[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-minimax-claim-check":3,"mdc--ke9y6j-key":34,"related-org-minimax-claim-check":931,"related-repo-minimax-claim-check":1134},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":23,"repoUrl":24,"updatedAt":25,"license":26,"forks":27,"topics":28,"repo":29,"sourceUrl":32,"mdContent":33},"claim-check","verify research claims against evidence","当需要检查论文草稿中的事实性论断是否有证据支撑、做引用-论断对齐审计、 找出没有出处的陈述、核对文内引用是否真能支撑所在句子时加载使用； 通常由 evidence-loop 或审稿类流程调用，不直接面向用户。同义场景： 论断支撑检查、claim 支撑审计、无支撑断言排查、证据覆盖检查、 引用与论断对齐、\"这段话有没有文献撑\"\"哪些说法没有引用\"。",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},"minimax","MiniMax","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fminimax.jpg","MiniMax-AI",[13,17,20],{"name":14,"slug":15,"type":16},"Research","research","tag",{"name":18,"slug":19,"type":16},"Audit","audit",{"name":21,"slug":22,"type":16},"Code Analysis","code-analysis",5,"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMiniMax-Code-Plugins","2026-08-21T03:59:02.154691",null,2,[],{"repoUrl":24,"stars":23,"forks":27,"topics":30,"description":31},[],"Community registry and contribution toolkit for MiniMax Code plugins.","https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMiniMax-Code-Plugins\u002Ftree\u002FHEAD\u002Fplugins\u002FHylouis233\u002Fopenscience\u002Fskills\u002Fclaim-check","---\nname: claim-check\ndescription: >-\n  当需要检查论文草稿中的事实性论断是否有证据支撑、做引用-论断对齐审计、\n  找出没有出处的陈述、核对文内引用是否真能支撑所在句子时加载使用；\n  通常由 evidence-loop 或审稿类流程调用，不直接面向用户。同义场景：\n  论断支撑检查、claim 支撑审计、无支撑断言排查、证据覆盖检查、\n  引用与论断对齐、\"这段话有没有文献撑\"\"哪些说法没有引用\"。\nuser-invocable: false\nmetadata:\n  domains: [verification]\n  last_reviewed: '2026-08-18'\n---\n\n# claim-check：正文 claim 支撑检查\n\n## 目的\n\n从论文草稿中抽取事实性 claim，逐条映射其支撑来源（文内文献引用 \u002F\nEvidenceItem \u002F 实验数据 \u002F 无支撑），产出无支撑 claim 清单与结构化审查结论。\n\n本技能只回答一个问题：「这句话有没有东西撑着？」\n不回答「这句话写得好不好、有没有价值」。\n\n## 前置检查\n\n1. 草稿文件存在且可读（`.md` \u002F `.tex` \u002F 纯文本）。\n2. 如存在上游产物，一并读取用于交叉核对：\n   - `output\u002Fliterature-search\u002F\u003Cslug>\u002Flatest\u002Fpapers.json`（文献库）；\n   - `output\u002Fliterature-survey\u002F\u003Cslug>\u002Flatest\u002Fevidence.json`（EvidenceItem 库）。\n3. 计算 slug，规则与上游技能一致：主题字符串做 Unicode NFKC 规范化、\n   转小写、去首尾空白、连续空白折叠为单个空格后，取 sha1 十六进制摘要\n   前 8 位。\n\n## 操作规程\n\n### 1. 切分与抽取\n\n- 按「节 → 段 → 句」切分草稿，跳过参考文献节、附录、致谢。\n- 抽取事实性 claim：关于外部世界、可被证伪的陈述。典型标志：\n  断言某方法优于另一方法、某现象普遍存在、某指标达到某数值、\n  「已有研究表明……」「X 已被广泛用于……」等。\n- 明确排除三类句子，不进入支撑检查：\n  - 观点与立场（「我们认为该方向很有前景」）；\n  - 方法描述（「本文采用三层卷积网络」——描述自己的做法，而非外部事实）；\n  - 数学定义、符号约定与纯过渡句。\n\n### 2. 支撑映射\n\n对每条事实性 claim，按以下优先级寻找支撑：\n\n1. **文献引用**：句内或句末存在文内引用标记（`[12]`、citekey、\n   `(Author, 2023)`）。若存在 papers.json，核对被引对象确实在文献库中；\n   不在则记 error（无源引用）。\n2. **EvidenceItem**：evidence.json 中存在 paper_id 匹配、且 quote 语义能\n   覆盖该 claim 的条目。\n3. **实验数据**：claim 明确指向本文自身的图 \u002F 表 \u002F 实验小节\n   （「如表 2 所示」「图 3 表明」）。\n4. **无支撑**：以上均无。\n\n### 3. 无支撑 claim 清单\n\n对每条无支撑 claim 记录：\n\n- 位置：节标题 + 段落序号 + 句序号；\n- claim 原文（逐字引用，不改写、不润色）；\n- 所需证据类型：文献引用 \u002F 实验数据 \u002F 统计数据；\n- 建议检索关键词（2-4 个英文词，供 evidence-loop 生成定向补检 query）。\n\n### 4. 输出与落盘\n\n- 目录：`output\u002Fclaim-check\u002F\u003Cslug>\u002Flatest\u002F`，写入 `unsupported-claims.md`\n  与 `review.json`。\n- 结论同时以 ```review 块输出，`check` 字段固定为 `citation`：\n  - 无支撑事实 claim → level `warn`；若属于关键论断（方法比较、性能断言、\n    领域定论类）可升为 `error`；\n  - 引用了文献库中不存在的 paper_id \u002F 编号 → level `error`（无源引用）；\n  - 有支撑的 claim 不逐条列出，只在统计条目中体现。\n\n### 5. claim 分类示例（抽取时的判定参照）\n\n| 例句 | 分类 | 是否检查 |\n| --- | --- | --- |\n| \"BERT 在 GLUE 基准上取得了当时最优结果\" | 事实性 claim | 是 |\n| \"实验表明本文方法比基线高 2.3 个点\" | 事实性 claim（支撑类型：实验数据） | 是 |\n| \"该数据集已被广泛用于公平性研究\" | 事实性 claim | 是 |\n| \"X 方法是 Y 任务的当前主流方案\" | 事实性 claim | 是 |\n| \"我们认为多模态是最有前景的方向\" | 观点立场 | 否 |\n| \"本文采用三层 BiLSTM 编码句子\" | 方法描述 | 否 |\n| \"令 x 表示输入序列\" | 定义约定 | 否 |\n\n判定拿不准时按「保守纳入」处理：宁可误报一条无支撑 claim，也不漏检。\n抽取粒度以「句」为最小单位；一句含多个独立事实断言时拆成多条 claim。\n\n### 6. 结果优先级\n\n- 先报 error（无源引用），再报 warn（无支撑 claim），最后给统计；\n- 同一位置的多个问题合并为一条，evidence 中注明「同处 N 个问题」；\n- 全部有支撑时也要输出一条 ok 级统计，避免「无输出 = 未检查」的歧义；\n- 支撑覆盖率低于 80% 时，在最终回复中明确提示「证据基础偏弱」；\n- 每条 warn \u002F error 的 title 必须含可定位信息（节名或编号），\n  禁止只写「存在问题」之类的空泛表述。\n\n## 输出模板\n\n清单文件开头附统计头：\n\n```markdown\n# claim-check 报告：\u003Cslug>\n- 事实性 claim：23 | 有支撑：20 | 无支撑：3 | 无源引用：1\n- 支撑覆盖率：87%\n```\n\n### 无支撑 claim 清单（unsupported-claims.md）\n\n| # | 位置 | claim 原文 | 所需证据类型 | 建议检索词 |\n| --- | --- | --- | --- | --- |\n| 1 | 引言 \u002F 段2 \u002F 句3 | \"已有研究表明该方法能将误差降低 30%\" | 文献引用 | error reduction; benchmark |\n| 2 | 相关工作 \u002F 段1 \u002F 句2 | \"现有方法普遍无法处理长序列\" | 文献引用 | long sequence; limitation |\n\n### review 块\n\n```review\n[\n  {\"level\": \"warn\", \"check\": \"citation\", \"title\": \"引言段2存在无支撑 claim\",\n   \"evidence\": \"“已有研究表明该方法能将误差降低 30%” 无文内引用、无 EvidenceItem\",\n   \"note\": \"需要文献引用；建议检索：error reduction benchmark\"},\n  {\"level\": \"error\", \"check\": \"citation\", \"title\": \"无源引用 [17]\",\n   \"evidence\": \"文中引用编号 [17] 在参考文献表与 papers.json 中均无对应条目\",\n   \"note\": \"删除该引用标记或补充真实来源\"},\n  {\"level\": \"ok\", \"check\": \"citation\", \"title\": \"支撑覆盖统计\",\n   \"evidence\": \"事实性 claim 共 23 条，有支撑 20 条\", \"note\": \"覆盖率 87%\"}\n]\n```\n\n## 本技能不做什么\n\n- 不判断 claim 的学术价值、新颖性或表述优劣，只判支撑有无。\n- 不核验参考文献条目的元数据真伪（交给 citation-verify）。