# Docsift

> Docsift — anishmoncivarghese-docsift. Use this tool when you need to extract specific information from large PDFs and Office files, and convert them into readable Markdown format. DocSift solves the problem of manually searching for answers in lengthy documents by returning only the relevant passages with page numbers and section headings. It is ideal for offline document analysis, providing a secure and private way to work with sensitive files without relying on cloud APIs or accounts.

Canonical page: https://skillsregistry.net/skills/anishmoncivarghese-docsift  
JSON: https://api.skillsregistry.net/v1/skills/anishmoncivarghese-docsift

## Description

DocSift converts PDFs and Office files into clean Markdown once, then returns only the passages that answer a question, with page numbers and section headings so answers can be cited. It runs entirely on your machine, using Docling for PDFs and MarkItDown for everything else, with no cloud APIs, accounts, or telemetry.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** file-system
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ygw2bw41oo)
- **Repository:** <https://github.com/anishmoncivarghese/docsift>

## 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": "anishmoncivarghese-docsift"
    }
  }
}
```

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