[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6NSKA1VM9Z3VJB198HVQ9XM":3,"skill-same:01M6NSKA1VM9Z3VJB198HVQ9XM":90},{"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":30,"publishedAt":51,"linkOnly":52,"markdownContent":53,"markdownBody":54,"frontMatter":55,"refName":38,"commitSha":61,"skillDirectory":62,"forksCount":13,"repositoryHtmlUrl":63,"repositoryHomepageUrl":6,"ownerHtmlUrl":64,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":65,"install":66,"resources":79},"01M6NSKA1VM9Z3VJB198HVQ9XM","api-security",null,"Authorized security assessment of REST, GraphQL, WebSocket, and SOAP APIs: discovery, authentication and authorization flaws (BOLA\u002FIDOR, JWT\u002FOAuth), rate-limit testing, and a structured multi-phase methodology.","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\u002Fapi-security\u002FSKILL.md",[17,22,25],{"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},"01JBSEEDCAT000000000000010","后端与接口",{"categoryNo":26,"categoryName":27,"taxonomyType":28,"taxonomyTypeDesc":29},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50],"security","api security","api","reverse","testing","limit","multi","main","community","security assessment","soap","discovery","websocket","GraphQL","REST","OAuth","license","authentication","assessment","github","2026-11-10 10:12:30",false,"---\nname: api-security\ndescription: \"Authorized security assessment of REST, GraphQL, WebSocket, and SOAP APIs: discovery, authentication and authorization flaws (BOLA\u002FIDOR, JWT\u002FOAuth), rate-limit testing, and a structured multi-phase methodology.\"\nrisk: offensive\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> **⚠️ AUTHORIZED USE ONLY**\n> This skill is for educational purposes or authorized security assessments only.\n> You must have explicit, written permission from the system owner before using this tool.\n> Misuse of this tool is illegal and strictly prohibited.\n\n> **Mandatory confirmation gate**\n> Before running any command that probes, exploits, changes, persists on, extracts data from, or attempts credential access against a target:\n> 1. Ask the user to state the exact target URL, IP, account, or resource.\n> 2. Ask the user to confirm written authorization and the permitted scope.\n> 3. Show the exact command(s) and explain their expected effect.\n> 4. Wait for explicit confirmation in the current conversation.\n>\n> Without that confirmation, remain read-only and provide defensive guidance only. Prefer a sandbox, disposable VM, or controlled lab.\n\n# API 安全测试\n## When to Use\n\n- An authorized assessment covers API endpoints and you need a structured discovery-to-report workflow.\n- Testing API authentication, authorization, or rate-limiting behavior within an approved scope.\n\n\n## 适用场景\n\n- REST API 安全测试（OpenAPI\u002FSwagger 驱动或盲测）\n- GraphQL 安全审计（内省、批查询、别名过载）\n- WebSocket 安全测试\n- JWT \u002F OAuth 2.0 认证测试\n- BOLA\u002FIDOR\u002FBFLA 授权漏洞检测\n- API 限速绕过与 DoS 测试\n\n## 10 阶段测试流程\n\n### Phase 1: API 发现与侦察\n\n```text\n主动发现：\n□ Vespasian: 无头浏览器爬取 → 自动生成 OpenAPI 3.0 \u002F GraphQL SDL 规范\n□ Entropy --discover: 从 robots.txt + JS 文件提取端点\n□ Kiterunner \u002F ffuf: 爆破未文档化的端点路径\n□ 检查常见路径: \u002Fswagger.json, \u002Fopenapi.json, \u002Fgraphql, \u002Fapi-docs\n\nGraphQL 内省（三级尝试）：\n  1. 