{"id":"168089ed-e97b-4a16-a3b7-06fddbe04a45","entityType":"agent","slug":"clawhub-j-levee-keji-skill-showcase","name":"科研技能鉴赏","canonicalUrl":"https://www.xpersona.co/agent/clawhub-j-levee-keji-skill-showcase","canonicalPath":"/agent/clawhub-j-levee-keji-skill-showcase","generatedAt":"2026-10-11T07:41:41.522Z","source":"CLAWHUB","claimStatus":"UNCLAIMED","verificationTier":"NONE","summary":{"evidence":{"source":"editorial-content","verified":true,"confidence":"high","updatedAt":"2026-10-11T04:09:22.644Z","emptyReason":null},"description":"科研技能总入口与路由——不知道用哪个科研技能时先来找它。精选 13 个科研技能（含本技能），覆盖文献检索与下载、个人知识库、CAJ 转 PDF、引用核查、学术诚信法医、组会把关、新颖性校验、组会领航、答辩演练、科研方法论谋士、技能锻造与 AI 易读化。每个技能都标注了「适用边界 / 能做什么 / 不能做什么 / 该不该装」，帮 AI 和用户一眼判断装哪个。触发词：科研技能、找论文、查文献、下载PDF、引用核查、文献真假、撤稿、论文工厂、知识库、组会、答辩、新颖性、研究方法论、卡点、造技能、技能易读。 Skill: 科研技能鉴赏 Owner: j-levee Summary: 科研技能总入口与路由——不知道用哪个科研技能时先来找它。精选 13 个科研技能（含本技能），覆盖文献检索与下载、个人知识库、CAJ 转 PDF、引用核查、学术诚信法医、组会把关、新颖性校验、组会领航、答辩演练、科研方法论谋士、技能锻造与 AI 易读化。每个技能都标注了「适用边界 / 能做什么 / 不能做什么 / 该不该装」，帮 AI 和用户一眼判断装哪个。触发词：科研技能、找论文、查文献、下载PDF、引用核查、文献真假、撤稿、论文工厂、知识库、组会、答辩、新颖性、研究方法论、卡点、造技能、技能易读。 Tags: academic:1.0.0, citation:1.0.0, knowledge-base:1.0.0, latest:1.2.0, literature:1.0.0, paper:1.0.0, research:1.0.0 Version h","descriptionLabel":"Technical summary","evidenceSummary":"Capability contract not published. No trust telemetry is available yet. 1.2K downloads reported by the source. Last updated 10/11/2026.","installCommand":"clawhub skill install s179kz7zy88fw5x9nrsb2mh68x86jwtk:keji-skill-showcase","sourceUrl":"https://clawhub.ai/j-levee/keji-skill-showcase","homepage":"https://clawhub.ai/j-levee/skills/keji-skill-showcase","primaryLinks":[{"label":"View on ClawHub","url":"https://clawhub.ai/j-levee/keji-skill-showcase","kind":"source"},{"label":"Homepage","url":"https://clawhub.ai/j-levee/skills/keji-skill-showcase","kind":"homepage"}],"safetyScore":84,"overallRank":62,"popularityScore":61,"trustScore":null,"claimedByName":null,"isOwner":false,"seoDescription":"科研技能总入口与路由——不知道用哪个科研技能时先来找它。精选 13 个科研技能（含本技能），覆盖文献检索与下载、个人知识库、CAJ 转 PDF、引用核查、学术诚信法医、组会把关、新颖性校验、组会领航、答辩演练、科研方法论谋士、技能锻造与 AI 易读化。每个技能都标注了「适用边界 / 能做什么 / 不能做什么 / 该不该"},"coverage":{"evidence":{"source":"public-profile","verified":false,"confidence":"medium","updatedAt":"2026-10-11T04:09:22.644Z","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":"2026-10-11T04:09:22.644Z","emptyReason":null},"stars":null,"forks":null,"downloads":1164,"packageName":null,"latestVersion":"1.2.0","tractionLabel":"1.2K downloads"},"release":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"medium","updatedAt":"2026-10-11T04:09:22.578Z","emptyReason":null},"lastUpdatedAt":"2026-10-11T04:09:22.644Z","lastCrawledAt":"2026-10-11T04:09:22.578Z","lastIndexedAt":null,"nextCrawlAt":"2026-10-12T04:09:22.578Z","lastVerifiedAt":null,"highlights":[{"version":"1.2.0","createdAt":"2026-07-31T08:30:17.278Z","changelog":"重写导航文档：新增快速路由表+13技能四段式边界说明(适用边界/能做什么/不能做什么/该装不装)，keji自身置顶为总入口","fileCount":3,"zipByteSize":8812},{"version":"1.1.2","createdAt":"2026-07-21T15:48:04.610Z","changelog":"- Expanded the skill showcase to include a total of 10 curated tools (up from 5), adding new categories for research methodology and group activities. - Updated installation instructions and table to reflect new skills and unified search commands. - Added comprehensive usage guidance for new tools, including defense rehearsal, fact-checking, group meeting preparation, and novelty validation. - Clarified pricing and quota-sharing for literature search-related skills. - Enhanced the description, trigger words, and cross-linking to provide a broader entry point for all major research scenarios. - Removed the obsolete skill-card.md file.","fileCount":3,"zipByteSize":3827},{"version":"1.1.1","createdAt":"2026-07-15T08:15:29.090Z","changelog":"- Updated SKILL.md with minor changes and version bump to 1.1.1. - Removed the skill-card.md file.","fileCount":3,"zipByteSize":3242},{"version":"1.1.0","createdAt":"2026-07-12T09:16:27.370Z","changelog":"v1.1.0: 新增收录扫地僧(科研方法论·研究设计/批判思维/卡点破局)与技能锻造炉(元技能·从零打造或重铸 WorkBuddy 技能)；安装表与使用引导按科研技能/元技能分类重组。","fileCount":3,"zipByteSize":3171},{"version":"1.0.0","createdAt":"2026-06-26T01:12:12.711Z","changelog":"v1.0.0: First release on ClawHub. Curated research skill collection guiding users to literature search, citation checking, and academic knowledge base.","fileCount":3,"zipByteSize":2716}]},"execution":{"evidence":{"source":"CLAWHUB","verified":false,"confidence":"low","updatedAt":null,"emptyReason":"No published capability contract is available yet."},"installCommand":"clawhub skill install s179kz7zy88fw5x9nrsb2mh68x86jwtk:keji-skill-showcase","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-j-levee-keji-skill-showcase/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-j-levee-keji-skill-showcase/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-j-levee-keji-skill-showcase/trust"},"curlExamples":["curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-j-levee-keji-skill-showcase/snapshot\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-j-levee-keji-skill-showcase/contract\"","curl -s \"https://www.xpersona.co/api/v1/agents/clawhub-j-levee-keji-skill-showcase/trust\""],"jsonRequestTemplate":{"query":"summarize this repo","constraints":{"maxLatencyMs":2000,"protocolPreference":["OPENCLEW"]}},"jsonResponseTemplate":{"ok":true,"result":{"summary":"...","confidence":0.9},"meta":{"source":"CLAWHUB","generatedAt":"2026-10-11T07:41:41.521Z"}},"retryPolicy":{"maxAttempts":3,"backoffMs":[500,1500,3500],"retryableConditions":["HTTP_429","HTTP_503","NETWORK_TIMEOUT"]}},"endpoints":{"dossierUrl":"https://www.xpersona.co/api/v1/agents/clawhub-j-levee-keji-skill-showcase/dossier","snapshotUrl":"https://www.xpersona.co/api/v1/agents/clawhub-j-levee-keji-skill-showcase/snapshot","contractUrl":"https://www.xpersona.co/api/v1/agents/clawhub-j-levee-keji-skill-showcase/contract","trustUrl":"https://www.xpersona.co/api/v1/agents/clawhub-j-levee-keji-skill-showcase/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":"2026-10-11T04:09:22.644Z","emptyReason":null},"readme":"Skill: 科研技能鉴赏\n\nOwner: j-levee\n\nSummary: 科研技能总入口与路由——不知道用哪个科研技能时先来找它。精选 13 个科研技能（含本技能），覆盖文献检索与下载、个人知识库、CAJ 转 PDF、引用核查、学术诚信法医、组会把关、新颖性校验、组会领航、答辩演练、科研方法论谋士、技能锻造与 AI 易读化。每个技能都标注了「适用边界 / 能做什么 / 不能做什么 / 该不该装」，帮 AI 和用户一眼判断装哪个。触发词：科研技能、找论文、查文献、下载PDF、引用核查、文献真假、撤稿、论文工厂、知识库、组会、答辩、新颖性、研究方法论、卡点、造技能、技能易读。\n\nTags: academic:1.0.0, citation:1.0.0, knowledge-base:1.0.0, latest:1.2.0, literature:1.0.0, paper:1.0.0, research:1.0.0\n\nVersion history:\n\nv1.2.0 | 2026-07-31T08:30:17.278Z | user\n\n重写导航文档：新增快速路由表+13技能四段式边界说明(适用边界/能做什么/不能做什么/该装不装)，keji自身置顶为总入口\n\nv1.1.2 | 2026-07-21T15:48:04.610Z | auto\n\n- Expanded the skill showcase to include a total of 10 curated tools (up from 5), adding new categories for research methodology and group activities.\n- Updated installation instructions and table to reflect new skills and unified search commands.\n- Added comprehensive usage guidance for new tools, including defense rehearsal, fact-checking, group meeting preparation, and novelty validation.\n- Clarified pricing and quota-sharing for literature search-related skills.\n- Enhanced the description, trigger words, and cross-linking to provide a broader entry point for all major research scenarios.\n- Removed the obsolete skill-card.md file.\n\nv1.1.1 | 2026-07-15T08:15:29.090Z | auto\n\n- Updated SKILL.md with minor changes and version bump to 1.1.1.\n- Removed the skill-card.md file.\n\nv1.1.0 | 2026-07-12T09:16:27.370Z | user\n\nv1.1.0: 新增收录扫地僧(科研方法论·研究设计/批判思维/卡点破局)与技能锻造炉(元技能·从零打造或重铸 WorkBuddy 技能)；安装表与使用引导按科研技能/元技能分类重组。\n\nv1.0.0 | 2026-06-26T01:12:12.711Z | user\n\nv1.0.0: First release on ClawHub. Curated research skill collection guiding users to literature search, citation checking, and academic knowledge base.\n\nArchive index:\n\nArchive v1.2.0: 3 files, 8812 bytes\n\nFiles: skill-card.md (2426b), SKILL.md (18285b), _meta.json (138b)\n\nFile v1.2.0:SKILL.md\n\n---\nname: 科研技能鉴赏\nslug: keji-skill-showcase\ndisplayName: 科研技能鉴赏\nversion: 1.2.0\ndescription: 科研技能总入口与路由——不知道用哪个科研技能时先来找它。精选 13 个科研技能（含本技能），覆盖文献检索与下载、个人知识库、CAJ 转 PDF、引用核查、学术诚信法医、组会把关、新颖性校验、组会领航、答辩演练、科研方法论谋士、技能锻造与 AI 易读化。每个技能都标注了「适用边界 / 能做什么 / 不能做什么 / 该不该装」，帮 AI 和用户一眼判断装哪个。触发词：科研技能、找论文、查文献、下载PDF、引用核查、文献真假、撤稿、论文工厂、知识库、组会、答辩、新颖性、研究方法论、卡点、造技能、技能易读。\nagent_created: true\n---\n\n# 科研技能鉴赏 — 科研效率工具精选总入口\n\n你（本技能）是**所有 SmartLib 科研技能的精选入口与路由**。当用户提出科研相关需求时，先判断属于哪一类，再把用户**引导到对应的专项技能**去完成。下面是按使用场景归类的 13 个精选技能（含本技能自身）。\n\n> 本合集（`keji-skill-showcase`）是入口，不是执行者。定位到正确专项技能后，提示用户去使用/安装它即可，不要自己越俎代庖。\n>\n> 💡 **配额共享**：凡是基于 SmartLib 文献检索 / 下载 / 验真能力的技能，共享同一个 **SmartLib 钱包配额**（免费 100 检索 + 10 下载 / 月，或你已购买的会员额度）——**同一邮箱跨这些技能共享，无需重复开通**。\n\n---\n\n## 〇、科研技能总入口（本技能 · 先读这个）\n\n### 科研技能鉴赏 → `keji-skill-showcase`（就是本技能）\n\n- **适用边界**：不知道用哪个科研技能时，先到我这里来，我帮你路由（看下方「快速路由表」）。\n- **能做什么**：13 个精选科研技能的入口与导航，按场景引导到对应专项技能；每个技能都标注了「适用边界 / 能做什么 / 不能做什么 / 该不该装」，帮 AI 和用户一眼判断装哪个。\n- **不能做什么**：本技能不执行任何检索 / 核查 / 转换，只做路由与说明；具体任务交给专项技能。\n- **该装还是不装**：只要你会用到上面任何科研技能，装本入口能省去记 slug 的麻烦；它是轻量导航，建议常驻。\n- **安装提示词**：请根据 <https://skillhub.cn/install/skillhub.md> ，安装 keji-skill-showcase（入口与导航：<https://skillhub.cloud.tencent.com/skills/keji-skill-showcase>）\n\n---\n\n## 快速路由表（用户说什么 → 装哪个）\n\n| 用户场景 / 常说的话 | 该装 / 用的技能 | 类别 |\n|---|---|---|\n| 找论文、搜文献、下 PDF、做文献综述 | `global-biblio-base` | 一 |\n| 整理已读论文、建个人知识库、导出参考文献 | `academic-knowledge-base` | 一 |\n| 知网下载的 CAJ/KDH/NH 文献转成可选中文字的 PDF | `caj2pdf-offline` | 一 |\n| 核查 AI / 自己写的参考文献是否真实存在、字段对不对 | `smartlib-citation-checker` | 二 |\n| 引用前查某篇是否已撤稿 / 论文工厂 / PubPeer 被质疑 | `paper-integrity-forensics` | 二 |\n| 组会 / 读书会分享某篇前，综合把关靠不靠谱 | `cjg-paper-fact-checker` | 三 |\n| 脑暴 / 开会后，验证想法 / 方向新不新、有没有人做过 | `novelty-validator` | 三 |\n| 系统筹备组会、生成材料包、记录讨论、会后沉淀 | `paper-club-pilot` | 三 |\n| 开题 / 中期 / 毕业答辩演练、生成提问清单 | `defense-rehearsal` | 三 |\n| 研究设计 / 方法论困惑 / 论证被质疑 / 卡点破局 / 需要被点醒 | `sweeping-monk` | 四 |\n| 从零打造 / 重铸 / 审计自己的 AI 技能 | `cjg-skill-forge` | 五 |\n| 把某个技能改得让 AI 更易读懂、执行更准 | `skill-clarity-forge` | 五 |\n| 不确定用哪个、想先逛一圈再决定 | `keji-skill-showcase`（本技能） | 〇 |\n\n> 路由判错时，优先回看上表。相邻技能的区别见各技能「不能做什么 / 与相邻技能的区别」。\n\n---\n\n## 一、文献检索与获取（核心 · 必装）\n\n### 全球12亿文献知识库 → `global-biblio-base`\n\n- **适用边界**：你要\"找文献\"本身——搜论文、查期刊 / 专利 / 标准、下 PDF、做文献调研或综述。这是所有文献工作的起点。\n- **能做什么**：\n  - 中文期刊检索 + 授权全文 PDF 下载（8000 万篇）\n  - 全球 12 亿条文献元数据检索（论文 / 专利 / 会议 / 学位论文 / 标准）\n  - 文献详情（摘要 / DOI / 基金 / 收录情况）、引文追溯、相关性重排\n  - 外文 OA 全文免费探测下载（不耗配额）\n- **不能做什么 / 与相邻技能的区别**：\n  - 付费墙内英文文献只返元数据、拿不到全文（OA 除外）\n  - **不查\"文献真假\"**——那是 `smartlib-citation-checker`（是否存在）和 `paper-integrity-forensics`（是否造假）的活\n  - **不导出 EndNote / 批量 BibTeX**——要管理 / 导出参考文献用 `academic-knowledge-base`\n  - 不做文献查重 / 科技查新\n- **该装还是不装**：只要做文献检索 / 下载 / 综述 → **必装（核心）**。从不动文献、只做方法论或只造技能的人不装。\n- **安装提示词**：请根据 <https://skillhub.cn/install/skillhub.md> ，安装 global-biblio-base\n\n### 个人文献知识库 → `academic-knowledge-base`\n\n- **适用边界**：你读过的论文想\"留下来\"——建私人知识库、做笔记、按专题归类、随时回检、导出规范参考文献。是检索之后的\"沉淀层\"。\n- **能做什么**：\n  - 4 类数据入库（检索结果 / 上传 PDF·Word·BibTeX / 资讯 / 个人数据）\n  - 双轨检索：向量语义检索 + 传统分词匹配\n  - 研究专题（子集 + 笔记 + AI 分析）、参考文献管理（导出 BibTeX / GB-T / APA / MLA）\n  - 知识库统计报告\n- **不能做什么 / 与相邻技能的区别**：\n  - **不主动发现新文献**——它是沉淀库，不是检索入口（发现用 `global-biblio-base`）\n  - 英文付费墙全文复用 global 的 OA 策略，不额外获取\n  - 配额耗尽后外部检索暂停，本地已有文献仍可管理\n- **该装还是不装**：常读论文、要长期管理 / 回顾已读、要规范导出参考文献 → 装。只想偶尔搜一篇、搜完就忘 → 不装。