pandoc-converter
Pandoc Converter
Convert documents between common formats using Pandoc.
Quick Start
# Basic conversion (format auto-detected from extensions)
python scripts/convert.py input.md output.docx
# Specify output format only
python scripts/convert.py document.md --to html
# Check if Pandoc is installed
python scripts/convert.py --check
# List supported formats
python scripts/convert.py --formats
Supported Formats
Document formats (read/write): markdown, html, docx, latex, epub, rtf, pptx, pdf
Data formats (read only): csv, tsv, xlsx
Markdown variants: gfm (GitHub), commonmark
For detailed compatibility, see references/format-compatibility.md.
Common Conversions
| From | To | Command |
|---|---|---|
| Markdown | Word | python scripts/convert.py doc.md doc.docx |
| Markdown | python scripts/convert.py doc.md doc.pdf |
|
| Markdown | HTML | python scripts/convert.py doc.md doc.html |
| Word | Markdown | python scripts/convert.py doc.docx doc.md |
| CSV | HTML table | python scripts/convert.py data.csv data.html |
| LaTeX | python scripts/convert.py paper.tex paper.pdf |
Options
| Option | Description |
|---|---|
--from <fmt> |
Override input format detection |
--to <fmt> |
Specify output format (if no output file) |
--standalone |
Include document headers/footers |
--toc |
Add table of contents |
--pdf-engine <eng> |
PDF engine: pdflatex, xelatex, lualatex |
Additional Pandoc options pass through directly.
Workflow
- Check installation: Run
python scripts/convert.py --check - If not installed: Follow the installation instructions provided
- Convert: Run the conversion with input and output files
- Present result: Provide the converted file to the user
Installation (if needed)
The script provides installation guidance, but here's a summary:
# macOS
brew install pandoc
# Ubuntu/Debian
sudo apt-get install pandoc
# For PDF output, also install LaTeX:
# macOS: brew install --cask mactex-no-gui
# Ubuntu: sudo apt-get install texlive-xetex
Limitations
- CSV/TSV/XLSX: Input only (converts to tables in other formats)
- PDF output: Requires LaTeX installation
- PPTX: Text extraction works; complex layouts may simplify
- Complex formatting: Some features may not transfer between formats
More from jrajasekera/claude-skills
openrouter-api
OpenRouter API integration for unified access to 400+ LLM models from 70+ providers. Use when building applications that need to call OpenRouter's API for chat completions, streaming, tool calling, structured outputs, or model routing. Triggers on OpenRouter, model routing, multi-model, provider fallbacks, or when users need to access multiple LLM providers through a single API.
18sqlite-optimization
Optimize SQLite database performance through configuration, schema design, indexing, and query tuning. Use when users ask to improve SQLite speed, reduce latency, optimize queries, configure PRAGMAs, fix slow queries, handle concurrency, optimize writes/inserts, or tune SQLite for production. Triggers on mentions of SQLite performance, slow queries, PRAGMA settings, WAL mode, indexing strategies, bulk inserts, or database maintenance (VACUUM, ANALYZE).
15venice-ai-api
Venice.ai API integration for privacy-first AI applications. Use when building applications with Venice.ai API for chat completions, image generation, video generation, text-to-speech, speech-to-text, or embeddings. Triggers on Venice, Venice.ai, uncensored AI, privacy-first AI, or when users need OpenAI-compatible API with uncensored models.
14z-ai-api
|
10codex-review
Use after creating design docs or implementation plans to get cross-agent review from Codex. Auto-triggers for non-trivial plans; asks first for simple changes. Captures feedback, addresses critical issues, presents minor concerns for user decision.
9article-extractor
Extract clean article content from URLs and save as markdown. Triggers when user provides a webpage URL and wants to download it, extract content, get a clean version without ads, capture an article for offline reading, save an article, grab content from a page, archive a webpage, clip an article, or read something later. Handles blog posts, news articles, tutorials, documentation pages, and similar web content. Supports Wayback Machine for dead links or paywalled content. This skill handles the entire workflow - do NOT use web_fetch or other tools first, just call the extraction script directly with the URL.
7