aidenwu0209/paddleocr-skills
2 skills4.2k installs70 starsGitHub
Install
npx skills add https://github.com/aidenwu0209/paddleocr-skillsSkills in this repo
1Paddleocr Text RecognitionThe paddleocr-text-recognition skill >-. Trigger keywords (routing): Bilingual trigger terms (Chinese and English) are listed in the YAML description above use that field for discovery and routing. - 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 - 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 Scripts declare their dependencies inline (PEP 723). No separate install step is needed uv resolves dependencies automatically: Scripts declare their dependencies inline (PEP 723). No separate install step is needed — uv resolves dependencies automatically: bash uv run scripts/ocr_caller.py --help Working directory: All uv run scripts/... commands below should be run from this skill's root directory (the directory containing this SKILL.md file). 1.3.9kinstalls2Paddleocr Doc Parsingpaddleocr-doc-parsing is an Apache-2.0 PaddleOCR skill requiring Python 3.9+, uv, and PaddleOCR API credentials (PADDLEOCR_DOC_PARSING_API_URL ending in /layout-parsing and PADDLEOCR_ACCESS_TOKEN). The layout_caller.py script accepts --file-url or --file-path, auto-detects PDF vs image types, saves JSON to a temp path by default, and returns text, tables, LaTeX formulas, figures, seals, and reading-order layout via PP-StructureV3 or PaddleOCR-VL endpoints. Helper scripts optimize_file.py compresses large images, split_pdf.py extracts page ranges for the 100-page PDF cap, and smoke_test.py validates configuration. Developers reach for paddleocr-doc-parsing on invoices, financial reports, academic papers, or multi-column scans—not simple OCR where speed beats structure.317installs