Skill audit report
Turn creator performance data into a documented retrospective, grounded hypotheses, and reusable content learnings.
OpenAgentSkill Trust Score
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
PASS86
1.5K GitHub stars
Stars/forks activity
INFO77
1.5K stars, 176 forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
12d since push
License clarity
WARN58
CC-BY-NC-4.0 (repository; verify skill-level terms) - confirm commercial-use terms
README/SKILL.md completeness
PASS90
Metadata includes enough usage and workflow context
Dependency/runtime risk
PASS90
no major dependency risk hints in public metadata
Install availability
PASS92
npx -y skills add Pluviobyte/rnskill --skill ra-复盘
Install command safety
PASS92
standard package or runtime install path
Permission surface
PASS86
filesystem or document access
Repository evidence
PASS86
https://github.com/Pluviobyte/rnskill/tree/main/skills/ra-%E5%A4%8D%E7%9B%98
Review status
INFO66
AI review data available
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx -y skills add Pluviobyte/rnskill --skill ra-复盘
Repository
88
https://github.com/Pluviobyte/rnskill/tree/main/skills/ra-%E5%A4%8D%E7%9B%98
License
58
CC-BY-NC-4.0 (repository; verify skill-level terms) - confirm commercial reuse terms before production use
Maintenance
100
12d since push
AI review
55
The workflow can touch private platform metrics and workspace files; review the data boundary first.
README/SKILL.md completeness
90
Usable description available
Dependency risk
90
no major dependency risk hints in public metadata
Install command safety
92
standard package or runtime install path
Permission surface
86
filesystem or document access
Stars/forks activity
77
1.5K stars, 176 forks; issue activity unavailable in current metadata
Adoption
88
1.5K 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
Build a reproducible local rough-cut workflow for talking-head or narrated screen-recording videos with transcript review gates.
1.5K Stars · Audit report
Create a consent-aware digital-avatar layer for AI video production with narration approval and final quality gates.
1.5K Stars · Audit report
Generate topic-first, two-part video-title candidates from an approved video brief or final script.
1.5K Stars · Audit report