[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PCTAK0FF4TC76C2TYQ3CC7":3,"skill-same:01M6PCTAK0FF4TC76C2TYQ3CC7":81},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":25,"publishedAt":46,"linkOnly":47,"markdownContent":48,"markdownBody":49,"frontMatter":50,"refName":33,"commitSha":56,"skillDirectory":57,"forksCount":13,"repositoryHtmlUrl":58,"repositoryHomepageUrl":6,"ownerHtmlUrl":59,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":60,"install":61,"resources":74},"01M6PCTAK0FF4TC76C2TYQ3CC7","reverse-browser-automation",null,"Automate browsers (Playwright) and Windows desktop applications (UI automation) for reverse-engineering evidence collection, UI-driven workflows, and network observation during analysis.","duc-duy-1612\u002FOnline-Delivery-Systems-Web","duc-duy-1612","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F192231384?v=4","01M6NSDKQQDKVTHZ8DZMZ1VYY6","01M6NSDKW8DDVTQHBT1HBDDJPT",0,"MIT","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Freverse-browser-automation\u002FSKILL.md",[17,22],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000008","测试与质量","SCENARIO","使用场景",{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45],"automation","reverse","reverse browser automation","browser","browser automation","reverse-engineering","for","main","community","evidence","analysis","collection","applications","https","license","desktop","windows","workflows","playwright","github","2026-11-10 10:12:30",false,"---\nname: reverse-browser-automation\ndescription: \"Automate browsers (Playwright) and Windows desktop applications (UI automation) for reverse-engineering evidence collection, UI-driven workflows, and network observation during analysis.\"\nrisk: safe\nsource: \"https:\u002F\u002Fgithub.com\u002Fzhaoxuya520\u002Freverse-skill\"\nsource_repo: \"zhaoxuya520\u002Freverse-skill\"\nsource_type: community\ndate_added: \"2026-08-25\"\nlicense: \"MIT\"\nlicense_source: \"https:\u002F\u002Fgithub.com\u002Fzhaoxuya520\u002Freverse-skill\u002Fblob\u002Fmain\u002FLICENSE\"\n---\n# 自动化操作 (Desktop & Browser Automation)\n## When to Use\n\n- Analysis requires scripted interaction with a browser or desktop application.\n- Collecting reproducible UI evidence (screenshots, network traces) during an assessment.\n\n\n## 适用范围\n\n当任务属于以下场景时使用本 skill：\n\n### 浏览器场景（Playwright \u002F agent-browser）\n- 打开网页并操作页面元素（点击、填表、提交）\n- 爬取页面内容或截图\n- 自动化登录流程\n- 渗透测试中与 Web 页面交互（提交 payload、触发 XSS）\n- 验证码页面的自动化处理\n- 批量表单提交\n\n### 桌面应用场景（OpenReverse）\n- 操作 Windows 桌面应用（IDA Pro、x64dbg、Wireshark 等）\n- 需要视觉驱动交互（CUA 模式）\n- 需要结构化 UI 操作（UIA 模式）\n- 桌面应用的网络流量观察（内置 mitmproxy）\n- 自动化逆向工具的 GUI 操作\n- 黑盒测试桌面软件\n\n### 与其他工具的分工\n\n| 场景 | 用什么 |\n|------|--------|\n| 操作网页（浏览器内） | **Playwright \u002F agent-browser** |\n| 操作桌面应用（Windows GUI） | **OpenReverse** |\n| 抓包分析、HTTP 请求捕获 | anything-analyzer 或 OpenReverse network lane |\n| JS 断点、Hook、CDP 调试 | jshookmcp |\n| 定位签名算法、补环境复现 | js-reverse |\n\n简单判断：\n- 目标是网页 → Playwright\n- 目标是 Windows 桌面应用 → OpenReverse\n- 两者都需要 → 组合使用\n\n---\n\n## Part 1: 浏览器自动化（Playwright \u002F agent-browser）\n\n### 核心工作流\n\n```bash\n# 1. 