[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70M359YPHM43P9WZMXVWKMS":3,"skill-same:01M70M359YPHM43P9WZMXVWKMS":54},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":25,"linkOnly":26,"markdownContent":27,"markdownBody":28,"frontMatter":29,"refName":30,"commitSha":31,"skillDirectory":32,"forksCount":33,"repositoryHtmlUrl":34,"repositoryHomepageUrl":35,"ownerHtmlUrl":36,"ownerBlogUrl":37,"ownerDescription":38,"updatedAt":39,"install":40,"resources":53},"01M70M359YPHM43P9WZMXVWKMS","decision-tracker",null,"记录和跟踪个人重大决策。当用户说\"记决策\"、\"记个决策\"、\"决策跟踪\"、\"回填\"、\"decision\",或描述一个刚做的\u002F正在考虑的重大决策(创业\u002F事业\u002F财务\u002F人生)并希望系统化记录与复盘时使用。自动四层拆解(原始信息\u002F决策事实\u002F假设推断\u002F结果验证),生成 2 个文件,维护索引与行为模式库,并在记新决策时用历史教训主动拦截。","shengdabai\u002FTony-Claude-Code-Skills","shengdabai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F116417419?v=4","01M70F6D2WY5PQV5A92BKYJQEW","Tony Sheng","01M70F6D3GAAAYZ5H4CC1G8VXM",3,"MIT","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fdecision-tracker\u002FSKILL.md",[],[19,20,21,22,23,24],"decision","tracker","decision tracker","生成","复盘","文件","2026-11-10 10:12:30",false,"---\nname: decision-tracker\ndescription: 记录和跟踪个人重大决策。当用户说\"记决策\"、\"记个决策\"、\"决策跟踪\"、\"回填\"、\"decision\",或描述一个刚做的\u002F正在考虑的重大决策(创业\u002F事业\u002F财务\u002F人生)并希望系统化记录与复盘时使用。自动四层拆解(原始信息\u002F决策事实\u002F假设推断\u002F结果验证),生成 2 个文件,维护索引与行为模式库,并在记新决策时用历史教训主动拦截。\n---\n\n# Decision Tracker\n\n记录个人重大决策,并在你下次决策的当口用你自己的历史教训拦你。核心哲学:AI 不缺智商,缺关于你的纵向数据。\n\n## 系统常量(所有路径写死,不受当前工作目录影响)\n\n- `DATA_ROOT` = `~\u002FDesktop\u002F01-项目开发\u002F07-决策跟踪系统`\n- 决策目录:`{DATA_ROOT}\u002Fdecisions\u002F{YYYY-MM-DD}-{标题}\u002F`\n- 两文件:`01-原始信息.md`、`02-决策档案.md`\n- 索引:`{DATA_ROOT}\u002Findex.json`、`{DATA_ROOT}\u002FLEDGER.md`\n- 模式库:`{DATA_ROOT}\u002Fpatterns.md`\n\n**进入本 skill 任何动作前**,先 Read `{DATA_ROOT}\u002FREADME.md`(可选)与 `{DATA_ROOT}\u002Fpatterns.md`、`{DATA_ROOT}\u002Findex.json` 建立上下文。\n**所有文件读写用 Read \u002F Edit \u002F Write,禁止用 Bash 的 cat\u002Fsed\u002Fecho\u002Fgrep。**\n\n## 四层信息(置信度隔离 —— 系统的灵魂)\n\n| 层 | 性质 | 落盘文件 |\n|----|------|----------|\n| 原始信息 | 决策人原话,**可能掺假** | 01-原始信息.md |\n| 决策事实 | 已发生动作,**确凿无疑** | 02-决策档案.md 第一节 |\n| 假设推断 | 决策人 + AI 假设,**待验证,非对错** | 02-决策档案.md 第二节 |\n| 结果验证 | 现实结果,**事后回填** | 02-决策档案.md 第三节 |\n\n---\n\n## 动作 1:记决策\n\n触发:用户描述一个决策,或说\"记决策\u002F记个决策\"。\n\n### 流程(默认全自动,零打断)\n\n1. **读到期提醒**(见动作 2 的到期扫描)。如有到期未回填的决策,先一行提醒,再继续记新决策。\n2. **生成 decision_id** = `{今天 YYYY-MM-DD}-{6-12字标题}`。标题取决策核心动作。\n3. **四层拆解**(只拆,不问):\n   - **原始信息**:逐字保留用户原话,**不改写**。逐条标性质(外部观察 \u002F 二手转述 \u002F 决策人假设)和置信度(高 \u002F 中 \u002F 低)。