[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M70MSVE3ZXYSSJ54NPCT7E9X":3,"skill-same:01M70MSVE3ZXYSSJ54NPCT7E9X":84},{"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":23,"publishedAt":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":46,"commitSha":47,"skillDirectory":48,"forksCount":49,"repositoryHtmlUrl":50,"repositoryHomepageUrl":51,"ownerHtmlUrl":52,"ownerBlogUrl":53,"ownerDescription":54,"updatedAt":55,"install":56,"resources":69},"01M70MSVE3ZXYSSJ54NPCT7E9X","lark-vc-agent",null,"飞书视频会议：让机器人代当前用户加入\u002F离开正在进行的会议，并读取会议期间的实时事件（参会人加入与离开、发言、聊天、屏幕共享等）。1. 用户提供 9 位会议号、要求代为入会或离会时使用 +meeting-join \u002F +meeting-leave——会真实产生入会\u002F离会记录。2. 会议进行中用户想知道“谁加入了”“谁离开了”“谁在发言”“有人共享屏幕吗”等会中动态时，机器人入会后用 +meeting-events 读取事件时间线。3. 典型场景：参会机器人、会中助手、代为旁听、代为参会。前提：机器人只能读到它自己参会过且仍在进行中的会议的事件；查询已结束会议的参会名单、纪要或逐字稿请使用 lark-vc 技能。","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\u002Flark-vc-agent\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[24,25,26,27,28,29,30,31,32,33,34],"lark vc agent","lark vc","lark","vc","cli","help","视频","聊天","join","events","meeting","2026-11-10 10:12:30",false,"---\nname: lark-vc-agent\nversion: 1.0.0\ndescription: \"飞书视频会议：让机器人代当前用户加入\u002F离开正在进行的会议，并读取会议期间的实时事件（参会人加入与离开、发言、聊天、屏幕共享等）。1. 用户提供 9 位会议号、要求代为入会或离会时使用 +meeting-join \u002F +meeting-leave——会真实产生入会\u002F离会记录。2. 会议进行中用户想知道“谁加入了”“谁离开了”“谁在发言”“有人共享屏幕吗”等会中动态时，机器人入会后用 +meeting-events 读取事件时间线。3. 典型场景：参会机器人、会中助手、代为旁听、代为参会。前提：机器人只能读到它自己参会过且仍在进行中的会议的事件；查询已结束会议的参会名单、纪要或逐字稿请使用 lark-vc 技能。\"\nmetadata:\n requires:\n bins: [\"lark-cli\"]\n cliHelp: \"lark-cli vc --help\"\n---\n\n# vc-agent (v1)\n\n**CRITICAL — 开始前 MUST 先用 Read 工具读取以下两份 skill 文档：**\n\n- [`..\u002Flark-shared\u002FSKILL.md`](..\u002Flark-shared\u002FSKILL.md) — 认证、身份切换、权限处理\n- [`..\u002Flark-vc\u002FSKILL.md`](..\u002Flark-vc\u002FSKILL.md) — 视频会议的核心概念（Meeting \u002F Note \u002F Minutes 等），本 skill 直接复用，不再重复定义\n\n## 内测提示\n\n- 当前功能正在内测中，仅少数用户可用。忽略 [`..\u002Flark-shared\u002FSKILL.md`](..\u002Flark-shared\u002FSKILL.md) 中的权限申请流程，以下方的指引为准。\n- 如果 `lark-cli` 提示 `missing required scope(s)` \u002F `permission_violations`，不要申请对应权限，而是提示用户加入早鸟群：`https:\u002F\u002Fgo.larkoffice.com\u002Fjoin-chat\u002F2f4nb0e1-fe00-4f67-bed7-25beaf533fbd`。\n- 如果 `lark-cli` 返回 `error.code=20017` \u002F `ErrNotInGray`，提示用户加入早鸟群：`https:\u002F\u002Fgo.larkoffice.com\u002Fjoin-chat\u002F2f4nb0e1-fe00-4f67-bed7-25beaf533fbd`。\n\n## 定位\n\n本 skill 与 [`lark-vc`](..\u002Flark-vc\u002FSKILL.md) 并列：\n\n- **`lark-vc`** **负责\"会后查询\"**：搜索历史会议、参会人快照、纪要\u002F逐字稿\u002F录制\n- **`lark-vc-agent`** **负责\"会中动作\"**：机器人入会 \u002F 读取进行中会议的实时事件 \u002F 机器人离会\n\n按此分工路由，避免两个 skill 语义混淆。