📄 skillActivePromisingmedium

caveman

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

Supported Platforms

🤖 Claude Code🖱️ Cursor🧠 Codex📟 Cline

Stars

71.4k

Skill Type

📖 Library & API Reference

Quality Score

102/200

License

MIT

Forks

4.0k

Last Updated

Jun 11, 2026

Discovered

Apr 20, 2026

Validation

Passed

github.com/JuliusBrussee/caveman

Quality Breakdown

102/ 200

Content Signals

○Gotchas/Edge Cases+40

✓Progressive Disclosure+30

○Trigger Description+20

○Verification/Safety+20

✓Code Examples+15

✓Composability+15

Repo Health

✓Recent Activity+15

✓Scripts/Automation+10

✓Real Usage (Issues)+10

✓Single Responsibility+10

○Config/Persistence+10

✓Install Instructions+5

Multi-platform bonus: +5 pts if tool supports 2+ platforms. Score derived from 12 structural signals — not stars or popularity.

medium

Requires extended permissions (shell access, subagents). Review before use.

Active

Updated within the last 90 days. Actively maintained.

Unverified skill. Always review source code before installing any skill from an unknown author.

Install scripts present (install.sh, install.ps1) that modify system state
Persistent configuration modifications across multiple AI tool directories (.claude/, .cursor/, .codex/, .windsurf/)
GitHub Actions workflow (sync-skill.yml) for automated CI/CD operations
Multiple hook installation scripts (hooks/install.sh, hooks/install.ps1) for shell integration
MCP server components (mcp-servers/caveman-shrink) with JavaScript execution
Python scripts with CLI capabilities (caveman-compress/scripts/) that could execute autonomously