\n- 不主动检索新文献补证据（交给 evidence-loop）。\n- 不修改草稿；只产出清单与建议。\n- 不检查观点类、方法描述类、定义类句子。\n- 不检查图表内容本身的正确性，只确认「指向图表」的引用关系存在。\n\n## 收尾与下一步\n\n1. 汇总：事实性 claim 总数、支撑覆盖率、无支撑条数、无源引用条数，\n   回复中附 ```review 块。\n2. 指向 `output\u002Fclaim-check\u002F\u003Cslug>\u002Flatest\u002F` 产物。\n3. 下一步：无支撑条目较多时建议进入 evidence-loop 做定向补检；\n   无源引用请用户确认后删除或补源。\n4. 若支撑覆盖率为 100%，明确告知用户「本次未发现无支撑问题」，不留歧义。\n",{"data":35,"body":41},{"name":4,"description":6,"user-invocable":36,"metadata":37},false,{"domains":38,"last_reviewed":40},[39],"verification","2026-08-18",{"type":42,"children":43},"root",[44,53,59,65,70,75,138,143,150,186,192,197,257,263,268,291,297,391,397,549,554,560,588,593,598,654,660,751,757,852,857,890,895,925],{"type":45,"tag":46,"props":47,"children":49},"element","h1",{"id":48},"claim-check正文-claim-支撑检查",[50],{"type":51,"value":52},"text","claim-check：正文 claim 支撑检查",{"type":45,"tag":54,"props":55,"children":57},"h2",{"id":56},"目的",[58],{"type":51,"value":56},{"type":45,"tag":60,"props":61,"children":62},"p",{},[63],{"type":51,"value":64},"从论文草稿中抽取事实性 claim，逐条映射其支撑来源（文内文献引用 \u002F\nEvidenceItem \u002F 实验数据 \u002F 无支撑），产出无支撑 claim 清单与结构化审查结论。",{"type":45,"tag":60,"props":66,"children":67},{},[68],{"type":51,"value":69},"本技能只回答一个问题：「这句话有没有东西撑着？」\n不回答「这句话写得好不好、有没有价值」。",{"type":45,"tag":54,"props":71,"children":73},{"id":72},"前置检查",[74],{"type":51,"value":72},{"type":45,"tag":76,"props":77,"children":78},"ol",{},[79,102,133],{"type":45,"tag":80,"props":81,"children":82},"li",{},[83,85,92,94,100],{"type":51,"value":84},"草稿文件存在且可读（",{"type":45,"tag":86,"props":87,"children":89},"code",{"className":88},[],[90],{"type":51,"value":91},".md",{"type":51,"value":93}," \u002F ",{"type":45,"tag":86,"props":95,"children":97},{"className":96},[],[98],{"type":51,"value":99},".tex",{"type":51,"value":101}," \u002F 纯文本）。",{"type":45,"tag":80,"props":103,"children":104},{},[105,107],{"type":51,"value":106},"如存在上游产物，一并读取用于交叉核对：\n",{"type":45,"tag":108,"props":109,"children":110},"ul",{},[111,122],{"type":45,"tag":80,"props":112,"children":113},{},[114,120],{"type":45,"tag":86,"props":115,"children":117},{"className":116},[],[118],{"type":51,"value":119},"output\u002Fliterature-search\u002F\u003Cslug>\u002Flatest\u002Fpapers.json",{"type":51,"value":121},"（文献库）；",{"type":45,"tag":80,"props":123,"children":124},{},[125,131],{"type":45,"tag":86,"props":126,"children":128},{"className":127},[],[129],{"type":51,"value":130},"output\u002Fliterature-survey\u002F\u003Cslug>\u002Flatest\u002Fevidence.json",{"type":51,"value":132},"（EvidenceItem 库）。",{"type":45,"tag":80,"props":134,"children":135},{},[136],{"type":51,"value":137},"计算 slug，规则与上游技能一致：主题字符串做 Unicode NFKC 规范化、\n转小写、去首尾空白、连续空白折叠为单个空格后，取 sha1 十六进制摘要\n前 8 位。",{"type":45,"tag":54,"props":139,"children":141},{"id":140},"操作规程",[142],{"type":51,"value":140},{"type":45,"tag":144,"props":145,"children":147},"h3",{"id":146},"_1-切分与抽取",[148],{"type":51,"value":149},"1. 切分与抽取",{"type":45,"tag":108,"props":151,"children":152},{},[153,158,163],{"type":45,"tag":80,"props":154,"children":155},{},[156],{"type":51,"value":157},"按「节 → 段 → 句」切分草稿，跳过参考文献节、附录、致谢。",{"type":45,"tag":80,"props":159,"children":160},{},[161],{"type":51,"value":162},"抽取事实性 claim：关于外部世界、可被证伪的陈述。典型标志：\n断言某方法优于另一方法、某现象普遍存在、某指标达到某数值、\n「已有研究表明……」「X 已被广泛用于……」等。",{"type":45,"tag":80,"props":164,"children":165},{},[166,168],{"type":51,"value":167},"明确排除三类句子，不进入支撑检查：\n",{"type":45,"tag":108,"props":169,"children":170},{},[171,176,181],{"type":45,"tag":80,"props":172,"children":173},{},[174],{"type":51,"value":175},"观点与立场（「我们认为该方向很有前景」）；",{"type":45,"tag":80,"props":177,"children":178},{},[179],{"type":51,"value":180},"方法描述（「本文采用三层卷积网络」——描述自己的做法，而非外部事实）；",{"type":45,"tag":80,"props":182,"children":183},{},[184],{"type":51,"value":185},"数学定义、符号约定与纯过渡句。",{"type":45,"tag":144,"props":187,"children":189},{"id":188},"_2-支撑映射",[190],{"type":51,"value":191},"2. 支撑映射",{"type":45,"tag":60,"props":193,"children":194},{},[195],{"type":51,"value":196},"对每条事实性 claim，按以下优先级寻找支撑：",{"type":45,"tag":76,"props":198,"children":199},{},[200,227,237,247],{"type":45,"tag":80,"props":201,"children":202},{},[203,209,211,217,219,225],{"type":45,"tag":204,"props":205,"children":206},"strong",{},[207],{"type":51,"value":208},"文献引用",{"type":51,"value":210},"：句内或句末存在文内引用标记（",{"type":45,"tag":86,"props":212,"children":214},{"className":213},[],[215],{"type":51,"value":216},"[12]",{"type":51,"value":218},"、citekey、\n",{"type":45,"tag":86,"props":220,"children":222},{"className":221},[],[223],{"type":51,"value":224},"(Author, 2023)",{"type":51,"value":226},"）。若存在 papers.json，核对被引对象确实在文献库中；\n不在则记 error（无源引用）。",{"type":45,"tag":80,"props":228,"children":229},{},[230,235],{"type":45,"tag":204,"props":231,"children":232},{},[233],{"type":51,"value":234},"EvidenceItem",{"type":51,"value":236},"：evidence.json 中存在 paper_id 匹配、且 quote 语义能\n覆盖该 claim 的条目。",{"type":45,"tag":80,"props":238,"children":239},{},[240,245],{"type":45,"tag":204,"props":241,"children":242},{},[243],{"type":51,"value":244},"实验数据",{"type":51,"value":246},"：claim 明确指向本文自身的图 \u002F 表 \u002F 实验小节\n（「如表 2 所示」「图 3 表明」）。",{"type":45,"tag":80,"props":248,"children":249},{},[250,255],{"type":45,"tag":204,"props":251,"children":252},{},[253],{"type":51,"value":254},"无支撑",{"type":51,"value":256},"：以上均无。",{"type":45,"tag":144,"props":258,"children":260},{"id":259},"_3-无支撑-claim-清单",[261],{"type":51,"value":262},"3. 