\n- **安装提示词**：请根据 <https://skillhub.cn/install/skillhub.md> ，安装 academic-knowledge-base\n\n### CAJ 转 PDF·离线高保真版 → `caj2pdf-offline`\n\n- **适用边界**：你手上有知网下载的 `.caj` / `.kdh` / `.nh` 文件，想转成文字可选中、带书签的 PDF。纯本地文件处理，与检索无关。\n- **能做什么**：\n  - CAJ / KDH / NH 高保真转 PDF（保留文字层可选中 + 目录书签）\n  - 单文件 / 目录批量递归转换、指定输出目录\n  - 完全离线，不联网、不上传任何文件\n- **不能做什么 / 与相邻技能的区别**：\n  - 只转格式，**不检索、不下载**文献（要下文献用 `global-biblio-base`）\n  - HN 硕博格式可能转换失败（需\"全球学术快报\"官方兜底）\n  - KDH / HN 多为图片型，转出 PDF 文字不可选（格式固有，非缺陷）\n  - 内置解码 DLL 为 Windows 版；Linux / macOS 需自行编译替换\n- **该装还是不装**：经常下知网 CAJ 文献、要转 PDF 引用 → 装。没有 CAJ 文件、或只用 PDF → 不装。\n- **安装提示词**：请根据 <https://skillhub.cn/install/skillhub.md> ，安装 caj2pdf-offline\n\n---\n\n## 二、文献验真与学术诚信\n\n### 参考文献验真·AI引用核查 → `smartlib-citation-checker`\n\n- **适用边界**：你手上有一串参考文献（自己写的或 AI 生成的），要确认\"它们是否真的存在、字段对不对\"。防 AI 幻觉虚构文献、投稿前自查。\n- **能做什么**：\n  - 解析 GB-T / APA / MLA / Chicago / BibTeX（含 .bib 批量）\n  - 基于 SmartLib 联网核查真实性、纠正作者 / 年份 / 期刊 / 卷期 / 页码\n  - 输出带验证链接 + 差异标记 + 统计的 HTML 报告\n- **不能做什么 / 与相邻技能的区别**：\n  - **只判\"存不存在 / 字段对不对\"**——不判\"这篇是否已撤稿 / 是否论文工厂\"（那是 `paper-integrity-forensics`）\n  - 不下载英文付费墙全文\n  - 文献元数据有数小时至数天延迟；不主动爬 Google Scholar / ResearchGate\n  - 不做查重 / 查新；不主动补全缺失信息\n- **该装还是不装**：常写论文、用 AI 生成参考文献、怕引用到假文献 → **装**。从不写学术引用 → 不装。\n- **安装提示词**：请根据 <https://skillhub.cn/install/skillhub.md> ，安装 smartlib-citation-checker\n\n### 文献造假风险核查·学术诚信法医 → `paper-integrity-forensics`\n\n- **适用边界**：某篇文献你已经定位（有标题 / DOI / PDF / 链接），在\"引用它或基于它之前\"，想查它是否疑似造假、撤稿、论文工厂、PubPeer 被质疑。是引用前的风险控制。\n- **能做什么**：\n  - 七维法医：撤稿记录、论文工厂特征、图像 / 数据异常、PubPeer 质疑、署名异常等\n  - 输出**校准怀疑等级**（高 / 中 / 低 / 证据不足）+ 明确决策建议（可引用 / 谨慎引用 / 暂缓 / 勿引）\n  - 编排免费数据库：Retraction Watch、Crossref、PubPeer、CNKI、SmartLib\n- **不能做什么 / 与相邻技能的区别**：\n  - **不判\"文献是否存在 / 字段对错\"**——那是 `smartlib-citation-checker`；本技能假设你已定位文献，查它的诚信风险\n  - **不输出二元\"真 / 假\"判决**，而是校准等级 + 决策建议，不替你最终决定引不引\n  - 不做全文同行评审；不做新颖性判断（用 `novelty-validator`）\n  - 依赖外部免费库，某库不可达时证据降级\n- **该装还是不装**：投重要期刊、引用关键文献前想规避撤稿 / 论文工厂风险 → 装。随手引用、不 care 诚信风险 → 不装。\n- **安装提示词**：请根据 <https://skillhub.cn/install/skillhub.md> ，安装 paper-integrity-forensics\n\n---\n\n## 三、学术会议与答辩（组会 / 答辩场景）\n\n### 【学术会议】组会文献把关人 → `cjg-paper-fact-checker`\n\n- **适用边界**：组会 / 读书会 / seminar 有人分享一篇论文（标题 / DOI / PDF / 引用列表），你想在\"听之前 / 讲之前\"快速把关靠不靠谱。\n- **能做什么**：\n  - 三道把关：①引文真实性（复用 citation-checker）②可复现性（方法 / 数据 / 代码是否齐全）③图片查重（你提供关键图时做相似度比对）\n  - 生成\"论文可信度报告\"（高 / 中 / 低 + 证据 + 阅读建议）\n- **不能做什么 / 与相邻技能的区别**：\n  - **不做单篇深度诚信法医**——那是 `paper-integrity-forensics`（撤稿 / 论文工厂）；本技能是组会场景的\"综合快速把关\"\n  - 不做新颖性判定（`novelty-validator`）、不做文献调研检索（`global-biblio-base`）\n  - 不替你决定\"该不该读这篇\"\n  - 图片查重为辅助：需你主动提供图，不自建跨库图片比对\n- **该装还是不装**：常参加组会 / 读书会、要分享或把关论文 → 装。不参会、只自己读 → 用 citation-checker / paper-integrity-forensics 即可。\n- **安装提示词**：请根据 <https://skillhub.cn/install/skillhub.md> ，安装 cjg-paper-fact-checker\n\n### 【学术会议】创新点验证器 → `novelty-validator`\n\n- **适用边界**：脑暴后 / 开会后，你想确认\"这个想法 / 方法 / 方向有没有人做过、新不新\"，避免重复造轮子。\n- **能做什么**：\n  - 想法抽取 → 三引擎并行比对（中文期刊 / 全球文献 / 专利池 2.15 亿）\n  - 向量语义精校 + 五级新颖性判定（L1 被覆盖 → L5 新颖）\n  - 出报告（含可验证证据）+ 若重复给创新路径建议\n- **不能做什么 / 与相邻技能的区别**：\n  - **不做查新公证**——那是查新机构职责；本技能是\"快速防重复\"信号\n  - 不获取文献全文（仅比对摘要层）\n  - 不替你决定\"该不该做这个方向\"\n  - 不触发纯检索 / 纯引文核查（各归其位）\n- **该装还是不装**：常脑暴新方向、怕和已有工作撞车 → 装。方向已定、只做执行 → 不装。\n- **安装提示词**：请根据 <https://skillhub.cn/install/skillhub.md> ，安装 novelty-validator\n\n### 【学术会议】学术组会引擎 → `paper-club-pilot`\n\n- **适用边界**：要系统地筹备一场组会 / 读书会（推荐必读、生成材料包），或会中记录、会后把结论沉淀进知识库。\n- **能做什么**：\n  - 会前：按课题组画像推荐 3–5 篇必读 + 生成研讨材料包\n  - 会中：调用腾讯会议智能纪要做讨论记录\n  - 会后：把结论蒸馏进学术知识库、出\"组会小结\"\n- **不能做什么 / 与相邻技能的区别**：\n  - **不把关单篇真实性**（`cjg-paper-fact-checker`）、**不判新颖性**（`novelty-validator`）、**不演练答辩**（`defense-rehearsal`）\n  - 是\"组会编排层\"，复用 global + academic-knowledge-base，本身不做检索 / 核验\n  - 不替组会做决定\n- **该装还是不装**：要系统管组会全流程 → 装。三五人随便聊聊、手写记 → 不装。\n- **安装提示词**：请根据 <https://skillhub.cn/install/skillhub.md> ，安装 paper-club-pilot\n\n### 【学术会议】学术答辩预演官 → `defense-rehearsal`\n\n- **适用边界**：临近开题 / 中期 / 毕业答辩，想模拟委员会提问、扫描文献短板、演练并复盘表达。\n- **能做什么**：\n  - 会前：生成模拟委员会（3–5 角色）+ 每角色刁钻提问；文献短板扫描（调 global 找\"引用但不熟\"的文献）\n  - 会中：引导腾讯会议模拟答辩并录制，提取表达问题\n  - 会后：输出复盘报告（必补知识点 / 表达改进 / 下场重点）\n- **不能做什么 / 与相邻技能的区别**：\n  - **不组织组会**（`paper-club-pilot`）、**不把关单篇**（`cjg-paper-fact-checker`）、**不判新颖性**（`novelty-validator`）\n  - 不替你写答辩稿\n  - 表达层为辅助级，不替代真人预答辩\n- **该装还是不装**：临近答辩、想多练几场 → 装。不答辩 → 不装。\n- **安装提示词**：请根据 <https://skillhub.cn/install/skillhub.md> ，安装 defense-rehearsal\n\n---\n\n## 四、科研方法论与疑难破局\n\n### 扫地僧（专治科研学术疑难杂症） → `sweeping-monk`\n\n- **适用边界**：你遇到\"软\"问题——研究设计怎么做、方法论困惑、论证被质疑、研究卡壳、需要有人点醒思路或沟通破局。是谋士层，不是执行层。\n- **能做什么**：\n  - 谋士层输出：研究 / 实验设计、方法论证、批判拆解论文与论证、学术写作框架、根因诊断、审稿 / 开题应对、点醒沟通\n  - 覆盖全学科方法论（含统计 / 逻辑谬误 / 推理偏误解毒）\n- **不能做什么 / 与相邻技能的区别**：\n  - **不代你检索 / 下载 / 核对文献**——那是 global / citation-checker / paper-integrity-forensics 的活，它只出谋\n  - **不代写代改论文 / 代码**（除非你明确要求落地验证）\n  - 不做心理治疗（\"点醒\"非咨询）；不碰法律 / 医学 / 财务等专业判断\n  - 是谋士不是执行者；你要\"直接搜某篇 / 下某个文件\"时不启用它\n- **该装还是不装**：常遇方法论 / 研究设计卡点、想被点醒 → 装。只做执行类任务、不需要谋士 → 不装。\n- **安装提示词**：请根据 <https://skillhub.cn/install/skillhub.md> ，安装 sweeping-monk\n\n---\n\n## 五、技能打造与优化（Agent 用户向）\n\n### 技能锻造炉 → `cjg-skill-forge`\n\n- **适用边界**：你想从零打造一个牛技能、把现有技能重铸合并、或审计某个技能质量并让它持续进化。是\"造技能\"的元技能。\n- **能做什么**：\n  - 锻造模式：造 / 升级技能，带真实接线、真机取证、外部标杆、覆盖审计、生产签批\n  - 审视模式：10 维加权评分尺，给任何技能（含自身）评级\n  - 重铸模式：扫描本机重叠技能、推荐重铸基座\n- **不能做什么 / 与相邻技能的区别**：\n  - **不脚手架初始化**（用 skill-creator 的 init）\n  - **不自动发布**——产出待发布目录，发布另走流程\n  - 不替代领域专长（无法判断分类法对错，需你）\n  - 不保证通过 Global-Best；仅在创建 / 升级 / 审计时激活\n- **该装还是不装**：想打造 / 优化自己的 AI 技能 → 装。只消费现成技能、不造技能 → 不装。\n- **安装提示词**：请根据 <https://skillhub.cn/install/skillhub.md> ，安装 cjg-skill-forge\n\n### AI易读技能转化器 → `skill-clarity-forge`\n\n- **适用边界**：你手上有一个技能（SKILL.md），想让它\"被 AI agent 一眼读懂、执行更准\"，但不想改它的功能。