标准内省查询\n  2. 精简查询（绕过 WAF 全量封禁）\n  3. 仅查 __schema { types { name } }（最小探测）\n```\n\n### Phase 2: 认证测试\n\n```text\nJWT 分析（jwt_tool \u002F Burp）：\n□ alg:none 攻击: 修改头部为 \"alg\":\"none\"，清空签名\n□ 密钥混淆: RS256 公钥 → HS256 对称密钥\n□ 弱 HMAC 密钥爆破: jwt_tool -C -d wordlist.txt\n□ 过期\u002F声明篡改: 修改 exp\u002Fiat\u002Fsub\u002Frole 声明\n□ kid 注入: ..\u002F..\u002Fetc\u002Fpasswd → HMAC 签名绕过\n\nOAuth 2.0：\n□ redirect_uri 操控 → 授权码泄漏\n□ CSRF via state 参数缺失\n□ Token 在 Referer 头泄漏\n□ PKCE 缺失检测\n\nGraphQL 认证：\n□ mutation 通过 GET 请求绕过认证（CSRF）\n□ 批查询认证绕过\n```\n\n### Phase 3: 授权测试（BOLA\u002FIDOR\u002FBFLA）\n\n```text\nBOLA（对象级授权绕过）：\n□ 遍历数字 ID: \u002Fuser\u002F1 → \u002Fuser\u002F2 → \u002Fuser\u002F3\n□ 遍历 UUID\n□ 遍历用户名\u002F邮箱\n□ Burp Autorize: 双会话重放对比\n\nBFLA（功能级授权绕过）：\n□ 普通用户执行管理员 API\n□ HTTP 方法切换: GET → PUT → PATCH → DELETE\n□ API 版本降级: \u002Fv2\u002Fadmin → \u002Fv1\u002Fadmin\n□ 批量操作注入: {\"users\": [1,2,3]} → {\"users\": [1,2,3,admin_id]}\n\n工具: Burp Autorize, AuthMatrix, Entropy (malicious_insider persona)\n```\n\n### Phase 4: GraphQL 专项\n\n```text\n内省泄漏 → 信息暴露检测\n别名过载 → 100+ 别名 DoS\n批查询 → 10+ 同时查询 DoS\n字段重复 → __typename × 500\n指令过载 → 递归 @skip\u002F@include\n循环查询 → 深度嵌套内省递归\n字段建议 → 错误消息信息泄漏\nGraphiQL\u002FPlayground 暴露 → IDE 公开风险\nGET 突变 → CSRF 风险\n追踪\u002F调试模式 → 元数据泄漏\n\n工具: FireTail, Escape DAST, api.sh (Phases 1-3)\n```\n\n### Phase 5: REST 输入验证\n\n```text\n□ HTTP 方法切换: GET→POST→PUT→DELETE→OPTIONS→PATCH\n□ Content-Type 篡改: JSON→XML→multipart\n□ NoSQL 注入: {\"username\": {\"$gt\": \"\"}}\n□ SSRF via URL 参数: webhook URL\u002F头像 URL\u002F导入 URL\n□ XXE in XML 端点\n□ 参数污染: \u002Fapi?role=user&role=admin\n□ 批量赋值: 向请求体添加 is_admin: true\n```\n\n### Phase 6: 业务逻辑与差分测试\n\n```text\n□ Entropy compare: diff v1 vs v2 API → 状态码变化\u002F字段删除\u002F延迟回归\n□ 多角色工作流测试: admin\u002Fuser\u002Freadonly 权限矩阵\n□ 优惠券\u002F积分\u002F价格操控\n□ 竞态条件: 并发请求测试 TOCTOU\n```\n\n### Phase 7: WebSocket 测试\n\n```text\n□ 端点发现\n□ 消息注入（注入 payload、原型污染）\n□ 超大消息处理\n□ 类型混淆\n□ 跨站点 WebSocket 劫持（CSWH）\n```\n\n### Phase 8: 限速与 DoS\n\n```text\n□ 限速绕过 via 头部: X-Forwarded-For, X-Real-IP\n□ 路径变体: \u002Fapi\u002F → \u002Fapi → \u002FApi\u002F → \u002FAPI\u002F\n□ Slowloris 低带宽耗尽\n□ GraphQL 批查询深度嵌套 DoS\n□ IP 轮换测试（ProxyCat 代理池）\n```\n\n### Phase 9: 数据暴露\n\n```text\n□ 响应过度暴露: 对比 API 返回 vs UI 展示\n□ 分页枚举: ?page=1&limit=10000\n□ 错误消息信息泄漏: 堆栈跟踪\u002F内部路径\u002FSQL 错误\n□ GraphQL 嵌套遍历访问越权数据\n□ OpenAPI 规范暴露敏感端点\n```\n\n### Phase 10: CI\u002FCD 集成\n\n```text\n□ Entropy --ci --watch: spec 变更时自动重跑\n□ Escape DAST: 按严重度阈值自动阻断构建\n□ 发现持久化为回归测试\n□ StackHawk（开发者优先、ZAP 内核）\n```\n\n## 工具链\n\n| 工具 | 用途 | 获取 |\n|------|------|------|\n| Vespasian | 流量 → OpenAPI\u002FGraphQL 规范 | GitHub: praetorian-inc\u002Fvespasian |\n| Entropy | LLM 生成攻击场景，5 personas | GitHub: arjinexe\u002Fentropy-chaos |\n| Escape DAST | 业务逻辑安全测试 | escape.tech |\n| api.sh | 8 阶段全协议攻击管道 | GitHub: Sharon-Needles\u002Fapi |\n| FireTail | GraphQL 12 专项测试 | firetail.ai |\n| jwt_tool | JWT 全面测试 | GitHub: ticarpi\u002Fjwt_tool |\n| Burp Autorize | 双会话授权对比 | Burp BApp Store |\n\n## 参考\n\n- `references\u002Frest-graphql-testing.md` — REST + GraphQL 深度测试\n- `references\u002Fjwt-oauth-testing.md` — JWT + OAuth 安全测试\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- Only run against APIs you are explicitly authorized to test.