Paddleocr Text Recognition

A straightforward OCR wrapper around PaddleOCR's API that pulls text from images, PDFs, and screenshots. Returns structured JSON with line-level text and optional bounding boxes. The setup is honest: you need to grab API credentials from paddleocr.com first, but after that it's just a uv run command with a URL or file path. Strong on CJK and handwritten text according to the docs. One thing to know: this is pure text extraction, not document parsing. If you need table structure or reading order from complex layouts, look elsewhere. For "get me the text from this screenshot" tasks, it does the job without ceremony.

skills.sh installs: 4K
GitHub stars: 35
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add aidenwu0209/paddleocr-skills --skill paddleocr-text-recognition --agent claude-code

Installs into .claude/skills of the current project.

Files

PaddleOCR Text Recognition Skill

When to Use This Skill

Trigger keywords (routing): Bilingual trigger terms (Chinese and English) are listed in the YAML description above—use that field for discovery and routing.

Use this skill for:

Extract text from images (screenshots, photos, scans)
Extract text from PDFs or document images when the goal is line/box-level text, not recovering table grids, formulas, or full reading-order layout
Extract text from URLs or local files that point to images/PDFs

Do not use for:

Plain text files, code files, or markdown documents that can be read directly as text
Documents with tables, formulas, charts, or complex layouts — use Document Parsing instead
Tasks that do not involve image-to-text conversion