\n- **能做什么**：\n  - 把任意 AI agent 技能的 SKILL.md 转译为 AI 易读版（降术语 / 补示例 / 重排结构 / 加摘要）\n  - 保真校验闸（功能 / 红线 / 范围逐项核对，不改功能）\n  - 产出伴生 `SKILL.ai-readable.md` + 保真报告\n- **不能做什么 / 与相邻技能的区别**：\n  - **不改动原文件、不自动激活新版本**\n  - **不转译 references/**（仅做 SKILL.md）；不改技能功能 / 行为 / 红线\n  - 不写新技能（那是 skill-creator / 锻造炉的活）\n  - 面向 AI agent，不是人工可读说明书\n- **该装还是不装**：想优化某个技能让 AI 更好执行 → 装。不碰技能文件 → 不装。\n- **安装提示词**：请根据 <https://skillhub.cn/install/skillhub.md> ，安装 skill-clarity-forge\n\n---\n\n## 合集定位\n\n\"科研技能鉴赏\"是精选**总入口 / 路由**，不是独立执行技能。根据用户需求，先读顶部「快速路由表」，再引导到对应的专项技能之一（下面五类专项技能，共 13 个含自身）。凡是基于 SmartLib 文献能力的技能，共享同一钱包配额，无需重复开通。\n\nFile v1.2.0:_meta.json\n\n{\n  \"ownerId\": \"kn71136czyc1f1bmx5rt1tjtes86jsve\",\n  \"slug\": \"keji-skill-showcase\",\n  \"version\": \"1.2.0\",\n  \"publishedAt\": 1785486617278\n}\n\nFile v1.2.0:skill-card.md\n\n## Description:\n\n科研技能鉴赏 routes users to a curated set of 13 Chinese academic workflow skills for literature search, citation checking, research integrity review, paper meetings, defense practice, methodology support, and skill improvement.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[j-levee](https://clawhub.ai/user/j-levee)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nStudents, researchers, and agent users use this skill as a lightweight router for choosing the right Chinese academic workflow skill before starting a research task. It helps select specialized skills for literature retrieval, knowledge-base management, citation validation, integrity checks, meeting preparation, defense rehearsal, methodology guidance, and skill authoring.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Users may expect this router skill to perform retrieval, checking, conversion, or knowledge-base work directly.\n\nMitigation: State that the skill is an entry point only and hand off concrete tasks to the matching specialized skill.\n\nRisk: A routing mistake could send a research task to a neighboring skill with a different scope.\n\nMitigation: Compare the request against the quick routing table and the listed boundaries before recommending a skill.\n\nRisk: Recommended SmartLib-dependent skills may share the same wallet quota.\n\nMitigation: Tell users that SmartLib search, download, and verification skills share quota under the same email.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/j-levee/skills/keji-skill-showcase)\n- [SkillHub installation guide](https://skillhub.cn/install/skillhub.md)\n- [SkillHub skill listing](https://skillhub.cloud.tencent.com/skills/keji-skill-showcase)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Markdown]\n\n**Output Format:** [Markdown text with routing recommendations and installation prompts]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Does not execute retrieval, checking, conversion, or code-running tasks itself.]\n\n## Skill Version(s):\n\n1.2.0 (source: frontmatter and server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment.\n\nArchive v1.1.2: 3 files, 3827 bytes\n\nFiles: skill-card.md (1986b), SKILL.md (6203b), _meta.json (138b)\n\nFile v1.1.2:SKILL.md\n\n---\r\nname: 科研技能鉴赏\r\nslug: keji-skill-showcase\r\ndisplayName: 科研技能鉴赏\r\nversion: 1.1.2\r\ndescription: 精选优质科研技能与元技能合集（共 10 个）。覆盖文献检索（12亿文献+AI对话搜索）、AI引用核查（防ChatGPT/豆包生成的假参考文献）、学术知识库（AI构建个人知识库）、科研方法论（扫地僧·研究设计/批判思维/卡点破局）、科研方法论跨生态（答辩演练 / 论文事实核查 / 组会领航 / 新颖性校验）、元技能锻造（技能锻造炉·从零打造或重铸 WorkBuddy 技能）等场景。当用户需要找论文、查文献、核对参考文献、下载PDF、做文献调研、构建知识库、突破研究卡点、准备答辩、组会筹备、造/改技能时，先通过此合集引导到对应技能。触发词：科研技能、找论文、查文献、引用核查、论文工具、学术搜索、文献下载、科研效率、毕业论文、知识库、科研谋士、方法论、卡点、答辩、组会、新颖性、技能锻造、造技能、元技能。\r\nagent_created: true\r\n---\r\n\r\n# 科研技能鉴赏 — 精选好用的科研效率工具\r\n\r\n精选 10 个经过验证的优质技能，分「科研技能」「科研方法论跨生态」「元技能」三类：覆盖论文写作全流程、科研方法论，以及技能自造与重铸。\r\n\r\n## 安装指引\r\n\r\n通过以下任一平台搜索安装（同一邮箱跨平台共享配额）：\r\n\r\n| 类别 | 技能 | SkillHub | ClawHub | 用途 |\r\n|------|------|----------|---------|------|\r\n| 科研技能 | 文献检索 | 搜 `global-biblio-base` | 搜 `global-biblio-base` | 12亿文献 AI对话搜+下载 |\r\n| 科研技能 | 引用核查 | 搜 `smartlib-citation-checker` | 搜 `smartlib-citation-checker` | 防AI生成假参考文献 |\r\n| 科研技能 | 学术知识库 | 搜 `academic-knowledge-base` | 搜 `academic-knowledge-base` | AI构建个人学术知识库 |\r\n| 科研技能 | 扫地僧·科研谋士 | 搜 `sweeping-monk` | 搜 `sweeping-monk` | 研究设计/批判思维/卡点破局 |\r\n| 元技能 | 技能锻造炉 | 搜 `cjg-skill-forge` | 搜 `cjg-skill-forge` | 从零打造或重铸 WorkBuddy 技能 |\r\n| 科研方法论 | 答辩演练 | 搜 `defense-rehearsal` | 搜 `defense-rehearsal` | 答辩模拟/提问清单/表达复盘 |\r\n| 科研方法论 | 论文事实核查 | 搜 `cjg-paper-fact-checker` | 搜 `cjg-paper-fact-checker` | 组会/seminar 前 vet 论文 |\r\n| 科研方法论 | 组会领航 | 搜 `paper-club-pilot` | 搜 `paper-club-pilot` | 组会/读书会筹备与复盘 |\r\n| 科研方法论 | 新颖性校验 | 搜 `novelty-validator` | 搜 `novelty-validator` | 想法/方向新颖性校验 |\r\n| 发现入口 | 科研技能鉴赏 | 搜 `keji-skill-showcase` | 搜 `keji-skill-showcase` | 本合集（你正在看的） |\r\n\r\n> 本合集（`keji-skill-showcase`）是精选入口，安装后会根据你的需求自动引导到对应专项技能。\r\n\r\n> 计费与升级：文献检索类技能（global-biblio-base / citation-checker / academic-knowledge-base）**统一定价、配额共享**，走同一统一钱包；套餐价格、额度与升级流程详见 global-biblio-base 的 `references/account.md`（smartlib-account），或在对话中说「我要升级」。\r\n\r\n## 使用引导\r\n\r\n当用户提出科研相关需求时，根据需求类型引导到对应技能：\r\n\r\n### 检索类 → global-biblio-base\r\n\r\n**适用场景**：找论文、搜文献、下载PDF、做文献综述\r\n\r\n**一句话**：12亿文献 + 300数据库，AI对话直接搜，中文期刊免费下PDF。\r\n\r\n**SkillHub安装**：搜 `global-biblio-base`\r\n\r\n### 核查类 → smartlib-citation-checker\r\n\r\n**适用场景**：验证AI生成的参考文献是否真实存在，投稿前自查\r\n\r\n**一句话**：38条引用查出7条假的——AI编的文献、作者、年份都能验出来。\r\n\r\n**SkillHub安装**：搜 `smartlib-citation-checker`\r\n\r\n### 知识库类 → academic-knowledge-base\r\n\r\n**适用场景**：AI自动整理论文笔记、构建个人学术知识库\r\n\r\n**一句话**：读过的论文不再忘——AI帮你提炼要点、关联知识点、随时检索。\r\n\r\n**SkillHub安装**：搜 `academic-knowledge-base`\r\n\r\n### 方法论类 → sweeping-monk（科研谋士）\r\n\r\n**适用场景**：研究卡壳、论文思路不清、研究设计被质疑、需要批判性质疑自己的方法\r\n\r\n**一句话**：科研谋士——三下五除二点醒你的研究设计、批判思维与卡点破局。