README 证据

<p align="center"> <img src=".github/assets/logo.png" alt="Tech Leads Club" width="400" /> </p>

<p align="center"> <img src="https://img.shields.io/npm/v/@tech-leads-club/agent-skills?style=flat-square&color=blue" alt="npm version" /> <img src="https://img.shields.io/npm/dt/@tech-leads-club/agent-skills?style=flat-square&color=blue" alt="total downloads" /> <img src="https://img.shields.io/npm/dm/@tech-leads-club/agent-skills?style=flat-square&color=blue" alt="monthly downloads" /> <img src="https://img.shields.io/github/license/tech-leads-club/agent-skills?style=flat-square" alt="license" /> <img src="https://img.shields.io/github/actions/workflow/status/tech-leads-club/agent-skills/release.yml?style=flat-square" alt="build status" /> </p>

<p align="center"> <img src="https://img.shields.io/badge/node-%3E%3D22-brightgreen?style=flat-square&logo=node.js" alt="node version" /> <img src="https://img.shields.io/badge/TypeScript-100%25-blue?style=flat-square&logo=typescript" alt="typescript" /> <img src="https://img.shields.io/badge/Nx%20Cloud-Enabled-blue?style=flat-square&logo=nx" alt="nx cloud" /> <img src="https://img.shields.io/badge/%20%20%F0%9F%93%A6%F0%9F%9A%80-semantic--release-e10079.svg?style=flat-square" alt="semantic-release" /> </p>

<p align="center"> <img src="https://img.shields.io/github/stars/tech-leads-club/agent-skills?style=flat-square&color=yellow" alt="github stars" /> <img src="https://img.shields.io/github/contributors/tech-leads-club/agent-skills?style=flat-square&color=orange" alt="contributors" /> <img src="https://img.shields.io/github/last-commit/tech-leads-club/agent-skills?style=flat-square" alt="last commit" /> <img src="https://img.shields.io/badge/AI-Powered%20Skills-purple?style=flat-square&logo=openai" alt="ai powered" /> </p>

<h1 align="center">🧠 Agent Skills</h1>

<p align="center"> <strong>The secure, validated skill registry for professional AI coding agents</strong> </p>

<p align="center"> In an ecosystem where <a href="https://github.com/snyk/agent-scan/blob/main/.github/reports/skills-report.pdf">over 13% of marketplace skills contain critical vulnerabilities</a>, <b>Agent Skills</b> stands apart as a hardened library of <b>verified</b>, <b>tested</b>, and <b>safe</b> capabilities. Extend <b>Antigravity</b>, <b>Claude Code</b>, <b>Cursor</b>, and more with absolute confidence. <

[excerpt truncated]

已选源码清单

• README.md
• package.json
• libs/core/README.md
• libs/core/package.json
• packages/cli/package.json
• packages/marketplace/README.md
• packages/marketplace/package.json
• packages/mcp/README.md
• packages/mcp/package.json
• packages/skills-catalog/package.json
• tools/skill-plugin/package.json
• packages/skills-catalog/skills/(architecture)/component-common-domain-detection/README.md

资料来源：README.md:1-120

资料来源：README.md:1-120

• .: README.md, package.json
• libs: libs/core/README.md, libs/core/package.json
• packages: packages/cli/package.json, packages/marketplace/README.md, packages/marketplace/package.json, packages/mcp/README.md, packages/mcp/package.json, packages/skills-catalog/package.json
• tools: tools/skill-plugin/package.json

资料来源：package.json:1-120

• Documentation signal: README.md
• Runtime/package signal: package.json
• Documentation signal: libs/core/README.md
• Runtime/package signal: libs/core/package.json
• Runtime/package signal: packages/cli/package.json
• Documentation signal: packages/marketplace/README.md
• Runtime/package signal: packages/marketplace/package.json
• Documentation signal: packages/mcp/README.md
• Runtime/package signal: packages/mcp/package.json
• Runtime/package signal: packages/skills-catalog/package.json