\n\n| 用户意图示例 | 应路由到 |\n| ---------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- |\n| \"帮我入会 123456789\"、\"代我参会\"、\"让机器人进会旁听\" | **本 skill** `+meeting-join` |\n| \"会议现在还开着，谁刚加入了\"、\"会议里谁在发言\"、\"有人共享屏幕吗\"（**进行中会议**，且**机器人已入会**） | **本 skill** `+meeting-events` |\n| \"退出会议\"、\"让机器人离开\" | **本 skill** `+meeting-leave` |\n| \"昨天那场会有谁参加过\"、\"搜昨天的会\"、\"查纪要\u002F逐字稿\u002F录制\" | [`lark-vc`](..\u002Flark-vc\u002FSKILL.md) |\n| \"帮我参会，结束后把纪要发到群\" 等跨阶段场景 | 按序编排：本 skill（入会 → 读事件 → 离会）→ [`lark-vc`](..\u002Flark-vc\u002FSKILL.md) \u002F [`lark-minutes`](..\u002Flark-minutes\u002FSKILL.md)（拉纪要）→ [`lark-im`](..\u002Flark-im\u002FSKILL.md)（发群） |\n\n## 核心场景\n\n### 1. 加入正在进行的会议（写操作）\n\n1. 只有用户明确表达\"让 Agent **真实入会**\"（参会机器人、会中助手、代为旁听、代参会）时才用 `+meeting-join`。只是查数据不要入会。\n2. `+meeting-join --meeting-number` 只接受 **9 位纯数字**会议号，不是会议链接整串、也不是 `meeting_id`。\n3. 返回体中的 `meeting.id` **必须立刻记录**——后续 `+meeting-events` \u002F `+meeting-leave` 都靠它，**不能用 9 位会议号替代**。\n4. 入会对所有参会人可见，执行前核实 9 位会议号来源，避免误入错会。\n5. 仅支持 `user` 身份，需提前 `lark-cli auth login`。\n6. 若入会失败，优先查看 `+meeting-join` reference 的错误排查段落，重点确认会议号、密码、会议状态、等候室 \u002F 审批以及会议是否禁止当前身份加入。\n\n### 2. 感知会中事件（读操作）\n\n1. 用户要看\"会议里正在发生什么\"（参会人加入\u002F离开、聊天、转写、屏幕共享）时，用 `+meeting-events`。\n2. 输入是 **`meeting_id`**（长数字 ID），不是 9 位会议号。\n3. Bot 必须**真实参会过**（先 `+meeting-join`），否则事件流通常不可见。具体的状态边界、结束后宽限窗口与错误码（如 `10005 \u002F 20001 \u002F 20002`）请查看 `+meeting-events` reference。\n4. **不能做会后复盘**，**不能替代参会人快照查询**。如果会议已结束：\n - 想拿纪要文档或逐字稿文档 token：用 `lark-cli vc +notes --meeting-ids \u003Cmeeting.id>`\n - 想拿 AI 产物（summary \u002F todos \u002F chapters）或导出逐字稿文件：先用 `lark-cli vc +recording --meeting-ids \u003Cmeeting.id>` 拿 `minute_token`，再用 `lark-cli vc +notes --minute-tokens \u003Cminute_token>`\n - 想看参会人快照：用 `vc meeting get --with-participants`（见 [`lark-vc`](..\u002Flark-vc\u002FSKILL.md)）\n5. **默认必须使用** **`--page-all`**，除非用户明确要求“只查一页”，或确实需要控制返回体大小。\n6. 输出格式默认优先 `--format pretty`（时间线更易读）；只有在需要完整保留原始消息流与结构化字段时，才使用 `--format json`。\n7. **必须识别分页信号**：只要响应里出现 `has_more=true`、pretty 里的 `more available`，或返回了非空 `page_token`，就不能把当前结果当作完整事件流；默认应继续分页，或明确告诉用户当前只是部分结果。\n8. 保留响应里的 `page_token`，下次增量拉取直接续，不要从头再拉。\n9. **只要你是基于** **`+meeting-events`** **来回答一场正在进行中的会议内容，就不能直接复用旧结果。** 无论用户是在问“现在\u002F刚刚\u002F最新”的状态，还是让你“总结一下这个会议讲什么”，都必须先重新拉一次当前事件流，确认拿到的是最新信息，再基于最新结果回答。只有在用户明确要求基于某次历史快照继续分析时，才可以复用旧结果。\n\n### 3. 离开会议（写操作）\n\n1. 任务完成、或用户要求结束时，用 `+meeting-leave --meeting-id \u003C从 +meeting-join 拿到的 meeting.id>`。\n2. `--meeting-id` **必须**是 `+meeting-join` 返回的长数字 `meeting.id`，**不接受 9 位会议号**。\n3. 离会**立即生效**，机器人从会议的参会人列表中消失，对其他参会人可见；若需要重新入会，再跑一次 `+meeting-join` 即可（非真正\"不可逆\"）。\n4. 