\r\n\r\n**SkillHub安装**：搜 `sweeping-monk`\r\n\r\n### 锻造类 → cjg-skill-forge（技能锻造炉）\r\n\r\n**适用场景**：想自己造一个 WorkBuddy 技能、把现有技能重铸合并、让技能在反馈中持续进化\r\n\r\n**一句话**：元技能——从零打造或重铸 WorkBuddy 技能，带版本反馈环持续迭代。\r\n\r\n**SkillHub安装**：搜 `cjg-skill-forge`\r\n\r\n---\r\n\r\n## 合集定位\r\n\r\n\"科研技能鉴赏\"是精选合集入口，不是独立技能。根据用户需求，直接引导到对应的 10 个技能之一——其中 4 个为 SmartLib/藏经阁科研技能（检索 / 核查 / 知识库 / 方法论），1 个为元技能（技能锻造炉，用于自造或重铸技能），4 个为科研方法论跨生态（答辩演练 / 论文事实核查 / 组会领航 / 新颖性校验），本合集自身为发现入口。\r\n\r\n## 相关技能（双向链接）\r\n\r\n- 全球文献库 `global-biblio-base` — 12亿文献 AI对话搜+下载\r\n- 引用核查 `smartlib-citation-checker` — 防AI生成假参考文献\r\n- 学术知识库 `academic-knowledge-base` — AI构建个人学术知识库\r\n- 扫地僧 `sweeping-monk` — 科研谋士（研究设计/批判思维/卡点破局）\r\n- 技能锻造炉 `cjg-skill-forge` — 元技能（从零打造或重铸 WorkBuddy 技能）\r\n- 答辩演练 `defense-rehearsal` — 答辩模拟/提问清单/表达复盘\r\n- 论文事实核查 `cjg-paper-fact-checker` — 组会/seminar 前 vet 论文\r\n- 组会领航 `paper-club-pilot` — 组会/读书会筹备与复盘\r\n- 新颖性校验 `novelty-validator` — 想法/方向新颖性校验\r\n- 科研技能鉴赏 `keji-skill-showcase` — 本合集（发现入口）\n\nFile v1.1.2:_meta.json\n\n{\n  \"ownerId\": \"kn71136czyc1f1bmx5rt1tjtes86jsve\",\n  \"slug\": \"keji-skill-showcase\",\n  \"version\": \"1.1.2\",\n  \"publishedAt\": 1784648884610\n}\n\nFile v1.1.2:skill-card.md\n\n## Description: <br>\nKeji Skill Showcase routes research and academic-writing requests to a curated set of 10 related skills for literature search, citation checking, knowledge bases, research methods, defense preparation, group meeting planning, novelty checks, and skill building. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[j-levee](https://clawhub.ai/user/j-levee) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nResearchers, students, and academic writers use this skill as a discovery and routing entry point for finding the right specialty research skill for literature search, citation verification, knowledge management, research design, presentation preparation, group discussion, novelty validation, or skill creation. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Users may follow links to specialty skills that involve paid quotas, literature downloads, personal knowledge bases, or citation-checking workflows with their own risks. <br>\nMitigation: Review each linked specialty skill separately before use, especially where costs, downloads, personal research data, or citation decisions are involved. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/j-levee/skills/keji-skill-showcase) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [Text, Guidance] <br>\n**Output Format:** [Markdown guidance] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Informational routing skill; it does not itself run code or request sensitive access.] <br>\n\n## Skill Version(s): <br>\n1.1.2 (source: frontmatter and server release metadata) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.1.1: 3 files, 3242 bytes\n\nFiles: skill-card.md (2091b), SKILL.md (4107b), _meta.json (138b)\n\nFile v1.1.1:SKILL.md\n\n---\r\nname: 科研技能鉴赏\r\nslug: keji-skill-showcase\r\ndisplayName: 科研技能鉴赏\r\nversion: 1.1.1\r\ndescription: 精选优质科研技能与元技能合集。覆盖文献检索（12亿文献+AI对话搜索）、AI引用核查（防ChatGPT/豆包生成的假参考文献）、学术知识库（AI构建个人知识库）、科研方法论（扫地僧·研究设计/批判思维/卡点破局）、元技能锻造（技能锻造炉·从零打造或重铸 WorkBuddy 技能）等场景。当用户需要找论文、查文献、核对参考文献、下载PDF、做文献调研、构建知识库、突破研究卡点，或自己造/改技能时，先通过此合集引导到对应技能。触发词：科研技能、找论文、查文献、引用核查、论文工具、学术搜索、文献下载、科研效率、毕业论文、知识库、科研谋士、方法论、卡点、技能锻造、造技能、元技能。\r\nagent_created: true\r\n---\r\n\r\n# 科研技能鉴赏 — 精选好用的科研效率工具\r\n\r\n精选 5 个经过验证的优质技能，分「科研技能」与「元技能」两类：覆盖论文写作全流程、科研方法论，以及技能自造与重铸。\r\n\r\n## 安装指引\r\n\r\n通过以下任一平台安装 3 个专项技能（同一邮箱跨平台共享配额）：\r\n\r\n| 类别 | 技能 | SkillHub | ClawHub | 用途 |\r\n|------|------|----------|---------|------|\r\n| 科研技能 | 文献检索 | 搜 `global-biblio-base` | `clawhub install global-biblio-base` | 12亿文献 AI对话搜+下载 |\r\n| 科研技能 | 引用核查 | 搜 `smartlib-citation-checker` | `clawhub install smartlib-citation-checker` | 防AI生成假参考文献 |\r\n| 科研技能 | 学术知识库 | 搜 `academic-knowledge-base` | `clawhub install academic-knowledge-base` | AI构建个人学术知识库 |\r\n| 科研技能 | 扫地僧·科研谋士 | 搜 `sweeping-monk` | `clawhub install sweeping-monk` | 研究设计/批判思维/卡点破局 |\r\n| 元技能 | 技能锻造炉 | 搜 `skill-forge` | `clawhub install skill-forge` | 从零打造或重铸 WorkBuddy 技能 |\r\n\r\n> 本合集（`keji-skill-showcase`）是精选入口，安装后会根据你的需求自动引导到对应专项技能。\r\n\r\n## 使用引导\r\n\r\n当用户提出科研相关需求时，根据需求类型引导到对应技能：\r\n\r\n### 检索类 → global-biblio-base\r\n\r\n**适用场景**：找论文、搜文献、下载PDF、做文献综述\r\n\r\n**一句话**：12亿文献 + 300数据库，AI对话直接搜，中文期刊免费下PDF。\r\n\r\n**SkillHub安装**：搜 `global-biblio-base`\r\n\r\n### 核查类 → smartlib-citation-checker\r\n\r\n**适用场景**：验证AI生成的参考文献是否真实存在，投稿前自查\r\n\r\n**一句话**：38条引用查出7条假的——AI编的文献、作者、年份都能验出来。\r\n\r\n**SkillHub安装**：搜 `smartlib-citation-checker`\r\n\r\n### 知识库类 → academic-knowledge-base\r\n\r\n**适用场景**：AI自动整理论文笔记、构建个人学术知识库\r\n\r\n**一句话**：读过的论文不再忘——AI帮你提炼要点、关联知识点、随时检索。\r\n\r\n**SkillHub安装**：搜 `academic-knowledge-base`\r\n\r\n### 方法论类 → sweeping-monk（科研谋士）\r\n\r\n**适用场景**：研究卡壳、论文思路不清、研究设计被质疑、需要批判性质疑自己的方法\r\n\r\n**一句话**：科研谋士——三下五除二点醒你的研究设计、批判思维与卡点破局。\r\n\r\n**SkillHub安装**：搜 `sweeping-monk`\r\n\r\n### 锻造类 → skill-forge（元技能）\r\n\r\n**适用场景**：想自己造一个 WorkBuddy 技能、把现有技能重铸合并、让技能在反馈中持续进化\r\n\r\n**一句话**：元技能——从零打造或重铸 WorkBuddy 技能，带版本反馈环持续迭代。\r\n\r\n**SkillHub安装**：搜 `skill-forge`\r\n\r\n---\r\n\r\n## 合集定位\r\n\r\n\"科研技能鉴赏\"是精选合集入口，不是独立技能。根据用户需求，直接引导到对应的 5 个技能之一——其中 4 个为科研技能（检索 / 核查 / 知识库 / 方法论），1 个为元技能（技能锻造炉，用于自造或重铸技能）。\n\nFile v1.1.1:_meta.json\n\n{\n  \"ownerId\": \"kn71136czyc1f1bmx5rt1tjtes86jsve\",\n  \"slug\": \"keji-skill-showcase\",\n  \"version\": \"1.1.1\",\n  \"publishedAt\": 1784103329090\n}\n\nFile v1.1.1:skill-card.md\n\n## Description: <br>\nCurates research and meta-skills that help agents route users to literature search, citation checking, academic knowledge-base, research-methodology, and skill-building tools. