Rebuild scanned Chinese books as structured Word documents using MinerU OCR, title mapping and proofreading against the original pages.
PDF Skills for Claude Code, Codex & AI Agents
These skills help an agent parse PDFs and scanned pages, run OCR, and convert documents to Word, Markdown, or PowerPoint. Other entries generate React-PDF output and support paper reading or translation.
18 skillsExplore PDF skills
7 skillsPDF Processing
Create and inspect PDFs, extract text and tables, merge pages and process forms or scanned documents.
Parse PDFs, scans and Office files into Markdown with MinerU, with OCR, formula and table extraction, batch processing and optional local parsing.
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.
Nature Image to PPT
Reconstruct slide images, scanned PDFs and image-only decks as object-level editable PowerPoint, with render comparisons.
Agent Vision Toolkit
Equip text-only agents with image questions, OCR, target localization, cropping, SVG tracing, and screenshot comparison tools.
Parse PDFs, scans and Office documents with OCR, structured extraction and stable page or block citations.
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 PDF skills
Choose OCR for scans, parsing or Markdown conversion for extraction, and document or React PDF skills when the result must be a new PDF.
- Extract text from a scanned PDF
- Convert a PDF into Markdown or Word
- Generate a structured PDF report