资料来源：libs/core/README.md:1-120

Pitfall Log / 踩坑日志

项目：tech-leads-club/agent-skills

摘要：发现 22 个潜在踩坑项，其中 0 个为 high/blocking；最高优先级：安装坑 - 失败模式：installation: NLPM audit findings: 1 bug + 3 security improvements (score 93/100)。

1. 安装坑 · 失败模式：installation: NLPM audit findings: 1 bug + 3 security improvements (score 93/100)

• 严重度：medium
• 证据强度：source_linked
• 发现：Developers should check this installation risk before relying on the project: NLPM audit findings: 1 bug + 3 security improvements (score 93/100)
• 对用户的影响：Developers may fail before the first successful local run: NLPM audit findings: 1 bug + 3 security improvements (score 93/100)
• 建议检查：Before packaging this project, run the relevant install/config/quickstart check for: NLPM audit findings: 1 bug + 3 security improvements (score 93/100). Context: Observed when using playwright
• 防护动作: State this as source-backed community evidence, not as Doramagic reproduction.
• 证据：failure_mode_cluster:github_issue | fmev_857542464c1234be71e1ef45c98be86b | https://github.com/tech-leads-club/agent-skills/issues/94 | NLPM audit findings: 1 bug + 3 security improvements (score 93/100)

2. 安装坑 · 失败模式：installation: docs(tlc-spec-driven): "Skill Integrations" table lacks links, steering agents to install thi...

• 严重度：medium
• 证据强度：source_linked
• 发现：Developers should check this installation risk before relying on the project: docs(tlc-spec-driven): "Skill Integrations" table lacks links, steering agents to install third-party forks
• 对用户的影响：Developers may fail before the first successful local run: docs(tlc-spec-driven): "Skill Integrations" table lacks links, steering agents to install third-party forks
• 建议检查：Before packaging this project, run the relevant install/config/quickstart check for: docs(tlc-spec-driven): "Skill Integrations" table lacks links, steering agents to install third-party forks. Context: Observed during installation or first-run setup.
• 防护动作: State this as source-backed community evidence, not as Doramagic reproduction.
• 证据：failure_mode_cluster:github_issue | fmev_c65dfb1700340aa66e99dd35a02955ea | https://github.com/tech-leads-club/agent-skills/issues/120 | docs(tlc-spec-driven): "Skill Integrations" table lacks links, steering agents to install third-party forks

3. 配置坑 · 可能修改宿主 AI 配置

• 严重度：medium
• 证据强度：source_linked
• 发现：项目面向 Claude/Cursor/Codex/Gemini/OpenCode 等宿主，或安装命令涉及用户配置目录。
• 对用户的影响：安装可能改变本机 AI 工具行为，用户需要知道写入位置和回滚方法。
• 建议检查：列出会写入的配置文件、目录和卸载/回滚步骤。
• 防护动作: 涉及宿主配置目录时必须给回滚路径，不能只给安装命令。
• 证据：capability.host_targets | github_repo:1137515077 | https://github.com/tech-leads-club/agent-skills | host_targets=claude, claude_code, cursor

4. 配置坑 · 失败模式：configuration: skills-catalog-v0.13.0

• 严重度：medium
• 证据强度：source_linked
• 发现：Developers should check this configuration risk before relying on the project: skills-catalog-v0.13.0
• 对用户的影响：Upgrade or migration may change expected behavior: skills-catalog-v0.13.0
• 建议检查：Before packaging this project, run the relevant install/config/quickstart check for: skills-catalog-v0.13.0. Context: Observed when using python
• 防护动作: State this as source-backed community evidence, not as Doramagic reproduction.
• 证据：failure_mode_cluster:github_release | fmev_a998e775343dcba0df328872809cccc7 | https://github.com/tech-leads-club/agent-skills/releases/tag/skills-catalog-v0.13.0 | skills-catalog-v0.13.0

5. 配置坑 · 失败模式：configuration: 🔐 Community Tool: OpenClaw Skill Security Scanner — Complementary security scanning for agent...

