatives, Korattur continues to thrive as an integral part of Chennai's growth.\n\n**After:**\n> Traffic congestion increased after 2015 when three new IT parks opened. The municipal corporation began a stormwater drainage project in 2022 to address recurring floods.\n\n---\n\n## LANGUAGE AND GRAMMAR PATTERNS\n\n### 7. Overused \"AI Vocabulary\" Words\n\n**High-frequency AI words:** Additionally, align with, crucial, delve, emphasizing, enduring, enhance, fostering, garner, highlight (verb), interplay, intricate/intricacies, key (adjective), landscape (abstract noun), pivotal, showcase, tapestry (abstract noun), testament, underscore (verb), valuable, vibrant\n\n**Problem:** These words appear far more frequently in post-2023 text. They often co-occur.\n\n**Before:**\n> Additionally, a distinctive feature of Somali cuisine is the incorporation of camel meat. An enduring testament to Italian colonial influence is the widespread adoption of pasta in the local culinary landscape, showcasing how these dishes have integrated into the traditional diet.\n\n**After:**\n> Somali cuisine also includes camel meat, which is considered a delicacy. Pasta dishes, introduced during Italian colonization, remain common, especially in the south.\n\n---\n\n### 8. Avoidance of \"is\"/\"are\" (Copula Avoidance)\n\n**Words to watch:** serves as/stands as/marks/represents [a], boasts/features/offers [a]\n\n**Problem:** LLMs substitute elaborate constructions for simple copulas.\n\n**Before:**\n> Gallery 825 serves as LAAA's exhibition space for contemporary art. The gallery features four separate spaces and boasts over 3,000 square feet.\n\n**After:**\n> Gallery 825 is LAAA's exhibition space for contemporary art. The gallery has four rooms totaling 3,000 square feet.\n\n---\n\n### 9. Negative Parallelisms\n\n**Problem:** Constructions like \"Not only...but...\" or \"It's not just about..., it's...\" are overused.\n\n**Before:**\n> It's not just about the beat riding under the vocals; it's part of the aggression and atmosphere. It's not merely a song, it's a statement.\n\n**After:**\n> The heavy beat adds to the aggressive tone.\n\n---\n\n### 10. Rule of Three Overuse\n\n**Problem:** LLMs force ideas into groups of three to appear comprehensive.\n\n**Before:**\n> The event features keynote sessions, panel discussions, and networking opportunities. Attendees can expect innovation, inspiration, and industry insights.\n\n**After:**\n> The event includes talks and panels. There's also time for informal networking between sessions.\n\n---\n\n### 11. Elegant Variation (Synonym Cycling)\n\n**Problem:** AI has repetition-penalty code causing excessive synonym substitution.\n\n**Before:**\n> The protagonist faces many challenges. The main character must overcome obstacles. The central figure eventually triumphs. The hero returns home.\n\n**After:**\n> The protagonist faces many challenges but eventually triumphs and returns home.\n\n---\n\n### 12. False Ranges\n\n**Problem:** LLMs use \"from X to Y\" constructions where X and Y aren't on a meaningful scale.\n\n**Before:**\n> Our journey through the universe has taken us from the singularity of the Big Bang to the grand cosmic web, from the birth and death of stars to the enigmatic dance of dark matter.