[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-minimax-literature-survey":3,"mdc-utixuw-key":37,"related-org-minimax-literature-survey":1173,"related-repo-minimax-literature-survey":1376},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":26,"repoUrl":27,"updatedAt":28,"license":29,"forks":30,"topics":31,"repo":32,"sourceUrl":35,"mdContent":36},"literature-survey","analyze and synthesize research literature","当用户需要对已检索到的文献集合做整体分析、写文献调研报告、梳理某领域的 研究概况 \u002F 共识 \u002F 争议 \u002F 空白、提取文献证据为综述写作做准备时使用。 同义场景：文献综述分析、领域调研、研究现状梳理、证据提取、文献精读笔记、 \"帮我分析这批论文讲了什么\"\"这个领域的研究现状如何\"\"这些文献有什么共识和分歧\"。",{"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",[13,17,20,23],{"name":14,"slug":15,"type":16},"Research","research","tag",{"name":18,"slug":19,"type":16},"Documentation","documentation",{"name":21,"slug":22,"type":16},"Summarization","summarization",{"name":24,"slug":25,"type":16},"Data Analysis","data-analysis",5,"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMiniMax-Code-Plugins","2026-08-21T03:59:19.04583",null,2,[],{"repoUrl":27,"stars":26,"forks":30,"topics":33,"description":34},[],"Community registry and contribution toolkit for MiniMax Code plugins.","https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMiniMax-Code-Plugins\u002Ftree\u002FHEAD\u002Fplugins\u002FHylouis233\u002Fopenscience\u002Fskills\u002Fliterature-survey","---\nname: literature-survey\ndescription: >-\n  当用户需要对已检索到的文献集合做整体分析、写文献调研报告、梳理某领域的\n  研究概况 \u002F 共识 \u002F 争议 \u002F 空白、提取文献证据为综述写作做准备时使用。\n  同义场景：文献综述分析、领域调研、研究现状梳理、证据提取、文献精读笔记、\n  \"帮我分析这批论文讲了什么\"\"这个领域的研究现状如何\"\"这些文献有什么共识和分歧\"。\nargument-hint: '[主题或 papers.json 路径]'\nmetadata:\n  domains: [literature]\n  last_reviewed: '2026-08-18'\n---\n\n# literature-survey：文献集合全局分析\n\n## 目的\n\n读取 literature-search 产出的 `papers.json`，逐篇提取证据（EvidenceItem），\n再按 8 个固定字段做全局综合，产出可被 review-writing 直接引用的\n`evidence.json` 与 `survey.md`。\n\n铁律：每一条 EvidenceItem 的 `quote` 必须来自真实读到的文本；读不到全文就\n只基于摘要并标注 `abstract-only`；任何字段没有证据就写「现有检索结果不足以\n支撑」，禁止编凑。\n\n## 前置检查\n\n1. `output\u002Fliterature-search\u002F\u003Cslug>\u002Flatest\u002Fpapers.json` 存在且非空；\n   若用户直接给了 papers.json 路径，以该文件为准。\n2. 条目关键字段（title \u002F abstract）大体完整；大面积缺 abstract 时提醒用户\n   分析深度将受限，并询问是否继续。\n3. slug 与上游一致：主题字符串做 Unicode NFKC 规范化、转小写、去首尾空白、\n   连续空白折叠为单个空格后，取 sha1 十六进制摘要前 8 位。\n\n## 操作规程\n\n### 1. 逐篇提取 EvidenceItem\n\n对每篇 PaperDocument：\n\n- 通读可及文本（abstract 必有；url 指向开放获取页面时可尝试读取更多正文）。\n- 提取 1-5 条 EvidenceItem：\n  `{paper_id, claim, quote, page, confidence}`。\n  - `claim`：用自己的话概括该文献支撑的一个论断；\n  - `quote`：逐字摘录支撑该论断的原文句子——必须是真实读到的文本，\n    不得凭印象改写；\n  - `page`：全文可得时填页码或小节号；只有摘要时填 `\"abstract\"`；\n  - `confidence`：`high`（全文核读）\u002F `medium`（摘要 + 部分正文）\u002F\n    `abstract-only`（仅摘要可读）。\n- 读不到全文的一律标 `abstract-only`，claim 措辞随之保守化\n  （用「该文摘要称……」而非直接断言）。\n\nconfidence 判定细则：\n\n| 等级 | 含义 | 典型情形 |\n| --- | --- | --- |\n| high | 全文可读且已核读相关段落 | 开放获取正文可及 |\n| medium | 摘要 + 部分正文（引言 \u002F 结论）可读 | 页面仅公开部分章节 |\n| abstract-only | 仅摘要可读 | 付费墙或仅元数据 |\n\n提取数量与排除规则：\n\n- 每篇 1-5 条，按与主题的相关度取量：核心文献取满，边缘文献 1 条即可；\n- 同一 claim 不从同一篇重复提取；\n- 与主题明显无关的文献不强行提取，在 survey.md 末尾附「已排除」清单及原因。\n\n### 2. 全局综合：8 字段\n\n严格按以下固定字段名输出——字段名一个都不能改，它们同时是\nreview-writing 中 evidence-map 的白名单：\n\n1. **领域整体研究概况**：该文献集合勾勒出的领域全貌与核心问题。\n2. **共性共识**：多篇文献一致认同的结论或做法。\n3. **争议矛盾**：文献之间结论冲突或立场分歧之处。\n4. **研究空白**：集合中无人解决、或被明确指出的未解问题。\n5. **时序演化**：按年份梳理研究重心与方法随时间的变化。\n6. **方法迭代**：关键技术路线的演进脉络（谁改进谁、解决了什么）。\n7. **子主题横向对比**：把文献按子主题分组，横向比较目标 \u002F 方法 \u002F 结论。\n8. **总结展望**：基于以上 7 项的综合判断与可能的下一步方向。\n\n### 3. 论断挂证据\n\n- 8 字段下的每个论断句末尾挂 EvidenceItem 引用：`[paper_id]`，\n  多条并列用 `[paper_id1, paper_id2]`。\n- 每个论断至少 1 条证据；共识类论断至少 2 条来自不同文献的证据。\n- 某字段凑不出任何有证据的论断 → 该字段只写一句\n  「现有检索结果不足以支撑此部分分析」，禁止编凑。\n\n### 4. 落盘\n\n目录 `output\u002Fliterature-survey\u002F\u003Cslug>\u002Flatest\u002F`：\n\n- `evidence.json`：全部 EvidenceItem 数组；\n- `survey.md`：按 8 字段组织的分析正文，论断带 `[paper_id]` 引用。\n\n## 输出模板\n\n### evidence.json\n\n```json\n[\n  {\n    \"paper_id\": \"https:\u002F\u002Fopenalex.org\u002FW0123456789\",\n    \"claim\": \"Transformer 完全基于注意力机制即可取得当时最优机器翻译效果\",\n    \"quote\": \"We propose a new simple network architecture, the Transformer, based solely on attention mechanisms ...\",\n    \"page\": \"abstract\",\n    \"confidence\": \"abstract-only\"\n  }\n]\n```\n\n### survey.md 骨架\n\n```markdown\n# \u003C主题> 文献调研分析\n\n## 领域整体研究概况\n……[paper_id]……\n\n## 共性共识\n……[paper_id1, paper_id2]……\n\n## 争议矛盾\n……\n\n## 研究空白\n……\n\n## 时序演化\n……\n\n## 方法迭代\n……\n\n## 子主题横向对比\n……\n\n## 总结展望\n……\n```\n\n## 本技能不做什么\n\n- 不写成文综述（交给 review-writing）；`survey.md` 是分析底稿而非成稿。\n- 不编造 quote 或页码；读不到就标 `abstract-only`。\n- 不核验参考文献真伪（交给 citation-verify）。\n- 不补充新检索；证据不足时如实标注，而不是自己临时补文献。\n- 不输出 8 字段之外的分析维度（新增维度会破坏 evidence-map 白名单契约）。\n\n## 收尾与下一步\n\n1. 汇总：文献篇数、EvidenceItem 条数、8 字段中证据充足 \u002F 不足各几项。\n2. 指向 `output\u002Fliterature-survey\u002F\u003Cslug>\u002Flatest\u002F`。\n3. 建议下一步：运行 review-writing 成文；或对证据不足的字段回到\n   literature-search 定向补检后重新分析。