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

155 stars 139 forksProductivity & Notes

Install

skills CLI (Claude Code, Cursor, Codex and more)
npx skills add kubestellar/console --skill caveman-compress
Manual install
git 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-compress

Personal 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)
Read the full skill on GitHub

Details

Skill name
caveman-compress
Path
.agents/skills/caveman-compress/SKILL.md
License
Apache-2.0
Repo updated
18 November 2026

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

155

kubestellar/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.

OtherIn 1 list139

Cavecrew

155

kubestellar/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".

AI, LLMs & AgentsIn 1 list139

Caveman Commit

155

kubestellar/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.

Git & Code ReviewIn 1 list139

Email Marketing

393

shawnpang/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.

Productivity & Notes46

Youtube Research Automation

492

cosmicstack-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

Productivity & Notes68

Fill in Notes

177

Polaris-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

Productivity & Notes13

Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.