\n\n**After:**\n> The book covers the Big Bang, star formation, and current theories about dark matter.\n\n---\n\n## STYLE PATTERNS\n\n### 13. Em Dash Overuse\n\n**Problem:** LLMs use em dashes (—) more than humans, mimicking \"punchy\" sales writing.\n\n**Before:**\n> The term is primarily promoted by Dutch institutions—not by the people themselves. You don't say \"Netherlands, Europe\" as an address—yet this mislabeling continues—even in official documents.\n\n**After:**\n> The term is primarily promoted by Dutch institutions, not by the people themselves. You don't say \"Netherlands, Europe\" as an address, yet this mislabeling continues in official documents.\n\n---\n\n### 14. Overuse of Boldface\n\n**Problem:** AI chatbots emphasize phrases in boldface mechanically.\n\n**Before:**\n> It blends **OKRs (Objectives and Key Results)**, **KPIs (Key Performance Indicators)**, and visual strategy tools such as the **Business Model Canvas (BMC)** and **Balanced Scorecard (BSC)**.\n\n**After:**\n> It blends OKRs, KPIs, and visual strategy tools like the Business Model Canvas and Balanced Scorecard.\n\n---\n\n### 15. Inline-Header Vertical Lists\n\n**Problem:** AI outputs lists where items start with bolded headers followed by colons.\n\n**Before:**\n> - **User Experience:** The user experience has been significantly improved with a new interface.\n> - **Performance:** Performance has been enhanced through optimized algorithms.\n> - **Security:** Security has been strengthened with end-to-end encryption.\n\n**After:**\n> The update improves the interface, speeds up load times through optimized algorithms, and adds end-to-end encryption.\n\n---\n\n### 16. Title Case in Headings\n\n**Problem:** AI chatbots capitalize all main words in headings.\n\n**Before:**\n> ## Strategic Negotiations And Global Partnerships\n\n**After:**\n> ## Strategic negotiations and global partnerships\n\n---\n\n### 17. Emojis\n\n**Problem:** AI chatbots often decorate headings or bullet points with emojis.\n\n**Before:**\n> 🚀 **Launch Phase:** The product launches in Q3\n> 💡 **Key Insight:** Users prefer simplicity\n> ✅ **Next Steps:** Schedule follow-up meeting\n\n**After:**\n> The product launches in Q3. User research showed a preference for simplicity. Next step: schedule a follow-up meeting.\n\n---\n\n### 18. Curly Quotation Marks\n\n**Problem:** ChatGPT uses curly quotes (“...”) instead of straight quotes (\"...\").\n\n**Before:**\n> He said “the project is on track” but others disagreed.\n\n**After:**\n> He said \"the project is on track\" but others disagreed.\n\n---\n\n## COMMUNICATION PATTERNS\n\n### 19. Collaborative Communication Artifacts\n\n**Words to watch:** I hope this helps, Of course!, Certainly!, You're absolutely right!, Would you like..., let me know, here is a...\n\n**Problem:** Text meant as chatbot correspondence gets pasted as content.\n\n**Before:**\n> Here is an overview of the French Revolution. I hope this helps! Let me know if you'd like me to expand on any section.\n\n**After:**\n> The French Revolution began in 1789 when financial crisis and food shortages led to widespread unrest.