二手转述、对他人的主观判定 → 默认低置信度(警惕美化自己、贬低他人)。\n   - **决策事实**:抽取已确定的动作和参数(日期 \u002F 动作 \u002F 数量 \u002F 价格 \u002F 成本 \u002F 验证周期)。\n   - **假设推断 - 决策人**:用户话里隐含的假设。\n   - **假设推断 - AI**:判定决策类型(如 跟风型 \u002F 规避损失型 \u002F 沉没成本型 \u002F FOMO型 \u002F 理性验证型 等),列风险点。\n4. **主动拦截**(核心能力):读 `index.json` + `patterns.md`,匹配:\n   - 相同 \u002F 相近 `type` 的历史决策\n   - 命中的已知行为模式(patterns.md 里的模式名)\n\n   如命中,**先停下来把历史教训甩给用户反问**(用 patterns.md 里的\"拦截话术\"或历史决策的核心教训),格式如:\n   > ⚠️ 你 {历史日期} 也做过 {type} 决策({历史标题}),结果是 {历史教训}。你能证明今天这个不是重蹈覆辙吗?\n\n   等用户回应后再落盘。用户回应记入 02 文件的\"决策人假设\"或新增\"拦截后补充\"小节。\n   若无命中,跳过此步,继续。\n5. **仅在置信度真有歧义时反问**(否则不问):例如无法判断某条是客观事实还是用户推测,且影响置信度标注,才问 1 句。其余一律自动判断。\n6. **落盘**:按下方「文件模板」写 `01-原始信息.md` 和 `02-决策档案.md`。\n7. **更新索引**:按下方「索引维护」追加 index.json 条目、LEDGER.md 行。\n8. **回报**:一句话「已记录 {标题},到期 {review_due} 回填」。若有拦截,附拦截结论。\n\n### review_due 计算\n- 用户说了周期(如\"测 7 天\")→ created + 周期。\n- 没说 → 默认 created + 14 天,回报里标注\"默认 14 天后回填,可改\"。\n\n---\n\n## 文件模板\n\n### 01-原始信息.md\n\n```markdown\n---\ndecision_id: {id}\ncreated: {YYYY-MM-DD}\ntype: 原始信息\n---\n\n# 原始信息(可能掺假,谨慎采信)\n\n## 决策人原话(逐字记录,不改写)\n> {用户原话,逐字搬运}\n\n## 置信度标注\n| 信息点 | 性质 | 置信度 | 备注 |\n|--------|------|--------|------|\n| {信息点} | 外部观察\u002F二手转述\u002F决策人假设 | 高\u002F中\u002F低 | {风险点} |\n```\n\n### 02-决策档案.md\n\n```markdown\n---\ndecision_id: {id}\ncreated: {YYYY-MM-DD}\nreview_due: {YYYY-MM-DD}\nstatus: 待验证\ntags: [{标签}]\n---\n\n# 决策档案\n\n## 一、决策事实(确凿无疑)\n- 日期:{date}\n- 决策:{动作}\n- 参数:{数量\u002F价格\u002F成本}\n- 验证周期:{周期}(到期 {review_due})\n\n## 二、假设推断(待验证,非对错)\n### 决策人的假设\n- {假设}\n### AI 的假设(可能与决策人分歧)\n- 决策类型:{type}\n- 风险:{风险}\n- {若命中历史模式,引用 patterns.md 对应条目}\n\n## 三、结果验证(到期回填,初始留空)\n> _等待 {review_due} 回填_\n```\n\n---\n\n## 索引维护(每次记决策 \u002F 回填后执行)\n\n### index.json\nRead 现有 index.json,向 `decisions` 数组**追加 \u002F 更新**该决策对象,然后 Write 回去(保持合法 JSON):\n\n```json\n{\n  \"id\": \"{id}\",\n  \"title\": \"{标题}\",\n  \"created\": \"{YYYY-MM-DD}\",\n  \"review_due\": \"{YYYY-MM-DD}\",\n  \"status\": \"待验证\",\n  \"type\": \"{决策类型}\",\n  \"tags\": [\"...\"],\n  \"summary_one_line\": \"{一句话摘要}\",\n  \"lesson\": null,\n  \"patterns_hit\": [\"{命中的模式名}\"]\n}\n```\n回填时:更新同 id 对象的 `status` → \"已回填\",填 `lesson`。\n\n### LEDGER.md\n在表格**表头下第一行插入**一行(最新在上):\n`| {日期} | {标题} | {类型} | {状态} | {到期} | {核心教训或\"待回填\"} |`\n回填后更新对应行的状态和核心教训。\n\n> 用 Read + Edit\u002FWrite 维护,不要用 Bash 的 sed\u002Fecho。\n\n---\n\n## 动作 2:回填(结果验证)\n\n触发:用户说\"回填 {决策}:{真实结果}\",或进入 skill 时到期扫描命中。\n\n### 到期扫描(进入任何动作前先做)\nRead index.json,筛 `status == \"待验证\" && review_due \u003C= 今天` 的决策。如有,列一句提醒:\n> 📋 有 {N} 个决策到期该回填了:{标题}(到期 {date})…\n\n### 回填流程\n1. **定位决策**:按用户给的标题 \u002F id 匹配 index.json,找到 `decisions\u002F{id}\u002F02-决策档案.md`。