# caveman-mcp

> Use this tool when you need to simplify complex markdown documents into concise, easy-to-read text while preserving essential code and structure. It solves the problem of overly verbose documentation by compressing markdown files into caveman-style prose, reducing token usage by 65%. The caveman-mcp tool takes markdown files as input and outputs simplified text, making it ideal for applications where readability and brevity are crucial.

Canonical page: https://skillsregistry.net/skills/alexruco-caveman  
JSON: https://api.skillsregistry.net/v1/skills/alexruco-caveman

## Description

MCP server that compresses markdown files into caveman-style prose, cutting token usage by 65% while preserving code and structure.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** file-system
- **Updated:** 2026-09-01

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ry0faiugju)
- **Repository:** <https://github.com/alexruco/caveman>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "alexruco-caveman"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/alexruco-caveman` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/alexruco-caveman/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt