caveman-compress
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.
Skill by quyenanh198
Chalk Labs
Need help deploying caveman-compress?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/quyenanh198-caveman-compress
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions: not checked yet.
What's inside
- Skill name
caveman-compress- Description
- 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"
- License
- MIT
- Instructions
- 104 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (8)
- SKILL.md
- __init__.py · scripts/
- __main__.py · scripts/
- benchmark.py · scripts/
- cli.py · scripts/
- compress.py · scripts/
- detect.py · scripts/
- validate.py · scripts/
SKILL.md (first lines)
# 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`, but NOT beside the source file — it lives in an out-of-tree data dir (`$XDG_DATA_HOME/caveman-compress/backups/<parent-dir-name>/`, or `%LOCALAPPDATA%\caveman-compress\backups\<parent-dir-name>\` on Windows) so skill auto-loaders don't re-ingest it as a live file. ## Trigger `/caveman-compress <filepath>` or when user asks to compress a memory file. ## Process 1. The compression scripts live in `scripts/` (adjacent to this SKILL.md). If the path is not immediately available, search for `scripts/__main__.py` next to this SKILL.md. 2. From the directory containing this SKILL.md, run: python3 -m scripts <absolute_filepath> 3. The CLI will: - detect file type (no tokens) - call Claude to compress - validate output (no tokens) - if errors: cherry-pick fix with Claude (targeted fixes only, no recompression) - retry up to 2 times - if still failing after 2 retries: report error to user, leave original file untouched 4. Return result to user ## Compression Rules ### Remove - Articles: a, an, the - Filler: just, really, basically, actually, simply, essentially, generally - Pleasantries: "sure", "certainly", "of course", "happy to", "I'd recommend" - Hedging: "it might be worth", "you could consider", "it would be good to" - Redundant phrasing: "in order to" → "to", "make sure to" → "ensure", "the reason is because" → "because" - Connective fluff: "however", "furthermore", "additionally", "in addition" ### Preserve EXACTLY (never modify) - Code blocks (fenced ``` and indented) - Inline code (`backtick content`) - URLs and links (full URLs, markdown links) - File paths (`/src/components/...`, `./config.yaml`) - Commands (`npm install`, `git commit`, `docker build`) - Technical terms (library names, API names, protocols, algorithms) - Proper nouns (project names, people, companies) - Dates, version numbers, numeric values - Environment variables (`$HOME`, `NODE_ENV`) ### Preserve Structure - All markdown headings (keep exact heading text, compress body below) - Bullet point hierarchy (keep nesting level) - Numbered lists (keep numbering) - Tables (compress cell text, keep structure) - Frontmatter/YAML headers in markdown files ### Compress - Use short synonyms: "big" not "extensive", "fix" not "implement a solution for", "use" not "utilize" - Fragments OK: "Run tests before commit" not "You should always run tests before committing" - Drop "you should", "make sure to", "remember to" — just state the action - Merge redundant bullets that say the same thing differently - Keep one example where multiple examples show the same pattern CRITICAL RULE: Anything inside ``` ... ``` must be copied EXACTLY. Do not: - remove comments - remove spacing - reorder lines - shorten commands - simplify anything Inline code (`...`) must be preserved EXACTLY. Do not modify anything inside backticks. If file contains code blocks: - Treat code blocks as read-only regions - Only compress text outside them - Do not merge sections around code ## Pattern Original: > You should always make sure to run the test suite before pushing any changes to the main branch. This is important because it helps catch bugs early and prevents broken builds from being deployed to production. Compressed: > Run tests before push to main. Catch bugs early, prevent broken prod deploys. Original: > The application uses a microservices architecture with the following components. The API gateway handles all incoming requests and routes them to the appropriate service. The authentication service is responsible for managing user sessions and JWT tokens. Compressed: > Microservices architecture. API gateway route all requests to services. Auth service manage user sessions + JWT tokens. ## Boundaries - ONLY compress natural language files (.md, .txt, .typ, .typst, .tex, extensionless) - NEVER modify: .py, .js, .ts, .json, .yaml, .yml, .toml, .env, .lock, .css, .html, .xml, .sql, .sh - If file has mixed content (prose + code), compress ONLY the prose sections - If unsure whether something is code or prose, leave it unchanged - Original file is backed up as FILE.original.md before overwriting — in the out-of-tree backup data dir (see Purpose), not beside the source file - Never compress FILE.original.md (skip it)
From quyenanh198/Skills, MIT.