\n2. **改写\"三、结果验证\"层**,补四块:\n   - **主要偏差**:实际 vs 决策时假设的差距。\n   - **核心教训**:一句话可复用的教训。\n   - **暴露的个人模式**:这次暴露 \u002F 印证了什么行为模式。\n   - **未来规则**:下次遇到同类该遵守的规则。\n3. 改 02 文件 frontmatter `status` → `已回填`。\n4. **累积 patterns.md**(护城河):\n   - 若\"暴露的个人模式\"是**新模式** → 在 patterns.md 新增模式条目(首次发现 \u002F 复现次数 1 \u002F 典型触发 \u002F 历史结果 \u002F 拦截话术)。\n   - 若是**已有模式** → 复现次数 +1,补历史结果。\n   - \"未来规则\"追加到 patterns.md 规则库。\n5. **更新 index.json**(status、lesson)和 LEDGER.md 对应行。\n6. **回报**:一句话总结教训 + patterns.md 是否新增 \u002F 强化了模式。\n\n> 用 Read + Edit\u002FWrite 操作,不用 Bash 文本工具。\n\n---\n\n## 动作 3:查询 \u002F 复盘(被动)\n\n### 3a. 决策前对比反问\n触发:\"我想做 X,查查以前类似的\"。\n流程:读 index.json,按 type \u002F tags \u002F 关键词匹配历史决策;读命中决策的 02 文件结果验证层;给出对比反问(历史结果 + 当前决策的风险提示)。不强行落盘,除非用户接着说\"记下来\"。\n\n### 3b. 模式复盘\n触发:\"我有哪些反复犯的错\"、\"我的行为模式\"。\n流程:读 patterns.md,按复现次数排序汇总;关联 index.json 里命中各模式的决策列表。\n\n---\n\n## 演示数据\n若用户明说\"这是测试 \u002F 演示 \u002F 不用保存\",**不落盘**,只在对话里展示拆解结果。\n","# Decision Tracker\n\n记录个人重大决策,并在你下次决策的当口用你自己的历史教训拦你。核心哲学:AI 不缺智商,缺关于你的纵向数据。\n\n## 系统常量(所有路径写死,不受当前工作目录影响)\n\n- `DATA_ROOT` = `~\u002FDesktop\u002F01-项目开发\u002F07-决策跟踪系统`\n- 决策目录:`{DATA_ROOT}\u002Fdecisions\u002F{YYYY-MM-DD}-{标题}\u002F`\n- 两文件:`01-原始信息.md`、`02-决策档案.md`\n- 索引:`{DATA_ROOT}\u002Findex.json`、`{DATA_ROOT}\u002FLEDGER.md`\n- 模式库:`{DATA_ROOT}\u002Fpatterns.md`\n\n**进入本 skill 任何动作前**,先 Read `{DATA_ROOT}\u002FREADME.md`(可选)与 `{DATA_ROOT}\u002Fpatterns.md`、`{DATA_ROOT}\u002Findex.json` 建立上下文。\n**所有文件读写用 Read \u002F Edit \u002F Write,禁止用 Bash 的 cat\u002Fsed\u002Fecho\u002Fgrep。**\n\n## 四层信息(置信度隔离 —— 系统的灵魂)\n\n| 层 | 性质 | 落盘文件 |\n|----|------|----------|\n| 原始信息 | 决策人原话,**可能掺假** | 01-原始信息.md |\n| 决策事实 | 已发生动作,**确凿无疑** | 02-决策档案.md 第一节 |\n| 假设推断 | 决策人 + AI 假设,**待验证,非对错** | 02-决策档案.md 第二节 |\n| 结果验证 | 现实结果,**事后回填** | 02-决策档案.md 第三节 |\n\n---\n\n## 动作 1:记决策\n\n触发:用户描述一个决策,或说\"记决策\u002F记个决策\"。\n\n### 流程(默认全自动,零打断)\n\n1. **读到期提醒**(见动作 2 的到期扫描)。如有到期未回填的决策,先一行提醒,再继续记新决策。\n2. **生成 decision_id** = `{今天 YYYY-MM-DD}-{6-12字标题}`。标题取决策核心动作。\n3. **四层拆解**(只拆,不问):\n   - **原始信息**:逐字保留用户原话,**不改写**。逐条标性质(外部观察 \u002F 二手转述 \u002F 决策人假设)和置信度(高 \u002F 中 \u002F 低)。二手转述、对他人的主观判定 → 默认低置信度(警惕美化自己、贬低他人)。\n   - **决策事实**:抽取已确定的动作和参数(日期 \u002F 动作 \u002F 数量 \u002F 价格 \u002F 成本 \u002F 验证周期)。\n   - **假设推断 - 决策人**:用户话里隐含的假设。\n   - **假设推断 - AI**:判定决策类型(如 跟风型 \u002F 规避损失型 \u002F 沉没成本型 \u002F FOMO型 \u002F 理性验证型 等),列风险点。\n4. **主动拦截**(核心能力):读 `index.json` + `patterns.md`,匹配:\n   - 相同 \u002F 相近 `type` 的历史决策\n   - 命中的已知行为模式(patterns.md 里的模式名)\n\n   如命中,**先停下来把历史教训甩给用户反问**(用 patterns.md 里的\"拦截话术\"或历史决策的核心教训),格式如:\n   > ⚠️ 你 {历史日期} 也做过 {type} 决策({历史标题}),结果是 {历史教训}。