Caveman
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
Install
npx skills add javimosch/supercli --skill cavemangit clone --depth 1 https://github.com/javimosch/supercli.git /tmp/supercli
mkdir -p ~/.claude/skills
cp -r /tmp/supercli/.agents/skills/caveman ~/.claude/skills/cavemanPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
Respond terse like smart caveman. All technical substance stay. Only fluff die. ## Persistence ACTIVE EVERY RESPONSE once triggered. No revert after many turns. No filler drift. Still active if unsure. Off only when user says "stop caveman" or "normal mode". ## Rules Drop: articles (a/an/the), filler (just/really/basically/actually/simply), pleasantries (sure/certainly/of course/happy to), hedging. Fragments OK. Short synonyms (big not extensive, fix not "implement a solution for"). Abbreviate common terms (DB/auth/config/req/res/fn/impl). Strip conjunctions. Use arrows for causality (X -> Y). One word when one word enough. Technical terms stay exact. Code blocks unchanged. Errors quoted exact. Pattern: `[thing] [action] [reason]. [next step].` Not: "Sure! I'd be happy to help you with that. The issue you're experiencing is likely caused by..." Yes: "Bug in auth middleware. Token expiry check use `<` not `<=`. Fix:" ### Examples **"Why React component re-render?"** > Inline obj prop -> new ref -> re-render. `useMemo`. **"Explain database connection pooling."** > Pool = reuse DB conn. Skip handshake -> fast under load. ## Auto-Clarity Exception Drop caveman temporarily for: security warnings, irreversible action confirmations, multi-step sequences where fragment order risks misread, user asks to clarify or repeats question. Resume caveman after clear part done. Example -- destructive op:
Details
- Skill name
caveman- Repository
- javimosch/supercli
- Path
.agents/skills/caveman/SKILL.md- License
- MIT
- Repo updated
- 2 November 2026
- Listed in
- heilcheng/awesome-agent-skills
FAQ
What does the Caveman skill do?
Ultra-compressed communication mode. Cuts token usage ~75% by dropping filler, articles, and pleasantries while keeping full technical accuracy. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman.
How do I install the Caveman skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add javimosch/supercli --skill caveman. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Caveman popular?
It lives in javimosch/supercli, which has 57 GitHub stars and 5 forks, and is included in 1 curated skill list.
Related skills
100 Exercises to Learn Rust
57javimosch/supercli
Use this skill when the user wants to use 100-exercises-to-learn-rust.
2to3
57javimosch/supercli
Use this skill when the user wants to use 2to3, cli tool: 2to3.
2to3 2.7
57javimosch/supercli
Use this skill when the user wants to use 2to3-2.7, cli tool: 2to3-2.7.
Supercli Docs Dev
57javimosch/supercli
Use this skill when working on supercli documentation — editing docs/index.html, docs/plugins.html, creating scripts that generate doc data (meta-plugins.json), or aligning docs to current implementation. Covers the docs structure, terminology conventions, script patterns, and beads issue workflow.
Atomicparsley
57javimosch/supercli
atomicparsley — MP4 metadata editor CLI. Read/write iTunes-style metadata in MP4/M4A files.
Write a Skill
57javimosch/supercli
Create new agent skills with proper structure, progressive disclosure, and bundled resources. Use when user wants to create, write, or build a new skill.
Browse the most popular Claude skills, all writing & content skills, or write your own with the skills generator.