打开页面\nagent-browser open \u003Curl>\n\n# 2. 获取可交互元素（返回 @e1, @e2... 引用）\nagent-browser snapshot -i\n\n# 3. 用引用操作元素\nagent-browser click @e1\nagent-browser fill @e2 \"text\"\n\n# 4. 完成后关闭\nagent-browser close\n```\n\n### 命令参考\n\n```bash\n# 导航\nagent-browser open \u003Curl>\nagent-browser close\n\n# 页面快照\nagent-browser snapshot        # 完整无障碍树\nagent-browser snapshot -i     # 仅可交互元素（推荐）\n\n# 交互操作\nagent-browser click @e1\nagent-browser fill @e2 \"text\"\nagent-browser type @e2 \"text\"\nagent-browser press Enter\nagent-browser scroll down 500\n\n# 获取信息\nagent-browser get text @e1\nagent-browser get title\nagent-browser get url\n\n# 等待\nagent-browser wait @e1\nagent-browser wait 2000\nagent-browser wait --load networkidle\n```\n\n### 注意事项\n- 必须执行 `agent-browser close`，否则进程泄漏\n- 操作前先 snapshot，不要猜元素引用\n- 提交表单后用 `wait --load networkidle` 等页面稳定\n\n---\n\n## Part 2: 桌面应用自动化（OpenReverse）\n\n### 概述\n\n[OpenReverse](https:\u002F\u002Fgithub.com\u002Fzhexulong\u002Fopenreverse) 是面向 AI Agent 的桌面交互与证据采集框架，支持：\n- **UIA 模式**：Windows UI Automation，结构化桌面控件操作\n- **CUA 模式**：视觉驱动交互（Computer Use Agent），适合复杂 GUI\n- **网络观察**：内置 mitmproxy 代理 + 本地抓取\n\n### 交互模式选择\n\n| 模式 | 适合场景 | 底层 |\n|------|---------|------|\n| UIA | 目标应用有标准 Windows 控件（按钮、文本框、列表） | Windows UI Automation API |\n| CUA | 目标应用 UI 复杂或非标准控件（IDA 的反汇编视图、自定义渲染界面） | 视觉识别 + 鼠标键盘 |\n\n### 网络观察模式\n\n| 模式 | 适合场景 |\n|------|---------|\n| Proxy Lane | 目标应用可以配置代理（推荐） |\n| Local Lane | 目标应用无法走代理，需要本地抓取 |\n\n### 安装与配置\n\n```bash\n# 1. Clone 项目\ngit clone https:\u002F\u002Fgithub.com\u002Fzhexulong\u002Fopenreverse.git\ncd openreverse\n\n# 2. 安装依赖\nnpm install\n\n# 3. 接入 Agent 宿主（Claude Code \u002F Codex \u002F Zed）\nnpm run init:agents -- --target=all \u002Fpath\u002Fto\u002Fproject\n\n# 4. 安装 CUA runtime（如果需要视觉驱动模式）\nnpm run install:cua-runtime\nnpm run doctor:cua-runtime\n\n# 5. 安装网络观察依赖（如果需要抓包）\nnpm run install:mitmproxy\nnpm run doctor:network\n```\n\n### 常见组合\n\n| 需求 | 配置 |\n|------|------|\n| 只操作桌面应用 | UIA 或 CUA，不接网络 lane |\n| 操作桌面应用 + 抓包 | UIA\u002FCUA + proxy lane |\n| 操作桌面应用 + 本地抓取 | UIA\u002FCUA + local lane |\n\n### 逆向场景示例\n\n```text\n场景：自动化操作 IDA Pro 进行批量分析\n\n1. 用 OpenReverse CUA 模式打开 IDA Pro\n2. 自动加载目标二进制\n3. 等待分析完成\n4. 通过 UI 操作导出函数列表\n5. 同时用 network lane 观察 IDA 的网络行为（如 Lumina 请求）\n```\n\n```text\n场景：自动化操作 x64dbg 调试\n\n1. 用 OpenReverse UIA 模式启动 x64dbg\n2. 加载目标程序\n3. 设置断点\n4. 运行并观察寄存器\u002F内存变化\n5. 截图保存证据\n```\n\n---\n\n## 按需自举（On-Demand Bootstrap）\n\n### 自动化能力边界\n\n| 工具 | 可自动安装 | 安装方式 | 说明 |\n|------|-----------|---------|------|\n| Playwright | ✓ | npm + npx playwright install | 浏览器自动化引擎 |\n| agent-browser CLI | ✓ | npm install -g agent-browser | 浏览器操作 CLI |\n| Node.js | ✓ | winget | 前置依赖 |\n| OpenReverse | ✗ | 手动 clone + npm install | 实验阶段，依赖较重 |\n| mitmproxy | ✗ | 手动安装 | OpenReverse 网络观察依赖 |\n\n### 自举触发\n\n- 浏览器操作缺 Playwright → 自动 bootstrap\n- 桌面操作需要 OpenReverse → 引导用户手动安装（给出完整步骤）\n\n### OpenReverse 手动安装引导\n\n如果 AI 检测到需要桌面应用自动化但 OpenReverse 未安装：\n\n```markdown\n⚠️ **需要 OpenReverse 进行桌面应用自动化**\n\n**安装步骤**：\n1. `git clone https:\u002F\u002Fgithub.com\u002Fzhexulong\u002Fopenreverse.git`\n2. `cd openreverse && npm install`\n3. `npm run init:agents -- --target=all \u003C你的项目路径>`\n4. 