• 严重度：medium
• 证据强度：source_linked
• 发现：Developers should check this configuration risk before relying on the project: 🔐 Community Tool: OpenClaw Skill Security Scanner — Complementary security scanning for agent skills
• 对用户的影响：Developers may misconfigure credentials, environment, or host setup: 🔐 Community Tool: OpenClaw Skill Security Scanner — Complementary security scanning for agent skills
• 建议检查：Before packaging this project, run the relevant install/config/quickstart check for: 🔐 Community Tool: OpenClaw Skill Security Scanner — Complementary security scanning for agent skills. Context: Source discussion did not expose a precise runtime context.
• 防护动作: State this as source-backed community evidence, not as Doramagic reproduction.
• 证据：failure_mode_cluster:github_issue | fmev_0fffb0b65e372ad96db72a5fb7f3a750 | https://github.com/tech-leads-club/agent-skills/issues/116 | 🔐 Community Tool: OpenClaw Skill Security Scanner — Complementary security scanning for agent skills

6. 能力坑 · 能力判断依赖假设

• 严重度：medium
• 证据强度：source_linked
• 发现：README/documentation is current enough for a first validation pass.
• 对用户的影响：假设不成立时，用户拿不到承诺的能力。
• 建议检查：将假设转成下游验证清单。
• 防护动作: 假设必须转成验证项；没有验证结果前不能写成事实。
• 证据：capability.assumptions | github_repo:1137515077 | https://github.com/tech-leads-club/agent-skills | README/documentation is current enough for a first validation pass.

7. 维护坑 · 维护活跃度未知

• 严重度：medium
• 证据强度：source_linked
• 发现：未记录 last_activity_observed。
• 对用户的影响：新项目、停更项目和活跃项目会被混在一起，推荐信任度下降。
• 建议检查：补 GitHub 最近 commit、release、issue/PR 响应信号。
• 防护动作: 维护活跃度未知时，推荐强度不能标为高信任。
• 证据：evidence.maintainer_signals | github_repo:1137515077 | https://github.com/tech-leads-club/agent-skills | last_activity_observed missing

8. 安全/权限坑 · 下游验证发现风险项

• 严重度：medium
• 证据强度：source_linked
• 发现：no_demo
• 对用户的影响：下游已经要求复核，不能在页面中弱化。
• 建议检查：进入安全/权限治理复核队列。
• 防护动作: 下游风险存在时必须保持 review/recommendation 降级。
• 证据：downstream_validation.risk_items | github_repo:1137515077 | https://github.com/tech-leads-club/agent-skills | no_demo; severity=medium

9. 安全/权限坑 · 存在评分风险

• 严重度：medium
• 证据强度：source_linked
• 发现：no_demo
• 对用户的影响：风险会影响是否适合普通用户安装。
• 建议检查：把风险写入边界卡，并确认是否需要人工复核。
• 防护动作: 评分风险必须进入边界卡，不能只作为内部分数。
• 证据：risks.scoring_risks | github_repo:1137515077 | https://github.com/tech-leads-club/agent-skills | no_demo; severity=medium

10. 安全/权限坑 · 来源证据：NLPM audit findings: 1 bug + 3 security improvements (score 93/100)

• 严重度：medium
• 证据强度：source_linked
• 发现：GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：NLPM audit findings: 1 bug + 3 security improvements (score 93/100)
• 对用户的影响：可能影响升级、迁移或版本选择。
• 建议检查：来源显示可能已有修复、规避或版本变化，说明书中必须标注适用版本。
• 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。
• 证据：community_evidence:github | cevd_345699a80eac41029de7ca06f4a42032 | https://github.com/tech-leads-club/agent-skills/issues/94 | 来源类型 github_issue 暴露的待验证使用条件。

11. 安全/权限坑 · 来源证据：[Security] Risco de Supply Chain e Indirect Prompt Injection no carregamento de skills (@latest)

• 严重度：medium
• 证据强度：source_linked
• 发现：GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：[Security] Risco de Supply Chain e Indirect Prompt Injection no carregamento de skills (@latest)
• 对用户的影响：可能增加新用户试用和生产接入成本。
• 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。
• 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。
• 证据：community_evidence:github | cevd_f0effd85824743eeabdfe10d47e84d05 | https://github.com/tech-leads-club/agent-skills/issues/114 | 来源讨论提到 node 相关条件，需在安装/试用前复核。

