Pdfx — AI skill for Claude Code
Self-contained Claude Code skill for any PDF task — generate publication-quality PDFs/ebooks from Markdown (WeasyPrint, AI cover, TOC, code highlighting) AND process existing PDFs (OCR, extract, merge.
How to install Pdfx
This entry records only its repository, not the path inside it, so there is no
exact command to give. Open docaohieu2808/pdfx and copy the folder into
~/.claude/skills/, or the file into ~/.claude/agents/.
What Pdfx does
Self-contained Claude Code skill for any PDF task — generate publication-quality PDFs/ebooks from Markdown (WeasyPrint, AI cover, TOC, code highlighting) AND process existing PDFs (OCR, extract, merge/split, forms, watermark, encrypt/decrypt).
Alternatives in AI
- Xerj — Local-first search engine and MCP server for AI agents 12.5k ★
- AGENTS.md - Skill Seekers — Concise reference for AI coding agents 11.1k ★
- Ante — Ghost in your shell 1.9k ★
README
pdfx — complete PDF toolkit (Claude Code skill)
A self-contained [Claude Code](https://claude.ai/code) / agent **skill** for *anything* PDF. Unlike typical `pdf` skills that only read or transform PDFs, **pdfx does both directions** — it also *produces* publication-quality PDFs from Markdown.
**One skill, two pillars.** Copy the `pdfx/` folder into any skills directory and it just works — bundled fonts, modular CLI scripts, reference guides. Depends on **no other skill**. Optional heavy engines auto-install on first use (or run `install.sh`).

A. Generate beautiful PDFs / ebooks (Markdown → PDF)
`Markdown → HTML (python-markdown + Pygments) → WeasyPrint → PDF` with published-grade print CSS:
- Designed cover — optional AI art via Gemini (free-tier key), a pre-made image, or a gradient.
- Auto-numbered TOC with dot leaders + real page numbers; optional depth-2 sub-entries.
- Part dividers (
--parts), a back-of-book A-Z index (--index), clickable PDF bookmarks. - Diagrams that actually render: inline
(shielded frommd_in_html) and```mermaidfences auto-rendered to SVG (Vietnamese-safe labels). - Syntax-highlighted code,
[B]/[I]/[A]/[!]badges, bundled Playfair Display + EB Garamond, A4/6×9, light/dark,--previewto auto-render page PNGs.
PDFX=/path/to/pdfx ; PY=python
$PY "$PDFX/scripts/build_ebook_from_markdown.py" \
--title "DevOps Handbook" --subtitle "Complete Reference" \
--gen-cover "a server scaling into a distributed cloud, glowing data-flow lines" \
--parts "1=Foundations,7=Build & Ship" --toc-depth 2 --index --preview \
--page a4 --theme light --accent "#2563eb" --output handbook.pdf ch01.md ch02.md ...
B. Process existing PDFs — `scripts/pdf_process.py` (35 subcommands)
| Group | Com
Related Skills
Nutrient Agent Skill
Document processing with Nutrient DWS API: convert (PDF/DOCX/XLSX/PPTX/HTML/images), extract text/tables, OCR
J Email Analysis
Process AI research newsletter emails (TLDR AI, The Batch, Import AI, etc.) -- extract links, categorize, down
Web Scraping Automation With AI Agent
A Firecrawl-based AI automation to source, scrape, and verify research based on a topic before publication. Th
Resume Tailor
Turn a job description into a tailored resume + cover letter (DOCX/PDF) with a skills-gap report and match sco
Autoconst Claude Drawing Takeoff
Turn a construction PDF drawing set into a priced Bill of Quantities in Excel. Deterministic vector-text extra
Omnilingua AI
Agentic AI translator: auto-detects Groq/OpenAI/Claude/Gemini keys, RAG translation memory, OCR + PDF, live vo
Related Agents
PDF Compiler
Compiles {file_prefix}_resume.tex and {file_prefix}_cover_letter.tex into PDFs with local pdflatex when it is
PDF Question Answerer
Use this agent when you need to analyze, extract information from, or answer questions about scientific PDFs.
Finance Filing
Process PDFs (receipts and invoices), extract data, prepare for filing to Drive and the Finances spreadsheet.