---

name: doc-converter description: Convert documents between formats — Word, PDF, HTML, Markdown, LaTeX via pandoc type: semantic user-invocable: true semantic: skillVersion: 1 permissions: graph: [read, write] memory: [recall, remember] assertions: - predicate: "doc:converted" requireProof: false queries: - predicate: "doc:converted" scope: agent - predicate: "doc:conversion_context" scope: agent allowedTools: ["*"] metadata: mayros: requires: bins: [pandoc]

doc-converter

Universal document converter powered by pandoc. Converts between 43+ input formats and 57+ output formats including Word, PDF, HTML, Markdown, LaTeX, EPUB, and more.

Installation

• macOS: brew install pandoc
• Ubuntu/Debian: sudo apt install pandoc
• Windows: winget install JohnMacFarlane.Pandoc
• Check version: pandoc --version (3.x recommended)

For PDF output you also need a LaTeX engine:

• macOS: brew install basictex
• Ubuntu/Debian: sudo apt install texlive-latex-base

Core Conversions

# Markdown -> Word (.docx)
pandoc input.md -o output.docx

# Word -> Markdown
pandoc input.docx -o output.md

# Markdown -> PDF (requires LaTeX: brew install basictex)
pandoc input.md -o output.pdf

# HTML -> Markdown
pandoc input.html -t markdown -o output.md

# Markdown -> HTML (standalone with CSS)
pandoc input.md -s -o output.html

# LaTeX -> Word
pandoc input.tex -o output.docx

# Word -> PDF
pandoc input.docx -o output.pdf

# CSV -> HTML table
pandoc input.csv -f csv -o output.html

# EPUB -> Markdown
pandoc input.epub -o output.md

# Multiple files -> single document
pandoc chapter1.md chapter2.md chapter3.md -o book.docx

Advanced Options

# With table of contents
pandoc input.md --toc -o output.pdf

# Custom template
pandoc input.md --template=template.tex -o output.pdf

# With metadata
pandoc input.md --metadata title="My Doc" --metadata author="Name" -o output.docx

# Extract media from docx
pandoc input.docx --extract-media=./media -o output.md

# Reference doc for styling
pandoc input.md --reference-doc=styled.docx -o output.docx

# List supported formats
pandoc --list-input-formats
pandoc --list-output-formats

Supported Formats

Input formats (43+): markdown, docx, html, latex, epub, rst, org, mediawiki, csv, json, textile, opml, docbook, jats, bibtex, biblatex, commonmark, gfm, creole, tikiwiki, twiki, haddock, native, and more.

Output formats (57+): docx, pdf, html, latex, epub, pptx, rst, asciidoc, revealjs, beamer, odt, rtf, plain, man, texinfo, docbook, jats, opml, icml, ms, native, and more.

Safety

• Show source format, target format, and file paths before converting
• Warn if the output file already exists to prevent accidental overwrites
• Confirm before large batch conversions (multiple input files)

Semantic Integration

• Use skill_assert with doc:converted to record each successful conversion
• Use skill_memory_context to recall previous conversion history for the agent
• Query doc:conversion_context to retrieve conversion metadata (formats, paths)