无支撑 claim 清单",{"type":45,"tag":60,"props":264,"children":265},{},[266],{"type":51,"value":267},"对每条无支撑 claim 记录：",{"type":45,"tag":108,"props":269,"children":270},{},[271,276,281,286],{"type":45,"tag":80,"props":272,"children":273},{},[274],{"type":51,"value":275},"位置：节标题 + 段落序号 + 句序号；",{"type":45,"tag":80,"props":277,"children":278},{},[279],{"type":51,"value":280},"claim 原文（逐字引用，不改写、不润色）；",{"type":45,"tag":80,"props":282,"children":283},{},[284],{"type":51,"value":285},"所需证据类型：文献引用 \u002F 实验数据 \u002F 统计数据；",{"type":45,"tag":80,"props":287,"children":288},{},[289],{"type":51,"value":290},"建议检索关键词（2-4 个英文词，供 evidence-loop 生成定向补检 query）。",{"type":45,"tag":144,"props":292,"children":294},{"id":293},"_4-输出与落盘",[295],{"type":51,"value":296},"4. 输出与落盘",{"type":45,"tag":108,"props":298,"children":299},{},[300,329],{"type":45,"tag":80,"props":301,"children":302},{},[303,305,311,313,319,321,327],{"type":51,"value":304},"目录：",{"type":45,"tag":86,"props":306,"children":308},{"className":307},[],[309],{"type":51,"value":310},"output\u002Fclaim-check\u002F\u003Cslug>\u002Flatest\u002F",{"type":51,"value":312},"，写入 ",{"type":45,"tag":86,"props":314,"children":316},{"className":315},[],[317],{"type":51,"value":318},"unsupported-claims.md",{"type":51,"value":320},"\n与 ",{"type":45,"tag":86,"props":322,"children":324},{"className":323},[],[325],{"type":51,"value":326},"review.json",{"type":51,"value":328},"。",{"type":45,"tag":80,"props":330,"children":331},{},[332,334,340,342,348,350],{"type":51,"value":333},"结论同时以 ```review 块输出，",{"type":45,"tag":86,"props":335,"children":337},{"className":336},[],[338],{"type":51,"value":339},"check",{"type":51,"value":341}," 字段固定为 ",{"type":45,"tag":86,"props":343,"children":345},{"className":344},[],[346],{"type":51,"value":347},"citation",{"type":51,"value":349},"：\n",{"type":45,"tag":108,"props":351,"children":352},{},[353,374,386],{"type":45,"tag":80,"props":354,"children":355},{},[356,358,364,366,372],{"type":51,"value":357},"无支撑事实 claim → level ",{"type":45,"tag":86,"props":359,"children":361},{"className":360},[],[362],{"type":51,"value":363},"warn",{"type":51,"value":365},"；若属于关键论断（方法比较、性能断言、\n领域定论类）可升为 ",{"type":45,"tag":86,"props":367,"children":369},{"className":368},[],[370],{"type":51,"value":371},"error",{"type":51,"value":373},"；",{"type":45,"tag":80,"props":375,"children":376},{},[377,379,384],{"type":51,"value":378},"引用了文献库中不存在的 paper_id \u002F 编号 → level ",{"type":45,"tag":86,"props":380,"children":382},{"className":381},[],[383],{"type":51,"value":371},{"type":51,"value":385},"（无源引用）；",{"type":45,"tag":80,"props":387,"children":388},{},[389],{"type":51,"value":390},"有支撑的 claim 不逐条列出，只在统计条目中体现。",{"type":45,"tag":144,"props":392,"children":394},{"id":393},"_5-claim-分类示例抽取时的判定参照",[395],{"type":51,"value":396},"5. claim 分类示例（抽取时的判定参照）",{"type":45,"tag":398,"props":399,"children":400},"table",{},[401,425],{"type":45,"tag":402,"props":403,"children":404},"thead",{},[405],{"type":45,"tag":406,"props":407,"children":408},"tr",{},[409,415,420],{"type":45,"tag":410,"props":411,"children":412},"th",{},[413],{"type":51,"value":414},"例句",{"type":45,"tag":410,"props":416,"children":417},{},[418],{"type":51,"value":419},"分类",{"type":45,"tag":410,"props":421,"children":422},{},[423],{"type":51,"value":424},"是否检查",{"type":45,"tag":426,"props":427,"children":428},"tbody",{},[429,448,465,481,497,515,532],{"type":45,"tag":406,"props":430,"children":431},{},[432,438,443],{"type":45,"tag":433,"props":434,"children":435},"td",{},[436],{"type":51,"value":437},"\"BERT 在 GLUE 基准上取得了当时最优结果\"",{"type":45,"tag":433,"props":439,"children":440},{},[441],{"type":51,"value":442},"事实性 claim",{"type":45,"tag":433,"props":444,"children":445},{},[446],{"type":51,"value":447},"是",{"type":45,"tag":406,"props":449,"children":450},{},[451,456,461],{"type":45,"tag":433,"props":452,"children":453},{},[454],{"type":51,"value":455},"\"实验表明本文方法比基线高 2.3 个点\"",{"type":45,"tag":433,"props":457,"children":458},{},[459],{"type":51,"value":460},"事实性 claim（支撑类型：实验数据）",{"type":45,"tag":433,"props":462,"children":463},{},[464],{"type":51,"value":447},{"type":45,"tag":406,"props":466,"children":467},{},[468,473,477],{"type":45,"tag":433,"props":469,"children":470},{},[471],{"type":51,"value":472},"\"该数据集已被广泛用于公平性研究\"",{"type":45,"tag":433,"props":474,"children":475},{},[476],{"type":51,"value":442},{"type":45,"tag":433,"props":478,"children":479},{},[480],{"type":51,"value":447},{"type":45,"tag":406,"props":482,"children":483},{},[484,489,493],{"type":45,"tag":433,"props":485,"children":486},{},[487],{"type":51,"value":488},"\"X 方法是 Y 任务的当前主流方案\"",{"type":45,"tag":433,"props":490,"children":491},{},[492],{"type":51,"value":442},{"type":45,"tag":433,"props":494,"children":495},{},[496],{"type":51,"value":447},{"type":45,"tag":406,"props":498,"children":499},{},[500,505,510],{"type":45,"tag":433,"props":501,"children":502},{},[503],{"type":51,"value":504},"\"我们认为多模态是最有前景的方向\"",{"type":45,"tag":433,"props":506,"children":507},{},[508],{"type":51,"value":509},"观点立场",{"type":45,"tag":433,"props":511,"children":512},{},[513],{"type":51,"value":514},"否",{"type":45,"tag":406,"props":516,"children":517},{},[518,523,528],{"type":45,"tag":433,"props":519,"children":520},{},[521],{"type":51,"value":522},"\"本文采用三层 