你能证明今天这个不是重蹈覆辙吗?\n\n   等用户回应后再落盘。用户回应记入 02 文件的\"决策人假设\"或新增\"拦截后补充\"小节。\n   若无命中,跳过此步,继续。\n5. **仅在置信度真有歧义时反问**(否则不问):例如无法判断某条是客观事实还是用户推测,且影响置信度标注,才问 1 句。其余一律自动判断。\n6. **落盘**:按下方「文件模板」写 `01-原始信息.md` 和 `02-决策档案.md`。\n7. **更新索引**:按下方「索引维护」追加 index.json 条目、LEDGER.md 行。\n8. **回报**:一句话「已记录 {标题},到期 {review_due} 回填」。若有拦截,附拦截结论。\n\n### review_due 计算\n- 用户说了周期(如\"测 7 天\")→ created + 周期。\n- 没说 → 默认 created + 14 天,回报里标注\"默认 14 天后回填,可改\"。\n\n---\n\n## 文件模板\n\n### 01-原始信息.md\n\n```markdown\n---\ndecision_id: {id}\ncreated: {YYYY-MM-DD}\ntype: 原始信息\n---\n\n# 原始信息(可能掺假,谨慎采信)\n\n## 决策人原话(逐字记录,不改写)\n> {用户原话,逐字搬运}\n\n## 置信度标注\n| 信息点 | 性质 | 置信度 | 备注 |\n|--------|------|--------|------|\n| {信息点} | 外部观察\u002F二手转述\u002F决策人假设 | 高\u002F中\u002F低 | {风险点} |\n```\n\n### 02-决策档案.md\n\n```markdown\n---\ndecision_id: {id}\ncreated: {YYYY-MM-DD}\nreview_due: {YYYY-MM-DD}\nstatus: 待验证\ntags: [{标签}]\n---\n\n# 决策档案\n\n## 一、决策事实(确凿无疑)\n- 日期:{date}\n- 决策:{动作}\n- 参数:{数量\u002F价格\u002F成本}\n- 验证周期:{周期}(到期 {review_due})\n\n## 二、假设推断(待验证,非对错)\n### 决策人的假设\n- {假设}\n### AI 的假设(可能与决策人分歧)\n- 决策类型:{type}\n- 风险:{风险}\n- {若命中历史模式,引用 patterns.md 对应条目}\n\n## 三、结果验证(到期回填,初始留空)\n> _等待 {review_due} 回填_\n```\n\n---\n\n## 索引维护(每次记决策 \u002F 回填后执行)\n\n### index.json\nRead 现有 index.json,向 `decisions` 数组**追加 \u002F 更新**该决策对象,然后 Write 回去(保持合法 JSON):\n\n```json\n{\n  \"id\": \"{id}\",\n  \"title\": \"{标题}\",\n  \"created\": \"{YYYY-MM-DD}\",\n  \"review_due\": \"{YYYY-MM-DD}\",\n  \"status\": \"待验证\",\n  \"type\": \"{决策类型}\",\n  \"tags\": [\"...\"],\n  \"summary_one_line\": \"{一句话摘要}\",\n  \"lesson\": null,\n  \"patterns_hit\": [\"{命中的模式名}\"]\n}\n```\n回填时:更新同 id 对象的 `status` → \"已回填\",填 `lesson`。\n\n### LEDGER.md\n在表格**表头下第一行插入**一行(最新在上):\n`| {日期} | {标题} | {类型} | {状态} | {到期} | {核心教训或\"待回填\"} |`\n回填后更新对应行的状态和核心教训。\n\n> 用 Read + Edit\u002FWrite 维护,不要用 Bash 的 sed\u002Fecho。\n\n---\n\n## 动作 2:回填(结果验证)\n\n触发:用户说\"回填 {决策}:{真实结果}\",或进入 skill 时到期扫描命中。\n\n### 到期扫描(进入任何动作前先做)\nRead index.json,筛 `status == \"待验证\" && review_due \u003C= 今天` 的决策。如有,列一句提醒:\n> 📋 有 {N} 个决策到期该回填了:{标题}(到期 {date})…\n\n### 回填流程\n1. **定位决策**:按用户给的标题 \u002F id 匹配 index.json,找到 `decisions\u002F{id}\u002F02-决策档案.md`。\n2. **改写\"三、结果验证\"层**,补四块:\n   - **主要偏差**:实际 vs 决策时假设的差距。\n   - **核心教训**:一句话可复用的教训。\n   - **暴露的个人模式**:这次暴露 \u002F 印证了什么行为模式。\n   - **未来规则**:下次遇到同类该遵守的规则。\n3. 改 02 文件 frontmatter `status` → `已回填`。\n4. **累积 patterns.md**(护城河):\n   - 若\"暴露的个人模式\"是**新模式** → 在 patterns.md 新增模式条目(首次发现 \u002F 复现次数 1 \u002F 典型触发 \u002F 历史结果 \u002F 拦截话术)。