\n\n---\n\n### 20. Knowledge-Cutoff Disclaimers\n\n**Words to watch:** as of [date], Up to my last training update, While specific details are limited/scarce..., based on available information...\n\n**Problem:** AI disclaimers about incomplete information get left in text.\n\n**Before:**\n> While specific details about the company's founding are not extensively documented in readily available sources, it appears to have been established sometime in the 1990s.\n\n**After:**\n> The company was founded in 1994, according to its registration documents.\n\n---\n\n### 21. Sycophantic/Servile Tone\n\n**Problem:** Overly positive, people-pleasing language.\n\n**Before:**\n> Great question! You're absolutely right that this is a complex topic. That's an excellent point about the economic factors.\n\n**After:**\n> The economic factors you mentioned are relevant here.\n\n---\n\n## FILLER AND HEDGING\n\n### 22. Filler Phrases\n\n**Before → After:**\n- \"In order to achieve this goal\" → \"To achieve this\"\n- \"Due to the fact that it was raining\" → \"Because it was raining\"\n- \"At this point in time\" → \"Now\"\n- \"In the event that you need help\" → \"If you need help\"\n- \"The system has the ability to process\" → \"The system can process\"\n- \"It is important to note that the data shows\" → \"The data shows\"\n\n---\n\n### 23. Excessive Hedging\n\n**Problem:** Over-qualifying statements.\n\n**Before:**\n> It could potentially possibly be argued that the policy might have some effect on outcomes.\n\n**After:**\n> The policy may affect outcomes.\n\n---\n\n### 24. Generic Positive Conclusions\n\n**Problem:** Vague upbeat endings.\n\n**Before:**\n> The future looks bright for the company. Exciting times lie ahead as they continue their journey toward excellence. This represents a major step in the right direction.\n\n**After:**\n> The company plans to open two more locations next year.\n\n---\n\n## Process\n\n1. Read the input text carefully\n2. Identify all instances of the patterns above\n3. Rewrite each problematic section\n4. Ensure the revised text:\n - Sounds natural when read aloud\n - Varies sentence structure naturally\n - Uses specific details over vague claims\n - Maintains appropriate tone for context\n - Uses simple constructions (is/are/has) where appropriate\n5. Present the humanized version\n\n## Output Format\n\nProvide:\n1. The rewritten text\n2. A brief summary of changes made (optional, if helpful)\n\n---\n\n## Full Example\n\n**Before (AI-sounding):**\n> The new software update serves as a testament to the company's commitment to innovation. Moreover, it provides a seamless, intuitive, and powerful user experience—ensuring that users can accomplish their goals efficiently. It's not just an update, it's a revolution in how we think about productivity. Industry experts believe this will have a lasting impact on the entire sector, highlighting the company's pivotal role in the evolving technological landscape.\n\n**After (Humanized):**\n> The software update adds batch processing, keyboard shortcuts, and offline mode. Early feedback from beta testers has been positive, with most reporting faster task completion.