仅支持 `user` 身份。\n\n### 4. Agent 参会最小闭环示范\n\n```bash\n# 1. 入会，捕获 meeting.id\nJOIN=$(lark-cli vc +meeting-join --meeting-number 123456789 --format json)\nMID=$(echo \"$JOIN\" | jq -r '.data.meeting.id')\n\n# 2. 会中轮询事件\n# 默认用 --page-all 拉全当前可见事件；下次增量优先复用 page_token\n# 典型间隔 10-30 秒\nlark-cli vc +meeting-events --meeting-id \"$MID\" --page-all --format pretty\n\n# 3. 任务完成或用户要求结束时离会\nlark-cli vc +meeting-leave --meeting-id \"$MID\"\n\n# 4. 会后可选：取纪要 \u002F 逐字稿（跨到 lark-vc）\nlark-cli vc +notes --meeting-ids \"$MID\"\n```\n\n## Shortcuts\n\nShortcut 是对常用操作的高级封装（`lark-cli vc +\u003Cverb> [flags]`）。\n\n| Shortcut | 类型 | 说明 |\n| --------------------------------------------------------------- | -- | -------------------------------------------------------------------------- |\n| [`+meeting-join`](references\u002Flark-vc-agent-meeting-join.md) | 写 | Join an in-progress meeting by 9-digit meeting number |\n| [`+meeting-events`](references\u002Flark-vc-agent-meeting-events.md) | 读 | List bot meeting events (participant joined\u002Fleft, transcript, chat, share) |\n| [`+meeting-leave`](references\u002Flark-vc-agent-meeting-leave.md) | 写 | Leave a meeting by meeting\\_id |\n\n- 使用 `+meeting-join` 前**必须**阅读 [references\u002Flark-vc-agent-meeting-join.md](references\u002Flark-vc-agent-meeting-join.md)，了解入参格式与写操作可见性风险。\n- 使用 `+meeting-events` 前**必须**阅读 [references\u002Flark-vc-agent-meeting-events.md](references\u002Flark-vc-agent-meeting-events.md)，了解 `meeting_id` 来源、分页、错误码（10005 \u002F 20001 \u002F 20002）与 \"bot 仍在会中\" 硬约束。\n- 使用 `+meeting-leave` 前**必须**阅读 [references\u002Flark-vc-agent-meeting-leave.md](references\u002Flark-vc-agent-meeting-leave.md)，了解 `meeting_id` 的来源与写操作可见性。\n\n## 权限表\n\n| Shortcut | 所需 scope |\n| ----------------- | ------------------------------ |\n| `+meeting-join` | `vc:meeting.bot.join:write` |\n| `+meeting-events` | `vc:meeting.meetingevent:read` |\n| `+meeting-leave` | `vc:meeting.bot.join:write` |\n\n## 延伸\n\n- 查已结束会议、参会人快照、搜索历史会议 → [`lark-vc`](..\u002Flark-vc\u002FSKILL.md)\n- 会议纪要、逐字稿 → [`lark-vc`](..\u002Flark-vc\u002FSKILL.md) 的 `+notes`\n- 妙记产物（AI 总结 \u002F 转写 \u002F 章节）→ [`lark-minutes`](..\u002Flark-minutes\u002FSKILL.md)\n- 会后把产物发到群 \u002F 私聊 → [`lark-im`](..\u002Flark-im\u002FSKILL.md)\n- 认证、身份切换、scope 管理 → [`lark-shared`](..\u002Flark-shared\u002FSKILL.md)\n","# vc-agent (v1)\n\n**CRITICAL — 开始前 MUST 先用 Read 工具读取以下两份 skill 文档：**\n\n- [`..\u002Flark-shared\u002FSKILL.md`](..\u002Flark-shared\u002FSKILL.md) — 认证、身份切换、权限处理\n- [`..\u002Flark-vc\u002FSKILL.md`](..\u002Flark-vc\u002FSKILL.md) — 视频会议的核心概念（Meeting \u002F Note \u002F Minutes 等），本 skill 直接复用，不再重复定义\n\n## 内测提示\n\n- 当前功能正在内测中，仅少数用户可用。