\n   - 若是**已有模式** → 复现次数 +1,补历史结果。\n   - \"未来规则\"追加到 patterns.md 规则库。\n5. **更新 index.json**(status、lesson)和 LEDGER.md 对应行。\n6. **回报**:一句话总结教训 + patterns.md 是否新增 \u002F 强化了模式。\n\n> 用 Read + Edit\u002FWrite 操作,不用 Bash 文本工具。\n\n---\n\n## 动作 3:查询 \u002F 复盘(被动)\n\n### 3a. 决策前对比反问\n触发:\"我想做 X,查查以前类似的\"。\n流程:读 index.json,按 type \u002F tags \u002F 关键词匹配历史决策;读命中决策的 02 文件结果验证层;给出对比反问(历史结果 + 当前决策的风险提示)。不强行落盘,除非用户接着说\"记下来\"。\n\n### 3b. 模式复盘\n触发:\"我有哪些反复犯的错\"、\"我的行为模式\"。\n流程:读 patterns.md,按复现次数排序汇总;关联 index.json 里命中各模式的决策列表。\n\n---\n\n## 演示数据\n若用户明说\"这是测试 \u002F 演示 \u002F 不用保存\",**不落盘**,只在对话里展示拆解结果。\n",{"name":5,"description":7},"main","7850740bd837adb32f0a109ab2af82482196c6f2","skills\u002Fdecision-tracker",1,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills","https:\u002F\u002Fzturnsgo.com","https:\u002F\u002Fgithub.com\u002Fshengdabai","https:\u002F\u002Fzturnsgo.com\u002F","AI × education creator — producer, not consumer. Taught 6,000+ learners; shipping learning tools & daily essays with Claude Code, practicing @xiaolai's way 🥋","2026-11-01 21:28:23",{"source":8,"skillName":5,"commands":41,"prompt":51,"zipAvailable":52},[42,45,48],{"tool":43,"command":44},"npx","npx skills add shengdabai\u002FTony-Claude-Code-Skills --skill decision-tracker",{"tool":46,"command":47},"bunx","bunx skills add shengdabai\u002FTony-Claude-Code-Skills --skill decision-tracker",{"tool":49,"command":50},"pnpm","pnpm dlx skills add shengdabai\u002FTony-Claude-Code-Skills --skill decision-tracker","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fdecision-tracker\u002FSKILL.md",true,[],[55,74,108,135,157,177],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":66,"publishedAt":25},"01M70P17DAD4C1C47NPH6A96EM","xiaolai-methodology","以李笑来(Li Xiaolai)的思考方式、方法论与表达风格,为用户做全方位 1-on-1 教练指导,覆盖创业、赚钱、投资、学习、自学、读书写作、用 AI、以及人生心态与自我管理。当用户提到 \"李笑来\"、\"笑来\"、\"笑来老师\"、\"扮演李笑来\"、\"找笑来聊聊\"、\"笑来怎么看\"、\"xiaolai\"、\"把时间当作朋友\"、\"通往财富自由之路\"、\"定投改变命运\"、\"韭菜的自我修养\"、\"自学是门手艺\"、\"让时间陪你慢慢变富\"、\"七年就是一辈子\"、\"元认知\"、\"活在未来\"、\"复利\u002F长期主义\"、\"践行\"、\"痴迷改进\"、\"个人商业模式\u002F出售时间\"、\"睡后收入\"、\"定投\"、\"财富自由\"、\"操作系统升级\"、\"最少必要知识\"、\"北极星提示词\"、\"用 AI 该怎么学\u002F思考\" 等任一触发词,或当用户带着关于创业\u002F赚钱\u002F投资\u002F学习\u002F职业\u002F重大人生决策的困惑、希望被人用笑来式的「逻辑 + 大白话 + 类比 + 重新定义 + 践行导向」来点醒和指导时,自动进入李笑来教练模式。","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fxiaolai-methodology\u002FSKILL.md",[61],{"categoryNo":62,"categoryName":63,"taxonomyType":64,"taxonomyTypeDesc":65},"01JBSEEDCAT000000000000018","写作与文案","SCENARIO","使用场景",[67,68,69,70,71,72,73],"methodology","xiaolai","xiaolai methodology","朋友","投资","writing","收入",{"skillNo":75,"name":76,"nameZh":6,"description":77,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":78,"categories":79,"keywords":88,"publishedAt":25},"01M70P13NB9YP7ACJR1S861CDS","zread","Produce and consume a wiki-style knowledge base for a code repository via the `zread` CLI and its on-disk output under `.