PaddlePaddlePaddlePaddleOfficialยท2 Agent Skills Included

PaddleOCR

Extract text, tables, and formulas from PDFs and images

Extracts text from images, screenshots, and scanned PDFs with line-level accuracy across 100+ languages. Converts complex documents into structured Markdown and JSON, preserving tables, formulas, charts, and reading order. Eliminates manual retyping of invoices, reports, and academic papers. Feeds clean, LLM-ready data directly into RAG pipelines and AI agent workflows.
npx skills add PaddlePaddle/PaddleOCR --all -g -y

All Skills in This Repository (2)

Pure Emerald Level Indicators

Frequently Asked Questions

FAQPage Schema
How to install PaddleOCR?โ–ผ

Run `npx skills add PaddlePaddle/PaddleOCR --all -g -y` in your terminal to install all skills in this suite globally.

How to extract text from images with AI?โ–ผ

Use the text recognition skill to pull exact machine-readable text from screenshots, photos, and scans, including CJK characters and small print. Just point it at a file or URL.

Can PaddleOCR convert PDFs to Markdown?โ–ผ

Yes. The document parsing skill converts complex PDFs into structured Markdown or JSON, keeping tables, LaTeX formulas, charts, and correct reading order intact.

Does PaddleOCR work with Claude Code and OpenClaw?โ–ผ

Yes. Both skills follow the universal SKILL.md standard and run in Claude Code, OpenClaw, Cursor, and other compatible agents with a PaddleOCR access token.

Can I use PaddleOCR without coding experience?โ–ผ

Yes. Once installed, your AI agent runs the OCR commands for you based on plain-English requests like extracting a table from an invoice.

Related Repositories in Data & Analytics

View All in Data & Analyticsโ†’