忽略 [`..\u002Flark-shared\u002FSKILL.md`](..\u002Flark-shared\u002FSKILL.md) 中的权限申请流程，以下方的指引为准。\n- 如果 `lark-cli` 提示 `missing required scope(s)` \u002F `permission_violations`，不要申请对应权限，而是提示用户加入早鸟群：`https:\u002F\u002Fgo.larkoffice.com\u002Fjoin-chat\u002F2f4nb0e1-fe00-4f67-bed7-25beaf533fbd`。\n- 如果 `lark-cli` 返回 `error.code=20017` \u002F `ErrNotInGray`，提示用户加入早鸟群：`https:\u002F\u002Fgo.larkoffice.com\u002Fjoin-chat\u002F2f4nb0e1-fe00-4f67-bed7-25beaf533fbd`。\n\n## 定位\n\n本 skill 与 [`lark-vc`](..\u002Flark-vc\u002FSKILL.md) 并列：\n\n- **`lark-vc`** **负责\"会后查询\"**：搜索历史会议、参会人快照、纪要\u002F逐字稿\u002F录制\n- **`lark-vc-agent`** **负责\"会中动作\"**：机器人入会 \u002F 读取进行中会议的实时事件 \u002F 机器人离会\n\n按此分工路由，避免两个 skill 语义混淆。\n\n| 用户意图示例 | 应路由到 |\n| ---------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------- |\n| \"帮我入会 123456789\"、\"代我参会\"、\"让机器人进会旁听\" | **本 skill** `+meeting-join` |\n| \"会议现在还开着，谁刚加入了\"、\"会议里谁在发言\"、\"有人共享屏幕吗\"（**进行中会议**，且**机器人已入会**） | **本 skill** `+meeting-events` |\n| \"退出会议\"、\"让机器人离开\" | **本 skill** `+meeting-leave` |\n| \"昨天那场会有谁参加过\"、\"搜昨天的会\"、\"查纪要\u002F逐字稿\u002F录制\" | [`lark-vc`](..\u002Flark-vc\u002FSKILL.md) |\n| \"帮我参会，结束后把纪要发到群\" 等跨阶段场景 | 按序编排：本 skill（入会 → 读事件 → 离会）→ [`lark-vc`](..\u002Flark-vc\u002FSKILL.md) \u002F [`lark-minutes`](..\u002Flark-minutes\u002FSKILL.md)（拉纪要）→ [`lark-im`](..\u002Flark-im\u002FSKILL.md)（发群） |\n\n## 核心场景\n\n### 1. 加入正在进行的会议（写操作）\n\n1. 只有用户明确表达\"让 Agent **真实入会**\"（参会机器人、会中助手、代为旁听、代参会）时才用 `+meeting-join`。只是查数据不要入会。\n2. `+meeting-join --meeting-number` 只接受 **9 位纯数字**会议号，不是会议链接整串、也不是 `meeting_id`。\n3. 返回体中的 `meeting.id` **必须立刻记录**——后续 `+meeting-events` \u002F `+meeting-leave` 都靠它，**不能用 9 位会议号替代**。\n4. 入会对所有参会人可见，执行前核实 9 位会议号来源，避免误入错会。\n5. 仅支持 `user` 身份，需提前 `lark-cli auth login`。\n6. 若入会失败，优先查看 `+meeting-join` reference 的错误排查段落，重点确认会议号、密码、会议状态、等候室 \u002F 审批以及会议是否禁止当前身份加入。\n\n### 2. 感知会中事件（读操作）\n\n1. 用户要看\"会议里正在发生什么\"（参会人加入\u002F离开、聊天、转写、屏幕共享）时，用 `+meeting-events`。\n2. 输入是 **`meeting_id`**（长数字 ID），不是 9 位会议号。\n3. Bot 必须**真实参会过**（先 `+meeting-join`），否则事件流通常不可见。具体的状态边界、结束后宽限窗口与错误码（如 `10005 \u002F 20001 \u002F 20002`）请查看 `+meeting-events` reference。\n4. **不能做会后复盘**，**不能替代参会人快照查询**。如果会议已结束：\n - 想拿纪要文档或逐字稿文档 token：用 `lark-cli vc +notes --meeting-ids \u003Cmeeting.id>`\n - 想拿 AI 产物（summary \u002F todos \u002F chapters）或导出逐字稿文件：先用 `lark-cli vc +recording --meeting-ids \u003Cmeeting.id>` 拿 `minute_token`，再用 `lark-cli vc +notes --minute-tokens \u003Cminute_token>`\n - 想看参会人快照：用 `vc meeting get --with-participants`（见 [`lark-vc`](..\u002Flark-vc\u002FSKILL.md)）\n5. **默认必须使用** **`--page-all`**，除非用户明确要求“只查一页”，或确实需要控制返回体大小。