\n",{"data":38,"body":44},{"name":4,"description":6,"argument-hint":39,"metadata":40},"[主题或 papers.json 路径]",{"domains":41,"last_reviewed":43},[42],"literature","2026-08-18",{"type":45,"children":46},"root",[47,56,62,93,114,119,145,150,157,162,273,278,362,367,385,391,396,480,486,519,525,537,567,572,577,814,820,1092,1097,1138,1143,1167],{"type":48,"tag":49,"props":50,"children":52},"element","h1",{"id":51},"literature-survey文献集合全局分析",[53],{"type":54,"value":55},"text","literature-survey：文献集合全局分析",{"type":48,"tag":57,"props":58,"children":60},"h2",{"id":59},"目的",[61],{"type":54,"value":59},{"type":48,"tag":63,"props":64,"children":65},"p",{},[66,68,75,77,83,85,91],{"type":54,"value":67},"读取 literature-search 产出的 ",{"type":48,"tag":69,"props":70,"children":72},"code",{"className":71},[],[73],{"type":54,"value":74},"papers.json",{"type":54,"value":76},"，逐篇提取证据（EvidenceItem），\n再按 8 个固定字段做全局综合，产出可被 review-writing 直接引用的\n",{"type":48,"tag":69,"props":78,"children":80},{"className":79},[],[81],{"type":54,"value":82},"evidence.json",{"type":54,"value":84}," 与 ",{"type":48,"tag":69,"props":86,"children":88},{"className":87},[],[89],{"type":54,"value":90},"survey.md",{"type":54,"value":92},"。",{"type":48,"tag":63,"props":94,"children":95},{},[96,98,104,106,112],{"type":54,"value":97},"铁律：每一条 EvidenceItem 的 ",{"type":48,"tag":69,"props":99,"children":101},{"className":100},[],[102],{"type":54,"value":103},"quote",{"type":54,"value":105}," 必须来自真实读到的文本；读不到全文就\n只基于摘要并标注 ",{"type":48,"tag":69,"props":107,"children":109},{"className":108},[],[110],{"type":54,"value":111},"abstract-only",{"type":54,"value":113},"；任何字段没有证据就写「现有检索结果不足以\n支撑」，禁止编凑。",{"type":48,"tag":57,"props":115,"children":117},{"id":116},"前置检查",[118],{"type":54,"value":116},{"type":48,"tag":120,"props":121,"children":122},"ol",{},[123,135,140],{"type":48,"tag":124,"props":125,"children":126},"li",{},[127,133],{"type":48,"tag":69,"props":128,"children":130},{"className":129},[],[131],{"type":54,"value":132},"output\u002Fliterature-search\u002F\u003Cslug>\u002Flatest\u002Fpapers.json",{"type":54,"value":134}," 存在且非空；\n若用户直接给了 papers.json 路径，以该文件为准。",{"type":48,"tag":124,"props":136,"children":137},{},[138],{"type":54,"value":139},"条目关键字段（title \u002F abstract）大体完整；大面积缺 abstract 时提醒用户\n分析深度将受限，并询问是否继续。",{"type":48,"tag":124,"props":141,"children":142},{},[143],{"type":54,"value":144},"slug 与上游一致：主题字符串做 Unicode NFKC 规范化、转小写、去首尾空白、\n连续空白折叠为单个空格后，取 sha1 十六进制摘要前 8 位。",{"type":48,"tag":57,"props":146,"children":148},{"id":147},"操作规程",[149],{"type":54,"value":147},{"type":48,"tag":151,"props":152,"children":154},"h3",{"id":153},"_1-逐篇提取-evidenceitem",[155],{"type":54,"value":156},"1. 逐篇提取 EvidenceItem",{"type":48,"tag":63,"props":158,"children":159},{},[160],{"type":54,"value":161},"对每篇 PaperDocument：",{"type":48,"tag":163,"props":164,"children":165},"ul",{},[166,171,261],{"type":48,"tag":124,"props":167,"children":168},{},[169],{"type":54,"value":170},"通读可及文本（abstract 必有；url 指向开放获取页面时可尝试读取更多正文）。",{"type":48,"tag":124,"props":172,"children":173},{},[174,176,182,184],{"type":54,"value":175},"提取 1-5 条 EvidenceItem：\n",{"type":48,"tag":69,"props":177,"children":179},{"className":178},[],[180],{"type":54,"value":181},"{paper_id, claim, quote, page, confidence}",{"type":54,"value":183},"。\n",{"type":48,"tag":163,"props":185,"children":186},{},[187,198,208,227],{"type":48,"tag":124,"props":188,"children":189},{},[190,196],{"type":48,"tag":69,"props":191,"children":193},{"className":192},[],[194],{"type":54,"value":195},"claim",{"type":54,"value":197},"：用自己的话概括该文献支撑的一个论断；",{"type":48,"tag":124,"props":199,"children":200},{},[201,206],{"type":48,"tag":69,"props":202,"children":204},{"className":203},[],[205],{"type":54,"value":103},{"type":54,"value":207},"：逐字摘录支撑该论断的原文句子——必须是真实读到的文本，\n不得凭印象改写；",{"type":48,"tag":124,"props":209,"children":210},{},[211,217,219,225],{"type":48,"tag":69,"props":212,"children":214},{"className":213},[],[215],{"type":54,"value":216},"page",{"type":54,"value":218},"：全文可得时填页码或小节号；只有摘要时填 ",{"type":48,"tag":69,"props":220,"children":222},{"className":221},[],[223],{"type":54,"value":224},"\"abstract\"",{"type":54,"value":226},"；",{"type":48,"tag":124,"props":228,"children":229},{},[230,236,238,244,246,252,254,259],{"type":48,"tag":69,"props":231,"children":233},{"className":232},[],[234],{"type":54,"value":235},"confidence",{"type":54,"value":237},"：",{"type":48,"tag":69,"props":239,"children":241},{"className":240},[],[242],{"type":54,"value":243},"high",{"type":54,"value":245},"（全文核读）\u002F ",{"type":48,"tag":69,"props":247,"children":249},{"className":248},[],[250],{"type":54,"value":251},"medium",{"type":54,"value":253},"（摘要 + 部分正文）\u002F\n",{"type":48,"tag":69,"props":255,"children":257},{"className":256},[],[258],{"type":54,"value":111},{"type":54,"value":260},"（仅摘要可读）。",{"type":48,"tag":124,"props":262,"children":263},{},[264,266,271],{"type":54,"value":265},"读不到全文的一律标 ",{"type":48,"tag":69,"props":267,"children":269},{"className":268},[],[270],{"type":54,"value":111},{"type":54,"value":272},"，claim 措辞随之保守化\n（用「该文摘要称……」而非直接断言）。",{"type":48,"tag":63,"props":274,"children":275},{},[276],{"type":54,"value":277},"confidence 判定细则：",{"type":48,"tag":279,"props":280,"children":281},"table",{},[282,306],{"type":48,"tag":283,"props":284,"children":285},"thead",{},[286],{"type":48,"tag":287,"props":288,"children":289},"tr",{},[290,296,301],{"type":48,"tag":291,"props":292,"children":293},"th",{},[294],{"type":54,"value":295},"等级",{"type":48,"tag":291,"props":297,"children":298},{},[299],{"type":54,"value":300},"含义",{"type":48,"tag":291,"props":302,"children":303},{},[304],{"type":54,"value":305},"典型情形",{"type":48,"tag":307,"props":308,"children":309},"tbody",{},[310,328,345],{"type":48,"tag":287,"props":311,"children":312},{},[313,318,323],{"type":48,"tag":314,"props":315,"children":316},"td",{},[317],{"type":54,"value":243},{"type":48,"tag":314,"props":319,"children":320},{},[321],{"type":54,"value":322},"全文可读且已核读相关段落",{"type":48,"tag":314,"props":324,"children":325},{},[326],{"type":54,"value":327},"开放获取正文可及",{"type":48,"tag":287,"props":329,"children":330},{},[331,335,340],{"type":48,"tag":314,"props":332,"children":333},{},[334],{"type":54,"value":251},{"type":48,"tag":314,"props":336,"children":337},{},[338],{"type":54,"value":339},"摘要 + 部分正文（引言 \u002F 结论）可读",{"type":48,"tag":314,"props":341,"children":342},{},[343],{"type":54,"value":344},"页面仅公开部分章节",{"type":48,"tag":287,"props":346,"children":347},{},[348,352,357],{"type":48,"tag":314,"props":349,"children":350},{},[351],{"type":54,"value":111},{"type":48,"tag":314,"props":353,"children":354},{},[355],{"type":54,"value":356},"仅摘要可读",{"type":48,"tag":314,"props":358,"children":359},{},[360],{"type":54,"value":361},"付费墙或仅元数据",{"type":48,"tag":63,"props":363,"children":364},{},[365],{"type":54,"value":366},"提取数量与排除规则：",{"type":48,"tag":163,"props":368,"children":369},{},[370,375,380],{"type":48,"tag":124,"props":371,"children":372},{},[373],{"type":54,"value":374},"每篇 1-5 条，按与主题的相关度取量：核心文献取满，边缘文献 1 条即可；",{"type":48,"tag":124,"props":376,"children":377},{},[378],{"type":54,"value":379},"同一 claim 不从同一篇重复提取；",{"type":48,"tag":124,"props":381,"children":382},{},[383],{"type":54,"value":384},"与主题明显无关的文献不强行提取，在 survey.md 末尾附「已排除」清单及原因。",{"type":48,"tag":151,"props":386,"children":388},{"id":387},"_2-全局综合8-字段",[389],{"type":54,"value":390},"2. 全局综合：8 字段",{"type":48,"tag":63,"props":392,"children":393},{},[394],{"type":54,"value":395},"严格按以下固定字段名输出——字段名一个都不能改，它们同时是\nreview-writing 中 evidence-map 的白名单：",{"type":48,"tag":120,"props":397,"children":398},{},[399,410,420,430,440,450,460,470],{"type":48,"tag":124,"props":400,"children":401},{},[402,408],{"type":48,"tag":403,"props":404,"children":405},"strong",{},[406],{"type":54,"value":407},"领域整体研究概况",{"type":54,"value":409},"：该文献集合勾勒出的领域全貌与核心问题。",{"type":48,"tag":124,"props":411,"children":412},{},[413,418],{"type":48,"tag":403,"props":414,"children":415},{},[416],{"type":54,"value":417},"共性共识",{"type":54,"value":419},"：多篇文献一致认同的结论或做法。",{"type":48,"tag":124,"props":421,"children":422},{},[423,428],{"type":48,"tag":403,"props":424,"children":425},{},[426],{"type":54,"value":427},"争议矛盾",{"type":54,"value":429},"：文献之间结论冲突或立场分歧之处。",{"type":48,"tag":124,"props":431,"children":432},{},[433,438],{"type":48,"tag":403,"props":434,"children":435},{},[436],{"type":54,"value":437},"研究空白",{"type":54,"value":439},"：集合中无人解决、或被明确指出的未解问题。",{"type":48,"tag":124,"props":441,"children":442},{},[443,448],{"type":48,"tag":403,"props":444,"children":445},{},[446],{"type":54,"value":447},"时序演化",{"type":54,"value":449},"：按年份梳理研究重心与方法随时间的变化。",{"type":48,"tag":124,"props":451,"children":452},{},[453,458],{"type":48,"tag":403,"props":454,"children":455},{},[456],{"type":54,"value":457},"方法迭代",{"type":54,"value":459},"：关键技术路线的演进脉络（谁改进谁、解决了什么）。",{"type":48,"tag":124,"props":461,"children":462},{},[463,468],{"type":48,"tag":403,"props":464,"children":465},{},[466],{"type":54,"value":467},"子主题横向对比",{"type":54,"value":469},"：把文献按子主题分组，横向比较目标 \u002F 方法 \u002F 结论。",{"type":48,"tag":124,"props":471,"children":472},{},[473,478],{"type":48,"tag":403,"props":474,"children":475},{},[476],{"type":54,"value":477},"总结展望",{"type":54,"value":479},"：基于以上 7 项的综合判断与可能的下一步方向。",{"type":48,"tag":151,"props":481,"children":483},{"id":482},"_3-论断挂证据",[484],{"type":54,"value":485},"3. 