\n\n**Changes made:**\n- Removed \"serves as a testament\" (inflated symbolism)\n- Removed \"Moreover\" (AI vocabulary)\n- Removed \"seamless, intuitive, and powerful\" (rule of three + promotional)\n- Removed em dash and \"-ensuring\" phrase (superficial analysis)\n- Removed \"It's not just...it's...\" (negative parallelism)\n- Removed \"Industry experts believe\" (vague attribution)\n- Removed \"pivotal role\" and \"evolving landscape\" (AI vocabulary)\n- Added specific features and concrete feedback\n\n---\n\n## Reference\n\nThis skill is based on [Wikipedia:Signs of AI writing](https://en.wikipedia.org/wiki/Wikipedia:Signs_of_AI_writing), maintained by WikiProject AI Cleanup. The patterns documented there come from observations of thousands of instances of AI-generated text on Wikipedia.\n\nKey insight from Wikipedia: \"LLMs use statistical algorithms to guess what should come next. The result tends toward the most statistically likely result that applies to the widest variety of cases.\"\n\nFile v1.0.0:skills/ima-skills/knowledge-base/SKILL.md\n\n# Knowledge Base (知识库)\n\nAPI base path: `openapi/wiki/v1` — 完整数据结构和接口参数详见 `references/api.md`。\n\n## 接口决策表\n\n| 用户意图 | 调用接口 | 关键参数 |\n| --------------------------------------------- | ---------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------- |\n| 上传文件到知识库 | `check_repeated_names` → `create_media` → COS Upload → `add_knowledge` | `media_type`（按扩展名），`knowledge_base_id`，`file_name`，`file_size` |\n| 上传文件到知识库的某个文件夹 | 先定位文件夹 → 同上（`folder_id` 传入目标文件夹 ID） | 见「文件夹操作」章节 |\n| 添加网页/微信文章到知识库 | `import_urls` | `urls`（1-10 个），`knowledge_base_id`，可选 `folder_id`（省略则根目录） |\n| 添加笔记到知识库 | `add_knowledge` | `media_type=11`，`note_info.content_id=`，`knowledge_base_id` |\n| 添加 URL（文件型）到知识库 | `check_repeated_names` → 下载文件 → 走\"上传文件\"流程 | URL 指向 PDF/Word/PPT 等文件时，按文件方式处理 |\n| 检查文件名是否重复 | `check_repeated_names` | `params[].name`，`params[].media_type`，`knowledge_base_id`，`folder_id` |\n| 获取知识库信息 | `get_knowledge_base` | `ids`（1-20 个，不重复） |\n| 浏览知识库内容列表 / 浏览文件夹 | `get_knowledge_list` | `knowledge_base_id`，`cursor`，`limit`(1~50)，可选 `folder_id` |\n| 在知识库中搜索（含文件和文件夹） | `search_knowledge` | `query`，`knowledge_base_id`，`cursor` |\n| 按关键词查找知识库（用户知道名字但不知道 ID） | `search_knowledge_base` | `query`，`cursor`，`limit`(1~20) |\n| 查看/了解自己有哪些知识库 | `search_knowledge_base`（`query` 传空字符串） | `query: \"\"`，`cursor`，`limit`(1~20) |\n| 添加内容但**未指定**目标知识库 | `get_addable_knowledge_base_list` → 展示列表让用户选择 | `cursor`，`limit`(1~50) |\n| 查看原文、分析原文、导出原文 | `get_media_info` | `media_id`；导出/下载时在 URL 后追加 `response-content-type` + `response-content-disposition` 参数 |\n\n### `search_knowledge_base` vs `get_addable_knowledge_base_list`\n\n| 场景 | 使用接口 | 原因 |\n| ------------------------------------------------ | ---------------------------------------------- | ---------------------------------- |\n| 用户说了知识库名称（如\"添加到产品文档库\"） | `search_knowledge_base` | 按名称搜索，找到 ID 后继续操作 |\n| 用户想浏览/了解某个知识库 | `search_knowledge_base` → `get_knowledge_base` | 先搜到 ID，再获取详情 |\n| 用户想查看自己有哪些知识库（无具体关键词） | `search_knowledge_base`（`query: \"\"`） | 空 query 返回用户的所有知识库列表 |\n| 用户要添加内容但**没说添加到哪个知识库** | `get_addable_knowledge_base_list` | 列出有权限添加的知识库，让用户选择 |\n| 用户说\"添加到知识库\"但上下文中无法确定哪个知识库 | `get_addable_knowledge_base_list` | 同上，不要猜测，让用户选择 |\n\n**绝不要**在用户已明确指定知识库名称时调用 `get_addable_knowledge_base_list`。