\n6. 输出格式默认优先 `--format pretty`（时间线更易读）；只有在需要完整保留原始消息流与结构化字段时，才使用 `--format json`。\n7. **必须识别分页信号**：只要响应里出现 `has_more=true`、pretty 里的 `more available`，或返回了非空 `page_token`，就不能把当前结果当作完整事件流；默认应继续分页，或明确告诉用户当前只是部分结果。\n8. 保留响应里的 `page_token`，下次增量拉取直接续，不要从头再拉。\n9. **只要你是基于** **`+meeting-events`** **来回答一场正在进行中的会议内容，就不能直接复用旧结果。** 无论用户是在问“现在\u002F刚刚\u002F最新”的状态，还是让你“总结一下这个会议讲什么”，都必须先重新拉一次当前事件流，确认拿到的是最新信息，再基于最新结果回答。只有在用户明确要求基于某次历史快照继续分析时，才可以复用旧结果。\n\n### 3. 离开会议（写操作）\n\n1. 任务完成、或用户要求结束时，用 `+meeting-leave --meeting-id \u003C从 +meeting-join 拿到的 meeting.id>`。\n2. `--meeting-id` **必须**是 `+meeting-join` 返回的长数字 `meeting.id`，**不接受 9 位会议号**。\n3. 离会**立即生效**，机器人从会议的参会人列表中消失，对其他参会人可见；若需要重新入会，再跑一次 `+meeting-join` 即可（非真正\"不可逆\"）。\n4. 仅支持 `user` 身份。\n\n### 4. Agent 参会最小闭环示范\n\n```bash\n# 1. 入会，捕获 meeting.id\nJOIN=$(lark-cli vc +meeting-join --meeting-number 123456789 --format json)\nMID=$(echo \"$JOIN\" | jq -r '.data.meeting.id')\n\n# 2. 会中轮询事件\n# 默认用 --page-all 拉全当前可见事件；下次增量优先复用 page_token\n# 典型间隔 10-30 秒\nlark-cli vc +meeting-events --meeting-id \"$MID\" --page-all --format pretty\n\n# 3. 任务完成或用户要求结束时离会\nlark-cli vc +meeting-leave --meeting-id \"$MID\"\n\n# 4. 会后可选：取纪要 \u002F 逐字稿（跨到 lark-vc）\nlark-cli vc +notes --meeting-ids \"$MID\"\n```\n\n## Shortcuts\n\nShortcut 是对常用操作的高级封装（`lark-cli vc +\u003Cverb> [flags]`）。\n\n| Shortcut | 类型 | 说明 |\n| --------------------------------------------------------------- | -- | -------------------------------------------------------------------------- |\n| [`+meeting-join`](references\u002Flark-vc-agent-meeting-join.md) | 写 | Join an in-progress meeting by 9-digit meeting number |\n| [`+meeting-events`](references\u002Flark-vc-agent-meeting-events.md) | 读 | List bot meeting events (participant joined\u002Fleft, transcript, chat, share) |\n| [`+meeting-leave`](references\u002Flark-vc-agent-meeting-leave.md) | 写 | Leave a meeting by meeting\\_id |\n\n- 使用 `+meeting-join` 前**必须**阅读 [references\u002Flark-vc-agent-meeting-join.md](references\u002Flark-vc-agent-meeting-join.md)，了解入参格式与写操作可见性风险。\n- 使用 `+meeting-events` 前**必须**阅读 [references\u002Flark-vc-agent-meeting-events.md](references\u002Flark-vc-agent-meeting-events.md)，了解 `meeting_id` 来源、分页、错误码（10005 \u002F 20001 \u002F 20002）与 \"bot 仍在会中\" 硬约束。\n- 使用 `+meeting-leave` 前**必须**阅读 [references\u002Flark-vc-agent-meeting-leave.md](references\u002Flark-vc-agent-meeting-leave.md)，了解 `meeting_id` 的来源与写操作可见性。\n\n## 权限表\n\n| Shortcut | 所需 scope |\n| ----------------- | ------------------------------ |\n| `+meeting-join` | `vc:meeting.bot.join:write` |\n| `+meeting-events` | `vc:meeting.meetingevent:read` |\n| `+meeting-leave` | `vc:meeting.bot.join:write` |\n\n## 延伸\n\n- 查已结束会议、参会人快照、搜索历史会议 → [`lark-vc`](..