12. 安全/权限坑 · 来源证据：ci: add env-security-scanner build verification step to CLAUDE.md

• 严重度：medium
• 证据强度：source_linked
• 发现：GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：ci: add env-security-scanner build verification step to CLAUDE.md
• 对用户的影响：可能增加新用户试用和生产接入成本。
• 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。
• 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。
• 证据：community_evidence:github | cevd_cbc0b9111607499a9661df5dd1e3af1d | https://github.com/tech-leads-club/agent-skills/issues/122 | 来源类型 github_issue 暴露的待验证使用条件。

13. 安全/权限坑 · 来源证据：docs(tlc-spec-driven): "Skill Integrations" table lacks links, steering agents to install third-party forks

• 严重度：medium
• 证据强度：source_linked
• 发现：GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：docs(tlc-spec-driven): "Skill Integrations" table lacks links, steering agents to install third-party forks
• 对用户的影响：可能增加新用户试用和生产接入成本。
• 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。
• 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。
• 证据：community_evidence:github | cevd_494e86d7ebd547a5ae267b0179361c12 | https://github.com/tech-leads-club/agent-skills/issues/120 | 来源类型 github_issue 暴露的待验证使用条件。

14. 安全/权限坑 · 来源证据：🔐 Community Tool: OpenClaw Skill Security Scanner — Complementary security scanning for agent skills

• 严重度：medium
• 证据强度：source_linked
• 发现：GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：🔐 Community Tool: OpenClaw Skill Security Scanner — Complementary security scanning for agent skills
• 对用户的影响：可能影响授权、密钥配置或安全边界。
• 建议检查：来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。
• 防护动作: 不得脱离来源链接放大为确定性结论；需要标注适用版本和复核状态。
• 证据：community_evidence:github | cevd_117530fda24f468a9e14d03ab7a21ea7 | https://github.com/tech-leads-club/agent-skills/issues/116 | 来源讨论提到 api key 相关条件，需在安装/试用前复核。

15. 能力坑 · 失败模式：capability: [Security] Risco de Supply Chain e Indirect Prompt Injection no carregamento de skills (@latest)

• 严重度：low
• 证据强度：source_linked
• 发现：Developers should check this capability risk before relying on the project: [Security] Risco de Supply Chain e Indirect Prompt Injection no carregamento de skills (@latest)
• 对用户的影响：Developers may hit a documented source-backed failure mode: [Security] Risco de Supply Chain e Indirect Prompt Injection no carregamento de skills (@latest)
• 建议检查：Before packaging this project, run the relevant install/config/quickstart check for: [Security] Risco de Supply Chain e Indirect Prompt Injection no carregamento de skills (@latest). Context: Source discussion did not expose a precise runtime context.
• 防护动作: State this as source-backed community evidence, not as Doramagic reproduction.
• 证据：failure_mode_cluster:github_issue | fmev_60b8fc0979ba3a24e45461021597db25 | https://github.com/tech-leads-club/agent-skills/issues/114 | [Security] Risco de Supply Chain e Indirect Prompt Injection no carregamento de skills (@latest)

16. 能力坑 · 失败模式：capability: ci: add env-security-scanner build verification step to CLAUDE.md

• 严重度：low
• 证据强度：source_linked
• 发现：Developers should check this capability risk before relying on the project: ci: add env-security-scanner build verification step to CLAUDE.md
• 对用户的影响：Developers may hit a documented source-backed failure mode: ci: add env-security-scanner build verification step to CLAUDE.md
• 建议检查：Before packaging this project, run the relevant install/config/quickstart check for: ci: add env-security-scanner build verification step to CLAUDE.md. Context: Observed when using python
• 防护动作: State this as source-backed community evidence, not as Doramagic reproduction.
• 证据：failure_mode_cluster:github_issue | fmev_bf6883a13250f5040ca6c51fa0fdfe6a | https://github.com/tech-leads-club/agent-skills/issues/122 | ci: add env-security-scanner build verification step to CLAUDE.md

