How do I install the Paddleocr Doc Parsing skill?

Run npx skillmds@latest add aresbit/paddleocr-doc-parsing in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Paddleocr Doc Parsing safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Paddleocr Doc Parsing?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Paddleocr Doc Parsing free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Paddleocr Doc Parsing?

aresbit (@aresbit) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Paddleocr Doc Parsing by aresbit — Agent Skill

Name: Paddleocr Doc Parsing
Author: aresbit

Paddleocr Doc Parsing

Document parsing and OCR using PaddleOCR. Extract text, tables, and structured data from PDFs and images (JPG, PNG, BMP, TIFF). Supports 110+ languages and outputs Markdown format preserving document layout. Use when processing documents for data extraction, invoice parsing, form recognition, or converting scanned documents to structured text. Requires PADDLEOCR_API_URL and PADDLEOCR_ACCESS_TOKEN environment variables.

aresbit Updated Sep 17, 2026

File contents

PaddleOCR Document Parsing

This skill integrates Baidu's PaddleOCR to provide powerful document parsing capabilities for Claude Code.

Features

Multi-format support: PDF, JPG, PNG, BMP, TIFF
Layout analysis: Automatically detects text, tables, formulas, headers, and other document elements
Multi-language OCR: Covers 110+ languages including Chinese, English, Japanese, Korean
Structured output: Returns Markdown format that preserves document hierarchy
Direct PDF support: No conversion needed, PDFs parsed directly via API

Setup

1. Get API Credentials

Visit PaddleOCR to get API credentials:

Register and verify your phone number
Select "PaddleOCR-VL-1.5" model
Copy TOKEN and API_URL from the example code
Free daily quota: tens of thousands of pages

2. Configure Environment Variables

Add to ~/.zshrc or ~/.claude/.env:

export PADDLEOCR_API_URL="your_api_url_here"
export PADDLEOCR_ACCESS_TOKEN="your_access_token_here"

Usage

Parse PDF Document

python3 scripts/parse_pdf_direct.py /path/to/document.pdf

Output:

Markdown printed to stdout
{filename}_ocr/ directory created in same folder as PDF
Each page saved as separate .md file
Images extracted and saved to output directory

Options:

python3 scripts/parse_pdf_direct.py /path/to/document.pdf --output /custom/output/dir
python3 scripts/parse_pdf_direct.py /path/to/document.pdf --format json

Parse Image

Same script handles images (fileType detected automatically):

python3 scripts/parse_pdf_direct.py /path/to/invoice.jpg

Scripts

Script	Purpose
`scripts/parse_pdf_direct.py`	Main parsing script for PDF and images
`scripts/parse_document.py`	Alternative script (legacy API format)
`scripts/extract_fields.py`	Field extraction for common document types

References

references/api_reference.md - API endpoint specifications
references/document_types.md - Supported documents and best practices

API Response Format

{
  "result": {
    "layoutParsingResults": [
      {
        "markdown": {
          "text": "## Page content...",
          "images": {"img1.png": "https://..."}
        }
      }
    ]
  }
}

Error Handling

The API may occasionally return 500 errors due to service load. The script includes automatic retry logic. If parsing fails:

Wait a few seconds
Retry the request
Check API credentials are correct

---name: paddleocr-doc-parsingdescription: Document parsing and OCR using PaddleOCR. Extract text, tables, and structured data from PDFs and images (JPG, PNG, BMP, TIFF). Supports 110+ languages and outputs Markdown format preserving document layout. Use when processing documents for data extraction, invoice parsing, form recognition, or converting scanned documents to structured text. Requires PADDLEOCR_API_URL and PADDLEOCR_ACCESS_TOKEN environment variables.---# PaddleOCR Document ParsingThis skill integrates Baidu's PaddleOCR to provide powerful document parsing capabilities for Claude Code.## Features- **Multi-format support**: PDF, JPG, PNG, BMP, TIFF- **Layout analysis**: Automatically detects text, tables, formulas, headers, and other document elements- **Multi-language OCR**: Covers 110+ languages including Chinese, English, Japanese, Korean- **Structured output**: Returns Markdown format that preserves document hierarchy- **Direct PDF support**: No conversion needed, PDFs parsed directly via API## Setup### 1. Get API CredentialsVisit [PaddleOCR](https://paddleocr.com) to get API credentials:1. Register and verify your phone number2. Select "PaddleOCR-VL-1.5" model3. Copy TOKEN and API_URL from the example code4. Free daily quota: tens of thousands of pages### 2. Configure Environment VariablesAdd to `~/.zshrc` or `~/.claude/.env`:```bashexport PADDLEOCR_API_URL="your_api_url_here"export PADDLEOCR_ACCESS_TOKEN="your_access_token_here"```## Usage### Parse PDF Document```bashpython3 scripts/parse_pdf_direct.py /path/to/document.pdf```**Output**:- Markdown printed to stdout- `{filename}_ocr/` directory created in same folder as PDF- Each page saved as separate `.md` file- Images extracted and saved to output directory**Options**:```bashpython3 scripts/parse_pdf_direct.py /path/to/document.pdf --output /custom/output/dirpython3 scripts/parse_pdf_direct.py /path/to/document.pdf --format json```### Parse ImageSame script handles images (fileType detected automatically):```bashpython3 scripts/parse_pdf_direct.py /path/to/invoice.jpg```## Scripts| Script | Purpose ||--------|---------|| `scripts/parse_pdf_direct.py` | Main parsing script for PDF and images || `scripts/parse_document.py` | Alternative script (legacy API format) || `scripts/extract_fields.py` | Field extraction for common document types |## References- `references/api_reference.md` - API endpoint specifications- `references/document_types.md` - Supported documents and best practices## API Response Format```json{ "result": { "layoutParsingResults": [ { "markdown": { "text": "## Page content...", "images": {"img1.png": "https://..."} } } ] }}```## Error HandlingThe API may occasionally return 500 errors due to service load. The script includes automatic retry logic. If parsing fails:1. Wait a few seconds2. Retry the request3. Check API credentials are correct

Frequently asked questions