\n- Some checks are intrusive; prefer non-production mirrors when available.\n\n> Adapted from [zhaoxuya520\u002Freverse-skill](https:\u002F\u002Fgithub.com\u002Fzhaoxuya520\u002Freverse-skill) (MIT).\n","> **⚠️ AUTHORIZED USE ONLY**\n> This skill is for educational purposes or authorized security assessments only.\n> You must have explicit, written permission from the system owner before using this tool.\n> Misuse of this tool is illegal and strictly prohibited.\n\n> **Mandatory confirmation gate**\n> Before running any command that probes, exploits, changes, persists on, extracts data from, or attempts credential access against a target:\n> 1. Ask the user to state the exact target URL, IP, account, or resource.\n> 2. Ask the user to confirm written authorization and the permitted scope.\n> 3. Show the exact command(s) and explain their expected effect.\n> 4. Wait for explicit confirmation in the current conversation.\n>\n> Without that confirmation, remain read-only and provide defensive guidance only. Prefer a sandbox, disposable VM, or controlled lab.\n\n# API 安全测试\n## When to Use\n\n- An authorized assessment covers API endpoints and you need a structured discovery-to-report workflow.\n- Testing API authentication, authorization, or rate-limiting behavior within an approved scope.\n\n\n## 适用场景\n\n- REST API 安全测试（OpenAPI\u002FSwagger 驱动或盲测）\n- GraphQL 安全审计（内省、批查询、别名过载）\n- WebSocket 安全测试\n- JWT \u002F OAuth 2.0 认证测试\n- BOLA\u002FIDOR\u002FBFLA 授权漏洞检测\n- API 限速绕过与 DoS 测试\n\n## 10 阶段测试流程\n\n### Phase 1: API 发现与侦察\n\n```text\n主动发现：\n□ Vespasian: 无头浏览器爬取 → 自动生成 OpenAPI 3.0 \u002F GraphQL SDL 规范\n□ Entropy --discover: 从 robots.txt + JS 文件提取端点\n□ Kiterunner \u002F ffuf: 爆破未文档化的端点路径\n□ 检查常见路径: \u002Fswagger.json, \u002Fopenapi.json, \u002Fgraphql, \u002Fapi-docs\n\nGraphQL 内省（三级尝试）：\n  1. 标准内省查询\n  2. 精简查询（绕过 WAF 全量封禁）\n  3. 仅查 __schema { types { name } }（最小探测）\n```\n\n### Phase 2: 认证测试\n\n```text\nJWT 分析（jwt_tool \u002F Burp）：\n□ alg:none 攻击: 修改头部为 \"alg\":\"none\"，清空签名\n□ 密钥混淆: RS256 公钥 → HS256 对称密钥\n□ 弱 HMAC 密钥爆破: jwt_tool -C -d wordlist.txt\n□ 过期\u002F声明篡改: 修改 exp\u002Fiat\u002Fsub\u002Frole 声明\n□ kid 注入: ..\u002F..\u002Fetc\u002Fpasswd → HMAC 签名绕过\n\nOAuth 2.0：\n□ redirect_uri 操控 → 授权码泄漏\n□ CSRF via state 参数缺失\n□ Token 在 Referer 头泄漏\n□ PKCE 缺失检测\n\nGraphQL 认证：\n□ mutation 通过 GET 请求绕过认证（CSRF）\n□ 批查询认证绕过\n```\n\n### Phase 3: 授权测试（BOLA\u002FIDOR\u002FBFLA）\n\n```text\nBOLA（对象级授权绕过）：\n□ 遍历数字 ID: \u002Fuser\u002F1 → \u002Fuser\u002F2 → \u002Fuser\u002F3\n□ 遍历 UUID\n□ 遍历用户名\u002F邮箱\n□ Burp Autorize: 双会话重放对比\n\nBFLA（功能级授权绕过）：\n□ 普通用户执行管理员 API\n□ HTTP 方法切换: GET → PUT → PATCH → DELETE\n□ API 版本降级: \u002Fv2\u002Fadmin → \u002Fv1\u002Fadmin\n□ 批量操作注入: {\"users\": [1,2,3]} → {\"users\": [1,2,3,admin_id]}\n\n工具: Burp Autorize, AuthMatrix, Entropy (malicious_insider persona)\n```\n\n### Phase 4: GraphQL 专项\n\n```text\n内省泄漏 → 信息暴露检测\n别名过载 → 100+ 别名 DoS\n批查询 → 10+ 同时查询 DoS\n字段重复 → __typename × 500\n指令过载 → 递归 @skip\u002F@include\n循环查询 → 深度嵌套内省递归\n字段建议 → 错误消息信息泄漏\nGraphiQL\u002FPlayground 暴露 → IDE 公开风险\nGET 突变 → CSRF 风险\n追踪\u002F调试模式 → 元数据泄漏\n\n工具: FireTail, Escape DAST, api.sh (Phases 1-3)\n```\n\n### Phase 5: REST 输入验证\n\n```text\n□ HTTP 方法切换: GET→POST→PUT→DELETE→OPTIONS→PATCH\n□ Content-Type 篡改: JSON→XML→multipart\n□ NoSQL 注入: {\"username\": {\"$gt\": \"\"}}\n□ SSRF via URL 参数: webhook URL\u002F头像 URL\u002F导入 URL\n□ XXE in XML 端点\n□ 参数污染: \u002Fapi?role=user&role=admin\n□ 批量赋值: 向请求体添加 is_admin: true\n```\n\n### Phase 6: 业务逻辑与差分测试\n\n```text\n□ Entropy compare: diff v1 vs v2 API → 状态码变化\u002F字段删除\u002F延迟回归\n□ 多角色工作流测试: admin\u002Fuser\u002Freadonly 权限矩阵\n□ 优惠券\u002F积分\u002F价格操控\n□ 竞态条件: 并发请求测试 TOCTOU\n```\n\n### Phase 7: WebSocket 测试\n\n```text\n□ 端点发现\n□ 消息注入（注入 payload、原型污染）\n□ 超大消息处理\n□ 类型混淆\n□ 跨站点 WebSocket 劫持（CSWH）\n```\n\n### Phase 8: 限速与 DoS\n\n```text\n□ 限速绕过 via 头部: X-Forwarded-For, X-Real-IP\n□ 路径变体: \u002Fapi\u002F → \u002Fapi → \u002FApi\u002F → \u002FAPI\u002F\n□ Slowloris 低带宽耗尽\n□ GraphQL 批查询深度嵌套 DoS\n□ IP 轮换测试（ProxyCat 代理池）\n```\n\n### Phase 9: 数据暴露\n\n```text\n□ 响应过度暴露: 对比 API 返回 vs UI 展示\n□ 分页枚举: ?page=1&limit=10000\n□ 错误消息信息泄漏: 堆栈跟踪\u002F内部路径\u002FSQL 错误\n□ GraphQL 嵌套遍历访问越权数据\n□ OpenAPI 规范暴露敏感端点\n```\n\n### Phase 10: CI\u002FCD 集成\n\n```text\n□ Entropy --ci --watch: spec 变更时自动重跑\n□ Escape DAST: 按严重度阈值自动阻断构建\n□ 发现持久化为回归测试\n□ StackHawk（开发者优先、ZAP 内核）\n```\n\n## 工具链\n\n| 工具 | 用途 | 获取 |\n|------|------|------|\n| Vespasian | 流量 → OpenAPI\u002FGraphQL 规范 | GitHub: praetorian-inc\u002Fvespasian |\n| Entropy | LLM 生成攻击场景，5 personas | GitHub: arjinexe\u002Fentropy-chaos |\n| Escape DAST | 业务逻辑安全测试 | escape.tech |\n| api.sh | 8 阶段全协议攻击管道 | GitHub: Sharon-Needles\u002Fapi |\n| FireTail | GraphQL 12 专项测试 | firetail.ai |\n| jwt_tool | JWT 全面测试 | GitHub: ticarpi\u002Fjwt_tool |\n| Burp Autorize | 双会话授权对比 | Burp BApp Store |\n\n## 参考\n\n- `references\u002Frest-graphql-testing.md` — REST + GraphQL 深度测试\n- `references\u002Fjwt-oauth-testing.md` — JWT + OAuth 安全测试\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- Only run against APIs you are explicitly authorized to test.\n- Some checks are intrusive; prefer non-production mirrors when available.\n\n> Adapted from [zhaoxuya520\u002Freverse-skill](https:\u002F\u002Fgithub.com\u002Fzhaoxuya520\u002Freverse-skill) (MIT).\n",{"name":5,"risk":56,"source":57,"license":14,"date_added":58,"description":7,"source_repo":59,"source_type":39,"license_source":60},"offensive","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\u002Fapi-security","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":67,"prompt":77,"zipAvailable":78},[68,71,74],{"tool":69,"command":70},"npx","npx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill api-security",{"tool":72,"command":73},"bunx","bunx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill api-security",{"tool":75,"command":76},"pnpm","pnpm dlx skills add duc-duy-1612\u002FOnline-Delivery-Systems-Web --skill api-security","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fapi-security\u002FSKILL.md",true,[80,86],{"path":81,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Fjwt-oauth-testing.md","REFERENCE","参考文档",2943,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fapi-security\u002Freferences\u002Fjwt-oauth-testing.md",{"path":87,"resourceType":82,"resourceTypeDesc":83,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Frest-graphql-testing.md",3296,"https:\u002F\u002Fgithub.com\u002Fduc-duy-1612\u002FOnline-Delivery-Systems-Web\u002Fblob\u002Fmain\u002F.agents\u002Fskills\u002Fapi-security\u002Freferences\u002Frest-graphql-testing.md",[91,117,141,164,185,209],{"skillNo":92,"name":93,"nameZh":6,"description":94,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":95,"categories":96,"keywords":100,"publishedAt":51},"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",[97],{"categoryNo":98,"categoryName":99,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000011","运维与部署",[101,102,103,104,49,105,93,106,107,108,109,110,39,38,111,112,113,114,115,116],"ZeRO","trust","zero