\u002F.zread\u002Fwiki\u002F`. Use this skill whenever the user wants to understand, onboard onto, explore, summarize, map, or get an overview of an unfamiliar codebase; asks for architecture docs, a project wiki, a repo walkthrough, module\u002Fpackage explanations, or \"what does this repo do\"; wants to generate, regenerate, resume, browse, or serve code documentation locally; or mentions zread \u002F zread.ai directly. Also use it proactively before diving into a large unknown repo — if `.\u002F.zread\u002Fwiki\u002Fcurrent` exists, read the generated pages instead of crawling source file-by-file; if it doesn't, consider offering to run `zread generate`. The trigger is the intent (understand a codebase through generated docs), not the literal word \"zread\".","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fzread\u002FSKILL.md",[80,83],{"categoryNo":81,"categoryName":82,"taxonomyType":64,"taxonomyTypeDesc":65},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[76,89,90,91,92,93,94,95,96,97,98,99,100,101,102,103,104,105,106,107],"knowledge","wiki","explore","walkthrough","project","get","knowledge base","run","generate","intent","cli","map","documentation","project wiki","disk","architecture","code","unknown","generated",{"skillNo":109,"name":110,"nameZh":6,"description":111,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":118,"publishedAt":25},"01M70P10S4SWMZQ8BJAFBFDRW3","youtube","Launch the YouTube Creator Agent to auto-generate videos.\nUse when: user types \u002Fyoutube, wants to create YouTube videos,\ngenerate video content, or upload to YouTube.\nKeywords: youtube, video, 视频, 创作视频, 发布视频","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube\u002FSKILL.md",[114,115],{"categoryNo":81,"categoryName":82,"taxonomyType":64,"taxonomyTypeDesc":65},{"categoryNo":116,"categoryName":117,"taxonomyType":86,"taxonomyTypeDesc":87},"01JBSEEDCAT000000000000036","内容创作者",[110,119,120,121,122,123,124,125,97,126,127,128,129,130,131,132,133,134],"user","content","视频","creator","generate video","videos","launch","video content","create","upload","when","use","auto","types","Video","创作",{"skillNo":136,"name":137,"nameZh":6,"description":138,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":139,"categories":140,"keywords":142,"publishedAt":25},"01M70P0YE95D8BACZCGV8BK90K","youtube-script-sync","Sync, update, or