论断挂证据",{"type":48,"tag":163,"props":487,"children":488},{},[489,509,514],{"type":48,"tag":124,"props":490,"children":491},{},[492,494,500,502,508],{"type":54,"value":493},"8 字段下的每个论断句末尾挂 EvidenceItem 引用：",{"type":48,"tag":69,"props":495,"children":497},{"className":496},[],[498],{"type":54,"value":499},"[paper_id]",{"type":54,"value":501},"，\n多条并列用 ",{"type":48,"tag":69,"props":503,"children":505},{"className":504},[],[506],{"type":54,"value":507},"[paper_id1, paper_id2]",{"type":54,"value":92},{"type":48,"tag":124,"props":510,"children":511},{},[512],{"type":54,"value":513},"每个论断至少 1 条证据；共识类论断至少 2 条来自不同文献的证据。",{"type":48,"tag":124,"props":515,"children":516},{},[517],{"type":54,"value":518},"某字段凑不出任何有证据的论断 → 该字段只写一句\n「现有检索结果不足以支撑此部分分析」，禁止编凑。",{"type":48,"tag":151,"props":520,"children":522},{"id":521},"_4-落盘",[523],{"type":54,"value":524},"4. 落盘",{"type":48,"tag":63,"props":526,"children":527},{},[528,530,536],{"type":54,"value":529},"目录 ",{"type":48,"tag":69,"props":531,"children":533},{"className":532},[],[534],{"type":54,"value":535},"output\u002Fliterature-survey\u002F\u003Cslug>\u002Flatest\u002F",{"type":54,"value":237},{"type":48,"tag":163,"props":538,"children":539},{},[540,550],{"type":48,"tag":124,"props":541,"children":542},{},[543,548],{"type":48,"tag":69,"props":544,"children":546},{"className":545},[],[547],{"type":54,"value":82},{"type":54,"value":549},"：全部 EvidenceItem 数组；",{"type":48,"tag":124,"props":551,"children":552},{},[553,558,560,565],{"type":48,"tag":69,"props":554,"children":556},{"className":555},[],[557],{"type":54,"value":90},{"type":54,"value":559},"：按 8 字段组织的分析正文，论断带 ",{"type":48,"tag":69,"props":561,"children":563},{"className":562},[],[564],{"type":54,"value":499},{"type":54,"value":566}," 引用。",{"type":48,"tag":57,"props":568,"children":570},{"id":569},"输出模板",[571],{"type":54,"value":569},{"type":48,"tag":151,"props":573,"children":575},{"id":574},"evidencejson",[576],{"type":54,"value":82},{"type":48,"tag":578,"props":579,"children":584},"pre",{"className":580,"code":581,"language":582,"meta":583,"style":583},"language-json shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","[\n  {\n    \"paper_id\": \"https:\u002F\u002Fopenalex.org\u002FW0123456789\",\n    \"claim\": \"Transformer 完全基于注意力机制即可取得当时最优机器翻译效果\",\n    \"quote\": \"We propose a new simple network architecture, the Transformer, based solely on attention mechanisms ...\",\n    \"page\": \"abstract\",\n    \"confidence\": \"abstract-only\"\n  }\n]\n","json","",[585],{"type":48,"tag":69,"props":586,"children":587},{"__ignoreMap":583},[588,600,608,653,690,726,763,796,805],{"type":48,"tag":589,"props":590,"children":593},"span",{"class":591,"line":592},"line",1,[594],{"type":48,"tag":589,"props":595,"children":597},{"style":596},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[598],{"type":54,"value":599},"[\n",{"type":48,"tag":589,"props":601,"children":602},{"class":591,"line":30},[603],{"type":48,"tag":589,"props":604,"children":605},{"style":596},[606],{"type":54,"value":607},"  {\n",{"type":48,"tag":589,"props":609,"children":611},{"class":591,"line":610},3,[612,617,623,628,633,638,644,648],{"type":48,"tag":589,"props":613,"children":614},{"style":596},[615],{"type":54,"value":616},"    \"",{"type":48,"tag":589,"props":618,"children":620},{"style":619},"--shiki-light:#9C3EDA;--shiki-default:#C792EA;--shiki-dark:#C792EA",[621],{"type":54,"value":622},"paper_id",{"type":48,"tag":589,"props":624,"children":625},{"style":596},[626],{"type":54,"value":627},"\"",{"type":48,"tag":589,"props":629,"children":630},{"style":596},[631],{"type":54,"value":632},":",{"type":48,"tag":589,"props":634,"children":635},{"style":596},[636],{"type":54,"value":637}," \"",{"type":48,"tag":589,"props":639,"children":641},{"style":640},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[642],{"type":54,"value":643},"https:\u002F\u002Fopenalex.org\u002FW0123456789",{"type":48,"tag":589,"props":645,"children":646},{"style":596},[647],{"type":54,"value":627},{"type":48,"tag":589,"props":649,"children":650},{"style":596},[651],{"type":54,"value":652},",\n",{"type":48,"tag":589,"props":654,"children":656},{"class":591,"line":655},4,[657,661,665,669,673,677,682,686],{"type":48,"tag":589,"props":658,"children":659},{"style":596},[660],{"type":54,"value":616},{"type":48,"tag":589,"props":662,"children":663},{"style":619},[664],{"type":54,"value":195},{"type":48,"tag":589,"props":666,"children":667},{"style":596},[668],{"type":54,"value":627},{"type":48,"tag":589,"props":670,"children":671},{"style":596},[672],{"type":54,"value":632},{"type":48,"tag":589,"props":674,"children":675},{"style":596},[676],{"type":54,"value":637},{"type":48,"tag":589,"props":678,"children":679},{"style":640},[680],{"type":54,"value":681},"Transformer 完全基于注意力机制即可取得当时最优机器翻译效果",{"type":48,"tag":589,"props":683,"children":684},{"style":596},[685],{"type":54,"value":627},{"type":48,"tag":589,"props":687,"children":688},{"style":596},[689],{"type":54,"value":652},{"type":48,"tag":589,"props":691,"children":692},{"class":591,"line":26},[693,697,701,705,709,713,718,722],{"type":48,"tag":589,"props":694,"children":695},{"style":596},[696],{"type":54,"value":616},{"type":48,"tag":589,"props":698,"children":699},{"style":619},[700],{"type":54,"value":103},{"type":48,"tag":589,"props":702,"children":703},{"style":596},[704],{"type":54,"value":627},{"type":48,"tag":589,"props":706,"children":707},{"style":596},[708],{"type":54,"value":632},{"type":48,"tag":589,"props":710,"children":711},{"style":596},[712],{"type":54,"value":637},{"type":48,"tag":589,"props":714,"children":715},{"style":640},[716],{"type":54,"value":717},"We