# MarkGrab

> Use this tool when you need to extract web content from various sources, such as HTML, YouTube, PDF, and DOCX files, and convert it into LLM-ready markdown format. MarkGrab solves the problem of manually scraping and formatting web data, providing a universal solution for text extraction from any URL. It takes in URLs and file types as input and outputs formatted markdown text, making it ideal for use cases requiring efficient web content processing.

Canonical page: https://skillsregistry.net/skills/io-github-arknill-markgrab  
JSON: https://api.skillsregistry.net/v1/skills/io-github-arknill-markgrab

## Description

Universal web content extraction — any URL to LLM-ready markdown. HTML, YouTube, PDF, DOCX.

## Trust

- **Trust score (0–1):** 0.29
- **Verification tier:** scanned
- **Last scanned:** 2026-08-28

## Facts

- **Version:** 0.1.2
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** social-media
- **Updated:** 2026-08-28

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.ArkNill%2Fmarkgrab)
- **Repository:** <https://github.com/QuartzUnit/markgrab>

## 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": "io-github-arknill-markgrab"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-arknill-markgrab` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-arknill-markgrab/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