如需视觉模式：`npm run install:cua-runtime`\n5. 如需网络观察：`npm run install:mitmproxy`\n\n**验证**：`npm run doctor:cua-runtime` 和 `npm run doctor:network`\n```\n\n---\n\n## 路由上下文\n\n**上游入口**: `skills\u002FSKILL.md`（总控）、`routing.md`\n**适用场景**: 任何需要自动化操作浏览器或桌面应用的任务\n**下游出口**:\n- 抓到的请求需要分析 → `anything-analyzer` 或 `js-reverse`\n- 需要 JS 调试\u002FHook → `jshookmcp`\n- 需要还原签名算法 → `js-reverse`\n- 桌面应用是逆向工具 → `ida-reverse\u002F`\n\n**同级关联模块**: `js-reverse`（浏览器操作后可能需要分析 JS）、`ida-reverse`（OpenReverse 可以自动化操作 IDA GUI）\n\n\n## 任务完成自检（声称完成前 MUST 通过）\n\n- [ ] 我是否执行了工作流中的每一步（而不是只阅读）？\n- [ ] 我是否基于 `tool-index` 使用了真实工具路径？\n- [ ] 我是否产出了可复现证据（命令\u002F脚本\u002F截图\u002F报告）？\n- [ ] 我是否完成并回写了 RULES 要求的 Checklist 项？\n\n## Limitations\n\n- UI selectors break on application updates; scripts need maintenance.\n- Windows desktop automation requires an OS with the matching accessibility stack.\n\n> Adapted from [zhaoxuya520\u002Freverse-skill](https:\u002F\u002Fgithub.com\u002Fzhaoxuya520\u002Freverse-skill) (MIT).\n","# 自动化操作 (Desktop & Browser Automation)\n## When to Use\n\n- Analysis requires scripted interaction with a browser or desktop application.\n- Collecting reproducible UI evidence (screenshots, network traces) during an assessment.\n\n\n## 适用范围\n\n当任务属于以下场景时使用本 skill：\n\n### 浏览器场景（Playwright \u002F agent-browser）\n- 打开网页并操作页面元素（点击、填表、提交）\n- 爬取页面内容或截图\n- 自动化登录流程\n- 渗透测试中与 Web 页面交互（提交 payload、触发 XSS）\n- 验证码页面的自动化处理\n- 批量表单提交\n\n### 桌面应用场景（OpenReverse）\n- 操作 Windows 桌面应用（IDA Pro、x64dbg、Wireshark 等）\n- 需要视觉驱动交互（CUA 模式）\n- 需要结构化 UI 操作（UIA 模式）\n- 桌面应用的网络流量观察（内置 mitmproxy）\n- 自动化逆向工具的 GUI 操作\n- 黑盒测试桌面软件\n\n### 与其他工具的分工\n\n| 场景 | 用什么 |\n|------|--------|\n| 操作网页（浏览器内） | **Playwright \u002F agent-browser** |\n| 操作桌面应用（Windows GUI） | **OpenReverse** |\n| 抓包分析、HTTP 请求捕获 | anything-analyzer 或 OpenReverse network lane |\n| JS 断点、Hook、CDP 调试 | jshookmcp |\n| 定位签名算法、补环境复现 | js-reverse |\n\n简单判断：\n- 目标是网页 → Playwright\n- 目标是 Windows 桌面应用 → OpenReverse\n- 两者都需要 → 组合使用\n\n---\n\n## Part 1: 浏览器自动化（Playwright \u002F agent-browser）\n\n### 核心工作流\n\n```bash\n# 1. 打开页面\nagent-browser open \u003Curl>\n\n# 2. 获取可交互元素（返回 @e1, @e2... 引用）\nagent-browser snapshot -i\n\n# 3. 用引用操作元素\nagent-browser click @e1\nagent-browser fill @e2 \"text\"\n\n# 4. 完成后关闭\nagent-browser close\n```\n\n### 命令参考\n\n```bash\n# 导航\nagent-browser open \u003Curl>\nagent-browser close\n\n# 页面快照\nagent-browser snapshot        # 完整无障碍树\nagent-browser snapshot -i     # 仅可交互元素（推荐）\n\n# 交互操作\nagent-browser click @e1\nagent-browser fill @e2 \"text\"\nagent-browser type @e2 \"text\"\nagent-browser press Enter\nagent-browser scroll down 500\n\n# 获取信息\nagent-browser get text @e1\nagent-browser get title\nagent-browser get url\n\n# 等待\nagent-browser wait @e1\nagent-browser wait 2000\nagent-browser wait --load networkidle\n```\n\n### 注意事项\n- 必须执行 `agent-browser close`，否则进程泄漏\n- 操作前先 snapshot，不要猜元素引用\n- 提交表单后用 `wait --load networkidle` 等页面稳定\n\n---\n\n## Part 2: 桌面应用自动化（OpenReverse）\n\n### 