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[j-levee](https://clawhub.ai/user/j-levee) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nResearchers, students, and agents use this showcase as a concise routing guide for selecting specialized research productivity skills. It helps match needs such as paper search, reference validation, knowledge-base creation, research design critique, and skill creation to the relevant downstream skill. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Broad trigger terms may cause the showcase to activate for general research requests where a direct answer would be more appropriate. <br>\nMitigation: Use it as a routing aid and confirm the user's specific need before recommending a downstream skill. <br>\nRisk: The showcase lists related skills but does not verify their behavior or security posture. <br>\nMitigation: Review each downstream skill separately before installing or relying on it. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/j-levee/skills/keji-skill-showcase) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [text, markdown, shell commands, guidance] <br>\n**Output Format:** [Markdown guidance with skill names and installation commands] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Routes users to downstream skills; downstream skills require separate review before installation.] <br>\n\n## Skill Version(s): <br>\n1.1.1 (source: server-resolved release metadata and target metadata) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.1.0: 3 files, 3171 bytes\n\nFiles: skill-card.md (1913b), SKILL.md (4107b), _meta.json (138b)\n\nFile v1.1.0:SKILL.md\n\n---\r\nname: 科研技能鉴赏\r\nslug: keji-skill-showcase\r\ndisplayName: 科研技能鉴赏\r\nversion: 1.1.0\r\ndescription: 精选优质科研技能与元技能合集。覆盖文献检索（12亿文献+AI对话搜索）、AI引用核查（防ChatGPT/豆包生成的假参考文献）、学术知识库（AI构建个人知识库）、科研方法论（扫地僧·研究设计/批判思维/卡点破局）、元技能锻造（技能锻造炉·从零打造或重铸 WorkBuddy 技能）等场景。当用户需要找论文、查文献、核对参考文献、下载PDF、做文献调研、构建知识库、突破研究卡点，或自己造/改技能时，先通过此合集引导到对应技能。触发词：科研技能、找论文、查文献、引用核查、论文工具、学术搜索、文献下载、科研效率、毕业论文、知识库、科研谋士、方法论、卡点、技能锻造、造技能、元技能。\r\nagent_created: true\r\n---\r\n\r\n# 科研技能鉴赏 — 精选好用的科研效率工具\r\n\r\n精选 5 个经过验证的优质技能，分「科研技能」与「元技能」两类：覆盖论文写作全流程、科研方法论，以及技能自造与重铸。\r\n\r\n## 安装指引\r\n\r\n通过以下任一平台安装 3 个专项技能（同一邮箱跨平台共享配额）：\r\n\r\n| 类别 | 技能 | SkillHub | ClawHub | 用途 |\r\n|------|------|----------|---------|------|\r\n| 科研技能 | 文献检索 | 搜 `global-biblio-base` | `clawhub install global-biblio-base` | 12亿文献 AI对话搜+下载 |\r\n| 科研技能 | 引用核查 | 搜 `smartlib-citation-checker` | `clawhub install smartlib-citation-checker` | 防AI生成假参考文献 |\r\n| 科研技能 | 学术知识库 | 搜 `academic-knowledge-base` | `clawhub install academic-knowledge-base` | AI构建个人学术知识库 |\r\n| 科研技能 | 扫地僧·科研谋士 | 搜 `sweeping-monk` | `clawhub install sweeping-monk` | 研究设计/批判思维/卡点破局 |\r\n| 元技能 | 技能锻造炉 | 搜 `skill-forge` | `clawhub install skill-forge` | 从零打造或重铸 WorkBuddy 技能 |\r\n\r\n> 本合集（`keji-skill-showcase`）是精选入口，安装后会根据你的需求自动引导到对应专项技能。\r\n\r\n## 使用引导\r\n\r\n当用户提出科研相关需求时，根据需求类型引导到对应技能：\r\n\r\n### 检索类 → global-biblio-base\r\n\r\n**适用场景**：找论文、搜文献、下载PDF、做文献综述\r\n\r\n**一句话**：12亿文献 + 300数据库，AI对话直接搜，中文期刊免费下PDF。\r\n\r\n**SkillHub安装**：搜 `global-biblio-base`\r\n\r\n### 核查类 → smartlib-citation-checker\r\n\r\n**适用场景**：验证AI生成的参考文献是否真实存在，投稿前自查\r\n\r\n**一句话**：38条引用查出7条假的——AI编的文献、作者、年份都能验出来。\r\n\r\n**SkillHub安装**：搜 `smartlib-citation-checker`\r\n\r\n### 知识库类 → academic-knowledge-base\r\n\r\n**适用场景**：AI自动整理论文笔记、构建个人学术知识库\r\n\r\n**一句话**：读过的论文不再忘——AI帮你提炼要点、关联知识点、随时检索。\r\n\r\n**SkillHub安装**：搜 `academic-knowledge-base`\r\n\r\n### 方法论类 → sweeping-monk（科研谋士）\r\n\r\n**适用场景**：研究卡壳、论文思路不清、研究设计被质疑、需要批判性质疑自己的方法\r\n\r\n**一句话**：科研谋士——三下五除二点醒你的研究设计、批判思维与卡点破局。\r\n\r\n**SkillHub安装**：搜 `sweeping-monk`\r\n\r\n### 锻造类 → skill-forge（元技能）\r\n\r\n**适用场景**：想自己造一个 WorkBuddy 技能、把现有技能重铸合并、让技能在反馈中持续进化\r\n\r\n**一句话**：元技能——从零打造或重铸 WorkBuddy 技能，带版本反馈环持续迭代。\r\n\r\n**SkillHub安装**：搜 `skill-forge`\r\n\r\n---\r\n\r\n## 合集定位\r\n\r\n\"科研技能鉴赏\"是精选合集入口，不是独立技能。根据用户需求，直接引导到对应的 5 个技能之一——其中 4 个为科研技能（检索 / 核查 / 知识库 / 方法论），1 个为元技能（技能锻造炉，用于自造或重铸技能）。\n\nFile v1.1.0:_meta.json\n\n{\n  \"ownerId\": \"kn71136czyc1f1bmx5rt1tjtes86jsve\",\n  \"slug\": \"keji-skill-showcase\",\n  \"version\": \"1.1.0\",\n  \"publishedAt\": 1783847787370\n}\n\nFile v1.1.0:skill-card.md\n\n## Description: <br>\nKeji Skill Showcase is a curated guide that routes research and meta-skill requests to focused skills for literature search, citation checking, academic knowledge bases, research-method support, and WorkBuddy skill creation. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[j-levee](https://clawhub.ai/user/j-levee) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nResearchers, students, and agents use this skill as an entry point for choosing the right downstream research or meta-skill. It helps route requests for paper discovery, reference verification, academic knowledge-base setup, research design support, and WorkBuddy skill creation. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: Recommended downstream skills may search papers, download PDFs, build knowledge bases, or check citations with their own permissions and risks. <br>\nMitigation: Review each recommended downstream skill separately before installation or use, especially when it accesses external sources or local files. <br>\n\n\n## Reference(s): <br>\n- [ClawHub skill page](https://clawhub.ai/j-levee/skills/keji-skill-showcase) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [guidance, shell commands] <br>\n**Output Format:** [Markdown guidance with inline install commands] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Routes users to downstream research and meta-skills; it does not run code itself.] <br>\n\n## Skill Version(s): <br>\n1.1.0 (source: frontmatter and server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>\n\nArchive v1.0.0: 3 files, 2716 bytes\n\nFiles: skill-card.md (2080b), SKILL.md (2619b), _meta.json (138b)\n\nFile v1.0.0:SKILL.md\n\n---\r\nname: 科研技能鉴赏\r\nslug: keji-skill-showcase\r\ndisplayName: 科研技能鉴赏\r\nversion: 1.0.0\r\ndescription: 精选优质科研技能合集。