# pagesift

> pagesift — yolow92-pagesift. Use this tool when you need to extract and convert web content into clean, structured data. Pagesift solves the problem of scraping and crawling URLs, PDFs, and Office files, outputting Markdown and JSON formats through its Firecrawl- and Jina Reader-compatible API. It provides a self-hosted, single-binary solution with Python and Node SDKs for seamless integration.

Canonical page: https://skillsregistry.net/skills/yolow92-pagesift  
JSON: https://api.skillsregistry.net/v1/skills/yolow92-pagesift

## Description

Self-hosted web scraper, crawler and document parser for AI agents: URLs, PDFs with OCR and Office files to clean Markdown/JSON. Firecrawl- and Jina-compatible API, MCP server, agent endpoint, Python/Node SDKs. Single Rust binary.

## Trust

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

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** AGPL-3.0
- **Updated:** 2026-11-08

## Source

- **Source listing:** [GitHub](https://github.com/YOLOW92/pagesift)

## 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": "yolow92-pagesift"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/yolow92-pagesift` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/yolow92-pagesift/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