[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-minimax-spatial-epi":3,"mdc-fu7hba-key":40,"related-repo-minimax-spatial-epi":961,"related-org-minimax-spatial-epi":1064},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":12,"stars":29,"repoUrl":30,"updatedAt":31,"license":32,"forks":33,"topics":34,"repo":35,"sourceUrl":38,"mdContent":39},"spatial-epi","analyze spatial epidemiology and disease data","当用户需要比较分地区发病率\u002F死亡率、计算标准化发病比 SMR、处理小区域 率不稳定问题、检测疾病空间聚集性、制作分级统计地图（choropleth）、 评审一张疾病地图的规范性时使用。同义场景：空间流行病学、疾病地图、 SMR 标化、间接标化、小区域估计、率平滑、Moran's I 莫兰指数、空间自相关、 扫描统计量、SaTScan、GeoDa、聚集性分析、热点分析、choropleth 制图规范、 \"帮我算算各县 SMR\"\"这病有没有空间聚集\"。",{"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",[13,17,20,23,26],{"name":14,"slug":15,"type":16},"Research","research","tag",{"name":18,"slug":19,"type":16},"Data Visualization","data-visualization",{"name":21,"slug":22,"type":16},"Healthcare","healthcare",{"name":24,"slug":25,"type":16},"Data Analysis","data-analysis",{"name":27,"slug":28,"type":16},"Statistics","statistics",5,"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMiniMax-Code-Plugins","2026-08-21T03:59:12.584368",null,2,[],{"repoUrl":30,"stars":29,"forks":33,"topics":36,"description":37},[],"Community registry and contribution toolkit for MiniMax Code plugins.","https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002FMiniMax-Code-Plugins\u002Ftree\u002FHEAD\u002Fplugins\u002FHylouis233\u002Fopenscience\u002Fskills\u002Fspatial-epi","---\nname: spatial-epi\ndescription: >-\n  当用户需要比较分地区发病率\u002F死亡率、计算标准化发病比 SMR、处理小区域\n  率不稳定问题、检测疾病空间聚集性、制作分级统计地图（choropleth）、\n  评审一张疾病地图的规范性时使用。同义场景：空间流行病学、疾病地图、\n  SMR 标化、间接标化、小区域估计、率平滑、Moran's I 莫兰指数、空间自相关、\n  扫描统计量、SaTScan、GeoDa、聚集性分析、热点分析、choropleth 制图规范、\n  \"帮我算算各县 SMR\"\"这病有没有空间聚集\"。\nargument-hint: '[地区-病例-人口 表路径]'\nmetadata:\n  domains: [epidemiology, public-health]\n  last_reviewed: '2026-08-18'\n---\n\n# spatial-epi：空间流行病学分析规程\n\n## 目的\n\n把\"分地区的病例数与人口数\"变成可审查的空间分析：从 SMR 计算与率的\n稳定性评估，到聚集性检测的方法选择，再到分级统计地图的制图规范。\n本技能不附带脚本（空间计算依赖 GIS\u002F统计环境），但给出逐步计算表格\n模板，保证每一步可手工复核。\n\n铁律：\n\n1. **地图会放大错觉**：小人口地区的率高波动是统计现象，不是\"热点\"\n   证据；任何聚集结论必须说明稳定性处理。\n2. **率必须有分母**：只画病例计数地图时，必须注明\"未按人口校正，\n   不反映风险高低\"。\n3. 边界与坐标：使用合规的行政区划边界数据（注意国界、争议地区\n   表达的合规性）；边界来源带来源标签。\n\n## 前置检查\n\n1. 数据三件套齐备：分区**病例数**、分区**人口数**（分母）、参照\n   **标准率**（全国\u002F全省或全研究区合计率）。缺分母时停止，回\n   epi-data-access 取人口数据。\n2. 地区口径一致：病例分区与人口分区同一套行政区划代码与年份；\n   区划调整年份要对齐，否则在备注中声明错位。\n3. 个案地址数据已按 epi-data-access 第 4 节去标识化；分析单元\n   不小于乡镇\u002F街道（更细单元需评估再识别风险）。\n4. 明确分析目的：描述分布 \u002F 找高风险区 \u002F 检验聚集存在性——三者\n   方法与结论强度不同。\n\n## 1 · 标准化发病比（SMR）\n\nSMR 回答：\"若该区人口结构下按标准率发病，预期会有多少例？实际\n观察是预期的几倍？\"（间接标化法）\n\n计算步骤（逐区一行）：\n\n1. 取得标准率 λ（如全研究区合计发病率 = 总病例\u002F总人口）。\n2. 每区**预期病例数** Eᵢ = λ × 该区人口 Pᵢ。（分年龄结构做标化时，\n   Eᵢ = Σⱼ λⱼ × Pᵢⱼ，j 为年龄组；年龄数据不可得时用粗率版并在\n   局限中声明。）\n3. **SMRᵢ** = 观察病例数 Oᵢ \u002F Eᵢ。SMR > 1 表示高于标准水平。\n4. 解读纪律：SMR 是**比值**，1.2 与 2.0 的差别要结合 Eᵢ 大小看；\n   Eᵢ 很小时 SMR 极不稳定（见第 2 节）。\n5. 不确定度：需要区间时按 Poisson 近似计算置信区间 [模型知识—\n   待核实：常用精确法或 Byar 近似，公式查统计教材后引用]。\n\n### 计算表格模板（粗率版）\n\n| 地区代码 | 病例 O | 人口 P | 预期 E = λ·P | SMR = O\u002FE | 备注 |\n| --- | --- | --- | --- | --- | --- |\n| … | … | … | … | … | … |\n\n表头注明：标准率 λ 取值与来源标签、人口口径年份、病例时间窗。\n\n## 2 · 率的面失稳与小区域平滑\n\n问题：人口小的区，1–2 个病例就会让率或 SMR 剧烈波动；分级地图上\n\"最高\"的往往是人口最小的区。这是**小样本噪声**，不是流行病学信号。\n\n处理概念（按从轻到重）：\n\n1. **合并相邻小单元**或累积多年数据，抬高每区期望数；\n2. **经验贝叶斯（EB）平滑**：把各区率向全局均值收缩，收缩幅度随\n   该区人口增大而减小 [模型知识—待核实：具体实现见 GeoDa 文档]；\n3. 报告纪律：平滑值与原始值**并列呈现**，不得只给平滑后数字；\n   说明平滑方法、参数与软件版本。\n\n## 3 · 聚集性检测方法概述\n\n两类常用方法，择一并说明理由：\n\n1. **全局\u002F局部空间自相关（Moran's I 与 LISA）**：检验\"率值相近的\n   区是否在空间上相邻\"。Moran's I 给全局一个数，LISA 定位到区\n   [模型知识—待核实]。工具建议：**GeoDa**（开源桌面软件）\n   [模型知识—待核实]。\n2. **空间扫描统计量**：用移动扫描圆\u002F窗口寻找\"窗口内率显著高于\n   窗口外\"的聚集区，输出最可能聚集区与统计量 [模型知识—待核实]。\n   工具建议：**SaTScan**（免费软件，需注册）[模型知识—待核实]。\n\n使用纪律：\n\n- 空间权重\u002F扫描参数的设定（邻接定义、最大窗口）影响结果，必须\n  写明并做一至两组参数敏感性对比；\n- 聚集显著 ≠ 病因线索成立：聚集可能源于诊断可及性、报告差异、\n  人口结构；讨论节列出非病因解释；\n- 本技能只给规程与工具指针，实际运行由用户在相应软件中完成，\n  结果与参数截图\u002F日志落盘并登记 provenance。\n\n## 4 · 分级统计地图（choropleth）制作规范\n\n1. **画什么**：优先画率或 SMR，不画原始计数；确需展示计数时\n   图题\u002F图注写明\"病例数，未按人口校正\"。\n2. **分级数**：4–7 级为宜 [模型知识—待核实：制图学通行建议]；\n   分级方法（等距\u002F分位数\u002F自然断点）写进图注，分位数法每级区数\n   相近但不反映数值间距，等距法反之——按讲述目的选择并说明。\n3. **配色**：使用色盲友好的顺序色板（如单色渐深或 ColorBrewer\n   顺序系列）[模型知识—待核实]；避免红绿对比；发散色板仅用于\n   以某基准为中心的双极变量（如 SMR 以 1 为中心）。