trust","architecture","verification","segmentation","devops-security","access","configure","only","active","critical","scope","scripts","relevant","implementing",{"skillNo":118,"name":119,"nameZh":6,"description":120,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":121,"categories":122,"keywords":123,"publishedAt":51},"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",[],[124,125,126,127,128,129,130,131,132,133,134,135,136,110,137,39,138,139,112,140],"delegate","zcode","zcode delegate","review","cli","orchestration","tasks","run","Bash","model","node","read","orchestrator","files","desktop app","app","agent-orchestration",{"skillNo":142,"name":143,"nameZh":6,"description":144,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":145,"categories":146,"keywords":147,"publishedAt":51},"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",[],[148,149,150,151,50,152,153,47,154,155,156,157,158,39,38,159,160,161,162,163],"transcript","youtube transcript","youtube","safe","codex","research","https","text","fetch","tooling","clean","local","output","deepapi","youtube transcripts","blob",{"skillNo":165,"name":166,"nameZh":6,"description":167,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":168,"categories":169,"keywords":175,"publishedAt":51},"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",[170,171,174],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":172,"categoryName":173,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体",{"categoryNo":26,"categoryName":27,"taxonomyType":28,"taxonomyTypeDesc":29},[148,149,150,176,151,177,50,152,47,178,33,179,180,156,181,39,38,182,183,184],"youtube transcript skills","gemini","search","Video","browse","api-integration","free","card","channels",{"skillNo":186,"name":187,"nameZh":6,"description":188,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":189,"categories":190,"keywords":195,"publishedAt":51},"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",[191,194],{"categoryNo":192,"categoryName":193,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000003","演示文稿",{"categoryNo":172,"categoryName":173,"taxonomyType":20,"taxonomyTypeDesc":21},[150,196,197,128,151,198,199,200,201,47,179,202,203,204,205,38,206,159,207,208],"youtube notetaker","notetaker","workflow","official","notes","code","markdown","slides","annotations","README","study","dair-academy","viewer",{"skillNo":210,"name":211,"nameZh":6,"description":212,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":213,"categories":214,"keywords":216,"publishedAt":51},"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",[215],{"categoryNo":23,"categoryName":24,"taxonomyType":20,"taxonomyTypeDesc":21},[217,150,218,219,151,177,178,220,221,33,179,180,156,222,181,39,38,182,223,162],"youtube full","full","google","server","dlp","credits","automatic"]