BiLSTM 编码句子\"",{"type":45,"tag":433,"props":524,"children":525},{},[526],{"type":51,"value":527},"方法描述",{"type":45,"tag":433,"props":529,"children":530},{},[531],{"type":51,"value":514},{"type":45,"tag":406,"props":533,"children":534},{},[535,540,545],{"type":45,"tag":433,"props":536,"children":537},{},[538],{"type":51,"value":539},"\"令 x 表示输入序列\"",{"type":45,"tag":433,"props":541,"children":542},{},[543],{"type":51,"value":544},"定义约定",{"type":45,"tag":433,"props":546,"children":547},{},[548],{"type":51,"value":514},{"type":45,"tag":60,"props":550,"children":551},{},[552],{"type":51,"value":553},"判定拿不准时按「保守纳入」处理：宁可误报一条无支撑 claim，也不漏检。\n抽取粒度以「句」为最小单位；一句含多个独立事实断言时拆成多条 claim。",{"type":45,"tag":144,"props":555,"children":557},{"id":556},"_6-结果优先级",[558],{"type":51,"value":559},"6. 结果优先级",{"type":45,"tag":108,"props":561,"children":562},{},[563,568,573,578,583],{"type":45,"tag":80,"props":564,"children":565},{},[566],{"type":51,"value":567},"先报 error（无源引用），再报 warn（无支撑 claim），最后给统计；",{"type":45,"tag":80,"props":569,"children":570},{},[571],{"type":51,"value":572},"同一位置的多个问题合并为一条，evidence 中注明「同处 N 个问题」；",{"type":45,"tag":80,"props":574,"children":575},{},[576],{"type":51,"value":577},"全部有支撑时也要输出一条 ok 级统计，避免「无输出 = 未检查」的歧义；",{"type":45,"tag":80,"props":579,"children":580},{},[581],{"type":51,"value":582},"支撑覆盖率低于 80% 时，在最终回复中明确提示「证据基础偏弱」；",{"type":45,"tag":80,"props":584,"children":585},{},[586],{"type":51,"value":587},"每条 warn \u002F error 的 title 必须含可定位信息（节名或编号），\n禁止只写「存在问题」之类的空泛表述。",{"type":45,"tag":54,"props":589,"children":591},{"id":590},"输出模板",[592],{"type":51,"value":590},{"type":45,"tag":60,"props":594,"children":595},{},[596],{"type":51,"value":597},"清单文件开头附统计头：",{"type":45,"tag":599,"props":600,"children":605},"pre",{"className":601,"code":602,"language":603,"meta":604,"style":604},"language-markdown shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","# claim-check 报告：\u003Cslug>\n- 事实性 claim：23 | 有支撑：20 | 无支撑：3 | 无源引用：1\n- 支撑覆盖率：87%\n","markdown","",[606],{"type":45,"tag":86,"props":607,"children":608},{"__ignoreMap":604},[609,627,641],{"type":45,"tag":610,"props":611,"children":614},"span",{"class":612,"line":613},"line",1,[615,621],{"type":45,"tag":610,"props":616,"children":618},{"style":617},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[619],{"type":51,"value":620},"# ",{"type":45,"tag":610,"props":622,"children":624},{"style":623},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[625],{"type":51,"value":626},"claim-check 报告：\u003Cslug>\n",{"type":45,"tag":610,"props":628,"children":629},{"class":612,"line":27},[630,635],{"type":45,"tag":610,"props":631,"children":632},{"style":617},[633],{"type":51,"value":634},"-",{"type":45,"tag":610,"props":636,"children":638},{"style":637},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[639],{"type":51,"value":640}," 事实性 claim：23 | 有支撑：20 | 无支撑：3 | 无源引用：1\n",{"type":45,"tag":610,"props":642,"children":644},{"class":612,"line":643},3,[645,649],{"type":45,"tag":610,"props":646,"children":647},{"style":617},[648],{"type":51,"value":634},{"type":45,"tag":610,"props":650,"children":651},{"style":637},[652],{"type":51,"value":653}," 支撑覆盖率：87%\n",{"type":45,"tag":144,"props":655,"children":657},{"id":656},"无支撑-claim-清单unsupported-claimsmd",[658],{"type":51,"value":659},"无支撑 claim 清单（unsupported-claims.md）",{"type":45,"tag":398,"props":661,"children":662},{},[663,694],{"type":45,"tag":402,"props":664,"children":665},{},[666],{"type":45,"tag":406,"props":667,"children":668},{},[669,674,679,684,689],{"type":45,"tag":410,"props":670,"children":671},{},[672],{"type":51,"value":673},"#",{"type":45,"tag":410,"props":675,"children":676},{},[677],{"type":51,"value":678},"位置",{"type":45,"tag":410,"props":680,"children":681},{},[682],{"type":51,"value":683},"claim 原文",{"type":45,"tag":410,"props":685,"children":686},{},[687],{"type":51,"value":688},"所需证据类型",{"type":45,"tag":410,"props":690,"children":691},{},[692],{"type":51,"value":693},"建议检索词",{"type":45,"tag":426,"props":695,"children":696},{},[697,724],{"type":45,"tag":406,"props":698,"children":699},{},[700,705,710,715,719],{"type":45,"tag":433,"props":701,"children":702},{},[703],{"type":51,"value":704},"1",{"type":45,"tag":433,"props":706,"children":707},{},[708],{"type":51,"value":709},"引言 \u002F 段2 \u002F 句3",{"type":45,"tag":433,"props":711,"children":712},{},[713],{"type":51,"value":714},"\"已有研究表明该方法能将误差降低 30%\"",{"type":45,"tag":433,"props":716,"children":717},{},[718],{"type":51,"value":208},{"type":45,"tag":433,"props":720,"children":721},{},[722],{"type":51,"value":723},"error reduction; benchmark",{"type":45,"tag":406,"props":725,"children":726},{},[727,732,737,742,746],{"type":45,"tag":433,"props":728,"children":729},{},[730],{"type":51,"value":731},"2",{"type":45,"tag":433,"props":733,"children":734},{},[735],{"type":51,"value":736},"相关工作 \u002F 段1 \u002F 