\n4. **图件要素**：标题含指标+时间窗、图注含分级方法与数据来源\n   标签、比例尺\u002F指北针按出版要求、底图边界来源合规声明。\n5. **伦理**：个案点图（dot map）不得精确到可再识别的位置；\n   聚集区结果对外发布前考虑对当地居民的影响（guardrail 第 8 条）。\n\n## 输出模板\n\n```markdown\n## 空间分析底稿（\u003C日期>）\n\n### 数据与口径\n- 病例：\u003C来源标签>，时间窗 \u003C起止>；人口：\u003C来源标签>，口径年 \u003C年份>\n- 行政区划：\u003C层级与版本>，区划调整对齐说明\n\n### SMR 表\n（第 1 节表格，含 λ 取值与来源）\n\n### 稳定性\n- 小期望数地区（E\u003C阈值的区）：\u003C列出>，处理方式：合并\u002FEB 平滑\u002F仅提示\n- 平滑与原始并列图：\u003C路径>\n\n### 聚集性\n- 方法与工具：\u003CMoran's I（GeoDa）\u002F 扫描统计量（SaTScan）>，\n  参数：\u003C权重\u002F窗口设定>\n- 结果：\u003C全局统计量\u002F聚集区清单>[实验数据]\n- 非病因解释：\u003C诊断可及性\u002F报告差异\u002F人口结构>\n\n### 地图\n- 图件路径：\u003Cfigures\u002F…>；分级方法、色板、来源标签齐备性自查通过\n```\n\n## 本技能不做什么\n\n- **不替代 GIS\u002F统计软件**：不手算 Moran's I 或扫描统计量；工具运行\n  与参数日志由用户完成，本技能审口径与解读。\n- **不做生态学因果推断**：地区水平的相关\u002F聚集不推出个体水平因果\n  （生态学谬误）；结论措辞限于\"提示空间分布特征\"。\n- **不提供精确到户的病例点位展示**：再识别风险高的展示形式一律\n  劝阻。\n- **不判断行政区划与地图合规细节**：国界与争议地区表达以官方\n  标准地图为准，拿不准时提示用户查标准地图服务，不自行裁决。\n- **不编造方法学参数**：平滑方法参数、检验公式等查文档后引用，\n  模型印象标 `[模型知识—待核实]`。\n\n## 收尾与下一步\n\n1. 汇总：SMR 表关键行、稳定性处理、聚集性结论（含非病因解释）。\n2. 指向产物（SMR 表、地图、工具日志）并登记 provenance。\n3. 建议下一步：\n   - 发现聚集区需现场核实 → `outbreak-analysis`；\n   - 地图与结果写入报告\u002F论文 → `epi-writing`；\n   - 缺人口或边界数据 → `epi-data-access`。\n",{"data":41,"body":48},{"name":4,"description":6,"argument-hint":42,"metadata":43},"[地区-病例-人口 表路径]",{"domains":44,"last_reviewed":47},[45,46],"epidemiology","public-health","2026-08-18",{"type":49,"children":50},"root",[51,60,66,72,77,108,113,157,163,168,173,228,235,311,316,322,334,339,381,387,392,452,457,476,482,548,553,828,833,893,898,955],{"type":52,"tag":53,"props":54,"children":56},"element","h1",{"id":55},"spatial-epi空间流行病学分析规程",[57],{"type":58,"value":59},"text","spatial-epi：空间流行病学分析规程",{"type":52,"tag":61,"props":62,"children":64},"h2",{"id":63},"目的",[65],{"type":58,"value":63},{"type":52,"tag":67,"props":68,"children":69},"p",{},[70],{"type":58,"value":71},"把\"分地区的病例数与人口数\"变成可审查的空间分析：从 SMR 计算与率的\n稳定性评估，到聚集性检测的方法选择，再到分级统计地图的制图规范。\n本技能不附带脚本（空间计算依赖 GIS\u002F统计环境），但给出逐步计算表格\n模板，保证每一步可手工复核。",{"type":52,"tag":67,"props":73,"children":74},{},[75],{"type":58,"value":76},"铁律：",{"type":52,"tag":78,"props":79,"children":80},"ol",{},[81,93,103],{"type":52,"tag":82,"props":83,"children":84},"li",{},[85,91],{"type":52,"tag":86,"props":87,"children":88},"strong",{},[89],{"type":58,"value":90},"地图会放大错觉",{"type":58,"value":92},"：小人口地区的率高波动是统计现象，不是\"热点\"\n证据；任何聚集结论必须说明稳定性处理。",{"type":52,"tag":82,"props":94,"children":95},{},[96,101],{"type":52,"tag":86,"props":97,"children":98},{},[99],{"type":58,"value":100},"率必须有分母",{"type":58,"value":102},"：只画病例计数地图时，必须注明\"未按人口校正，\n不反映风险高低\"。",{"type":52,"tag":82,"props":104,"children":105},{},[106],{"type":58,"value":107},"边界与坐标：使用合规的行政区划边界数据（注意国界、争议地区\n表达的合规性）；边界来源带来源标签。",{"type":52,"tag":61,"props":109,"children":111},{"id":110},"前置检查",[112],{"type":58,"value":110},{"type":52,"tag":78,"props":114,"children":115},{},[116,142,147,152],{"type":52,"tag":82,"props":117,"children":118},{},[119,121,126,128,133,135,140],{"type":58,"value":120},"数据三件套齐备：分区",{"type":52,"tag":86,"props":122,"children":123},{},[124],{"type":58,"value":125},"病例数",{"type":58,"value":127},"、分区",{"type":52,"tag":86,"props":129,"children":130},{},[131],{"type":58,"value":132},"人口数",{"type":58,"value":134},"（分母）、参照\n",{"type":52,"tag":86,"props":136,"children":137},{},[138],{"type":58,"value":139},"标准率",{"type":58,"value":141},"（全国\u002F全省或全研究区合计率）。缺分母时停止，回\nepi-data-access 取人口数据。",{"type":52,"tag":82,"props":143,"children":144},{},[145],{"type":58,"value":146},"地区口径一致：病例分区与人口分区同一套行政区划代码与年份；\n区划调整年份要对齐，否则在备注中声明错位。",{"type":52,"tag":82,"props":148,"children":149},{},[150],{"type":58,"value":151},"个案地址数据已按 epi-data-access 第 4 节去标识化；分析单元\n不小于乡镇\u002F街道（更细单元需评估再识别风险）。",{"type":52,"tag":82,"props":153,"children":154},{},[155],{"type":58,"value":156},"明确分析目的：描述分布 \u002F 找高风险区 \u002F 检验聚集存在性——三者\n方法与结论强度不同。",{"type":52,"tag":61,"props":158,"children":160},{"id":159},"_1-标准化发病比smr",[161],{"type":58,"value":162},"1 · 标准化发病比（SMR）",{"type":52,"tag":67,"props":164,"children":165},{},[166],{"type":58,"value":167},"SMR 回答：\"若该区人口结构下按标准率发病，预期会有多少例？实际\n观察是预期的几倍？