概述\n\n[OpenReverse](https:\u002F\u002Fgithub.com\u002Fzhexulong\u002Fopenreverse) 是面向 AI Agent 的桌面交互与证据采集框架，支持：\n- **UIA 模式**：Windows UI Automation，结构化桌面控件操作\n- **CUA 模式**：视觉驱动交互（Computer Use Agent），适合复杂 GUI\n- **网络观察**：内置 mitmproxy 代理 + 本地抓取\n\n### 交互模式选择\n\n| 模式 | 适合场景 | 底层 |\n|------|---------|------|\n| UIA | 目标应用有标准 Windows 控件（按钮、文本框、列表） | Windows UI Automation API |\n| CUA | 目标应用 UI 复杂或非标准控件（IDA 的反汇编视图、自定义渲染界面） | 视觉识别 + 鼠标键盘 |\n\n### 网络观察模式\n\n| 模式 | 适合场景 |\n|------|---------|\n| Proxy Lane | 目标应用可以配置代理（推荐） |\n| Local Lane | 目标应用无法走代理，需要本地抓取 |\n\n### 安装与配置\n\n```bash\n# 1. Clone 项目\ngit clone https:\u002F\u002Fgithub.com\u002Fzhexulong\u002Fopenreverse.git\ncd openreverse\n\n# 2. 安装依赖\nnpm install\n\n# 3. 接入 Agent 宿主（Claude Code \u002F Codex \u002F Zed）\nnpm run init:agents -- --target=all \u002Fpath\u002Fto\u002Fproject\n\n# 4. 安装 CUA runtime（如果需要视觉驱动模式）\nnpm run install:cua-runtime\nnpm run doctor:cua-runtime\n\n# 5. 安装网络观察依赖（如果需要抓包）\nnpm run install:mitmproxy\nnpm run doctor:network\n```\n\n### 常见组合\n\n| 需求 | 配置 |\n|------|------|\n| 只操作桌面应用 | UIA 或 CUA，不接网络 lane |\n| 操作桌面应用 + 抓包 | UIA\u002FCUA + proxy lane |\n| 操作桌面应用 + 本地抓取 | UIA\u002FCUA + local lane |\n\n### 逆向场景示例\n\n```text\n场景：自动化操作 IDA Pro 进行批量分析\n\n1. 用 OpenReverse CUA 模式打开 IDA Pro\n2. 自动加载目标二进制\n3. 等待分析完成\n4. 通过 UI 操作导出函数列表\n5. 同时用 network lane 观察 IDA 的网络行为（如 Lumina 请求）\n```\n\n```text\n场景：自动化操作 x64dbg 调试\n\n1. 用 OpenReverse UIA 模式启动 x64dbg\n2. 加载目标程序\n3. 设置断点\n4. 运行并观察寄存器\u002F内存变化\n5. 截图保存证据\n```\n\n---\n\n## 按需自举（On-Demand Bootstrap）\n\n### 自动化能力边界\n\n| 工具 | 可自动安装 | 安装方式 | 说明 |\n|------|-----------|---------|------|\n| Playwright | ✓ | npm + npx playwright install | 浏览器自动化引擎 |\n| agent-browser CLI | ✓ | npm install -g agent-browser | 浏览器操作 CLI |\n| Node.js | ✓ | winget | 前置依赖 |\n| OpenReverse | ✗ | 手动 clone + npm install | 实验阶段，依赖较重 |\n| mitmproxy | ✗ | 手动安装 | OpenReverse 网络观察依赖 |\n\n### 自举触发\n\n- 浏览器操作缺 Playwright → 自动 bootstrap\n- 桌面操作需要 OpenReverse → 引导用户手动安装（给出完整步骤）\n\n### OpenReverse 手动安装引导\n\n如果 AI 检测到需要桌面应用自动化但 OpenReverse 未安装：\n\n```markdown\n⚠️ **需要 OpenReverse 进行桌面应用自动化**\n\n**安装步骤**：\n1. `git clone https:\u002F\u002Fgithub.com\u002Fzhexulong\u002Fopenreverse.git`\n2. `cd openreverse && npm install`\n3. `npm run init:agents -- --target=all \u003C你的项目路径>`\n4. 如需视觉模式：`npm run install:cua-runtime`\n5. 如需网络观察：`npm run install:mitmproxy`\n\n**验证**：`npm run doctor:cua-runtime` 和 `npm run doctor:network`\n```\n\n---\n\n## 路由上下文\n\n**上游入口**: `skills\u002FSKILL.md`（总控）、`routing.md`\n**适用场景**: 任何需要自动化操作浏览器或桌面应用的任务\n**下游出口**:\n- 抓到的请求需要分析 → `anything-analyzer` 或 `js-reverse`\n- 需要 JS 调试\u002FHook → `jshookmcp`\n- 需要还原签名算法 → `js-reverse`\n- 桌面应用是逆向工具 → `ida-reverse\u002F`\n\n**同级关联模块**: `js-reverse`（浏览器操作后可能需要分析 JS）、`ida-reverse`（OpenReverse 可以自动化操作 IDA GUI）\n\n\n## 任务完成自检（声称完成前 MUST 通过）\n\n- [ ] 我是否执行了工作流中的每一步（而不是只阅读）？\n- [ ] 我是否基于 `tool-index` 使用了真实工具路径？\n- [ ] 我是否产出了可复现证据（命令\u002F脚本\u002F截图\u002F报告）？\n- [ ] 我是否完成并回写了 RULES 要求的 Checklist 项？\n\n## Limitations\n\n- UI selectors break on application updates; scripts need maintenance.