Agent skill · data analytics · aiskillstore
pdf-page-extract
Extract rich data from PDF pages including text spans with metadata, rendered PNG images, and page mapping. Creates persistent artifacts for downstream processing.
Why this skill is useful
Adds executable Python scripts for PDF data extraction, including rich text metadata and image rendering that extend the AI's capabilities.
What it needs
Requires pdfplumber, pymupdf installed locally. About 5k tokens when loaded. Last updated 2026-08-07. 405 stars on the source repository.
What this skill does
PDF Page Extract Skill Purpose This skill extracts all necessary data from PDF pages to enable accurate AI-driven HTML generation. It produces three critical artifacts: 1. Rich extraction data - Text spans with font metadata (sizes, styles, positions) 2. Rendered PNG image - Visual reference for AI to understand page layout 3. Page mapping - Authoritative mapping of PDF indices to book pages This is the deterministic, Python-based foundation for the entire pipeline. All extracted data is saved to persistent files for traceability and future processing. What to Do 1. Validate input parameters Check PDF file exists and is readable Verify page range (PDF indices or book pages) Confirm output directory structure 2. Establish page mapping (if not already done) Run: python3 Calypso/tools/readpagefooters.py Scans page footers to establish PDF index → book page mapping Saves to: analysis/pagemapping.json 3. Extract rich page data using PyMuPDF and pdfplumber Run: python3 Calypso/tools/richextractor.py Extracts text spans with font metadata: Font name and size Bold/italic flags Position (bounding box) Color information Analyzes page structure to identify: Likely headings (by size and style) Paragraphs (regular text) Potential lists Detects tables using pdfplumber Saves to: analysis/chapterXX/richextraction.json 4. Render PDF page to PNG Convert page to high-resolution PNG image (300+ DPI) Maintains visual fidelity for AI reference Saves to: output/chapterXX/pageartifacts/pageYY/02pageXX.png 5. Extract embedded images (if present) Run: python3 Calypso/tools/extractimages.py Extracts all images from page Saves: output/chapterXX/images/pageYYimage.png Creates metadata: pageYYimages.json 6. …
How to use it
Reference it in AdaL, Claude Code, Cursor or any coding agent — nothing to install:
@skills aiskillstore/pdf-page-extract