\"（间接标化法）",{"type":52,"tag":67,"props":169,"children":170},{},[171],{"type":58,"value":172},"计算步骤（逐区一行）：",{"type":52,"tag":78,"props":174,"children":175},{},[176,181,193,203,215],{"type":52,"tag":82,"props":177,"children":178},{},[179],{"type":58,"value":180},"取得标准率 λ（如全研究区合计发病率 = 总病例\u002F总人口）。",{"type":52,"tag":82,"props":182,"children":183},{},[184,186,191],{"type":58,"value":185},"每区",{"type":52,"tag":86,"props":187,"children":188},{},[189],{"type":58,"value":190},"预期病例数",{"type":58,"value":192}," Eᵢ = λ × 该区人口 Pᵢ。（分年龄结构做标化时，\nEᵢ = Σⱼ λⱼ × Pᵢⱼ，j 为年龄组；年龄数据不可得时用粗率版并在\n局限中声明。）",{"type":52,"tag":82,"props":194,"children":195},{},[196,201],{"type":52,"tag":86,"props":197,"children":198},{},[199],{"type":58,"value":200},"SMRᵢ",{"type":58,"value":202}," = 观察病例数 Oᵢ \u002F Eᵢ。SMR > 1 表示高于标准水平。",{"type":52,"tag":82,"props":204,"children":205},{},[206,208,213],{"type":58,"value":207},"解读纪律：SMR 是",{"type":52,"tag":86,"props":209,"children":210},{},[211],{"type":58,"value":212},"比值",{"type":58,"value":214},"，1.2 与 2.0 的差别要结合 Eᵢ 大小看；\nEᵢ 很小时 SMR 极不稳定（见第 2 节）。",{"type":52,"tag":82,"props":216,"children":217},{},[218,220,226],{"type":58,"value":219},"不确定度：需要区间时按 Poisson 近似计算置信区间 ",{"type":52,"tag":221,"props":222,"children":223},"span",{},[224],{"type":58,"value":225},"模型知识—\n待核实：常用精确法或 Byar 近似，公式查统计教材后引用",{"type":58,"value":227},"。",{"type":52,"tag":229,"props":230,"children":232},"h3",{"id":231},"计算表格模板粗率版",[233],{"type":58,"value":234},"计算表格模板（粗率版）",{"type":52,"tag":236,"props":237,"children":238},"table",{},[239,278],{"type":52,"tag":240,"props":241,"children":242},"thead",{},[243],{"type":52,"tag":244,"props":245,"children":246},"tr",{},[247,253,258,263,268,273],{"type":52,"tag":248,"props":249,"children":250},"th",{},[251],{"type":58,"value":252},"地区代码",{"type":52,"tag":248,"props":254,"children":255},{},[256],{"type":58,"value":257},"病例 O",{"type":52,"tag":248,"props":259,"children":260},{},[261],{"type":58,"value":262},"人口 P",{"type":52,"tag":248,"props":264,"children":265},{},[266],{"type":58,"value":267},"预期 E = λ·P",{"type":52,"tag":248,"props":269,"children":270},{},[271],{"type":58,"value":272},"SMR = O\u002FE",{"type":52,"tag":248,"props":274,"children":275},{},[276],{"type":58,"value":277},"备注",{"type":52,"tag":279,"props":280,"children":281},"tbody",{},[282],{"type":52,"tag":244,"props":283,"children":284},{},[285,291,295,299,303,307],{"type":52,"tag":286,"props":287,"children":288},"td",{},[289],{"type":58,"value":290},"…",{"type":52,"tag":286,"props":292,"children":293},{},[294],{"type":58,"value":290},{"type":52,"tag":286,"props":296,"children":297},{},[298],{"type":58,"value":290},{"type":52,"tag":286,"props":300,"children":301},{},[302],{"type":58,"value":290},{"type":52,"tag":286,"props":304,"children":305},{},[306],{"type":58,"value":290},{"type":52,"tag":286,"props":308,"children":309},{},[310],{"type":58,"value":290},{"type":52,"tag":67,"props":312,"children":313},{},[314],{"type":58,"value":315},"表头注明：标准率 λ 取值与来源标签、人口口径年份、病例时间窗。",{"type":52,"tag":61,"props":317,"children":319},{"id":318},"_2-率的面失稳与小区域平滑",[320],{"type":58,"value":321},"2 · 率的面失稳与小区域平滑",{"type":52,"tag":67,"props":323,"children":324},{},[325,327,332],{"type":58,"value":326},"问题：人口小的区，1–2 个病例就会让率或 SMR 剧烈波动；分级地图上\n\"最高\"的往往是人口最小的区。这是",{"type":52,"tag":86,"props":328,"children":329},{},[330],{"type":58,"value":331},"小样本噪声",{"type":58,"value":333},"，不是流行病学信号。",{"type":52,"tag":67,"props":335,"children":336},{},[337],{"type":58,"value":338},"处理概念（按从轻到重）：",{"type":52,"tag":78,"props":340,"children":341},{},[342,352,369],{"type":52,"tag":82,"props":343,"children":344},{},[345,350],{"type":52,"tag":86,"props":346,"children":347},{},[348],{"type":58,"value":349},"合并相邻小单元",{"type":58,"value":351},"或累积多年数据，抬高每区期望数；",{"type":52,"tag":82,"props":353,"children":354},{},[355,360,362,367],{"type":52,"tag":86,"props":356,"children":357},{},[358],{"type":58,"value":359},"经验贝叶斯（EB）平滑",{"type":58,"value":361},"：把各区率向全局均值收缩，收缩幅度随\n该区人口增大而减小 ",{"type":52,"tag":221,"props":363,"children":364},{},[365],{"type":58,"value":366},"模型知识—待核实：具体实现见 GeoDa 文档",{"type":58,"value":368},"；",{"type":52,"tag":82,"props":370,"children":371},{},[372,374,379],{"type":58,"value":373},"报告纪律：平滑值与原始值",{"type":52,"tag":86,"props":375,"children":376},{},[377],{"type":58,"value":378},"并列呈现",{"type":58,"value":380},"，不得只给平滑后数字；\n说明平滑方法、参数与软件版本。",{"type":52,"tag":61,"props":382,"children":384},{"id":383},"_3-聚集性检测方法概述",[385],{"type":58,"value":386},"3 · 聚集性检测方法概述",{"type":52,"tag":67,"props":388,"children":389},{},[390],{"type":58,"value":391},"两类常用方法，择一并说明理由：",{"type":52,"tag":78,"props":393,"children":394},{},[395,424],{"type":52,"tag":82,"props":396,"children":397},{},[398,403,405,410,412,417,419,423],{"type":52,"tag":86,"props":399,"children":400},{},[401],{"type":58,"value":402},"全局\u002F局部空间自相关（Moran's I 与 LISA）",{"type":58,"value":404},"：检验\"率值相近的\n区是否在空间上相邻\"。