\n- Windows desktop automation requires an OS with the matching accessibility stack.\n\n> Adapted from [zhaoxuya520\u002Freverse-skill](https:\u002F\u002Fgithub.com\u002Fzhaoxuya520\u002Freverse-skill) (MIT).\n",{"name":5,"risk":51,"source":52,"license":14,"date_added":53,"description":7,"source_repo":54,"source_type":34,"license_source":55},"safe","https:\u002F\u002Fgithub.com\u002Fzhaoxuya520\u002Freverse-skill","2026-08-25","zhaoxuya520\u002Freverse-skill","https:\u002F\u002Fgithub.com\u002Fzhaoxuya520\u002Freverse-skill\u002Fblob\u002Fmain\u002FLICENSE","f3312ba749561b6159f477dbfc9313c875d40a56",".agents\u002Fskills_archive\u002Freverse-browser-automation","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612","2026-10-25 23:50:58",{"source":8,"skillName":5,"commands":62,"prompt":72,"zipAvailable":73},[63,66,69],{"tool":64,"command":65},"npx","npx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill reverse-browser-automation",{"tool":67,"command":68},"bunx","bunx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill reverse-browser-automation",{"tool":70,"command":71},"pnpm","pnpm dlx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill reverse-browser-automation","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Freverse-browser-automation\u002FSKILL.md",true,[75],{"path":76,"resourceType":77,"resourceTypeDesc":78,"sizeBytes":79,"sourceHtmlUrl":80},"references\u002Fplaywright-cheatsheet.md","REFERENCE","参考文档",9829,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Freverse-browser-automation\u002Freferences\u002Fplaywright-cheatsheet.md",[82,109,133,154,182,206],{"skillNo":83,"name":84,"nameZh":6,"description":85,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":86,"categories":87,"keywords":91,"publishedAt":46},"01M6Q0FA5FZ410Z33Z3TFQ4DBA","zero-trust","Implement zero-trust network architecture. Configure identity-based access, micro-segmentation, and continuous verification. Use when implementing modern security architectures.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzero-trust\u002FSKILL.md",[88],{"categoryNo":89,"categoryName":90,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[92,93,94,95,96,97,84,98,99,100,101,102,34,33,103,104,105,106,107,108],"ZeRO","trust","zero trust","architecture","assessment","verification","segmentation","devops-security","access","configure","only","active","critical","scope","scripts","relevant","implementing",{"skillNo":110,"name":111,"nameZh":6,"description":112,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":113,"categories":114,"keywords":115,"publishedAt":46},"01M6Q0F1YZJW3KX5FBKEVZ8CV4","zcode-delegate","Delegate coding tasks to the Z.AI ZCode CLI only when the user explicitly requests it, while the orchestrator retains review and landing responsibility.