propose a new simple network architecture, the Transformer, based solely on attention mechanisms ...",{"type":48,"tag":589,"props":719,"children":720},{"style":596},[721],{"type":54,"value":627},{"type":48,"tag":589,"props":723,"children":724},{"style":596},[725],{"type":54,"value":652},{"type":48,"tag":589,"props":727,"children":729},{"class":591,"line":728},6,[730,734,738,742,746,750,755,759],{"type":48,"tag":589,"props":731,"children":732},{"style":596},[733],{"type":54,"value":616},{"type":48,"tag":589,"props":735,"children":736},{"style":619},[737],{"type":54,"value":216},{"type":48,"tag":589,"props":739,"children":740},{"style":596},[741],{"type":54,"value":627},{"type":48,"tag":589,"props":743,"children":744},{"style":596},[745],{"type":54,"value":632},{"type":48,"tag":589,"props":747,"children":748},{"style":596},[749],{"type":54,"value":637},{"type":48,"tag":589,"props":751,"children":752},{"style":640},[753],{"type":54,"value":754},"abstract",{"type":48,"tag":589,"props":756,"children":757},{"style":596},[758],{"type":54,"value":627},{"type":48,"tag":589,"props":760,"children":761},{"style":596},[762],{"type":54,"value":652},{"type":48,"tag":589,"props":764,"children":766},{"class":591,"line":765},7,[767,771,775,779,783,787,791],{"type":48,"tag":589,"props":768,"children":769},{"style":596},[770],{"type":54,"value":616},{"type":48,"tag":589,"props":772,"children":773},{"style":619},[774],{"type":54,"value":235},{"type":48,"tag":589,"props":776,"children":777},{"style":596},[778],{"type":54,"value":627},{"type":48,"tag":589,"props":780,"children":781},{"style":596},[782],{"type":54,"value":632},{"type":48,"tag":589,"props":784,"children":785},{"style":596},[786],{"type":54,"value":637},{"type":48,"tag":589,"props":788,"children":789},{"style":640},[790],{"type":54,"value":111},{"type":48,"tag":589,"props":792,"children":793},{"style":596},[794],{"type":54,"value":795},"\"\n",{"type":48,"tag":589,"props":797,"children":799},{"class":591,"line":798},8,[800],{"type":48,"tag":589,"props":801,"children":802},{"style":596},[803],{"type":54,"value":804},"  }\n",{"type":48,"tag":589,"props":806,"children":808},{"class":591,"line":807},9,[809],{"type":48,"tag":589,"props":810,"children":811},{"style":596},[812],{"type":54,"value":813},"]\n",{"type":48,"tag":151,"props":815,"children":817},{"id":816},"surveymd-骨架",[818],{"type":54,"value":819},"survey.md 骨架",{"type":48,"tag":578,"props":821,"children":825},{"className":822,"code":823,"language":824,"meta":583,"style":583},"language-markdown shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","# \u003C主题> 文献调研分析\n\n## 领域整体研究概况\n……[paper_id]……\n\n## 共性共识\n……[paper_id1, paper_id2]……\n\n## 争议矛盾\n……\n\n## 研究空白\n……\n\n## 时序演化\n……\n\n## 方法迭代\n……\n\n## 子主题横向对比\n……\n\n## 总结展望\n……\n","markdown",[826],{"type":48,"tag":69,"props":827,"children":828},{"__ignoreMap":583},[829,843,852,865,893,900,912,920,927,939,947,955,968,976,984,997,1005,1013,1026,1034,1042,1055,1063,1071,1084],{"type":48,"tag":589,"props":830,"children":831},{"class":591,"line":592},[832,837],{"type":48,"tag":589,"props":833,"children":834},{"style":596},[835],{"type":54,"value":836},"# ",{"type":48,"tag":589,"props":838,"children":840},{"style":839},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[841],{"type":54,"value":842},"\u003C主题> 文献调研分析\n",{"type":48,"tag":589,"props":844,"children":845},{"class":591,"line":30},[846],{"type":48,"tag":589,"props":847,"children":849},{"emptyLinePlaceholder":848},true,[850],{"type":54,"value":851},"\n",{"type":48,"tag":589,"props":853,"children":854},{"class":591,"line":610},[855,860],{"type":48,"tag":589,"props":856,"children":857},{"style":596},[858],{"type":54,"value":859},"## ",{"type":48,"tag":589,"props":861,"children":862},{"style":839},[863],{"type":54,"value":864},"领域整体研究概况\n",{"type":48,"tag":589,"props":866,"children":867},{"class":591,"line":655},[868,874,879,883,888],{"type":48,"tag":589,"props":869,"children":871},{"style":870},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[872],{"type":54,"value":873},"……",{"type":48,"tag":589,"props":875,"children":876},{"style":596},[877],{"type":54,"value":878},"[",{"type":48,"tag":589,"props":880,"children":881},{"style":640},[882],{"type":54,"value":622},{"type":48,"tag":589,"props":884,"children":885},{"style":596},[886],{"type":54,"value":887},"]",{"type":48,"tag":589,"props":889,"children":890},{"style":870},[891],{"type":54,"value":892},"……\n",{"type":48,"tag":589,"props":894,"children":895},{"class":591,"line":26},[896],{