Moran's I 给全局一个数，LISA 定位到区\n",{"type":52,"tag":221,"props":406,"children":407},{},[408],{"type":58,"value":409},"模型知识—待核实",{"type":58,"value":411},"。工具建议：",{"type":52,"tag":86,"props":413,"children":414},{},[415],{"type":58,"value":416},"GeoDa",{"type":58,"value":418},"（开源桌面软件）\n",{"type":52,"tag":221,"props":420,"children":421},{},[422],{"type":58,"value":409},{"type":58,"value":227},{"type":52,"tag":82,"props":425,"children":426},{},[427,432,434,438,440,445,447,451],{"type":52,"tag":86,"props":428,"children":429},{},[430],{"type":58,"value":431},"空间扫描统计量",{"type":58,"value":433},"：用移动扫描圆\u002F窗口寻找\"窗口内率显著高于\n窗口外\"的聚集区，输出最可能聚集区与统计量 ",{"type":52,"tag":221,"props":435,"children":436},{},[437],{"type":58,"value":409},{"type":58,"value":439},"。\n工具建议：",{"type":52,"tag":86,"props":441,"children":442},{},[443],{"type":58,"value":444},"SaTScan",{"type":58,"value":446},"（免费软件，需注册）",{"type":52,"tag":221,"props":448,"children":449},{},[450],{"type":58,"value":409},{"type":58,"value":227},{"type":52,"tag":67,"props":453,"children":454},{},[455],{"type":58,"value":456},"使用纪律：",{"type":52,"tag":458,"props":459,"children":460},"ul",{},[461,466,471],{"type":52,"tag":82,"props":462,"children":463},{},[464],{"type":58,"value":465},"空间权重\u002F扫描参数的设定（邻接定义、最大窗口）影响结果，必须\n写明并做一至两组参数敏感性对比；",{"type":52,"tag":82,"props":467,"children":468},{},[469],{"type":58,"value":470},"聚集显著 ≠ 病因线索成立：聚集可能源于诊断可及性、报告差异、\n人口结构；讨论节列出非病因解释；",{"type":52,"tag":82,"props":472,"children":473},{},[474],{"type":58,"value":475},"本技能只给规程与工具指针，实际运行由用户在相应软件中完成，\n结果与参数截图\u002F日志落盘并登记 provenance。",{"type":52,"tag":61,"props":477,"children":479},{"id":478},"_4-分级统计地图choropleth制作规范",[480],{"type":58,"value":481},"4 · 分级统计地图（choropleth）制作规范",{"type":52,"tag":78,"props":483,"children":484},{},[485,495,512,528,538],{"type":52,"tag":82,"props":486,"children":487},{},[488,493],{"type":52,"tag":86,"props":489,"children":490},{},[491],{"type":58,"value":492},"画什么",{"type":58,"value":494},"：优先画率或 SMR，不画原始计数；确需展示计数时\n图题\u002F图注写明\"病例数，未按人口校正\"。",{"type":52,"tag":82,"props":496,"children":497},{},[498,503,505,510],{"type":52,"tag":86,"props":499,"children":500},{},[501],{"type":58,"value":502},"分级数",{"type":58,"value":504},"：4–7 级为宜 ",{"type":52,"tag":221,"props":506,"children":507},{},[508],{"type":58,"value":509},"模型知识—待核实：制图学通行建议",{"type":58,"value":511},"；\n分级方法（等距\u002F分位数\u002F自然断点）写进图注，分位数法每级区数\n相近但不反映数值间距，等距法反之——按讲述目的选择并说明。",{"type":52,"tag":82,"props":513,"children":514},{},[515,520,522,526],{"type":52,"tag":86,"props":516,"children":517},{},[518],{"type":58,"value":519},"配色",{"type":58,"value":521},"：使用色盲友好的顺序色板（如单色渐深或 ColorBrewer\n顺序系列）",{"type":52,"tag":221,"props":523,"children":524},{},[525],{"type":58,"value":409},{"type":58,"value":527},"；避免红绿对比；发散色板仅用于\n以某基准为中心的双极变量（如 SMR 以 1 为中心）。",{"type":52,"tag":82,"props":529,"children":530},{},[531,536],{"type":52,"tag":86,"props":532,"children":533},{},[534],{"type":58,"value":535},"图件要素",{"type":58,"value":537},"：标题含指标+时间窗、图注含分级方法与数据来源\n标签、比例尺\u002F指北针按出版要求、底图边界来源合规声明。",{"type":52,"tag":82,"props":539,"children":540},{},[541,546],{"type":52,"tag":86,"props":542,"children":543},{},[544],{"type":58,"value":545},"伦理",{"type":58,"value":547},"：个案点图（dot map）不得精确到可再识别的位置；\n聚集区结果对外发布前考虑对当地居民的影响（guardrail 第 8 条）。",{"type":52,"tag":61,"props":549,"children":551},{"id":550},"输出模板",[552],{"type":58,"value":550},{"type":52,"tag":554,"props":555,"children":560},"pre",{"className":556,"code":557,"language":558,"meta":559,"style":559},"language-markdown shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","## 空间分析底稿（\u003C日期>）\n\n### 数据与口径\n- 病例：\u003C来源标签>，时间窗 \u003C起止>；人口：\u003C来源标签>，口径年 \u003C年份>\n- 行政区划：\u003C层级与版本>，区划调整对齐说明\n\n### SMR 表\n（第 1 节表格，含 λ 取值与来源）\n\n### 稳定性\n- 小期望数地区（E\u003C阈值的区）：\u003C列出>，处理方式：合并\u002FEB 平滑\u002F仅提示\n- 平滑与原始并列图：\u003C路径>\n\n### 聚集性\n- 方法与工具：\u003CMoran's I（GeoDa）\u002F 扫描统计量（SaTScan）>，\n  参数：\u003C权重\u002F窗口设定>\n- 结果：\u003C全局统计量\u002F聚集区清单>[实验数据]\n- 非病因解释：\u003C诊断可及性\u002F报告差异\u002F人口结构>\n\n### 地图\n- 