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fzcode-delegate\u002FSKILL.md",[],[116,117,118,119,120,121,122,123,124,125,126,127,128,102,129,34,130,131,104,132],"delegate","zcode","zcode delegate","review","cli","orchestration","tasks","run","Bash","model","node","read","orchestrator","files","desktop app","app","agent-orchestration",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":139,"publishedAt":46},"01M6Q0ETK41VGNMYEXW0T00AJN","youtube-transcript","Fetch YouTube transcripts through DeepAPI or local fallback tooling and save clean text output.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript\u002FSKILL.md",[],[140,141,142,51,45,143,144,40,39,145,146,147,148,34,33,149,150,151,152,153],"transcript","youtube transcript","youtube","codex","research","text","fetch","tooling","clean","local","output","deepapi","youtube transcripts","blob",{"skillNo":155,"name":156,"nameZh":6,"description":157,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":158,"categories":159,"keywords":171,"publishedAt":46},"01M6Q0EPPH2PVMDW40017F8WX0","youtube-transcript-skills","Fetch YouTube video transcripts, search videos\u002Fchannels, browse channels, and extract playlists via the getyoutubetranscript.com API - free tier, no card required.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-transcript-skills\u002FSKILL.md",[160,163,166],{"categoryNo":161,"categoryName":162,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":164,"categoryName":165,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":167,"categoryName":168,"taxonomyType":169,"taxonomyTypeDesc":170},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[140,141,142,172,51,173,45,143,40,174,175,176,177,146,178,34,33,179,180,181],"youtube transcript skills","gemini","search","api","Video","browse","api-integration","free","card","channels",{"skillNo":183,"name":184,"nameZh":6,"description":185,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":186,"categories":187,"keywords":192,"publishedAt":46},"01M6Q0EAB96PX83W5PTE8A0R8D","youtube-notetaker","Turn YouTube talks into local study notes with slides, transcripts, editable annotations, and a markdown-backed viewer.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-notetaker\u002FSKILL.md",[188,191],{"categoryNo":189,"categoryName":190,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":164,"categoryName":165,"taxonomyType":20,"taxonomyTypeDesc":21},[142,193,194,120,51,195,196,197,198,40,176,199,200,201,202,33,203,149,204,205],"youtube notetaker","notetaker","workflow","official","notes","code","markdown","slides","annotations","README","study","dair-academy","viewer",{"skillNo":207,"name":208,"nameZh":6,"description":209,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":210,"categories":211,"keywords":213,"publishedAt":46},"01M6Q0E55F0GW5MX48V8HXS8B5","youtube-full","Fetch YouTube transcripts, search videos, browse channels, and extract playlists via TranscriptAPI — no yt-dlp, no Google API key, works from any cloud server.","https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills_archive\u002Fyoutube-full\u002FSKILL.md",[212],{"categoryNo":161,"categoryName":162,"taxonomyType":20,"taxonomyTypeDesc":21},[214,142,215,216,51,173,174,217,218,175,176,177,146,219,178,34,33,179,220,152],"youtube full","full","google","server","dlp","credits","automatic"]