"type":48,"tag":589,"props":897,"children":898},{"emptyLinePlaceholder":848},[899],{"type":54,"value":851},{"type":48,"tag":589,"props":901,"children":902},{"class":591,"line":728},[903,907],{"type":48,"tag":589,"props":904,"children":905},{"style":596},[906],{"type":54,"value":859},{"type":48,"tag":589,"props":908,"children":909},{"style":839},[910],{"type":54,"value":911},"共性共识\n",{"type":48,"tag":589,"props":913,"children":914},{"class":591,"line":765},[915],{"type":48,"tag":589,"props":916,"children":917},{"style":870},[918],{"type":54,"value":919},"……[paper_id1, paper_id2]……\n",{"type":48,"tag":589,"props":921,"children":922},{"class":591,"line":798},[923],{"type":48,"tag":589,"props":924,"children":925},{"emptyLinePlaceholder":848},[926],{"type":54,"value":851},{"type":48,"tag":589,"props":928,"children":929},{"class":591,"line":807},[930,934],{"type":48,"tag":589,"props":931,"children":932},{"style":596},[933],{"type":54,"value":859},{"type":48,"tag":589,"props":935,"children":936},{"style":839},[937],{"type":54,"value":938},"争议矛盾\n",{"type":48,"tag":589,"props":940,"children":942},{"class":591,"line":941},10,[943],{"type":48,"tag":589,"props":944,"children":945},{"style":870},[946],{"type":54,"value":892},{"type":48,"tag":589,"props":948,"children":950},{"class":591,"line":949},11,[951],{"type":48,"tag":589,"props":952,"children":953},{"emptyLinePlaceholder":848},[954],{"type":54,"value":851},{"type":48,"tag":589,"props":956,"children":958},{"class":591,"line":957},12,[959,963],{"type":48,"tag":589,"props":960,"children":961},{"style":596},[962],{"type":54,"value":859},{"type":48,"tag":589,"props":964,"children":965},{"style":839},[966],{"type":54,"value":967},"研究空白\n",{"type":48,"tag":589,"props":969,"children":971},{"class":591,"line":970},13,[972],{"type":48,"tag":589,"props":973,"children":974},{"style":870},[975],{"type":54,"value":892},{"type":48,"tag":589,"props":977,"children":979},{"class":591,"line":978},14,[980],{"type":48,"tag":589,"props":981,"children":982},{"emptyLinePlaceholder":848},[983],{"type":54,"value":851},{"type":48,"tag":589,"props":985,"children":987},{"class":591,"line":986},15,[988,992],{"type":48,"tag":589,"props":989,"children":990},{"style":596},[991],{"type":54,"value":859},{"type":48,"tag":589,"props":993,"children":994},{"style":839},[995],{"type":54,"value":996},"时序演化\n",{"type":48,"tag":589,"props":998,"children":1000},{"class":591,"line":999},16,[1001],{"type":48,"tag":589,"props":1002,"children":1003},{"style":870},[1004],{"type":54,"value":892},{"type":48,"tag":589,"props":1006,"children":1008},{"class":591,"line":1007},17,[1009],{"type":48,"tag":589,"props":1010,"children":1011},{"emptyLinePlaceholder":848},[1012],{"type":54,"value":851},{"type":48,"tag":589,"props":1014,"children":1016},{"class":591,"line":1015},18,[1017,1021],{"type":48,"tag":589,"props":1018,"children":1019},{"style":596},[1020],{"type":54,"value":859},{"type":48,"tag":589,"props":1022,"children":1023},{"style":839},[1024],{"type":54,"value":1025},"方法迭代\n",{"type":48,"tag":589,"props":1027,"children":1029},{"class":591,"line":1028},19,[1030],{"type":48,"tag":589,"props":1031,"children":1032},{"style":870},[1033],{"type":54,"value":892},{"type":48,"tag":589,"props":1035,"children":1037},{"class":591,"line":1036},20,[1038],{"type":48,"tag":589,"props":1039,"children":1040},{"emptyLinePlaceholder":848},[1041],{"type":54,"value":851},{"type":48,"tag":589,"props":1043,"children":1045},{"class":591,"line":1044},21,[1046,1050],{"type":48,"tag":589,"props":1047,"children":1048},{"style":596},[1049],{"type":54,"value":859},{"type":48,"tag":589,"props":1051,"children":1052},{"style":839},[1053],{"type":54,"value":1054},"子主题横向对比\n",{"type":48,"tag":589,"props":1056,"children":1058},{"class":591,"line":1057},22,[1059],{"type":48,"tag":589,"props":1060,"children":1061},{"style":870},[1062],{"type":54,"value":892},{"type":48,"tag":589,"props":1064,"children":1066},{"class":591,"line":1065},23,[1067],{"type":48,"tag":589,"props":1068,"children":1069},{"emptyLinePlaceholder":848},[1070],{"type":54,"value":851},{"type":48,"tag":589,"props":1072,"children":1074},{"class":591,"line":1073},24,[1075,1079],{"type":48,"tag":589,"props":1076,"children":1077},{"style":596},[1078],{"type":54,"value":859},{"type":48,"tag":589,"props":1080,"children":1081},{"style":839},[1082],{"type":54,"value":1083},"总结展望\n",{"type":48,"tag":589,"props":1085,"children":1087},{"class":591,"line":1086},25,[1088],{"type":48,"tag":589,"props":1089,"children":1090},{"style":870},[1091],{"type":54,"value":892},{"type":48,"tag":57,"props":1093,"children":1095},{"id":1094},"本技能不做什么",[1096],{"type":54,"value":1094},{"type":48,"tag":163,"props":1098,"children":1099},{},[1100,1112,1123,1128,1133],{"type":48,"tag":124,"props":1101,"children":1102},{},[1103,1105,1110],{"type":54,"value":1104},"不写成文综述（交给 