图件路径：\u003Cfigures\u002F…>；分级方法、色板、来源标签齐备性自查通过\n","markdown","",[561],{"type":52,"tag":562,"props":563,"children":564},"code",{"__ignoreMap":559},[565,582,591,605,620,632,640,653,662,670,683,696,709,717,730,743,752,781,794,802,815],{"type":52,"tag":221,"props":566,"children":569},{"class":567,"line":568},"line",1,[570,576],{"type":52,"tag":221,"props":571,"children":573},{"style":572},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[574],{"type":58,"value":575},"## ",{"type":52,"tag":221,"props":577,"children":579},{"style":578},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[580],{"type":58,"value":581},"空间分析底稿（\u003C日期>）\n",{"type":52,"tag":221,"props":583,"children":584},{"class":567,"line":33},[585],{"type":52,"tag":221,"props":586,"children":588},{"emptyLinePlaceholder":587},true,[589],{"type":58,"value":590},"\n",{"type":52,"tag":221,"props":592,"children":594},{"class":567,"line":593},3,[595,600],{"type":52,"tag":221,"props":596,"children":597},{"style":572},[598],{"type":58,"value":599},"### ",{"type":52,"tag":221,"props":601,"children":602},{"style":578},[603],{"type":58,"value":604},"数据与口径\n",{"type":52,"tag":221,"props":606,"children":608},{"class":567,"line":607},4,[609,614],{"type":52,"tag":221,"props":610,"children":611},{"style":572},[612],{"type":58,"value":613},"-",{"type":52,"tag":221,"props":615,"children":617},{"style":616},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[618],{"type":58,"value":619}," 病例：\u003C来源标签>，时间窗 \u003C起止>；人口：\u003C来源标签>，口径年 \u003C年份>\n",{"type":52,"tag":221,"props":621,"children":622},{"class":567,"line":29},[623,627],{"type":52,"tag":221,"props":624,"children":625},{"style":572},[626],{"type":58,"value":613},{"type":52,"tag":221,"props":628,"children":629},{"style":616},[630],{"type":58,"value":631}," 行政区划：\u003C层级与版本>，区划调整对齐说明\n",{"type":52,"tag":221,"props":633,"children":635},{"class":567,"line":634},6,[636],{"type":52,"tag":221,"props":637,"children":638},{"emptyLinePlaceholder":587},[639],{"type":58,"value":590},{"type":52,"tag":221,"props":641,"children":643},{"class":567,"line":642},7,[644,648],{"type":52,"tag":221,"props":645,"children":646},{"style":572},[647],{"type":58,"value":599},{"type":52,"tag":221,"props":649,"children":650},{"style":578},[651],{"type":58,"value":652},"SMR 表\n",{"type":52,"tag":221,"props":654,"children":656},{"class":567,"line":655},8,[657],{"type":52,"tag":221,"props":658,"children":659},{"style":616},[660],{"type":58,"value":661},"（第 1 节表格，含 λ 取值与来源）\n",{"type":52,"tag":221,"props":663,"children":665},{"class":567,"line":664},9,[666],{"type":52,"tag":221,"props":667,"children":668},{"emptyLinePlaceholder":587},[669],{"type":58,"value":590},{"type":52,"tag":221,"props":671,"children":673},{"class":567,"line":672},10,[674,678],{"type":52,"tag":221,"props":675,"children":676},{"style":572},[677],{"type":58,"value":599},{"type":52,"tag":221,"props":679,"children":680},{"style":578},[681],{"type":58,"value":682},"稳定性\n",{"type":52,"tag":221,"props":684,"children":686},{"class":567,"line":685},11,[687,691],{"type":52,"tag":221,"props":688,"children":689},{"style":572},[690],{"type":58,"value":613},{"type":52,"tag":221,"props":692,"children":693},{"style":616},[694],{"type":58,"value":695}," 小期望数地区（E\u003C阈值的区）：\u003C列出>，处理方式：合并\u002FEB 平滑\u002F仅提示\n",{"type":52,"tag":221,"props":697,"children":699},{"class":567,"line":698},12,[700,704],{"type":52,"tag":221,"props":701,"children":702},{"style":572},[703],{"type":58,"value":613},{"type":52,"tag":221,"props":705,"children":706},{"style":616},[707],{"type":58,"value":708}," 平滑与原始并列图：\u003C路径>\n",{"type":52,"tag":221,"props":710,"children":712},{"class":567,"line":711},13,[713],{"type":52,"tag":221,"props":714,"children":715},{"emptyLinePlaceholder":587},[716],{"type":58,"value":590},{"type":52,"tag":221,"props":718,"children":720},{"class":567,"line":719},14,[721,725],{"type":52,"tag":221,"props":722,"children":723},{"style":572},[724],{"type":58,"value":599},{"type":52,"tag":221,"props":726,"children":727},{"style":578},[728],{"type":58,"value":729},"聚集性\n",{"type":52,"tag":221,"props":731,"children":733},{"class":567,"line":732},15,[734,738],{"type":52,"tag":221,"props":735,"children":736},{"style":572},[737],{"type":58,"value":613},{"type":52,"tag":221,"props":739,"children":740},{"style":616},[741],{"type":58,"value":742}," 方法与工具：\u003CMoran's I（GeoDa）\u002F 