句2",{"type":45,"tag":433,"props":738,"children":739},{},[740],{"type":51,"value":741},"\"现有方法普遍无法处理长序列\"",{"type":45,"tag":433,"props":743,"children":744},{},[745],{"type":51,"value":208},{"type":45,"tag":433,"props":747,"children":748},{},[749],{"type":51,"value":750},"long sequence; limitation",{"type":45,"tag":144,"props":752,"children":754},{"id":753},"review-块",[755],{"type":51,"value":756},"review 块",{"type":45,"tag":599,"props":758,"children":762},{"className":759,"code":760,"language":761,"meta":604,"style":604},"language-review shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","[\n  {\"level\": \"warn\", \"check\": \"citation\", \"title\": \"引言段2存在无支撑 claim\",\n   \"evidence\": \"“已有研究表明该方法能将误差降低 30%” 无文内引用、无 EvidenceItem\",\n   \"note\": \"需要文献引用；建议检索：error reduction benchmark\"},\n  {\"level\": \"error\", \"check\": \"citation\", \"title\": \"无源引用 [17]\",\n   \"evidence\": \"文中引用编号 [17] 在参考文献表与 papers.json 中均无对应条目\",\n   \"note\": \"删除该引用标记或补充真实来源\"},\n  {\"level\": \"ok\", \"check\": \"citation\", \"title\": \"支撑覆盖统计\",\n   \"evidence\": \"事实性 claim 共 23 条，有支撑 20 条\", \"note\": \"覆盖率 87%\"}\n]\n","review",[763],{"type":45,"tag":86,"props":764,"children":765},{"__ignoreMap":604},[766,774,782,790,799,807,816,825,834,843],{"type":45,"tag":610,"props":767,"children":768},{"class":612,"line":613},[769],{"type":45,"tag":610,"props":770,"children":771},{},[772],{"type":51,"value":773},"[\n",{"type":45,"tag":610,"props":775,"children":776},{"class":612,"line":27},[777],{"type":45,"tag":610,"props":778,"children":779},{},[780],{"type":51,"value":781},"  {\"level\": \"warn\", \"check\": \"citation\", \"title\": \"引言段2存在无支撑 claim\",\n",{"type":45,"tag":610,"props":783,"children":784},{"class":612,"line":643},[785],{"type":45,"tag":610,"props":786,"children":787},{},[788],{"type":51,"value":789},"   \"evidence\": \"“已有研究表明该方法能将误差降低 30%” 无文内引用、无 EvidenceItem\",\n",{"type":45,"tag":610,"props":791,"children":793},{"class":612,"line":792},4,[794],{"type":45,"tag":610,"props":795,"children":796},{},[797],{"type":51,"value":798},"   \"note\": \"需要文献引用；建议检索：error reduction benchmark\"},\n",{"type":45,"tag":610,"props":800,"children":801},{"class":612,"line":23},[802],{"type":45,"tag":610,"props":803,"children":804},{},[805],{"type":51,"value":806},"  {\"level\": \"error\", \"check\": \"citation\", \"title\": \"无源引用 [17]\",\n",{"type":45,"tag":610,"props":808,"children":810},{"class":612,"line":809},6,[811],{"type":45,"tag":610,"props":812,"children":813},{},[814],{"type":51,"value":815},"   \"evidence\": \"文中引用编号 [17] 在参考文献表与 papers.json 中均无对应条目\",\n",{"type":45,"tag":610,"props":817,"children":819},{"class":612,"line":818},7,[820],{"type":45,"tag":610,"props":821,"children":822},{},[823],{"type":51,"value":824},"   \"note\": \"删除该引用标记或补充真实来源\"},\n",{"type":45,"tag":610,"props":826,"children":828},{"class":612,"line":827},8,[829],{"type":45,"tag":610,"props":830,"children":831},{},[832],{"type":51,"value":833},"  {\"level\": \"ok\", \"check\": \"citation\", \"title\": \"支撑覆盖统计\",\n",{"type":45,"tag":610,"props":835,"children":837},{"class":612,"line":836},9,[838],{"type":45,"tag":610,"props":839,"children":840},{},[841],{"type":51,"value":842},"   \"evidence\": \"事实性 claim 共 23 条，有支撑 20 条\", \"note\": \"覆盖率 87%\"}\n",{"type":45,"tag":610,"props":844,"children":846},{"class":612,"line":845},10,[847],{"type":45,"tag":610,"props":848,"children":849},{},[850],{"type":51,"value":851},"]\n",{"type":45,"tag":54,"props":853,"children":855},{"id":854},"本技能不做什么",[856],{"type":51,"value":854},{"type":45,"tag":108,"props":858,"children":859},{},[860,865,870,875,880,885],{"type":45,"tag":80,"props":861,"children":862},{},[863],{"type":51,"value":864},"不判断 claim 的学术价值、新颖性或表述优劣，只判支撑有无。",{"type":45,"tag":80,"props":866,"children":867},{},[868],{"type":51,"value":869},"不核验参考文献条目的元数据真伪（交给 citation-verify）。",{"type":45,"tag":80,"props":871,"children":872},{},[873],{"type":51,"value":874},"不主动检索新文献补证据（交给 evidence-loop）。",{"type":45,"tag":80,"props":876,"children":877},{},[878],{"type":51,"value":879},"不修改草稿；只产出清单与建议。",{"type":45,"tag":80,"props":881,"children":882},{},[883],{"type":51,"value":884},"不检查观点类、方法描述类、定义类句子。",{"type":45,"tag":80,"props":886,"children":887},{},[888],{"type":51,"value":889},"不检查图表内容本身的正确性，只确认「指向图表」的引用关系存在。",{"type":45,"tag":54,"props":891,"children":893},{"id":892},"收尾与下一步",[894],{"type":51,"value":892},{"type":45,"tag":76,"props":896,"children":897},{},[898,903,915,920],{"type":45,"tag":80,"props":899,"children":900},{},[901],{"type":51,"value":902},"汇总：事实性 claim 总数、支撑覆盖率、无支撑条数、无源引用条数，\n回复中附 ```review 块。",{"type":45,"tag":80,"props":904,"children":905},{},[906,908,913],{"type":51,"value":907},"指向 ",{"type":45,"tag":86,"props":909,"children":911},{"className":910},[],[912],{"type":51,"value":310},{"type":51,"value":914}," 产物。",{"type":45,"tag":80,"props":916,"children":917},{},[918],{"type":51,"value":919},"下一步：无支撑条目较多时建议进入 evidence-loop 做定向补检；\n无源引用请用户确认后删除或补源。",{"type":45,"tag":80,"props":921,"children":922},{},[923],{"type":51,"value":924},"若支撑覆盖率为 100%，明确告知用户「本次未发现无支撑问题」，不留歧义。",{"type":45,"tag":926,"props":927,"children":928},"style",{},[929],{"type":51,"value":930},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":932,"total":1133},[933,957,973,992,1007,1027,1045,1063,1078,1094,1113,1123],{"slug":934,"name":934,"fn":935,"description":936,"org":937,"tags":938,"stars":954,"repoUrl":955,"updatedAt":956},"android-native-dev","develop Android native applications","Android native application development and UI design guide. Covers Material Design 3, Kotlin\u002FCompose development, project configuration, accessibility, and build troubleshooting. Read this before Android native application development.