Skill audit report
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman:compress <filepath> or "compress memory file"
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
INFO76
561 GitHub stars
Stars/forks activity
INFO71
561 stars, 161 forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
14d since push
License clarity
PASS86
MIT
README/SKILL.md completeness
PASS86
Metadata includes enough usage and workflow context
Dependency/runtime risk
FAIL28
command execution surface, credential or environment access
Install availability
PASS92
npx skills add HoangNguyen0403/agent-skills-standard --skill caveman-compress
Install command safety
PASS92
standard package or runtime install path
Permission surface
FAIL18
secrets or environment access, shell or command execution
Repository evidence
PASS86
https://github.com/HoangNguyen0403/agent-skills-standard/tree/develop/.agents/skills/caveman-compress
Review status
INFO66
AI review data available
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add HoangNguyen0403/agent-skills-standard --skill caveman-compress
Repository
88
https://github.com/HoangNguyen0403/agent-skills-standard/tree/develop/.agents/skills/caveman-compress
License
86
MIT
Maintenance
100
14d since push
AI review
55
Skill relies on external Claude API which may require API key and incur costs.
README/SKILL.md completeness
86
Usable description available
Dependency risk
28
command execution surface, credential or environment access
Install command safety
92
standard package or runtime install path
Permission surface
18
secrets or environment access, shell or command execution
Stars/forks activity
71
561 stars, 161 forks; issue activity unavailable in current metadata
Adoption
88
561 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
Create beautiful slides on the web using a coding agent's frontend skills
29K Stars · Audit report
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
169K Stars · Audit report
Platform to build admin panels, internal tools, and dashboards. Integrates with 25+ databases and any API.
41K Stars · Audit report