Skill audit report
将用户提供的需求资料或参考项目链接转化为面向产品、设计、研发和测试的完整产品设计交付物：产品需求文档（PRD）、设计交付说明、数据库表结构 SQL、研发实现说明和测试验收用例；当用户提供网站、Web 应用、后台系统、移动端 H5 或原型的参考链接时，使用 chrome-devtools-mcp 深入浏览和交互分析，并输出参考项目分析.md。用户提到“产品设计”、需求梳理、PRD、业务流程、功能流程、数据表设计、根据需求设计数据库、参考项目、竞品链接、分析这个网站/系统/页面或希望复刻某个产品功能时，主动使用此技能。开始前先识别资料来源（知识库、本地目录、参考链接或两两结合），阅读/分析资料后确认数据库类型及表名、字段名命名规范，再进行设计并输出完整交付物。用户未指定资料位置也未提供参考项目链接时，默认通过 doudou-wiki 技能从项目知识库（`kb/`）获取需求资料。
OpenAgentSkill Trust Score
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
WARN48
41 GitHub stars
Stars/forks activity
WARN43
41 stars, 9 forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
16d since push
License clarity
PASS86
MIT
README/SKILL.md completeness
INFO76
Public metadata needs stronger README/SKILL.md context
Dependency/runtime risk
PASS82
database surface
Install availability
PASS92
npx skills add undsky/doudou-ai-coding-skills --skill doudou-product
Install command safety
PASS92
standard package or runtime install path
Permission surface
INFO74
filesystem or document access, database access
Repository evidence
PASS86
https://github.com/undsky/doudou-ai-coding-skills/tree/master/skills/doudou-product
Review status
WARN46
AI review approval is missing
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add undsky/doudou-ai-coding-skills --skill doudou-product
Repository
88
https://github.com/undsky/doudou-ai-coding-skills/tree/master/skills/doudou-product
License
86
MIT
Maintenance
100
16d since push
AI review
55
Review approval is missing
README/SKILL.md completeness
84
Usable description available
Dependency risk
82
database surface
Install command safety
92
standard package or runtime install path
Permission surface
74
filesystem or document access, database access
Stars/forks activity
43
41 stars, 9 forks; issue activity unavailable in current metadata
Adoption
42
41 GitHub stars
Warnings
Method
This report combines public metadata, AI review output, repository freshness, install readiness, OpenAgentSkill events, quality scoring, trust checks, and the agent safety gate. It is not a full source-code security review.
Compare nearby options