Rebuild scanned Chinese books as structured Word documents using MinerU OCR, title mapping and proofreading against the original pages.
19Stars1Forks
Repository last pushed
OCR Skills for Claude Code, Codex & AI Agents
These skills help an agent extract text from scans and carry it into another document format. Members cover PDF processing, MinerU, scanned PDF conversion, image-to-PPT work, and vision tools.
8 skillsExplore OCR skills
7 skills
Free
Documents
PDF Processing
Create and inspect PDFs, extract text and tables, merge pages and process forms or scanned documents.
193.4KStars22.8KForks
Repository last pushed
Anthropic
Parse PDFs, scans and Office files into Markdown with MinerU, with OCR, formula and table extraction, batch processing and optional local parsing.
133Stars6Forks
Repository last pushed
Free
Presentations
Image to Editable PPT
Rebuild slide images, scanned PDFs and image-based PPTX into editable PowerPoint text, tables and shapes, with separate visual assets and validation.
3.3KStars178Forks
Repository last pushed
ningzimu
Free
Presentations
Nature Image to PPT
Reconstruct slide images, scanned PDFs and image-only decks as object-level editable PowerPoint, with render comparisons.
53.3KStars2.8KForks
Repository last pushed
Yuan1z0825 and contributors
Free
Other utilities
Agent Vision Toolkit
Equip text-only agents with image questions, OCR, target localization, cropping, SVG tracing, and screenshot comparison tools.
1.3KStars50Forks
Repository last pushed
anionex
Parse PDFs, scans and Office documents with OCR, structured extraction and stable page or block citations.
83.5KStars6.9KForks
Repository last pushed
Related topics
Related guides
- Best PDF Skills for AI Agents: Extraction, Editing and Reading
Choose PDF skills for text extraction, page operations, document creation and paper reading. Compare specific workflows, dependencies and useful handoff checks.
How to choose OCR skills
Use a document parser when layout matters, a PDF-to-Word workflow for editable output, and a vision skill when the scan contains tables or diagrams.
- Extract text from scanned pages
- Convert a scanned PDF into an editable DOCX
- Recover tables from a document image