Skill audit report
Official repo of 𝗚𝗲𝗻𝗲𝗿𝗮𝘁𝗶𝘃𝗲 𝗠𝗼𝗱𝗲𝗹𝘀: 𝗪𝗵𝗮𝘁 𝗗𝗼 𝗧𝗵𝗲𝘆 𝗞𝗻𝗼𝘄? 𝗗𝗼 𝗧𝗵𝗲𝘆 𝗞𝗻𝗼𝘄 𝗧𝗵𝗶𝗻𝗴𝘀? 𝗟𝗲𝘁'𝘀 𝗙𝗶𝗻𝗱 𝗢𝘂𝘁! (Previously titled 𝘐𝘯𝘵𝘳𝘪𝘯𝘴𝘪𝘤 𝘓𝘰𝘙𝘈: 𝘈 𝘎𝘦𝘯𝘦𝘳𝘢𝘭𝘪𝘴𝘵 𝘈𝘱𝘱𝘳𝘰𝘢𝘤𝘩 𝘧𝘰𝘳 𝘋𝘪𝘴𝘤𝘰𝘷𝘦𝘳𝘪𝘯𝘨 𝘒𝘯𝘰𝘸𝘭𝘦𝘥𝘨𝘦 𝘪𝘯 𝘎𝘦𝘯𝘦𝘳𝘢𝘵𝘪𝘷𝘦 𝘔𝘰𝘥𝘦𝘭𝘴))
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
INFO62
191 GitHub stars
Stars/forks activity
WARN51
191 stars, 8 forks; issue activity unavailable in current metadata
Recent maintenance
FAIL38
2y since push
License clarity
WARN42
Unknown
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 skills add duxiaodan/intrinsic-lora
Install command safety
PASS92
standard package or runtime install path
Permission surface
PASS86
filesystem or document access
Repository evidence
PASS86
https://github.com/duxiaodan/intrinsic-lora
Review status
PASS88
AI review data available
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add duxiaodan/intrinsic-lora
Repository
88
https://github.com/duxiaodan/intrinsic-lora
License
45
Unknown
Maintenance
38
2y since push
AI review
88
Approved with no listed issues
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
51
191 stars, 8 forks; issue activity unavailable in current metadata
Adoption
68
191 GitHub stars
Financial decision safety
58
Research-only use: do not treat output as financial advice or execute a position without human approval.
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
AI watermark remover. CLI and Python library to strip visible and invisible AI watermarks (Gemini / Nano Banana sparkle, SynthID) and provenance metadata (C2PA, EXIF, IPTC) from images.
4.3K Stars · Audit report
Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks
4.2K Stars · Audit report
Superfast AI decision making and intelligent processing of multi-modal data.
3.9K Stars · Audit report