# rag-scrape

> rag-scrape — owerryking-beep-rag-scrape. Use this tool when you need to convert URLs into RAG-ready Markdown, solving data preparation and embedding challenges for large language models. It takes a URL as input and outputs formatted Markdown with embeddings, headings, and change-aware indexing. Ideal for use cases requiring automated document processing and integration with language models, such as data crawling and knowledge graph construction.

Canonical page: https://skillsregistry.net/skills/owerryking-beep-rag-scrape  
JSON: https://api.skillsregistry.net/v1/skills/owerryking-beep-rag-scrape

## Description

URL → RAG-ready Markdown in one API call: heading-aligned chunks, embeddings, change-aware re-indexing, docs crawler + llms.txt, MCP server. Free tier.

## Trust

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

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/owerryking-beep/rag-scrape)

## 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": "owerryking-beep-rag-scrape"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/owerryking-beep-rag-scrape` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/owerryking-beep-rag-scrape/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