# Docpick

> Use this tool when you need to extract structured data from documents such as invoices, receipts, and tax forms with high accuracy and security. Docpick solves data extraction problems by combining OCR engines with local LLMs, providing validated JSON output through an on-premise interface. It is ideal for use cases requiring zero cloud dependencies and support for built-in schemas with checkdigit verification and cross-field rules.

Canonical page: https://skillsregistry.net/skills/quartzunit-docpick  
JSON: https://api.skillsregistry.net/v1/skills/quartzunit-docpick

## Description

Docpick combines local OCR engines (PaddleOCR, EasyOCR, GOT-OCR2.0) with local LLMs to extract structured JSON from documents. Features 8 built-in schemas for invoices, receipts, bills of lading, and tax forms. Includes validation with checkdigit verification and cross-field rules. Runs entirely on-premise with zero cloud dependencies.

## Trust

- **Trust score (0–1):** 0.55
- **Verification tier:** scanned
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** finance
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/quartzunit-docpick)
- **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": "quartzunit-docpick"
    }
  }
}
```

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