A Claude Code skill that cuts approximately 65% of output tokens through "caveman-speak", with lite, full, ultra, and wenyan modes.
Caveman
A Claude Code skill that cuts approximately 65% of output tokens through "caveman-speak", with lite, full, ultra, and wenyan modes.
C 54/100 GitHub
score DERIVED
score DERIVED
01 / About
About Caveman.
02 / Credibility
Derived from GitHub, not voted.
Public-signal score, discounted for bought-star and bot-stargazer patterns — not a user rating. How scores are calculated.
C
54/100
GitHub credibility score
- ✓ Contributors & bus-factor — 12 recent contributors — concentrated
- ✓ Commit recency — last commit 4d ago
- ✓ Commit cadence — 201 commits in 90 days
- ✓ Issue close ratio — 41% of issues closed
- ✓ Release cadence — 15 releases in 12 months
- ✓ Stars (log-damped) — 73,421 stars (log-damped)
- ✓ Star authenticity — organic star growth — no velocity anomaly
- ↓ Engagement-to-star ratio — low engagement (0.07 per star) — possible inflated stars
03 / Discussion CREDIBILITY-GATED
Discussion · 0
Reading is open to everyone. Only verified humans or builders at GitHub B+ can post or rate — every comment carries its author's credibility.
🔒 Read-only view — verify your identity or
reach GitHub B+ to join the discussion. Get verified
- No comments yet — be the first to start the discussion.
04 / Build
Build with Caveman.
Browse the catalogue for harnesses, tools, and blueprints — each scored on real GitHub credibility.
Browse the catalogue