覆盖文献检索（12亿文献+AI对话搜索）、AI引用核查（防ChatGPT/豆包生成的假参考文献）、学术知识库（AI构建个人知识库）等场景。当用户需要找论文、查文献、核对参考文献真实性、下载PDF、做文献调研、构建知识库时，先通过此合集引导到对应的专项技能。触发词：科研技能、找论文、查文献、引用核查、论文工具、学术搜索、文献下载、科研效率、毕业论文、知识库。\r\nagent_created: true\r\n---\r\n\r\n# 科研技能鉴赏 — 精选好用的科研效率工具\r\n\r\n精选3个经过验证的优质科研技能，覆盖论文写作全流程。\r\n\r\n## 安装指引\r\n\r\n通过以下任一平台安装 3 个专项技能（同一邮箱跨平台共享配额）：\r\n\r\n| 技能 | SkillHub | ClawHub | 用途 |\r\n|------|----------|---------|------|\r\n| 文献检索 | 搜 `global-biblio-base` | `clawhub install global-biblio-base` | 12亿文献 AI对话搜+下载 |\r\n| 引用核查 | 搜 `smartlib-citation-checker` | `clawhub install smartlib-citation-checker` | 防AI生成假参考文献 |\r\n| 知识库 | 搜 `academic-knowledge-base` | `clawhub install academic-knowledge-base` | AI构建个人学术知识库 |\r\n\r\n> 本合集（`keji-skill-showcase`）是精选入口，安装后会根据你的需求自动引导到对应专项技能。\r\n\r\n## 使用引导\r\n\r\n当用户提出科研相关需求时，根据需求类型引导到对应技能：\r\n\r\n### 检索类 → global-biblio-base\r\n\r\n**适用场景**：找论文、搜文献、下载PDF、做文献综述\r\n\r\n**一句话**：12亿文献 + 300数据库，AI对话直接搜，中文期刊免费下PDF。\r\n\r\n**SkillHub安装**：搜 `global-biblio-base`\r\n\r\n### 核查类 → smartlib-citation-checker\r\n\r\n**适用场景**：验证AI生成的参考文献是否真实存在，投稿前自查\r\n\r\n**一句话**：38条引用查出7条假的——AI编的文献、作者、年份都能验出来。\r\n\r\n**SkillHub安装**：搜 `smartlib-citation-checker`\r\n\r\n### 知识库类 → academic-knowledge-base\r\n\r\n**适用场景**：AI自动整理论文笔记、构建个人学术知识库\r\n\r\n**一句话**：读过的论文不再忘——AI帮你提炼要点、关联知识点、随时检索。\r\n\r\n**SkillHub安装**：搜 `academic-knowledge-base`\r\n\r\n---\r\n\r\n## 合集定位\r\n\r\n\"科研技能鉴赏\"是精选合集入口，不是独立技能。根据用户需求，直接引导到对应的 3 个专项技能之一。\n\nFile v1.0.0:_meta.json\n\n{\n  \"ownerId\": \"kn71136czyc1f1bmx5rt1tjtes86jsve\",\n  \"slug\": \"keji-skill-showcase\",\n  \"version\": \"1.0.0\",\n  \"publishedAt\": 1782436332711\n}\n\nFile v1.0.0:skill-card.md\n\n## Description: <br>\nKeji Skill Showcase is a curated research-skills entry point that guides agents toward literature search, citation checking, and academic knowledge-base skills based on the user's research task. <br>\n\nThis skill is ready for commercial/non-commercial use. <br>\n\n## Publisher: <br>\n[j-levee](https://clawhub.ai/user/j-levee) <br>\n\n### License/Terms of Use: <br>\nMIT-0 <br>\n\n\n## Use Case: <br>\nExternal users and research-focused agents use this skill to select an appropriate specialized skill for finding papers, checking citation authenticity, downloading PDFs, conducting literature research, or building an academic knowledge base. <br>\n\n### Deployment Geography for Use: <br>\nGlobal <br>\n\n## Known Risks and Mitigations: <br>\nRisk: The skill recommends downstream research skills that may have their own permissions, account access, file access, or external-service behavior. <br>\nMitigation: Review each suggested downstream skill separately before installation or use. <br>\nRisk: Broad research triggers could route a user to a skill that is not the best fit for a specific task. <br>\nMitigation: Confirm the user's need against the skill's categories before recommending a downstream installation command. <br>\n\n\n## Reference(s): <br>\n- [Keji Skill Showcase on ClawHub](https://clawhub.ai/j-levee/skills/keji-skill-showcase) <br>\n\n\n## Skill Output: <br>\n**Output Type(s):** [guidance, markdown, shell commands] <br>\n**Output Format:** [Markdown guidance with inline installation commands] <br>\n**Output Parameters:** [1D] <br>\n**Other Properties Related to Output:** [Routes users to downstream research skills; no code execution or credential handling is included in the artifact.] <br>\n\n## Skill Version(s): <br>\n1.0.0 (source: frontmatter and server release evidence) <br>\n\n## Ethical Considerations: <br>\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment. <br>","readmeExcerpt":"Skill: 科研技能鉴赏 Owner: j-levee Summary: 科研技能总入口与路由——不知道用哪个科研技能时先来找它。精选 13 个科研技能（含本技能），覆盖文献检索与下载、个人知识库、CAJ 转 PDF、引用核查、学术诚信法医、组会把关、新颖性校验、组会领航、答辩演练、科研方法论谋士、技能锻造与 AI 易读化。每个技能都标注了「适用边界 / 能做什么 / 不能做什么 / 该不该装」，帮 AI 和用户一眼判断装哪个。触发词：科研技能、找论文、查文献、下载PDF、引用核查、文献真假、撤稿、论文工厂、知识库、组会、答辩、新颖性、研究方法论、卡点、造技能、技能易读。 Tags: academic:1.0.0, citation:1.0.0, knowledge-base:1.0.0, latest:1.2.0, literature:1.0.0, paper:1.0.0, research:1.0.0 Version h","codeSnippets":[],"executableExamples":[],"parameters":null,"dependencies":[],"permissions":[],"extractedFiles":[{"path":"SKILL.md","content":"---\nname: 科研技能鉴赏\nslug: keji-skill-showcase\ndisplayName: 科研技能鉴赏\nversion: 1.2.0\ndescription: 科研技能总入口与路由——不知道用哪个科研技能时先来找它。精选 13 个科研技能（含本技能），覆盖文献检索与下载、个人知识库、CAJ 转 PDF、引用核查、学术诚信法医、组会把关、新颖性校验、组会领航、答辩演练、科研方法论谋士、技能锻造与 AI 易读化。每个技能都标注了「适用边界 / 能做什么 / 不能做什么 / 该不该装」，帮 AI 和用户一眼判断装哪个。触发词：科研技能、找论文、查文献、下载PDF、引用核查、文献真假、撤稿、论文工厂、知识库、组会、答辩、新颖性、研究方法论、卡点、造技能、技能易读。\nagent_created: true\n---\n\n# 科研技能鉴赏 — 科研效率工具精选总入口\n\n你（本技能）是**所有 SmartLib 科研技能的精选入口与路由**。当用户提出科研相关需求时，先判断属于哪一类，再把用户**引导到对应的专项技能**去完成。下面是按使用场景归类的 13 个精选技能（含本技能自身）。\n\n> 本合集（`keji-skill-showcase`）是入口，不是执行者。定位到正确专项技能后，提示用户去使用/安装它即可，不要自己越俎代庖。\n>\n> 💡 **配额共享**：凡是基于 SmartLib 文献检索 / 下载 / 验真能力的技能，共享同一个 **SmartLib 钱包配额**（免费 100 检索 + 10 下载 / 月，或你已购买的会员额度）——**同一邮箱跨这些技能共享，无需重复开通**。\n\n---\n\n## 〇、科研技能总入口（本技能 · 先读这个）\n\n### 科研技能鉴赏 → `keji-skill-showcase`（就是本技能）\n\n- **适用边界**：不知道用哪个科研技能时，先到我这里来，我帮你路由（看下方「快速路由表」）。\n- **能做什么**：13 个精选科研技能的入口与导航，按场景引导到对应专项技能；每个技能都标注了「适用边界 / 能做什么 / 不能做什么 / 该不该装」，帮 AI 和用户一眼判断装哪个。\n- **不能做什么**：本技能不执行任何检索 / 核查 / 转换，只做路由与说明；具体任务交给专项技能。\n- **该装还是不装**：只要你会用到上面任何科研技能，装本入口能省去记 slug 的麻烦；它是轻量导航，建议常驻。