扫描统计量（SaTScan）>，\n",{"type":52,"tag":221,"props":744,"children":746},{"class":567,"line":745},16,[747],{"type":52,"tag":221,"props":748,"children":749},{"style":616},[750],{"type":58,"value":751},"  参数：\u003C权重\u002F窗口设定>\n",{"type":52,"tag":221,"props":753,"children":755},{"class":567,"line":754},17,[756,760,765,770,776],{"type":52,"tag":221,"props":757,"children":758},{"style":572},[759],{"type":58,"value":613},{"type":52,"tag":221,"props":761,"children":762},{"style":616},[763],{"type":58,"value":764}," 结果：\u003C全局统计量\u002F聚集区清单>",{"type":52,"tag":221,"props":766,"children":767},{"style":572},[768],{"type":58,"value":769},"[",{"type":52,"tag":221,"props":771,"children":773},{"style":772},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[774],{"type":58,"value":775},"实验数据",{"type":52,"tag":221,"props":777,"children":778},{"style":572},[779],{"type":58,"value":780},"]\n",{"type":52,"tag":221,"props":782,"children":784},{"class":567,"line":783},18,[785,789],{"type":52,"tag":221,"props":786,"children":787},{"style":572},[788],{"type":58,"value":613},{"type":52,"tag":221,"props":790,"children":791},{"style":616},[792],{"type":58,"value":793}," 非病因解释：\u003C诊断可及性\u002F报告差异\u002F人口结构>\n",{"type":52,"tag":221,"props":795,"children":797},{"class":567,"line":796},19,[798],{"type":52,"tag":221,"props":799,"children":800},{"emptyLinePlaceholder":587},[801],{"type":58,"value":590},{"type":52,"tag":221,"props":803,"children":805},{"class":567,"line":804},20,[806,810],{"type":52,"tag":221,"props":807,"children":808},{"style":572},[809],{"type":58,"value":599},{"type":52,"tag":221,"props":811,"children":812},{"style":578},[813],{"type":58,"value":814},"地图\n",{"type":52,"tag":221,"props":816,"children":818},{"class":567,"line":817},21,[819,823],{"type":52,"tag":221,"props":820,"children":821},{"style":572},[822],{"type":58,"value":613},{"type":52,"tag":221,"props":824,"children":825},{"style":616},[826],{"type":58,"value":827}," 图件路径：\u003Cfigures\u002F…>；分级方法、色板、来源标签齐备性自查通过\n",{"type":52,"tag":61,"props":829,"children":831},{"id":830},"本技能不做什么",[832],{"type":58,"value":830},{"type":52,"tag":458,"props":834,"children":835},{},[836,846,856,866,876],{"type":52,"tag":82,"props":837,"children":838},{},[839,844],{"type":52,"tag":86,"props":840,"children":841},{},[842],{"type":58,"value":843},"不替代 GIS\u002F统计软件",{"type":58,"value":845},"：不手算 Moran's I 或扫描统计量；工具运行\n与参数日志由用户完成，本技能审口径与解读。",{"type":52,"tag":82,"props":847,"children":848},{},[849,854],{"type":52,"tag":86,"props":850,"children":851},{},[852],{"type":58,"value":853},"不做生态学因果推断",{"type":58,"value":855},"：地区水平的相关\u002F聚集不推出个体水平因果\n（生态学谬误）；结论措辞限于\"提示空间分布特征\"。",{"type":52,"tag":82,"props":857,"children":858},{},[859,864],{"type":52,"tag":86,"props":860,"children":861},{},[862],{"type":58,"value":863},"不提供精确到户的病例点位展示",{"type":58,"value":865},"：再识别风险高的展示形式一律\n劝阻。",{"type":52,"tag":82,"props":867,"children":868},{},[869,874],{"type":52,"tag":86,"props":870,"children":871},{},[872],{"type":58,"value":873},"不判断行政区划与地图合规细节",{"type":58,"value":875},"：国界与争议地区表达以官方\n标准地图为准，拿不准时提示用户查标准地图服务，不自行裁决。",{"type":52,"tag":82,"props":877,"children":878},{},[879,884,886,892],{"type":52,"tag":86,"props":880,"children":881},{},[882],{"type":58,"value":883},"不编造方法学参数",{"type":58,"value":885},"：平滑方法参数、检验公式等查文档后引用，\n模型印象标 ",{"type":52,"tag":562,"props":887,"children":889},{"className":888},[],[890],{"type":58,"value":891},"[模型知识—待核实]",{"type":58,"value":227},{"type":52,"tag":61,"props":894,"children":896},{"id":895},"收尾与下一步",[897],{"type":58,"value":895},{"type":52,"tag":78,"props":899,"children":900},{},[901,906,911],{"type":52,"tag":82,"props":902,"children":903},{},[904],{"type":58,"value":905},"汇总：SMR 表关键行、稳定性处理、聚集性结论（含非病因解释）。",{"type":52,"tag":82,"props":907,"children":908},{},[909],{"type":58,"value":910},"指向产物（SMR 表、地图、工具日志）并登记 provenance。",{"type":52,"tag":82,"props":912,"children":913},{},[914,916],{"type":58,"value":915},"建议下一步：\n",{"type":52,"tag":458,"props":917,"children":918},{},[919,931,943],{"type":52,"tag":82,"props":920,"children":921},{},[922,924,930],{"type":58,"value":923},"发现聚集区需现场核实 → ",{"type":52,"tag":562,"props":925,"children":927},{"className":926},[],[928],{"type":58,"value":929},"outbreak-analysis",{"type":58,"value":368},{"type":52,"tag":82,"props":932,"children":933},{},[934,936,942],{"type":58,"value":935},"地图与结果写入报告\u002F论文 → ",{"type":52,"tag":562,"props":937,"children":939},{"className":938},[],[940],{"type":58,"value":941},"epi-writing",{"type":58,"value":368},{"type":52,"tag":82,"props":944,"children":945},{},[946,948,954],{"type":58,"value":947},"缺人口或边界数据 → ",{"type":52,"tag":562,"props":949,"children":951},{"className":950},[],[952],{"type":58,"value":953},"epi-data-access",{"type":58,"value":227},{"type":52,"tag":956,"props":957,"children":958},"style",{},[959],{"type":58,"value":960},"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":962,"total":1063},[963,979,996,1008,1022,1037,1051],{"slug":964,"name":964,"fn":965,"description":966,"org":967,"tags":968,"stars":29,"repoUrl":30,"updatedAt":978},"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},[969,972,975],{"name":970,"slug":971,"type":16},"Content Creation","content-creation",{"name":973,"slug":974,"type":16},"MCP","mcp",{"name":976,"slug":977,"type":16},"Task Management","task-management","2026-08-18T03:49:38.751656",{"slug":980,"name":980,"fn":981,"description":982,"org":983,"tags":984,"stars":29,"repoUrl":30,"updatedAt":995},"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},[985,988,991,994],{"name":986,"slug":987,"type":16},"Code Analysis","code-analysis",{"name":989,"slug":990,"type":16},"Documentation","documentation",{"name":992,"slug":993,"type":16},"QA","qa",{"name":14,"slug":15,"type":16},"2026-08-21T03:59:17.615117",{"slug":997,"name":997,"fn":998,"description":999,"org":1000,"tags":1001,"stars":29,"repoUrl":30,"updatedAt":1007},"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},[1002,1005,1006],{"name":1003,"slug":1004,"type":16},"Audit","audit",{"name":986,"slug":987,"type":16},{"name":14,"slug":15,"type":16},"2026-08-21T03:59:02.154691",{"slug":1009,"name":1009,"fn":1010,"description":1011,"org":1012,"tags":1013,"stars":29,"repoUrl":30,"updatedAt":1021},"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},[1014,1017,1020],{"name":1015,"slug":1016,"type":16},"Data Cleaning","data-cleaning",{"name":1018,"slug":1019,"type":16},"Documents","documents",{"name":14,"slug":15,"type":16},"2026-08-21T03:59:12.24404",{"slug":1023,"name":1023,"fn":1024,"description":1025,"org":1026,"tags":1027,"stars":29,"repoUrl":30,"updatedAt":1036},"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},[1028,1029,1032,1035],{"name":989,"slug":990,"type":16},{"name":1030,"slug":1031,"type":16},"Onboarding","onboarding",{"name":1033,"slug":1034,"type":16},"Productivity","productivity",{"name":14,"slug":15,"type":16},"2026-08-21T03:59:58.579998",{"slug":1038,"name":1038,"fn":1039,"description":1040,"org":1041,"tags":1042,"stars":29,"repoUrl":30,"updatedAt":1050},"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},[1043,1046,1049],{"name":1044,"slug":1045,"type":16},"Best Practices","best-practices",{"name":1047,"slug":1048,"type":16},"Configuration","configuration",{"name":14,"slug":15,"type":16},"2026-08-21T03:59:35.867596",{"slug":1052,"name":1052,"fn":1053,"description":1054,"org":1055,"tags":1056,"stars":29,"repoUrl":30,"updatedAt":1062},"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},[1057,1058,1061],{"name":973,"slug":974,"type":16},{"name":1059,"slug":1060,"type":16},"Scheduling","scheduling",{"name":976,"slug":977,"type":16},"2026-08-18T03:49:37.126385",36,{"items":1065,"total":1264},[1066,1090,1106,1125,1140,1160,1178,1196,1211,1227,1244,1254],{"slug":1067,"name":1067,"fn":1068,"description":1069,"org":1070,"tags":1071,"stars":1087,"repoUrl":1088,"updatedAt":1089},"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},[1072,1075,1078,1081,1084],{"name":1073,"slug":1074,"type":16},"Accessibility","accessibility",{"name":1076,"slug":1077,"type":16},"Android","android",{"name":1079,"slug":1080,"type":16},"Kotlin","kotlin",{"name":1082,"slug":1083,"type":16},"Mobile","mobile",{"name":1085,"slug":1086,"type":16},"UI