# extract-llms-docs

> extract-llms-docs — nirholas-extract-llms-docs. Use this tool when you need to extract documentation for AI agents from websites with llms.txt support, solving the problem of manually gathering and formatting data. It takes in website URLs and llms.txt files as input and outputs documentation in multiple formats, such as JSON, CSV, and Markdown. Ideal for use cases where automated documentation extraction is required, such as in AI model training and knowledge graph construction.

Canonical page: https://skillsregistry.net/skills/nirholas-extract-llms-docs  
JSON: https://api.skillsregistry.net/v1/skills/nirholas-extract-llms-docs

## Description

Extract documentation for AI agents from any site with llms.txt support. Features MCP server, REST API, batch processing, and multiple export formats.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** ai-ml
- **Updated:** 2026-09-26

## Source

- **Source listing:** [GitHub](https://github.com/nirholas/extract-llms-docs)

## 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": "nirholas-extract-llms-docs"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/nirholas-extract-llms-docs` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/nirholas-extract-llms-docs/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