17. 维护坑 · issue/PR 响应质量未知

• 严重度：low
• 证据强度：source_linked
• 发现：issue_or_pr_quality=unknown。
• 对用户的影响：用户无法判断遇到问题后是否有人维护。
• 建议检查：抽样最近 issue/PR，判断是否长期无人处理。
• 防护动作: issue/PR 响应未知时，必须提示维护风险。
• 证据：evidence.maintainer_signals | github_repo:1137515077 | https://github.com/tech-leads-club/agent-skills | issue_or_pr_quality=unknown

18. 维护坑 · 发布节奏不明确

• 严重度：low
• 证据强度：source_linked
• 发现：release_recency=unknown。
• 对用户的影响：安装命令和文档可能落后于代码，用户踩坑概率升高。
• 建议检查：确认最近 release/tag 和 README 安装命令是否一致。
• 防护动作: 发布节奏未知或过期时，安装说明必须标注可能漂移。
• 证据：evidence.maintainer_signals | github_repo:1137515077 | https://github.com/tech-leads-club/agent-skills | release_recency=unknown

19. 维护坑 · 失败模式：maintenance: mcp-v0.1.3

• 严重度：low
• 证据强度：source_linked
• 发现：Developers should check this maintenance risk before relying on the project: mcp-v0.1.3
• 对用户的影响：Upgrade or migration may change expected behavior: mcp-v0.1.3
• 建议检查：Before packaging this project, run the relevant install/config/quickstart check for: mcp-v0.1.3. Context: Source discussion did not expose a precise runtime context.
• 防护动作: State this as source-backed community evidence, not as Doramagic reproduction.
• 证据：failure_mode_cluster:github_release | fmev_27dd72b66dc4d6418e5e4a13ced71472 | https://github.com/tech-leads-club/agent-skills/releases/tag/mcp-v0.1.3 | mcp-v0.1.3

20. 维护坑 · 失败模式：maintenance: skills-catalog-v0.14.0

• 严重度：low
• 证据强度：source_linked
• 发现：Developers should check this maintenance risk before relying on the project: skills-catalog-v0.14.0
• 对用户的影响：Upgrade or migration may change expected behavior: skills-catalog-v0.14.0
• 建议检查：Before packaging this project, run the relevant install/config/quickstart check for: skills-catalog-v0.14.0. Context: Source discussion did not expose a precise runtime context.
• 防护动作: State this as source-backed community evidence, not as Doramagic reproduction.
• 证据：failure_mode_cluster:github_release | fmev_57b9b4d2174ab6bc12d6322c6117660a | https://github.com/tech-leads-club/agent-skills/releases/tag/skills-catalog-v0.14.0 | skills-catalog-v0.14.0

21. 维护坑 · 失败模式：maintenance: skills-catalog-v0.14.1

• 严重度：low
• 证据强度：source_linked
• 发现：Developers should check this maintenance risk before relying on the project: skills-catalog-v0.14.1
• 对用户的影响：Upgrade or migration may change expected behavior: skills-catalog-v0.14.1
• 建议检查：Before packaging this project, run the relevant install/config/quickstart check for: skills-catalog-v0.14.1. Context: Source discussion did not expose a precise runtime context.
• 防护动作: State this as source-backed community evidence, not as Doramagic reproduction.
• 证据：failure_mode_cluster:github_release | fmev_3eecd9269b977af384db44d187c96ca7 | https://github.com/tech-leads-club/agent-skills/releases/tag/skills-catalog-v0.14.1 | skills-catalog-v0.14.1

22. 维护坑 · 失败模式：maintenance: v1.4.7

• 严重度：low
• 证据强度：source_linked
• 发现：Developers should check this maintenance risk before relying on the project: v1.4.7
• 对用户的影响：Upgrade or migration may change expected behavior: v1.4.7
• 建议检查：Before packaging this project, run the relevant install/config/quickstart check for: v1.4.7. Context: Source discussion did not expose a precise runtime context.
• 防护动作: State this as source-backed community evidence, not as Doramagic reproduction.
• 证据：failure_mode_cluster:github_release | fmev_eaee1d76d0958d062a4989d354a3635b | https://github.com/tech-leads-club/agent-skills/releases/tag/v1.4.7 | v1.4.7