Skill audit report
After a code change (diff/fix/requirement change), decide what to regression-test: changed files → functions → features → cases traceability; outputs a ranked list. Not for: editing case files (test-case-writing), long-term strategy (test-strategy). 代码变更后判断回归哪些测试：沿改动分析链产出分级回归清单。不用于：用例增量修改、长期策略。
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
WARN48
29 GitHub stars
Stars/forks activity
WARN43
29 stars, 6 forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
10d since push
License clarity
PASS86
MIT
README/SKILL.md completeness
INFO76
Public metadata needs stronger README/SKILL.md context
Dependency/runtime risk
INFO64
command execution surface, network or browser surface
Install availability
PASS92
npx skills add fishzjp/qa-skills --skill regression-testing
Install command safety
PASS92
standard package or runtime install path
Permission surface
WARN50
shell or command execution, network or browser access
Repository evidence
PASS86
https://github.com/fishzjp/qa-skills/tree/main/skills/regression-testing
Review status
WARN46
AI review approval is missing
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add fishzjp/qa-skills --skill regression-testing
Repository
88
https://github.com/fishzjp/qa-skills/tree/main/skills/regression-testing
License
86
MIT
Maintenance
100
10d since push
AI review
55
Review approval is missing
README/SKILL.md completeness
84
Usable description available
Dependency risk
64
command execution surface, network or browser surface
Install command safety
92
standard package or runtime install path
Permission surface
50
shell or command execution, network or browser access
Stars/forks activity
43
29 stars, 6 forks; issue activity unavailable in current metadata
Adoption
42
29 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.