review-writing）；",{"type":48,"tag":69,"props":1106,"children":1108},{"className":1107},[],[1109],{"type":54,"value":90},{"type":54,"value":1111}," 是分析底稿而非成稿。",{"type":48,"tag":124,"props":1113,"children":1114},{},[1115,1117,1122],{"type":54,"value":1116},"不编造 quote 或页码；读不到就标 ",{"type":48,"tag":69,"props":1118,"children":1120},{"className":1119},[],[1121],{"type":54,"value":111},{"type":54,"value":92},{"type":48,"tag":124,"props":1124,"children":1125},{},[1126],{"type":54,"value":1127},"不核验参考文献真伪（交给 citation-verify）。",{"type":48,"tag":124,"props":1129,"children":1130},{},[1131],{"type":54,"value":1132},"不补充新检索；证据不足时如实标注，而不是自己临时补文献。",{"type":48,"tag":124,"props":1134,"children":1135},{},[1136],{"type":54,"value":1137},"不输出 8 字段之外的分析维度（新增维度会破坏 evidence-map 白名单契约）。",{"type":48,"tag":57,"props":1139,"children":1141},{"id":1140},"收尾与下一步",[1142],{"type":54,"value":1140},{"type":48,"tag":120,"props":1144,"children":1145},{},[1146,1151,1162],{"type":48,"tag":124,"props":1147,"children":1148},{},[1149],{"type":54,"value":1150},"汇总：文献篇数、EvidenceItem 条数、8 字段中证据充足 \u002F 不足各几项。",{"type":48,"tag":124,"props":1152,"children":1153},{},[1154,1156,1161],{"type":54,"value":1155},"指向 ",{"type":48,"tag":69,"props":1157,"children":1159},{"className":1158},[],[1160],{"type":54,"value":535},{"type":54,"value":92},{"type":48,"tag":124,"props":1163,"children":1164},{},[1165],{"type":54,"value":1166},"建议下一步：运行 review-writing 成文；或对证据不足的字段回到\nliterature-search 定向补检后重新分析。",{"type":48,"tag":1168,"props":1169,"children":1170},"style",{},[1171],{"type":54,"value":1172},"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":1174,"total":1375},[1175,1199,1215,1234,1249,1269,1287,1305,1320,1336,1355,1365],{"slug":1176,"name":1176,"fn":1177,"description":1178,"org":1179,"tags":1180,"stars":1196,"repoUrl":1197,"updatedAt":1198},"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},[1181,1184,1187,1190,1193],{"name":1182,"slug":1183,"type":16},"Accessibility","accessibility",{"name":1185,"slug":1186,"type":16},"Android","android",{"name":1188,"slug":1189,"type":16},"Kotlin","kotlin",{"name":1191,"slug":1192,"type":16},"Mobile","mobile",{"name":1194,"slug":1195,"type":16},"UI Components","ui-components",13030,"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002Fskills","2026-07-13T06:16:54.247834",{"slug":1200,"name":1200,"fn":1201,"description":1202,"org":1203,"tags":1204,"stars":1196,"repoUrl":1197,"updatedAt":1214},"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},[1205,1208,1211],{"name":1206,"slug":1207,"type":16},"Agents","agents",{"name":1209,"slug":1210,"type":16},"Audio","audio",{"name":1212,"slug":1213,"type":16},"Creative","creative","2026-07-13T06:16:35.130644",{"slug":1216,"name":1216,"fn":1217,"description":1218,"org":1219,"tags":1220,"stars":1196,"repoUrl":1197,"updatedAt":1233},"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},[1221,1224,1227,1230],{"name":1222,"slug":1223,"type":16},"Design","design",{"name":1225,"slug":1226,"type":16},"Presentations","presentations",{"name":1228,"slug":1229,"type":16},"Themes","themes",{"name":1231,"slug":1232,"type":16},"Typography","typography","2026-07-13T06:17:02.785587",{"slug":1235,"name":1235,"fn":1236,"description":1237,"org":1238,"tags":1239,"stars":1196,"repoUrl":1197,"updatedAt":1248},"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},[1240,1241,1244,1247],{"name":1222,"slug":1223,"type":16},{"name":1242,"slug":1243,"type":16},"Design System","design-system",{"name":1245,"slug":1246,"type":16},"PowerPoint","powerpoint",{"name":1225,"slug":1226,"type":16},"2026-07-13T06:17:10.398389",{"slug":1250,"name":1250,"fn":1251,"description":1252,"org":1253,"tags":1254,"stars":1196,"repoUrl":1197,"updatedAt":1268},"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},[1255,1258,1261,1262,1265],{"name":1256,"slug":1257,"type":16},"Dart","dart",{"name":1259,"slug":1260,"type":16},"Flutter","flutter",{"name":1191,"slug":1192,"type":16},{"name":1263,"slug":1264,"type":16},"Performance","performance",{"name":1266,"slug":1267,"type":16},"State Management","state-management","2026-07-13T06:16:36.626679",{"slug":1270,"name":1270,"fn":1271,"description":1272,"org":1273,"tags":1274,"stars":1196,"repoUrl":1197,"updatedAt":1286},"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},[1275,1278,1279,1280,1283],{"name":1276,"slug":1277,"type":16},"Animation","animation",{"name":1212,"slug":1213,"type":16},{"name":1222,"slug":1223,"type":16},{"name":1281,"slug":1282,"type":16},"Frontend","frontend",{"name":1284,"slug":1285,"type":16},"Web Development","web-development","2026-07-13T06:16:39.108827",{"slug":1288,"name":1288,"fn":1289,"description":1290,"org":1291,"tags":1292,"stars":1196,"repoUrl":1197,"updatedAt":1304},"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},[1293,1296,1297,1300,1303],{"name":1294,"slug":1295,"type":16},"Backend","backend",{"name":1281,"slug":1282,"type":16},{"name":1298,"slug":1299,"type":16},"Full-stack","full-stack",{"name":1301,"slug":1302,"type":16},"REST