Skill audit report
Motor de estado. Rastreia tudo entre sessões — capítulos, scores, decisões, handoffs. Sem isso, o contexto se perde e o pipeline desmorona. Usar no INÍCIO e FIM de toda sessão de trabalho no livro. É a peça mais crítica do sistema.
OpenAgentSkill Trust Score
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
INFO62
115 GitHub stars
Stars/forks activity
WARN57
115 stars, 38 forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
26d since push
License clarity
PASS86
MIT
README/SKILL.md completeness
INFO76
Public metadata needs stronger README/SKILL.md context
Dependency/runtime risk
PASS90
no major dependency risk hints in public metadata
Install availability
PASS92
npx skills add felipelobomotta-blip/book-genesis-studio --skill manuscript-manager
Install command safety
PASS92
standard package or runtime install path
Permission surface
PASS100
no high-risk permission surface in public metadata
Repository evidence
PASS86
https://github.com/felipelobomotta-blip/book-genesis-studio/tree/master/skills/manuscript-manager
Review status
INFO66
AI review data available
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add felipelobomotta-blip/book-genesis-studio --skill manuscript-manager
Repository
88
https://github.com/felipelobomotta-blip/book-genesis-studio/tree/master/skills/manuscript-manager
License
86
MIT
Maintenance
100
26d since push
AI review
55
SKILL.md does not explicitly instruct the agent to treat PROJECT_STATE.yaml and other project files as untrusted data, leaving room for prompt injection if a state file contains instructions.
README/SKILL.md completeness
84
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
100
no high-risk permission surface in public metadata
Stars/forks activity
57
115 stars, 38 forks; issue activity unavailable in current metadata
Adoption
68
115 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