More from quyenanh198/Skills
- 0.529score
chinese-via-hanviet
quyenanh198
Teaches Mandarin Chinese to a Vietnamese-speaking learner by bridging through Hán-Việt (Sino-Vietnamese) readings and vocabulary, and by flagging only the…
SkillBFreshness: BClaude Code +9 - 0.529score
analyze-report
quyenanh198
Builds a multi-timeframe technical analysis and change report for any publicly traded stock — current snapshot, entry-point read across 1-hour/daily/weekly…
SkillBFreshness: BClaude Code +9 - 0.524score
divergent-thinking
quyenanh198
Open-ended ideation — generate a wide spread of distinct options or angles on a problem, breadth before evaluation.
SkillBFreshness: BClaude Code +9 - 0.524score
fiction-writing
quyenanh198
Write or revise narrative prose — scene structure, character voice, pacing, dialogue.
SkillBFreshness: BClaude Code +9 - 0.524score
review-and-test
quyenanh198
Review code for bugs and correctness gaps, then write failing TDD-style tests for each confirmed gap before any fix is applied.
SkillBFreshness: BClaude Code +9 - 0.524score
code-review-checklist
quyenanh198
A general checklist for reviewing code changes for correctness, security, and maintainability.
SkillBFreshness: BClaude Code +9 - 0.520score
notebooklm
quyenanh198
Control NotebookLM (renamed "Gemini Notebook" as of July 2026 — same product, same URL) via browser automation using the Claude Chrome Extension.
SkillBFreshness: BClaude Code +9 - 0.519score
commit-message
quyenanh198
Drafts a conventional commit message from the currently staged git changes.
SkillBFreshness: BClaude Code +9 - 0.499score
learn
quyenanh198
Use this skill when the user wants intellectual understanding — learning how or why something works, not getting a task done or soliciting Claude's judgment.
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 13, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/quyenanh198/Skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
Same skill elsewhere
Copies of this SKILL.md published by others; search shows only one of them.
- 0.621score
caveman-compress
kubestellar
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.
SkillBFreshness: B★ 150Claude Code +9 - 0.366score
caveman-compress
chinkan
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.
SkillAFreshness: A★ 10Claude Code +9 - 0.363score
caveman-compress
Sarthib7
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.
SkillAFreshness: A★ 10Claude Code +9 - 0.350score
caveman-compress
storm-software
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.
SkillAFreshness: A★ 3Claude Code +9 - 0.346score
caveman-compress
storm-software
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.
SkillAFreshness: A★ 2Claude Code +9 - 0.330score
caveman-compress
uhstray-io
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.
SkillBFreshness: B★ 5Claude Code +9 - 0.327score
caveman-compress
juliusbrussee
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.
SkillAFreshness: AClaude Code +9 - 0.324score
caveman-compress
bmschwartz
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.
SkillAFreshness: AClaude Code +9 - 0.320score
caveman-compress
christiansalazar-wk
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.
SkillBFreshness: B★ 2Claude Code +9 - 0.313score
caveman-compress
cavaldos
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.
SkillBFreshness: B★ 1Claude Code +9 - 0.311score
caveman-compress
tassiovale
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.
SkillCFreshness: C★ 12Claude Code +9 - 0.308score
caveman-compress
CliffVale
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.
SkillBFreshness: B★ 1Claude Code +9
More from quyenanh198
- 0.529score
chinese-via-hanviet
quyenanh198
Teaches Mandarin Chinese to a Vietnamese-speaking learner by bridging through Hán-Việt (Sino-Vietnamese) readings and vocabulary, and by flagging only the…
SkillBFreshness: BClaude Code +9 - 0.529score
analyze-report
quyenanh198
Builds a multi-timeframe technical analysis and change report for any publicly traded stock — current snapshot, entry-point read across 1-hour/daily/weekly…
SkillBFreshness: BClaude Code +9 - 0.524score
divergent-thinking
quyenanh198
Open-ended ideation — generate a wide spread of distinct options or angles on a problem, breadth before evaluation.
SkillBFreshness: BClaude Code +9 - 0.524score
fiction-writing
quyenanh198
Write or revise narrative prose — scene structure, character voice, pacing, dialogue.
SkillBFreshness: BClaude Code +9 - 0.524score
review-and-test
quyenanh198
Review code for bugs and correctness gaps, then write failing TDD-style tests for each confirmed gap before any fix is applied.
SkillBFreshness: BClaude Code +9 - 0.524score
code-review-checklist
quyenanh198
A general checklist for reviewing code changes for correctness, security, and maintainability.
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get caveman-compress running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
caveman-compress skill. Agent Mart. https://agentmart.dev/skills/quyenanh198-caveman-compress (last updated 2026-10-24)