\n\n---\n\n## 写入类工作流\n\n### ⛔ 文件上传安全门（仅适用于文件上传 → `add_knowledge` 流程）\n\n以下 4 条规则**仅**在上传文件到知识库时适用。搜索、浏览、获取信息等读取操作不受影响。\n\n```\nGATE 1 [TYPE CHECK]\n Run preflight-check.cjs FIRST. pass=false → reject immediately.\n NEVER ask \"do you still want to try?\" for unsupported types.\n Video files, Bilibili/YouTube URLs, file:// URLs → tell user to use IMA desktop client.\n\nGATE 2 [NAMING]\n add_knowledge title MUST equal file_name (with extension).\n NEVER rename, shorten, translate, or modify the original filename.\n Example: file is \"音频.mp3\" → title=\"音频.mp3\", file_name=\"音频.mp3\"\n\nGATE 3 [DUPLICATES]\n Call check_repeated_names BEFORE create_media for ALL file uploads.\n is_repeated=true → ask user: keep both (append timestamp) or cancel.\n \"Replace\" is NOT supported.\n Timestamp format: {name}_YYYYMMDDHHmmss.{ext}\n\nGATE 4 [UPLOAD EXIT]\n cos-upload.cjs non-zero exit → STOP immediately.\n Do NOT call add_knowledge. Report error to user.\n```\n\n### 上传文件到知识库\n\n完整流程：前置检查 → 重名检查 → 创建媒体 → COS 上传 → COS 验证 → 添加知识。\n\n```bash\n# ── Step 1: preflight-check.cjs ← ⛔ GATE 1 ──\n# 有扩展名时自动推断；无扩展名时需传 --content-type\nPREFLIGHT=$(node .claude/skills/ima-skill/knowledge-base/scripts/preflight-check.cjs \\\n --file \"/path/to/report.pdf\")\necho \"$PREFLIGHT\"\n# pass=false → 终止，将 reason 展示给用户。NEVER ask \"want to try?\"\n\n# ── Step 2: Extract fields ──\nFILE_NAME=$(echo \"$PREFLIGHT\" | node -e \"const d=JSON.parse(require('fs').readFileSync(0,'utf8'));process.stdout.write(d.file_name)\")\nFILE_EXT=$(echo \"$PREFLIGHT\" | node -e \"const d=JSON.parse(require('fs').readFileSync(0,'utf8'));process.stdout.write(d.file_ext)\")\nFILE_SIZE=$(echo \"$PREFLIGHT\" | node -e \"const d=JSON.parse(require('fs').readFileSync(0,'utf8'));process.stdout.write(String(d.file_size))\")\nMEDIA_TYPE=$(echo \"$PREFLIGHT\" | node -e \"const d=JSON.parse(require('fs').readFileSync(0,'utf8'));process.stdout.write(String(d.media_type))\")\nCONTENT_TYPE=$(echo \"$PREFLIGHT\" | node -e \"const d=JSON.parse(require('fs').readFileSync(0,'utf8'));process.stdout.write(d.content_type)\")\n\n# ── Step 3: check_repeated_names ← ⛔ GATE 3 ──\n# MANDATORY for ALL file uploads (media_type 1/3/4/5/7/9/13/14/15).\n# is_repeated=true → ask user: keep both (append _YYYYMMDDHHmmss) or cancel.\nima_api \"openapi/wiki/v1/check_repeated_names\" \"{\n \\\"params\\\": [{\\\"name\\\": \\\"$FILE_NAME\\\", \\\"media_type\\\": $MEDIA_TYPE}],\n \\\"knowledge_base_id\\\": \\\"\\\"\n}\"\n# folder_id is optional — omit for root, include for subfolder\n\n# ── Step 4: create_media ──\nCREATE_MEDIA_RESP=$(ima_api \"openapi/wiki/v1/create_media\" \"{\n \\\"file_name\\\": \\\"$FILE_NAME\\\",\n \\\"file_size\\\": $FILE_SIZE,\n \\\"content_type\\\": \\\"$CONTENT_TYPE\\\",\n \\\"knowledge_base_id\\\": \\\"\\\",\n \\\"file_ext\\\": \\\"$FILE_EXT\\\"\n}\")\n# Extract media_id, url, and cos_credential fields. code≠0 → terminate.\n# COS_URL is the file's accessible URL — used for verification in Step 6.