caveman-compress
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.
Skill by bmschwartz
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/bmschwartz-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
- unknown
- Instructions
- 104 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
Files (9)
- README.md
- SKILL.md
- __init__.py · scripts/
- __main__.py · scripts/
- benchmark.py · scripts/
- cli.py · scripts/
- compress.py · scripts/
- detect.py · scripts/
- validate.py · scripts/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from bmschwartz/claude-files
- 0.570score
building-pydantic-ai-agents
pydantic
Build AI agents with Pydantic AI — tools, capabilities, structured output, streaming, testing, and multi-agent patterns.
SkillAFreshness: AClaude Code +9 - 0.565score
deep-review
bmschwartz
Deep multi-model review pipeline with deliberation, structured verdicts, and learning extraction (invoke as /deep-review — not Cursor's built-in /review).
SkillAFreshness: AClaude Code +9 - 0.524score
feature
bmschwartz
Orchestrates feature development with TDD + adversarial convergence via autonomous feedback loops.
SkillBFreshness: BClaude Code +9 - 0.524score
consult
bmschwartz
Use when you're mid-discussion on an architectural or design decision, on the fence between options, and want an independent second opinion from an external…
SkillBFreshness: BClaude Code +9 - 0.405score
polish
bmschwartz
Semantic cleanup pass for committed work.
SkillDFreshness: DClaude Code +9 - 0.225score
grill-me
bmschwartz
Interview the user relentlessly about a plan or design until reaching shared understanding, resolving each branch of the decision tree.
SkillDFreshness: DClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 30, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/bmschwartz/claude-files
- 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 - 0.320score
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 - 0.303score
caveman-compress
quyenanh198
Compress natural language memory files (CLAUDE.md, todos, preferences) into caveman format to save input tokens.
SkillBFreshness: BClaude Code +9
More from bmschwartz
- 0.565score
deep-review
bmschwartz
Deep multi-model review pipeline with deliberation, structured verdicts, and learning extraction (invoke as /deep-review — not Cursor's built-in /review).
SkillAFreshness: AClaude Code +9 - 0.524score
feature
bmschwartz
Orchestrates feature development with TDD + adversarial convergence via autonomous feedback loops.
SkillBFreshness: BClaude Code +9 - 0.524score
consult
bmschwartz
Use when you're mid-discussion on an architectural or design decision, on the fence between options, and want an independent second opinion from an external…
SkillBFreshness: BClaude Code +9 - 0.405score
polish
bmschwartz
Semantic cleanup pass for committed work.
SkillDFreshness: DClaude 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/bmschwartz-caveman-compress (last updated 2026-10-24)