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[939,942,945,948,951],{"name":940,"slug":941,"type":16},"Accessibility","accessibility",{"name":943,"slug":944,"type":16},"Android","android",{"name":946,"slug":947,"type":16},"Kotlin","kotlin",{"name":949,"slug":950,"type":16},"Mobile","mobile",{"name":952,"slug":953,"type":16},"UI Components","ui-components",13030,"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002Fskills","2026-07-13T06:16:54.247834",{"slug":958,"name":958,"fn":959,"description":960,"org":961,"tags":962,"stars":954,"repoUrl":955,"updatedAt":972},"buddy-sings","generate singing performances for AI companions","Use when user wants their Claude Code pet (\u002Fbuddy) to sing a song. Triggers on any request that combines the concept of their Claude Code buddy, pet, or companion with singing or music. Supports multilingual triggers — match equivalent phrases in any language.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[963,966,969],{"name":964,"slug":965,"type":16},"Agents","agents",{"name":967,"slug":968,"type":16},"Audio","audio",{"name":970,"slug":971,"type":16},"Creative","creative","2026-07-13T06:16:35.130644",{"slug":974,"name":974,"fn":975,"description":976,"org":977,"tags":978,"stars":954,"repoUrl":955,"updatedAt":991},"color-font-skill","select color palettes and font pairings","Choose presentation-ready color palettes and font pairings for PPT\u002Fdesign tasks. Use when users ask for visual theme choices, brand-safe palettes, or font recommendations. Triggers include: 配色, 色板, 字体, color palette, font, PPT配色, 字体搭配.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[979,982,985,988],{"name":980,"slug":981,"type":16},"Design","design",{"name":983,"slug":984,"type":16},"Presentations","presentations",{"name":986,"slug":987,"type":16},"Themes","themes",{"name":989,"slug":990,"type":16},"Typography","typography","2026-07-13T06:17:02.785587",{"slug":993,"name":993,"fn":994,"description":995,"org":996,"tags":997,"stars":954,"repoUrl":955,"updatedAt":1006},"design-style-skill","select visual design systems for presentations","Select a consistent visual design system for PPT slides using radius\u002Fspacing style recipes. Use when users ask for overall style direction or component styling consistency. Includes Sharp\u002FSoft\u002FRounded\u002FPill recipes, component mappings, typography\u002Fspacing rules, and mixing guidance. Triggers: 风格, style, radius, spacing, 圆角, 间距, PPT风格, 视觉风格, design style, component style.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[998,999,1002,1005],{"name":980,"slug":981,"type":16},{"name":1000,"slug":1001,"type":16},"Design System","design-system",{"name":1003,"slug":1004,"type":16},"PowerPoint","powerpoint",{"name":983,"slug":984,"type":16},"2026-07-13T06:17:10.398389",{"slug":1008,"name":1008,"fn":1009,"description":1010,"org":1011,"tags":1012,"stars":954,"repoUrl":955,"updatedAt":1026},"flutter-dev","build cross-platform apps with Flutter","Flutter cross-platform development guide covering widget patterns, Riverpod\u002FBloc state management, GoRouter navigation, performance optimization, and platform-specific implementations. Includes const optimization, responsive layouts, testing strategies, and DevTools profiling.\nUse when: building Flutter apps, implementing state management (Riverpod\u002FBloc), setting up GoRouter navigation, creating custom widgets, optimizing performance, writing widget tests, cross-platform development.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1013,1016,1019,1020,1023],{"name":1014,"slug":1015,"type":16},"Dart","dart",{"name":1017,"slug":1018,"type":16},"Flutter","flutter",{"name":949,"slug":950,"type":16},{"name":1021,"slug":1022,"type":16},"Performance","performance",{"name":1024,"slug":1025,"type":16},"State Management","state-management","2026-07-13T06:16:36.626679",{"slug":1028,"name":1028,"fn":1029,"description":1030,"org":1031,"tags":1032,"stars":954,"repoUrl":955,"updatedAt":1044},"frontend-dev","build visually striking frontend web pages","Full-stack frontend development combining premium UI design, cinematic animations,\nAI-generated media assets, persuasive copywriting, and visual art. Builds complete,\nvisually striking web pages with real media, advanced motion, and compelling copy.\nUse when: building landing pages, marketing sites, product pages, dashboards,\ngenerating media assets (image\u002Fvideo\u002Faudio\u002Fmusic), writing conversion copy,\ncreating generative art, or implementing cinematic scroll animations.