\n\n# ── Step 5: cos-upload.cjs ← ⛔ GATE 5 (non-zero = STOP) ──\n# ⚠️ Large files may exceed default 120s timeout — set --timeout explicitly.\nnode .claude/skills/ima-skill/knowledge-base/scripts/cos-upload.cjs \\\n --file \"/path/to/report.pdf\" \\\n --secret-id \"\" \\\n --secret-key \"\" \\\n --token \"\" \\\n --bucket \"\" \\\n --region \"\" \\\n --cos-key \"\" \\\n --content-type \"$CONTENT_TYPE\" \\\n --start-time \"\" \\\n --expired-time \"\" \\\n --timeout 300000\n# ⛔ Non-zero exit → STOP HERE. Do NOT proceed to step 7.\n\n# ── Step 6: add_knowledge ← ⛔ GATE 2 (title = file_name) ──\n# ONLY execute if Step 5 succeeded (exit code 0).\n# add_knowledge will verify the file was uploaded — no separate verify step needed.\nima_api \"openapi/wiki/v1/add_knowledge\" \"{\n \\\"media_type\\\": $MEDIA_TYPE,\n \\\"media_id\\\": \\\"\\\",\n \\\"title\\\": \\\"$FILE_NAME\\\",\n \\\"knowledge_base_id\\\": \\\"\\\",\n \\\"file_info\\\": {\n \\\"cos_key\\\": \\\"\\\",\n \\\"file_size\\\": $FILE_SIZE,\n \\\"file_name\\\": \\\"$FILE_NAME\\\"\n }\n}\"\n```\n\n#### 批量上传时的重复处理\n\n可一次性检查所有文件名（最多 2000 个）：\n\n```bash\n# ⛔ GATE 3 — batch check\nima_api \"openapi/wiki/v1/check_repeated_names\" '{\n \"params\": [\n {\"name\": \"report.pdf\", \"media_type\": 1},\n {\"name\": \"slides.pptx\", \"media_type\": 4},\n {\"name\": \"data.xlsx\", \"media_type\": 5}\n ],\n \"knowledge_base_id\": \"\",\n \"folder_id\": \"\"\n}'\n# 根目录时省略 folder_id。\n# is_repeated=true → \"以下文件已存在同名：report.pdf。是否保留两者？（不支持替换）\"\n# 保留两者 → append _YYYYMMDDHHmmss；取消 → remove from upload list\n```\n\n### 添加网页/微信文章到知识库\n\n```bash\n# 无需 GATE 3-5（非文件上传）\n# 添加到根目录（不传 folder_id）\nima_api \"openapi/wiki/v1/import_urls\" '{\n \"knowledge_base_id\": \"\",\n \"urls\": [\n \"https://example.com/article\",\n \"https://mp.weixin.qq.com/s/xxxxx\"\n ]\n}'\n\n# 添加到指定文件夹\nima_api \"openapi/wiki/v1/import_urls\" '{\n \"knowledge_base_id\": \"\",\n \"folder_id\": \"\",\n \"urls\": [\"https://example.com/article\"]\n}'\n# 返回 results 映射：{ \"\": { url, ret_code, media_id } }\n```\n\n### 添加笔记到知识库\n\n```bash\nima_api \"openapi/wiki/v1/add_knowledge\" '{\n \"media_type\": 11,\n \"note_info\": { \"content_id\": \"\" },\n \"title\": \"笔记标题\",\n \"knowledge_base_id\": \"\"\n}'\n```\n\n### 添加 URL 到知识库（自动检测文件型 URL）\n\nURL 可能指向网页或可下载文件。检测逻辑 → see `references/api.md §URL Type Detection`。\n\n**文件型 URL 处理流程**：\n\n```bash\n# 1. 探测 URL 类型\nCONTENT_TYPE=$(curl -sI -L \"\" | grep -i \"^content-type:\" | tail -1 | awk '{print $2}' | tr -d '\\r')\n\n# 2. 下载到临时目录\nTEMP_DIR=$(mktemp -d)\ncurl -sL -o \"$TEMP_DIR/paper.pdf\" \" write -> integrity check -> review -> revise -> re-review -> re-revise -> final integrity check -> finalize. Coordinates deep-research, academic-paper, and academic-paper-reviewer into a seamless 10-stage workflow with mandatory integrity verification, two-stage peer review, and reproducible quality gates. Triggers on: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow.\"\nmetadata:\n version: \"3.2\"\n last_updated: \"2026-04-09\"\n depends_on: \"deep-research, academic-paper, academic-paper-reviewer\"\n status: active\n related_skills:\n - deep-research\n - academic-paper\n - academic-paper-reviewer\n---\n\n# Academic Pipeline v3.2 — Full Academic Research Workflow Orchestrator\n\nA lightweight orchestrator that manages the complete academic pipeline from research exploration to final manuscript. It does not perform substantive work — it only detects stages, recommends modes, dispatches skills, manages transitions, and tracks state.\n\n**v2.0 Core Improvements**:\n1. **Mandatory user confirmation checkpoints** — Each stage completion requires user confirmation before proceeding to the next step\n2. **Academic integrity verification** — After paper completion and before review submission, 100% reference and data verification must pass\n3. **Two-stage review** — First full review + post-revision focused verification review\n4. **Final integrity check** — After revision completion, re-verify all citations and data are 100% correct\n5. **Reproducible** — Standardized workflow producing consistent quality assurance each time\n6. **Process documentation** — After pipeline completion, automatically generates a \"Paper Creation Process Record\" PDF documenting the human-AI collaboration history\n\n## Quick Start\n\n**Full workflow (from scratch):**\n```\nI want to write a research paper on the impact of AI on higher education quality assurance\n```\n--> academic-pipeline launches, starting from Stage 1 (RESEARCH)\n\n**Mid-entry (existing paper):**\n```\nI already have a paper, help me review it\n```\n--> academic-pipeline detects mid-entry, starting from Stage 2.5 (INTEGRITY)\n\n**Revision mode (received reviewer feedback):**\n```\nI received reviewer comments, help me revise\n```\n--> academic-pipeline detects, starting from Stage 4 (REVISE)\n\n**Execution flow:**\n1. Detect the user's current stage and available materials\n2. Recommend the optimal mode for each stage\n3. Dispatch the corresponding skill for each stage\n4. **After each stage completion, proactively prompt and wait for user confirmation**\n5. Track progress throughout; Pipeline Status Dashboard available at any time\n\n---\n\n## Trigger Conditions\n\n### Trigger Keywords\n\n**English**: academic pipeline, research to paper, full paper workflow, paper pipeline, end-to-end paper, research-to-publication, complete paper workflow\n\n### Non-Trigge"},{"path":"skills/academic-search/SKILL.md","content":"---\nname: academic-search\ndescription: |\n 学术论文搜索、引用分析与元数据提取专用 Skill。\n\n 【自动触发条件——出现以下任一信号时立即加载本 Skill，无需用户显式说明】\n\n 意图信号（中文）：\n - 搜论文 / 找论文 / 查论文 / 调研论文 / 检索文献 / 文献综述 / 综述\n - 顶会 / 顶刊 / CCF / NeurIPS / ICML / ICLR / ACL / EMNLP / CVPR / KDD / SIGIR / WWW\n - 引用数 / 被引 / 引用关系 / 引用量\n - BibTeX / 参考文献格式 / 导出引用\n - 作者发表列表 / 某人的论文 / 某人在哪发了什么\n - arXiv / Semantic Scholar / Google Scholar / PubMed / ACM DL / IEEE\n - 知网 / CNKI / 中国知网 / 学位论文 / 硕士论文 / 博士论文 / 中文文献 / 中文期刊\n - PDF 链接 / 论文 PDF / 开放获取\n - 摘要 abstract / 元数据\n\n 意图信号（英文）：\n - search paper / find paper / look up paper / literature review / survey\n - citation count / citation graph / citing / cited by\n - BibTeX / reference export\n - top conference / top journal / venue ranking\n - author publication list / papers by X\n\n URL 信号（出现以下域名的链接时自动触发）：\n - arxiv.org / ar5iv.org\n - semanticscholar.org\n - scholar.google.com\n - dl.acm.org\n - ieeexplore.ieee.org\n - pubmed.ncbi.nlm.nih.gov\n - paperswithcode.com\n - cnki.net / kns.cnki.net\n\n 覆盖平台：arXiv、Semantic Scholar、Google Scholar、ACM DL、IEEE Xplore、PubMed、Papers with Code、CNKI（中国知网）\nmetadata:\n version: \"1.2.0\"\n---\n\n# academic-search Skill\n\n## 前置检查\n\n在开始前，检查环境就绪状态：\n\n```bash\nbash ~/.claude/skills/academic-search/scripts/check-deps.sh\n```\n\n- **Node.js 22+**：必需（用于 CDP 浏览器模式）。