skills.rest
lucasmiachon-blip
lucasmiachon-blipCOMMUNITY
Explore all skills by this author →
GitHub

document-conversion

Convert EPUB, PDF, and Office documents into PDF, Markdown, HTML, or JSON.

Updated Aug 27, 2026
Search Tags:#pdf#markdown#pandoc#epub#docling#calibre
One-click install
npx skills add https://github.com/lucasmiachon-blip/OLMO --skill document-conversion-lucasmiachon-blip
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: document-conversion
Source: https://github.com/lucasmiachon-blip/OLMO/tree/main/.claude/skills/document-conversion
Command: npx skills add https://github.com/lucasmiachon-blip/OLMO --skill document-conversion-lucasmiachon-blip

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill addresses the tedious, error-prone workflow of converting documents across formats (EPUB, PDF, DOCX/PPTX) and generating outputs suitable for reading, study, and AI ingestion.

Core Features & Use Cases

  • Canonical pipelines: EPUB→PDF using Pandoc+xelatex with sandboxed security, PDF→Markdown via Docling, and optional HTML/JSON outputs for AI ingestion.
  • Fallbacks & compatibility: Calibre-based conversion when structure is complex; venv-isolated Docling for safe data handling.
  • Use Case: A researcher wants to convert a 300-page EPUB textbook to PDF for offline reading and to Markdown for AI-assisted note extraction.

Quick Start

Use this skill to convert a sample EPUB to PDF and extract Markdown from a PDF you already have.

Frequently Asked Questions about document-conversion

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert an EPUB to PDF for offline reading?▼

To convert EPUB to PDF, this skill uses Pandoc with a sandboxed xelatex engine to produce readable PDFs, falling back to Calibre if the document structure is complex.

Can I extract Markdown from a PDF for AI ingestion?▼

Yes, you can extract Markdown from PDF for AI ingestion using Docling within an isolated Python virtual environment, ensuring safe data handling and structured output.

What is the best way to convert DOCX to HTML or JSON?▼

The best way to convert DOCX to HTML or JSON involves using established conversion pipelines that transform Office formats into structured data suitable for downstream applications.

Does this document conversion approach require installing Pandoc and Calibre?▼

Yes, this approach requires explicit toolchains including Pandoc with a sandboxed LaTeX engine and Calibre as a fallback to validate output integrity across various formats.

Why does EPUB to PDF conversion fail on complex documents?▼

EPUB to PDF conversion fails when standard tools cannot parse complex structures, requiring Calibre as a fallback mechanism to handle the formatting and produce valid output.

Related Skills

Explore More Content & Communication Skills→
Team-CommonlyTeam-Commonly
1.3k

pandic-office

Convert Markdown documents to PDF, DOCX, EPUB, and HTML using pandoc.

Official
Intermediate
groundnutygroundnuty

analyze-paper

Extract metadata and generate structured markdown notes from research paper PDFs.

Community
Intermediate
omerakbenomerakben
1

canvas-code-execution

Execute Python and JavaScript code securely in a sandboxed Canvas environment.

Community
Advanced
skaile-aiskaile-ai

use-docling

Convert and extract content from local documents using the docling CLI.

Official
Intermediate