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1033,1036,1037,1038,1041],{"name":1034,"slug":1035,"type":16},"Animation","animation",{"name":970,"slug":971,"type":16},{"name":980,"slug":981,"type":16},{"name":1039,"slug":1040,"type":16},"Frontend","frontend",{"name":1042,"slug":1043,"type":16},"Web Development","web-development","2026-07-13T06:16:39.108827",{"slug":1046,"name":1046,"fn":1047,"description":1048,"org":1049,"tags":1050,"stars":954,"repoUrl":955,"updatedAt":1062},"fullstack-dev","build full-stack web applications","Full-stack backend architecture and frontend-backend integration guide.\nTRIGGER when: building a full-stack app, creating REST API with frontend, scaffolding backend service,\nbuilding todo app, building CRUD app, building real-time app, building chat app,\nExpress + React, Next.js API, Node.js backend, Python backend, Go backend,\ndesigning service layers, implementing error handling, managing config\u002Fauth,\nsetting up API clients, implementing auth flows, handling file uploads,\nadding real-time features (SSE\u002FWebSocket), hardening for production.\nDO NOT TRIGGER when: pure frontend UI work, pure CSS\u002Fstyling, database schema only.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1051,1054,1055,1058,1061],{"name":1052,"slug":1053,"type":16},"Backend","backend",{"name":1039,"slug":1040,"type":16},{"name":1056,"slug":1057,"type":16},"Full-stack","full-stack",{"name":1059,"slug":1060,"type":16},"REST API","rest-api",{"name":1042,"slug":1043,"type":16},"2026-07-13T06:16:43.219005",{"slug":1064,"name":1064,"fn":1065,"description":1066,"org":1067,"tags":1068,"stars":954,"repoUrl":955,"updatedAt":1077},"gif-sticker-maker","create animated GIF stickers from photos","Convert photos (people, pets, objects, logos) into 4 animated GIF stickers with captions.\nUse when: user wants to create cartoon stickers, GIF expressions, emoji packs, animated avatars,\nor convert photos to Funko Pop \u002F Pop Mart blind box style animations.\nTriggers: sticker, GIF, cartoon, emoji, expression pack, avatar animation.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1069,1070,1071,1074],{"name":1034,"slug":1035,"type":16},{"name":970,"slug":971,"type":16},{"name":1072,"slug":1073,"type":16},"Images","images",{"name":1075,"slug":1076,"type":16},"Media","media","2026-07-13T06:16:51.74461",{"slug":1079,"name":1079,"fn":1080,"description":1081,"org":1082,"tags":1083,"stars":954,"repoUrl":955,"updatedAt":1093},"ios-application-dev","develop iOS applications with SwiftUI and UIKit","iOS application development guide covering UIKit, SnapKit, and SwiftUI. Includes touch targets, safe areas, navigation patterns, Dynamic Type, Dark Mode, accessibility, collection views, common UI components, and SwiftUI design guidelines. For detailed references on specific topics, see the reference files.\nUse when: developing iOS apps, implementing UI, reviewing iOS code, working with UIKit\u002FSnapKit\u002FSwiftUI layouts, building iPhone interfaces, Swift mobile development, Apple HIG compliance, iOS accessibility implementation.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1084,1085,1088,1089,1092],{"name":940,"slug":941,"type":16},{"name":1086,"slug":1087,"type":16},"iOS","ios",{"name":949,"slug":950,"type":16},{"name":1090,"slug":1091,"type":16},"SwiftUI","swiftui",{"name":952,"slug":953,"type":16},"2026-07-13T06:16:55.686092",{"slug":1095,"name":1095,"fn":1096,"description":1097,"org":1098,"tags":1099,"stars":954,"repoUrl":955,"updatedAt":1112},"minimax-docx","create and edit DOCX documents","Professional DOCX document creation, editing, and formatting using OpenXML SDK (.NET). Three pipelines: (A) create new documents from scratch, (B) fill\u002Fedit content in existing documents, (C) apply template formatting with XSD validation gate-check. MUST use this skill whenever the user wants to produce, modify, or format a Word document — including when they say \"write a report\", \"draft a proposal\", \"make a contract\", \"fill in this form\", \"reformat to match this template\", or any task whose final output is a .docx file. Even if the user doesn't mention \"docx\" explicitly, if the task implies a printable\u002Fformal document, use this skill.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1100,1103,1106,1109],{"name":1101,"slug":1102,"type":16},"Documents","documents",{"name":1104,"slug":1105,"type":16},"DOCX","docx",{"name":1107,"slug":1108,"type":16},"Office","office",{"name":1110,"slug":1111,"type":16},"Templates","templates","2026-07-13T06:16:40.461868",{"slug":1114,"name":1114,"fn":1115,"description":1116,"org":1117,"tags":1118,"stars":954,"repoUrl":955,"updatedAt":1122},"minimax-music-gen","generate music and audio tracks","Use when user wants to generate music, songs, or audio tracks. Triggers on any request involving music creation, song writing, lyrics generation, audio production, or covers. Also triggers when user provides lyrics and wants them turned into a song, or describes a mood\u002Fscene and wants background music. Supports multilingual triggers — match equivalent phrases in any language. Do NOT use for music playback of existing files, music theory questions, or music recommendation without generation.