API","rest-api",{"name":1284,"slug":1285,"type":16},"2026-07-13T06:16:43.219005",{"slug":1306,"name":1306,"fn":1307,"description":1308,"org":1309,"tags":1310,"stars":1196,"repoUrl":1197,"updatedAt":1319},"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},[1311,1312,1313,1316],{"name":1276,"slug":1277,"type":16},{"name":1212,"slug":1213,"type":16},{"name":1314,"slug":1315,"type":16},"Images","images",{"name":1317,"slug":1318,"type":16},"Media","media","2026-07-13T06:16:51.74461",{"slug":1321,"name":1321,"fn":1322,"description":1323,"org":1324,"tags":1325,"stars":1196,"repoUrl":1197,"updatedAt":1335},"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},[1326,1327,1330,1331,1334],{"name":1182,"slug":1183,"type":16},{"name":1328,"slug":1329,"type":16},"iOS","ios",{"name":1191,"slug":1192,"type":16},{"name":1332,"slug":1333,"type":16},"SwiftUI","swiftui",{"name":1194,"slug":1195,"type":16},"2026-07-13T06:16:55.686092",{"slug":1337,"name":1337,"fn":1338,"description":1339,"org":1340,"tags":1341,"stars":1196,"repoUrl":1197,"updatedAt":1354},"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},[1342,1345,1348,1351],{"name":1343,"slug":1344,"type":16},"Documents","documents",{"name":1346,"slug":1347,"type":16},"DOCX","docx",{"name":1349,"slug":1350,"type":16},"Office","office",{"name":1352,"slug":1353,"type":16},"Templates","templates","2026-07-13T06:16:40.461868",{"slug":1356,"name":1356,"fn":1357,"description":1358,"org":1359,"tags":1360,"stars":1196,"repoUrl":1197,"updatedAt":1364},"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},[1361,1362,1363],{"name":1209,"slug":1210,"type":16},{"name":1212,"slug":1213,"type":16},{"name":1317,"slug":1318,"type":16},"2026-07-13T06:16:50.381758",{"slug":1366,"name":1366,"fn":1367,"description":1368,"org":1369,"tags":1370,"stars":1196,"repoUrl":1197,"updatedAt":1374},"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},[1371,1372,1373],{"name":1209,"slug":1210,"type":16},{"name":1212,"slug":1213,"type":16},{"name":1317,"slug":1318,"type":16},"2026-07-13T06:16:57.002997",84,{"items":1377,"total":1474},[1378,1394,1409,1421,1433,1448,1462],{"slug":1379,"name":1379,"fn":1380,"description":1381,"org":1382,"tags":1383,"stars":26,"repoUrl":27,"updatedAt":1393},"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},[1384,1387,1390],{"name":1385,"slug":1386,"type":16},"Content Creation","content-creation",{"name":1388,"slug":1389,"type":16},"MCP","mcp",{"name":1391,"slug":1392,"type":16},"Task Management","task-management","2026-08-18T03:49:38.751656",{"slug":1395,"name":1395,"fn":1396,"description":1397,"org":1398,"tags":1399,"stars":26,"repoUrl":27,"updatedAt":1408},"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},[1400,1403,1404,1407],{"name":1401,"slug":1402,"type":16},"Code Analysis","code-analysis",{"name":18,"slug":19,"type":16},{"name":1405,"slug":1406,"type":16},"QA","qa",{"name":14,"slug":15,"type":16},"2026-08-21T03:59:17.615117",{"slug":1410,"name":1410,"fn":1411,"description":1412,"org":1413,"tags":1414,"stars":26,"repoUrl":27,"updatedAt":1420},"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},[1415,1418,1419],{"name":1416,"slug":1417,"type":16},"Audit","audit",{"name":1401,"slug":1402,"type":16},{"name":14,"slug":15,"type":16},"2026-08-21T03:59:02.154691",{"slug":1422,"name":1422,"fn":1423,"description":1424,"org":1425,"tags":1426,"stars":26,"repoUrl":27,"updatedAt":1432},"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},[1427,1430,1431],{"name":1428,"slug":1429,"type":16},"Data Cleaning","data-cleaning",{"name":1343,"slug":1344,"type":16},{"name":14,"slug":15,"type":16},"2026-08-21T03:59:12.24404",{"slug":1434,"name":1434,"fn":1435,"description":1436,"org":1437,"tags":1438,"stars":26,"repoUrl":27,"updatedAt":1447},"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},[1439,1440,1443,1446],{"name":18,"slug":19,"type":16},{"name":1441,"slug":1442,"type":16},"Onboarding","onboarding",{"name":1444,"slug":1445,"type":16},"Productivity","productivity",{"name":14,"slug":15,"type":16},"2026-08-21T03:59:58.579998",{"slug":1449,"name":1449,"fn":1450,"description":1451,"org":1452,"tags":1453,"stars":26,"repoUrl":27,"updatedAt":1461},"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},[1454,1457,1460],{"name":1455,"slug":1456,"type":16},"Best Practices","best-practices",{"name":1458,"slug":1459,"type":16},"Configuration","configuration",{"name":14,"slug":15,"type":16},"2026-08-21T03:59:35.867596",{"slug":1463,"name":1463,"fn":1464,"description":1465,"org":1466,"tags":1467,"stars":26,"repoUrl":27,"updatedAt":1473},"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},[1468,1469,1472],{"name":1388,"slug":1389,"type":16},{"name":1470,"slug":1471,"type":16},"Scheduling","scheduling",{"name":1391,"slug":1392,"type":16},"2026-08-18T03:49:37.126385",36]