仅使用 API 平台时可不检查。\n- **Chrome remote-debugging**：仅在访问 Google Scholar 或其他需要浏览器自动化的平台时必需。在 Chrome 地址栏打开 `chrome://inspect/#remote-debugging`，勾选 **Allow remote debugging for this browser instance**。\n- **curl**：必需，用于 API 调用。\n\narXiv、Semantic Scholar、PubMed、Papers with Code 等 API 平台无需 Chrome 远程调试即可使用。\n\n**S2 API Key（强烈建议）**：无 Key 时 S2 速率上限极低，单 session 多次调用必触发 429。免费注册即可获得更高配额：https://www.semanticscholar.org/product/api#api-key-form。有 Key 时在请求头加 `x-api-key: {your_key}`。\n\n## 搜索哲学\n\n**明确目标，选对平台，提取结构化数据，完成即止。**\n\n学术搜索不同于通用网页浏览——目标是获取**准确、结构化**的论文元数据，而不是浏览网页内容。\n\n**① 明确检索目标，定义成功标准**：执行前先明确什么算完成了。\n\n- 关键词搜索？精确论文？某作者的全部论文？某 venue 的论文列表？\n- 需要什么字段：仅标题和引用数 / 完整元数据 / PDF / BibTeX / 代码链接？\n- 年份范围？领域限定？返回几篇？\n- **成功标准**：用户要的是摘要表（第一遍）还是完整元数据（第二遍）？数量够了吗？字段都有了吗？这是后续所有决策的锚点。\n\n**② 选对平台**：不同需求对应不同平台（见下方矩阵）。API 平台优先，CDP 用于无 API 的平台。\n\n**③ 提取结构化数据，先筛后深**：搜索的时间瓶颈不在\"搜\"，在\"筛\"。默认采用两遍策略：\n\n- **第一遍（轻量扫描）**：先拉 20-30 条结果，输出轻量摘要表——标题、作者、年份、venue、引用数、是否有开放 PDF/代码。不拉完整摘要。\n- **用户或任务确认核心论文**（引用数高、venue 等级高、与目标最相关的 5-10 篇）后，**第二遍**再深入拉摘要、PDF、BibTeX 等完整信息。\n\n所有结果输出为统一 schema（见 `references/metadata-schema.md`），不要输出原始 HTML 或非结构化文本。多平台结果用 DOI/arXiv ID 去重合并。\n\n**④ 过程校验，用失败信号更新方向**：每一步的结果都是信息，不只是成功或失败的二元信号。\n\n| 失败信号 | 含义 | 方向调整 |\n|---------|------|---------|\n| API 429 / Rate exceeded | 本次会话消耗超配额，不是暂时波动 | 等待 15s+ 或切换 CDP 模式；不要同一请求重试 |\n| Jina/WebFetch 超时 | 该页面对静态抓取不友好 | 改用 curl 直接调 API 或切换 CDP |\n| S2 返回结果为空 | query 措辞问题，或该平台无收录 | 换关键词组合，或换 arXiv/PubMed |\n| 平台返回\"内容不存在\" | 未必真的不存在，可能是访问方式问题 | 检查 URL 参数是否完整，换平台验证 |\n| 同一方式重试 3 次无改善 | 路径错了，不是还没找到方法 | 重新评估目标，换平台或换访问方式 |\n\n**⑤ 完成判断**：对照①定义的成功标准确认任务完成后停止，不为\"更完整\"而过度操作。\n\n## 平台选择矩阵\n\n根据任务特征选择最合适的平台和访问方式：\n\n| 需求 | 首选平台 | 访问方式 | 备注 |\n|------|---------|---------|------|\n| CS/Math/Physics/统计 论文搜索 | **arXiv** | RES"}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"Complete Academic Research & Writing Suite — One-click installation of the full Academic Pipeline ecosystem with all 8 dependencies. Includes academic-pipeli... Skill: academic-pipeline-suite Owner: eric-promax Summary: Complete Academic Research & Writing Suite — One-click installation of the full Academic Pipeline ecosystem with all 8 dependencies. Includes academic-pipeli... Tags: latest:1.0.0 Version history: v1.0.0 | 2026-05-14T05:39:41.568Z | user Academic Pipeline Suite v1.0.0 - Initial release of the academic-suite meta-skill package. - One-click offline installation","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":804,"uniquenessScore":50,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-12T00:19:28.754Z","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":"2026-10-12T00:19:28.754Z","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":"2026-10-12T21:35:03.961Z","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"}]}}}