# Docpick

> Use this tool when you need to extract relevant information from unstructured documents and convert it into structured data. Docpick solves problems of manual data entry and information retrieval by utilizing local OCR and LLM technologies to accurately extract data from documents. It takes in documents and outputs structured JSON data, making it ideal for automating document processing workflows.

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

## Description

Schema-driven document extraction with local OCR + LLM. Document in, Structured JSON out.

## Trust

- **Trust score (0–1):** 0.54
- **Verification tier:** scanned
- **Last scanned:** 2026-08-28

## Facts

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

## Source

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

## 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-docpick"
    }
  }
}
```

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