Skill audit report
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
OpenAgentSkill Trust Score
The Trust Score helps an agent decide whether a skill is safe enough to shortlist before installation.
GitHub adoption
WARN48
86 GitHub stars
Stars/forks activity
WARN48
86 stars, 21 forks; issue activity unavailable in current metadata
Recent maintenance
PASS100
25d since push
License clarity
PASS86
MIT
README/SKILL.md completeness
PASS86
Metadata includes enough usage and workflow context
Dependency/runtime risk
WARN56
credential or environment access, network or browser surface
Install availability
PASS92
npx skills add thedesignproject/agent-skills --skill caveman
Install command safety
PASS92
standard package or runtime install path
Permission surface
WARN48
secrets or environment access, network or browser access
Repository evidence
PASS86
https://github.com/thedesignproject/agent-skills/tree/main/skills/caveman
Review status
INFO66
AI review data available
Agent Proven outcomes
INFO54
No agent outcome data yet
Checks
Install path
92
npx skills add thedesignproject/agent-skills --skill caveman
Repository
88
https://github.com/thedesignproject/agent-skills/tree/main/skills/caveman
License
86
MIT
Maintenance
100
25d since push
AI review
55
The claim of ~75% token reduction is unverified and could be seen as marketing language, though it does not affect safety or functionality.
README/SKILL.md completeness
86
Usable description available
Dependency risk
56
credential or environment access, network or browser surface
Install command safety
92
standard package or runtime install path
Permission surface
48
secrets or environment access, network or browser access
Stars/forks activity
48
86 stars, 21 forks; issue activity unavailable in current metadata
Adoption
68
86 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
Eliminates predictable AI writing patterns from prose while preserving specific meaning and reader trust.
16K Stars · Audit report
Applies Cursor's prose-discipline rules to remove filler and AI writing tells from agent-facing and user-facing text.
4.8K Stars · Audit report
Rewrites AI-sounding text so it reads naturally while preserving every factual claim and matching the writer's voice.
37K Stars · Audit report