caveman-compress

The caveman-compress skill reduces input token usage by rewriting natural language files into a concise, caveman-style format while preserving technical content, code blocks, and file structure.

224.1K
Installs
3
Use cases
5/10
Quality

Is caveman-compress safe to install?

Review the source first

Review the source first: our audit of caveman-compress's source files found 1 shell command, 0 external URLs, file reads and writes (high risk). Every command and URL listed appears verbatim in the skill's source. The skill executes shell commands and overwrites local files. It creates a backup of the original file before modification.

How we audit skills: our security review methodology.

Who is this skill for?

Developers and users who want to optimize memory files like CLAUDE.md, todos, and preferences to save token costs.

What can you do with it?

  • Compressing markdown documentation to reduce token consumption.
  • Summarizing project todo lists while maintaining technical instructions.
  • Optimizing preference files for AI agent memory.

How good is this skill?

Quality score: 5/10. The skill documentation is clear, provides specific compression rules, and includes safety mechanisms like backups and error handling.

What does the skill file contain?

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_filep...

Frequently asked questions

Does the tool modify code blocks?

No. The tool preserves code blocks, inline code, file paths, and commands exactly as they appear.

What happens if the compression fails?

The tool attempts to fix errors up to two times. If it still fails, it reports the error to the user and leaves the original file untouched.

Can I recover my original file?

Yes. The tool saves a human-readable backup as <filename>.original.md before overwriting the original file.

Data sourced from juliusbrussee/caveman on GitHub. Install counts from skills.sh. The summary and security audit are derived from the skill's source files: every command and URL listed appears verbatim in the source.

Related skills

supabase-postgres-best-practices

264.3K

Developers and database administrators working with Postgres and Supabase

This skill provides a structured set of Postgres performance optimization rules and best practices maintained by Supabase. It guides developers in writing, reviewing, and optimizing SQL queries, schema designs, and database configurations.

lowpostgressupabasesupabase

convex-performance-audit

79.2K

Developers working with Convex applications who need to optimize slow features, resolve high-resource usage, or address transaction contention

The convex-performance-audit skill provides a structured workflow for diagnosing and resolving performance issues in Convex applications, including read amplification, OCC conflicts, subscription costs, and function limits.

highconvexperformanceget-convex

firecrawl-scrape

70.3K

Users who need to extract clean text content from websites for analysis or processing

The firecrawl-scrape skill extracts content from URLs into LLM-optimized markdown. It handles static and JavaScript-rendered pages and supports concurrent scraping of multiple URLs.

highscrapingweb-extractionfirecrawl

obsidian-markdown

51.9K

Users working with Obsidian vault files who need to generate or modify notes using Obsidian-specific syntax

The obsidian-markdown skill provides instructions and syntax patterns for creating and editing Obsidian Flavored Markdown. It supports wikilinks, embeds, callouts, frontmatter properties, tags, comments, highlights, LaTeX math, Mermaid diagrams, and footnotes.

noneobsidianmarkdownkepano