Caveman Compress
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress memory file
Install
npx skills add kubestellar/console --skill caveman-compressgit clone --depth 1 https://github.com/kubestellar/console.git /tmp/console
mkdir -p ~/.claude/skills
cp -r /tmp/console/.agents/skills/caveman-compress ~/.claude/skills/caveman-compressPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Caveman Compress ## Purpose Compress natural language files (CLAUDE.md, todos, preferences) into caveman-speak to reduce input tokens. Compressed version overwrites original. Human-readable backup saved as `<filename>.original.md`. ## Trigger `/caveman-compress <filepath>` or when user asks to compress a memory file. ## Process 1. The compression scripts live in `scripts/` (adjacent to this SKILL.md). If the path is not immediately available, search for `scripts/__main__.py` next to this SKILL.md. 2. From the directory containing this SKILL.md, run: python3 -m scripts <absolute_filepath> 3. The CLI will: - detect file type (no tokens) - call Claude to compress - validate output (no tokens) - if errors: cherry-pick fix with Claude (targeted fixes only, no recompression) - retry up to 2 times - if still failing after 2 retries: report error to user, leave original file untouched 4. Return result to user ## Compression Rules ### Remove - Articles: a, an, the - Filler: just, really, basically, actually, simply, essentially, generally - Pleasantries: "sure", "certainly", "of course", "happy to", "I'd recommend" - Hedging: "it might be worth", "you could consider", "it would be good to" - Redundant phrasing: "in order to" → "to", "make sure to" → "ensure", "the reason is because" → "because" - Connective fluff: "however", "furthermore", "additionally", "in addition" ### Preserve EXACTLY (never modify)
Details
- Skill name
caveman-compress- Repository
- kubestellar/console
- Path
.agents/skills/caveman-compress/SKILL.md- License
- Apache-2.0
- Repo updated
- 18 November 2026
- Listed in
- heilcheng/awesome-agent-skills
FAQ
What does the Caveman Compress skill do?
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens. Preserves all technical substance, code, URLs, and structure. Compressed version overwrites the original file. Human-readable backup saved as FILE.original.md. Trigger: /caveman-compress FILEPATH or "compress memory file
How do I install the Caveman Compress skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add kubestellar/console --skill caveman-compress. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Caveman Compress popular?
It lives in kubestellar/console, which has 155 GitHub stars and 139 forks, and is included in 1 curated skill list.
Related skills
Caveman
155kubestellar/console
Ultra-compressed communication mode. Cuts output tokens 65% (measured) 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.
Cavecrew
155kubestellar/console
Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".
Caveman Commit
155kubestellar/console
Ultra-compressed commit message generator. Cuts noise from commit messages while preserving intent and reasoning. Conventional Commits format. Subject ≤50 chars, body only when "why" isn't obvious. Use when user says "write a commit", "commit message", "generate commit", "/commit", or invokes /caveman-commit. Auto-triggers when staging changes.
Email Marketing
393shawnpang/startup-founder-skills
When the user needs to design, write, or optimize email sequences -- including welcome series, nurture campaigns, re-engagement flows, onboarding emails, or newsletter strategy.
Youtube Research Automation
492cosmicstack-labs/mercury-agent-skills
Design agent workflows that pull YouTube transcripts, search videos and channels, and monitor new uploads without Google API quotas or OAuth setup
Fill in Notes
177Polaris-Aeterna/loom-notes
Turn a textbook chapter, lecture, or paper into beautiful "fill-in" study notes — written to be READ (clean statements, intuition) yet engineered to be FILLED (blanks, proof skeletons, "your turn" computations) so the reader learns by active recall. Notes are typeset with the Loom XeLaTeX class in this repo. Use when the user wants study notes from a source with gaps to fill in, worked examples restaged as exercises, or theorems stated but proofs left open. Triggers: "make fill-in notes", "turn this chapter into notes I can fill in", "guided / skeleton study notes", "study notes from this book
Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.