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1119,1120,1121],{"name":967,"slug":968,"type":16},{"name":970,"slug":971,"type":16},{"name":1075,"slug":1076,"type":16},"2026-07-13T06:16:50.381758",{"slug":1124,"name":1124,"fn":1125,"description":1126,"org":1127,"tags":1128,"stars":954,"repoUrl":955,"updatedAt":1132},"minimax-music-playlist","generate personalized music playlists","Generate personalized music playlists by analyzing the user's music taste and generation feedback history. Triggers on any request involving playlist generation, music taste profiling, or personalized music recommendations. Supports multilingual triggers — match equivalent phrases in any language.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1129,1130,1131],{"name":967,"slug":968,"type":16},{"name":970,"slug":971,"type":16},{"name":1075,"slug":1076,"type":16},"2026-07-13T06:16:57.002997",84,{"items":1135,"total":1226},[1136,1152,1167,1173,1185,1200,1214],{"slug":1137,"name":1137,"fn":1138,"description":1139,"org":1140,"tags":1141,"stars":23,"repoUrl":24,"updatedAt":1151},"article2tasks","convert articles into Dida365 tasks","将技术周报（批量）或单篇文章整理为滴答清单待办事项，自动分类到已有清单并打标签，全程通过 MCP 写入，跨平台无需任何本地脚本。当用户提供周报内容、文章链接，或提及「周报」「文章汇总」「添加到滴答」时，使用此技能。",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1142,1145,1148],{"name":1143,"slug":1144,"type":16},"Content Creation","content-creation",{"name":1146,"slug":1147,"type":16},"MCP","mcp",{"name":1149,"slug":1150,"type":16},"Task Management","task-management","2026-08-18T03:49:38.751656",{"slug":1153,"name":1153,"fn":1154,"description":1155,"org":1156,"tags":1157,"stars":23,"repoUrl":24,"updatedAt":1166},"citation-verify","verify academic citation accuracy","当用户需要核验参考文献真实性、检查 BibTeX 条目是否有误、审查论文引用是否可靠、 排查 bibliography 中的错误条目、验证 DOI 与题录是否对得上、发现参考文献张冠李戴、 做投稿前引用体检或审稿引用抽查时使用。同义场景：参考文献核验、引用核查、 文献真伪鉴别、bib 文件检查、参考文献纠错、引用元数据比对、 \"帮我看看这些参考文献有没有问题\"\"这个 DOI 对得上吗\"\"有没有编造的引用\"。",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1158,1159,1162,1165],{"name":21,"slug":22,"type":16},{"name":1160,"slug":1161,"type":16},"Documentation","documentation",{"name":1163,"slug":1164,"type":16},"QA","qa",{"name":14,"slug":15,"type":16},"2026-08-21T03:59:17.615117",{"slug":4,"name":4,"fn":5,"description":6,"org":1168,"tags":1169,"stars":23,"repoUrl":24,"updatedAt":25},{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1170,1171,1172],{"name":18,"slug":19,"type":16},{"name":21,"slug":22,"type":16},{"name":14,"slug":15,"type":16},{"slug":1174,"name":1174,"fn":1175,"description":1176,"org":1177,"tags":1178,"stars":23,"repoUrl":24,"updatedAt":1184},"cn-literature","search and organize Chinese academic literature","当用户需要检索或整理中文文献（CNKI 知网、万方、维普、超星）、把中文数据库 导出的题录文件解析成统一 PaperDocument、或把中文文献与英文检索结果合并去重 时使用。同义场景：中文文献检索、知网导出题录解析、万方检索、Refworks\u002FEndNote 格式转换、\"帮我把这份 CNKI 导出的 txt 整理成文献表\"\"中文核心期刊上关于 X 有哪些研究\"。",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1179,1182,1183],{"name":1180,"slug":1181,"type":16},"Data Cleaning","data-cleaning",{"name":1101,"slug":1102,"type":16},{"name":14,"slug":15,"type":16},"2026-08-21T03:59:12.24404",{"slug":1186,"name":1186,"fn":1187,"description":1188,"org":1189,"tags":1190,"stars":23,"repoUrl":24,"updatedAt":1199},"cold-start-interview","initialize research profiles via interviews","当用户首次使用科研工作台、研究画像仍为空白，或用户主动说\"先做个访谈\"\"重新设置我的研究信息\"\"初始化画像\"\"cold start\"\"重新 interview\"时使用。本技能通过结构化访谈收集用户的研究领域、常用数据源、算力环境、写作语言与目标期刊、引用格式、团队协作规范、伦理合规要求，并把回答以散文形式写回插件根目录 CLAUDE.md 的研究画像部分。支持 quick（2 分钟 5 问）、full（完整 15 问）、--redo（推翻重谈）、--check（只检查画像完整度不提问）四种模式，支持中断后续谈。同义触发场景：新用户引导、首次配置、研究背景调查、填研究档案、更新个人研究信息、check 画像。",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1191,1192,1195,1198],{"name":1160,"slug":1161,"type":16},{"name":1193,"slug":1194,"type":16},"Onboarding","onboarding",{"name":1196,"slug":1197,"type":16},"Productivity","productivity",{"name":14,"slug":15,"type":16},"2026-08-21T03:59:58.579998",{"slug":1201,"name":1201,"fn":1202,"description":1203,"org":1204,"tags":1205,"stars":23,"repoUrl":24,"updatedAt":1213},"customize","customize research guardrails and settings","当用户想修改研究画像或共享守则（guardrails）时使用：换了研究领域、换了目标期刊、换了引用格式、换了算力环境、合规要求变化、想调整某条 guardrail 的严格程度。同义触发场景：改一下画像、更新我的研究信息、修改 CLAUDE.md、调整设置、换引用格式、customize、个性化配置、改规则、重新配置工作台。本技能是画像与守则的唯一维护入口：读取 CLAUDE.md、与用户逐项确认修改点、写回文件、并明确告知哪些 skill 的行为会因此变化。",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1206,1209,1212],{"name":1207,"slug":1208,"type":16},"Best Practices","best-practices",{"name":1210,"slug":1211,"type":16},"Configuration","configuration",{"name":14,"slug":15,"type":16},"2026-08-21T03:59:35.867596",{"slug":1215,"name":1215,"fn":1216,"description":1217,"org":1218,"tags":1219,"stars":23,"repoUrl":24,"updatedAt":1225},"dida365","manage Dida365 tasks and habits","Manage 滴答清单 (Dida365 China) tasks, lists, habits, focus records and countdowns through the official Dida365 MCP server at mcp.dida365.com. Use when the user asks to check, plan, create, update, complete or review tasks and habits on dida365.com, or asks about focus history and countdowns.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":11},[1220,1221,1224],{"name":1146,"slug":1147,"type":16},{"name":1222,"slug":1223,"type":16},"Scheduling","scheduling",{"name":1149,"slug":1150,"type":16},"2026-08-18T03:49:37.126385",36]