# paddleocr-doc-parsing-v2

> paddleocr-doc-parsing-v2 — hiotec-paddleocr-doc-parsing-v2. Use this tool when you need to extract text and data from documents, such as invoices, receipts, and contracts, to automate data entry and document processing tasks. It solves problems like manual data extraction, document scanning, and text recognition, providing outputs like parsed text, tables, and structured data. The tool takes document images or files as input and returns extracted text and data in a structured format.

Canonical page: https://skillsregistry.net/skills/hiotec-paddleocr-doc-parsing-v2  
JSON: https://api.skillsregistry.net/v1/skills/hiotec-paddleocr-doc-parsing-v2

## Description

Parse documents using PaddleOCR's API.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-05-20

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** instructions
- **Runtime environment:** llm
- **Category:** file-system
- **Updated:** 2026-09-16

## Source

- **Source listing:** [ClawHub](https://clawskills.sh/skills/hiotec-paddleocr-doc-parsing-v2)

## 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": "hiotec-paddleocr-doc-parsing-v2"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/hiotec-paddleocr-doc-parsing-v2` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/hiotec-paddleocr-doc-parsing-v2/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