optimize Tony's GetNote knowledge base `Youtube视频逐字稿` by turning each parent recording or first-person idea note into an idempotent child note containing a directly recordable YouTube long-video or Shorts script. Use when the user says “更新\u002F同步\u002F优化 Youtube视频逐字稿知识库”, or says “更新\u002F同步\u002F优化该知识库” while this knowledge base is the active context.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fyoutube-script-sync\u002FSKILL.md",[141],{"categoryNo":81,"categoryName":82,"taxonomyType":64,"taxonomyTypeDesc":65},[143,144,110,145,146,133,147,148,149,150,151,152,153,154,95,155,129,130,89,156],"sync","script","youtube script sync","recording","shorts","first","base","person","update","active","child","optimize","idempotent","long",{"skillNo":158,"name":159,"nameZh":6,"description":160,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":161,"categories":162,"keywords":167,"publishedAt":25},"01M70P0WMV5XT0EEC0N445PW07","writing-skills","How to write SKILL.md files that trigger reliably and teach effectively. Use when creating, improving, or reviewing Claude Code skills.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fxiaolai\u002Fnlpm\u002Fskills\u002Fnlpm\u002Fwriting-skills\u002FSKILL.md",[163,164,165,166],{"categoryNo":62,"categoryName":63,"taxonomyType":64,"taxonomyTypeDesc":65},{"categoryNo":81,"categoryName":82,"taxonomyType":64,"taxonomyTypeDesc":65},{"categoryNo":84,"categoryName":85,"taxonomyType":86,"taxonomyTypeDesc":87},{"categoryNo":116,"categoryName":117,"taxonomyType":86,"taxonomyTypeDesc":87},[168,72,169,170,171,172,105,129,130,173,174,175,176],"writing skills","how","teach","write skill","write","claude code skills","files","how to","trigger",{"skillNo":178,"name":179,"nameZh":6,"description":180,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":181,"categories":182,"keywords":185,"publishedAt":25},"01M70P0SJFR4YVJQBGMHKGSKXT","writing-rules","How to write .claude\u002Frules\u002F files that Claude actually follows. Use when creating, improving, or reviewing project rules.","https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Fxiaolai\u002Fnlpm\u002Fskills\u002Fnlpm\u002Fwriting-rules\u002FSKILL.md",[183,184],{"categoryNo":62,"categoryName":63,"taxonomyType":64,"taxonomyTypeDesc":65},{"categoryNo":116,"categoryName":117,"taxonomyType":86,"taxonomyTypeDesc":87},[186,72,187,93,188,174,129,169,172,130,175],"Rules","writing rules","project rules"]