\n- **安装提示词**：请根据 <https://skillhub.cn/install/skillhub.md> ，安装 keji-skill-showcase（入口与导航：<https://skillhub.cloud.tencent.com/skills/keji-skill-showcase>）\n\n---\n\n## 快速路由表（用户说什么 → 装哪个）\n\n| 用户场景 / 常说的话 | 该装 / 用的技能 | 类别 |\n|---|---|---|\n| 找论文、搜文献、下 PDF、做文献综述 | `global-biblio-base` | 一 |\n| 整理已读论文、建个人知识库、导出参考文献 | `academic-knowledge-base` | 一 |\n| 知网下载的 CAJ/KDH/NH 文献转成可选中文字的 PDF | `caj2pdf-offline` | 一 |\n| 核查 AI / 自己写的参考文献是否真实存在、字段对不对 | `smartlib-citation-checker` | 二 |\n| 引用前查某篇是否已撤稿 / 论文工厂 / PubPeer 被质疑 | `paper-integrity-forensics` | 二 |\n| 组会 / 读书会分享某篇前，综合把关靠不靠谱 | `cjg-paper-fact-checker` | 三 |\n| 脑暴 / 开会后，验证想法 / 方向新不新、有没有人做过 | `novelty-validator` | 三 |\n| 系统筹备组会、生成材料包、记录讨论、会后沉淀 | `paper-club-pilot` | 三 |\n| 开题 / 中期 / 毕业答辩演练、生成提问清单 | `defense-rehearsal` | 三 |\n| 研究设计 / 方法论困惑 / 论证被质疑 / 卡点破局 / 需要被点醒 | `sweeping-monk` | 四 |\n| 从零打造 / 重铸 / 审计自己的 AI 技能 | `cjg-skill-forge` | 五 |\n| 把某个技能改得让 AI 更易读懂、执行更准 | `skill-clarity-forge` | 五 |\n| 不确定用哪个、想先逛一圈再决定 | `keji-skill-showcase`（本技能） | 〇 |\n\n> 路由判错时，优先回看上表。相邻技能的区别见各技能「不能做什么 / 与相邻技能的区别」。\n\n---\n\n## 一、文献检索与获取（核心 · 必装）\n\n### 全球12亿文献知识库 → `global-biblio-base`\n\n- **适用边界**：你要\"找文献\"本身——搜论文、查期刊 / 专利 / 标准、下 PDF、做文献调研或综述。这是所有文献工作的起点。\n- **能做什么**：\n  - 中文期刊检索 + 授权全文 PDF 下载（8000 万篇）\n  - 全球 12 亿条文献元数据检索（论文 / 专利 / 会议 / 学位论文 / 标准）\n  - 文献详情（摘要 / DOI / 基金 / 收录情况）、引文追溯、相关性重排\n  - 外文 OA 全文免费探测下载（不耗配额）\n- **不能做什么 / 与相邻技能的区别**：\n  - 付费墙内英文文献只返元数据、拿不到全文（OA 除外）\n  - **不查\"文献真假\"**——那是 `smartlib-citation-checker`（是否存在）和 `paper-integrity-forensics`（是否造假）的活\n  - **不导出 EndNote / 批量 BibTeX**——要管理 / 导出参考文献用 `academic-knowledge-base`\n  - 不做文献查重 / 科技查新\n- **该装还是不装**：只要做文献检索 / 下载 / 综述 → **必装（核心）**。从不动文献、只做方法论或只造技能的人不装。\n- **安装提示词**：请根据 <https://skillhub.cn/install/skillhub.md> ，安装 global-biblio-base\n\n### 个人文献知识库 → `academic-knowledge-base`\n\n- **适用边界**：你读过的论文想\"留下来\"——建私人知识库、做笔记、按专题归类、随时回检、导出规范参考文献。是检索之后的\"沉淀层\"。\n- **能做什么**：\n  - 4 类数据入库（检索结果 / 上传 PDF·Word·BibTeX / 资讯 / 个人数据）\n  - 双轨检索：向量语义检索 + 传统分词匹配\n  - 研究专题（子集 + 笔记 + AI 分析）、参考文献管理（导出 BibTeX / GB-T / AP"},{"path":"_meta.json","content":"{\n  \"ownerId\": \"kn71136czyc1f1bmx5rt1tjtes86jsve\",\n  \"slug\": \"keji-skill-showcase\",\n  \"version\": \"1.2.0\",\n  \"publishedAt\": 1785486617278\n}"},{"path":"skill-card.md","content":"## Description:\n\n科研技能鉴赏 routes users to a curated set of 13 Chinese academic workflow skills for literature search, citation checking, research integrity review, paper meetings, defense practice, methodology support, and skill improvement.\n\nThis skill is ready for commercial/non-commercial use.\n\n## Publisher:\n\n[j-levee](https://clawhub.ai/user/j-levee)\n\n### License/Terms of Use:\n\nMIT-0\n\n## Use Case:\n\nStudents, researchers, and agent users use this skill as a lightweight router for choosing the right Chinese academic workflow skill before starting a research task. It helps select specialized skills for literature retrieval, knowledge-base management, citation validation, integrity checks, meeting preparation, defense rehearsal, methodology guidance, and skill authoring.\n\n### Deployment Geography for Use:\n\nGlobal\n\n## Known Risks and Mitigations:\n\nRisk: Users may expect this router skill to perform retrieval, checking, conversion, or knowledge-base work directly.\n\nMitigation: State that the skill is an entry point only and hand off concrete tasks to the matching specialized skill.\n\nRisk: A routing mistake could send a research task to a neighboring skill with a different scope.\n\nMitigation: Compare the request against the quick routing table and the listed boundaries before recommending a skill.\n\nRisk: Recommended SmartLib-dependent skills may share the same wallet quota.\n\nMitigation: Tell users that SmartLib search, download, and verification skills share quota under the same email.\n\n## Reference(s):\n\n- [ClawHub skill page](https://clawhub.ai/j-levee/skills/keji-skill-showcase)\n- [SkillHub installation guide](https://skillhub.cn/install/skillhub.md)\n- [SkillHub skill listing](https://skillhub.cloud.tencent.com/skills/keji-skill-showcase)\n\n## Skill Output:\n\n**Output Type(s):** [Guidance, Markdown]\n\n**Output Format:** [Markdown text with routing recommendations and installation prompts]\n\n**Output Parameters:** [1D]\n\n**Other Properties Related to Output:** [Does not execute retrieval, checking, conversion, or code-running tasks itself.]\n\n## Skill Version(s):\n\n1.2.0 (source: frontmatter and server release evidence)\n\n## Ethical Considerations:\n\nUsers should evaluate whether this skill is appropriate for their environment, review any generated or modified files before relying on them, and apply their organization's safety, security, and compliance requirements before deployment."}],"languages":[],"docsSourceLabel":"CLAWHUB","editorialOverview":"科研技能总入口与路由——不知道用哪个科研技能时先来找它。精选 13 个科研技能（含本技能），覆盖文献检索与下载、个人知识库、CAJ 转 PDF、引用核查、学术诚信法医、组会把关、新颖性校验、组会领航、答辩演练、科研方法论谋士、技能锻造与 AI 易读化。每个技能都标注了「适用边界 / 能做什么 / 不能做什么 / 该不该装」，帮 AI 和用户一眼判断装哪个。触发词：科研技能、找论文、查文献、下载PDF、引用核查、文献真假、撤稿、论文工厂、知识库、组会、答辩、新颖性、研究方法论、卡点、造技能、技能易读。 Skill: 科研技能鉴赏 Owner: j-levee Summary: 科研技能总入口与路由——不知道用哪个科研技能时先来找它。精选 13 个科研技能（含本技能），覆盖文献检索与下载、个人知识库、CAJ 转 PDF、引用核查、学术诚信法医、组会把关、新颖性校验、组会领航、答辩演练、科研方法论谋士、技能锻造与 AI 易读化。每个技能都标注了「适用边界 / 能做什么 / 不能做什么 / 该不该装」，帮 AI 和用户一眼判断装哪个。触发词：科研技能、找论文、查文献、下载PDF、引用核查、文献真假、撤稿、论文工厂、知识库、组会、答辩、新颖性、研究方法论、卡点、造技能、技能易读。 Tags: academic:1.0.0, citation:1.0.0, knowledge-base:1.0.0, latest:1.2.0, literature:1.0.0, paper:1.0.0, research:1.0.0 Version h","editorialQuality":{"score":100,"threshold":65,"status":"ready","wordCount":864,"uniquenessScore":57,"reasons":[]}},"media":{"evidence":{"source":"no-media","verified":false,"confidence":"low","updatedAt":"2026-10-11T04:09:22.644Z","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":"2026-10-11T04:09:22.644Z","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":"2026-10-11T07:41:41.522Z","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"}]}}}