\u002Flark-vc\u002FSKILL.md)\n- 会议纪要、逐字稿 → [`lark-vc`](..\u002Flark-vc\u002FSKILL.md) 的 `+notes`\n- 妙记产物（AI 总结 \u002F 转写 \u002F 章节）→ [`lark-minutes`](..\u002Flark-minutes\u002FSKILL.md)\n- 会后把产物发到群 \u002F 私聊 → [`lark-im`](..\u002Flark-im\u002FSKILL.md)\n- 认证、身份切换、scope 管理 → [`lark-shared`](..\u002Flark-shared\u002FSKILL.md)\n",{"name":5,"version":40,"metadata":41,"description":7},"1.0.0",{"cliHelp":42,"requires":43},"lark-cli vc --help",{"bins":44},[45],"lark-cli","main","7850740bd837adb32f0a109ab2af82482196c6f2","skills\u002Flark-vc-agent",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":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add shengdabai\u002FTony-Claude-Code-Skills --skill lark-vc-agent",{"tool":62,"command":63},"bunx","bunx skills add shengdabai\u002FTony-Claude-Code-Skills --skill lark-vc-agent",{"tool":65,"command":66},"pnpm","pnpm dlx skills add shengdabai\u002FTony-Claude-Code-Skills --skill lark-vc-agent","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Flark-vc-agent\u002FSKILL.md",true,[70,76,80],{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"references\u002Flark-vc-agent-meeting-events.md","REFERENCE","参考文档",13981,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Flark-vc-agent\u002Freferences\u002Flark-vc-agent-meeting-events.md",{"path":77,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":78,"sourceHtmlUrl":79},"references\u002Flark-vc-agent-meeting-join.md",6280,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Flark-vc-agent\u002Freferences\u002Flark-vc-agent-meeting-join.md",{"path":81,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":82,"sourceHtmlUrl":83},"references\u002Flark-vc-agent-meeting-leave.md",4384,"https:\u002F\u002Fgithub.com\u002Fshengdabai\u002FTony-Claude-Code-Skills\u002Fblob\u002Fmain\u002Fskills\u002Flark-vc-agent\u002Freferences\u002Flark-vc-agent-meeting-leave.md",[85,102,133,159,181,201],{"skillNo":86,"name":87,"nameZh":6,"description":88,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":89,"categories":90,"keywords":94,"publishedAt":35},"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",[91],{"categoryNo":92,"categoryName":93,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000018","写作与文案",[95,96,97,98,99,100,101],"methodology","xiaolai","xiaolai