Writing
Plugin
caveman-claude-skill
Ultra-compressed communication mode for Claude. Cuts token usage ~75% by dropping linguistic fluff while preserving full technical accuracy.
Plugin Signal32/100Fair
maintained24
capable14
documented55
adopted56
Install
$ npx -y skills add amanattar/caveman-claude-skill --agent claude-code
Stats
415
Stars
59
Forks
Quiet
Maintenance
6mo ago
Last commit
6mo ago
Created
1d ago
Added
What's inside
README
caveman skill
Ultra-compressed communication mode for Claude. Cuts token usage ~75% by dropping linguistic fluff while preserving full technical accuracy.
What It Does
Switches Claude's response style to terse, caveman-like communication. Articles gone. Filler gone. Hedging gone. Technical substance stays intact. Code blocks and error messages always quoted exactly.
Trigger Phrases
caveman modetalk like cavemanuse cavemanless tokensbe brief/caveman
Intensity Levels
Switch anytime with /caveman <level>. Default is full.
| Level | Style |
|---|---|
lite | No filler or hedging. Articles and full sentences kept. Professional but tight. |
full | Drop articles. Fragments OK. Short synonyms. Classic caveman. |
ultra | Abbreviate everything (DB/auth/fn/req/res). Arrows for causality. One word when one word enough. |
wenyan-lite | Semi-classical Chinese. Drop filler, keep grammar structure. |
wenyan-full | Full ζθ¨ζ. ~80-90% character reduction. Classical particles and patterns. |
wenyan-ultra | Maximum classical Chinese compression. Extreme terseness. |
Quick Example
Prompt: "Why does my React component re-render?"
| Level | Response |
|---|---|
| lite | "Your component re-renders because you create a new object reference each render. Wrap it in useMemo." |
| full | "New object ref each render. Inline object prop = new ref = re-render. Wrap in useMemo." |
| ultra | "Inline obj prop β new ref β re-render. useMemo." |
| wenyan-full | "η©εΊζ°εη
§οΌθ΄ιηΉͺγuseMemoε
δΉγ" |
Auto-Clarity Exceptions
Caveman mode pauses automatically for:
- Security warnings
- Irreversible or destructive action confirmations
- Multi-step sequences where fragment order risks misread
- Situations where the user is confused
Normal caveman resumes immediately after the critical part.
Boundaries
- Code, commits, and PRs: always written normally regardless of level.
- Level persists across the session until changed.
stop cavemanornormal modeexits caveman entirely.
File
SKILL.md β loaded by Claude at runtime to apply caveman rules.
File tree
FAQ
caveman-claude-skill is a Claude Code plugin with 1 hand-picked skill, indexed on Flowy in the Writing category. Install it with the command on its page. It includes caveman-claude-skill. Its skills do not fire on their own yet. Request auto-invocation to have Flowy route them as you prompt. Free and open source.
- What is caveman-claude-skill?
- Ultra-compressed communication mode for Claude. Cuts token usage ~75% by dropping linguistic fluff while preserving full technical accuracy.
- How do I install caveman-claude-skill?
- Run these in Claude Code: npx -y skills add amanattar/caveman-claude-skill --agent claude-code. Then prompt normally.
- Does caveman-claude-skill auto-invoke its skills?
- Not yet. It is indexed on Flowy as a plain plugin. Request auto-invocation on its page and Flowy will route its skills for you as you prompt.
- Is caveman-claude-skill free?
- Yes. Flowy is free and open source, with nothing gated. You can read every skill in full before you install.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it