Components","ui-components",13030,"https:\u002F\u002Fgithub.com\u002FMiniMax-AI\u002Fskills","2026-07-13T06:16:54.247834",{"slug":1091,"name":1091,"fn":1092,"description":1093,"org":1094,"tags":1095,"stars":1087,"repoUrl":1088,"updatedAt":1105},"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},[1096,1099,1102],{"name":1097,"slug":1098,"type":16},"Agents","agents",{"name":1100,"slug":1101,"type":16},"Audio","audio",{"name":1103,"slug":1104,"type":16},"Creative","creative","2026-07-13T06:16:35.130644",{"slug":1107,"name":1107,"fn":1108,"description":1109,"org":1110,"tags":1111,"stars":1087,"repoUrl":1088,"updatedAt":1124},"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},[1112,1115,1118,1121],{"name":1113,"slug":1114,"type":16},"Design","design",{"name":1116,"slug":1117,"type":16},"Presentations","presentations",{"name":1119,"slug":1120,"type":16},"Themes","themes",{"name":1122,"slug":1123,"type":16},"Typography","typography","2026-07-13T06:17:02.785587",{"slug":1126,"name":1126,"fn":1127,"description":1128,"org":1129,"tags":1130,"stars":1087,"repoUrl":1088,"updatedAt":1139},"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},[1131,1132,1135,1138],{"name":1113,"slug":1114,"type":16},{"name":1133,"slug":1134,"type":16},"Design System","design-system",{"name":1136,"slug":1137,"type":16},"PowerPoint","powerpoint",{"name":1116,"slug":1117,"type":16},"2026-07-13T06:17:10.398389",{"slug":1141,"name":1141,"fn":1142,"description":1143,"org":1144,"tags":1145,"stars":1087,"repoUrl":1088,"updatedAt":1159},"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},[1146,1149,1152,1153,1156],{"name":1147,"slug":1148,"type":16},"Dart","dart",{"name":1150,"slug":1151,"type":16},"Flutter","flutter",{"name":1082,"slug":1083,"type":16},{"name":1154,"slug":1155,"type":16},"Performance","performance",{"name":1157,"slug":1158,"type":16},"State Management","state-management","2026-07-13T06:16:36.626679",{"slug":1161,"name":1161,"fn":1162,"description":1163,"org":1164,"tags":1165,"stars":1087,"repoUrl":1088,"updatedAt":1177},"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},[1166,1169,1170,1171,1174],{"name":1167,"slug":1168,"type":16},"Animation","animation",{"name":1103,"slug":1104,"type":16},{"name":1113,"slug":1114,"type":16},{"name":1172,"slug":1173,"type":16},"Frontend","frontend",{"name":1175,"slug":1176,"type":16},"Web Development","web-development","2026-07-13T06:16:39.108827",{"slug":1179,"name":1179,"fn":1180,"description":1181,"org":1182,"tags":1183,"stars":1087,"repoUrl":1088,"updatedAt":1195},"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},[1184,1187,1188,1191,1194],{"name":1185,"slug":1186,"type":16},"Backend","backend",{"name":1172,"slug":1173,"type":16},{"name":1189,"slug":1190,"type":16},"Full-stack","full-stack",{"name":1192,"slug":1193,"type":16},"REST API","rest-api",{"name":1175,"slug":1176,"type":16},"2026-07-13T06:16:43.219005",{"slug":1197,"name":1197,"fn":1198,"description":1199,"org":1200,"tags":1201,"stars":1087,"repoUrl":1088,"updatedAt":1210},"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},[1202,1203,1204,1207],{"name":1167,"slug":1168,"type":16},{"name":1103,"slug":1104,"type":16},{"name":1205,"slug":1206,"type":16},"Images","images",{"name":1208,"slug":1209,"type":16},"Media","media","2026-07-13T06:16:51.74461",{"slug":1212,"name":1212,"fn":1213,"description":1214,"org":1215,"tags":1216,"stars":1087,"repoUrl":1088,"updatedAt":1226},"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},[1217,1218,1221,1222,1225],{"name":1073,"slug":1074,"type":16},{"name":1219,"slug":1220,"type":16},"iOS","ios",{"name":1082,"slug":1083,"type":16},{"name":1223,"slug":1224,"type":16},"SwiftUI","swiftui",{"name":1085,"slug":1086,"type":16},"2026-07-13T06:16:55.686092",{"slug":1228,"name":1228,"fn":1229,"description":1230,"org":1231,"tags":1232,"stars":1087,"repoUrl":1088,"updatedAt":1243},"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},[1233,1234,1237,1240],{"name":1018,"slug":1019,"type":16},{"name":1235,"slug":1236,"type":16},"DOCX","docx",{"name":1238,"slug":1239,"type":16},"Office","office",{"name":1241,"slug":1242,"type":16},"Templates","templates","2026-07-13T06:16:40.461868",{"slug":1245,"name":1245,"fn":1246,"description":1247,"org":1248,"tags":1249,"stars":1087,"repoUrl":1088,"updatedAt":1253},"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},[1250,1251,1252],{"name":1100,"slug":1101,"type":16},{"name":1103,"slug":1104,"type":16},{"name":1208,"slug":1209,"type":16},"2026-07-13T06:16:50.381758",{"slug":1255,"name":1255,"fn":1256,"description":1257,"org":1258,"tags":1259,"stars":1087,"repoUrl":1088,"updatedAt":1263},"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},[1260,1261,1262],{"name":1100,"slug":1101,"type":16},{"name":1103,"slug":1104,"type":16},{"name":1208,"slug":1209,"type":16},"2026-07-13T06:16:57.002997",84]