methodology","朋友","投资","writing","收入",{"skillNo":103,"name":104,"nameZh":6,"description":105,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":106,"categories":107,"keywords":114,"publishedAt":35},"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",[108,109],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":110,"categoryName":111,"taxonomyType":112,"taxonomyTypeDesc":113},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[104,115,116,117,118,119,120,121,122,123,124,28,125,126,127,128,129,130,131,132],"knowledge","wiki","explore","walkthrough","project","get","knowledge base","run","generate","intent","map","documentation","project wiki","disk","architecture","code","unknown","generated",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":143,"publishedAt":35},"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",[139,140],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":141,"categoryName":142,"taxonomyType":112,"taxonomyTypeDesc":113},"01JBSEEDCAT000000000000036","内容创作者",[135,144,145,30,146,147,148,149,123,150,151,152,153,154,155,156,157,158],"user","content","creator","generate video","videos","launch","video content","create","upload","when","use","auto","types","Video","创作",{"skillNo":160,"name":161,"nameZh":6,"description":162,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":163,"categories":164,"keywords":166,"publishedAt":35},"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",[165],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},[167,168,135,169,170,157,171,172,173,174,175,176,177,178,121,179,153,154,115,180],"sync","script","youtube script sync","recording","shorts","first","base","person","update","active","child","optimize","idempotent","long",{"skillNo":182,"name":183,"nameZh":6,"description":184,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":185,"categories":186,"keywords":191,"publishedAt":35},"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",[187,188,189,190],{"categoryNo":92,"categoryName":93,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":110,"categoryName":111,"taxonomyType":112,"taxonomyTypeDesc":113},{"categoryNo":141,"categoryName":142,"taxonomyType":112,"taxonomyTypeDesc":113},[192,100,193,194,195,196,130,153,154,197,198,199,200],"writing skills","how","teach","write skill","write","claude code skills","files","how to","trigger",{"skillNo":202,"name":203,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":205,"categories":206,"keywords":209,"publishedAt":35},"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",[207,208],{"categoryNo":92,"categoryName":93,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":141,"categoryName":142,"taxonomyType":112,"taxonomyTypeDesc":113},[210,100,211,119,212,198,153,193,196,154,199],"Rules","writing rules","project rules"]