Markdown Converter
Turn PDFs, Office files, spreadsheets, and web exports into clean Markdown so your coding agent can read, summarize, and refactor them without manual copy-paste.
Overview
Markdown Converter is an agent skill most often used in Build (also Idea research and Grow content) that converts PDF, Office, web, media, and archive inputs to Markdown via `uvx markitdown` for LLM processing.
Install
npx skills add https://github.com/intellectronica/agent-skills --skill markdown-converterWhat is this skill?
- Runs via `uvx markitdown` with no local install—stdout, `-o` file output, or stdin pipes
- Supports documents (PDF, Word, PowerPoint, Excel), web/data (HTML, CSV, JSON, XML), media (image EXIF+OCR, audio+transcr
- Optional Azure Document Intelligence (`-d`, `-e`) and third-party plugins (`--use-plugins`, `--list-plugins`) for harder
- Extension and MIME hints (`-x`, `-m`, `-c`) when piping unknown buffers into the converter
- Supports document, web/data, media, and archive families including PDF, DOCX, PPTX, XLSX, HTML, CSV, JSON, XML, images,
- CLI exposes optional Azure Document Intelligence (`-d`) and third-party plugin flags (`--use-plugins`, `--list-plugins`)
Adoption & trust: 1.4k installs on skills.sh; 270 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have specs, reports, or spreadsheets locked in binary formats your agent cannot search, diff, or edit as Markdown.
Who is it for?
Solo builders ingesting client PDFs, legacy Word specs, Excel data sheets, or HTML exports into a repo or chat context before coding or writing docs.
Skip if: Builders who only need quick human reading without Markdown, or teams that require guaranteed layout fidelity instead of text-oriented conversion.
When should I use this skill?
Converting PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls), HTML, CSV, JSON, XML, images (EXIF/OCR), audio (transcription), ZIP archives, YouTube URLs, or EPub to Markdown for LLM processing or text analysis.
What do I get? / Deliverables
You get a `.md` file or stdout stream ready for agent summarization, doc migration, and text analysis—optionally with Azure Document Intelligence or plugins for difficult layouts.
- Markdown file or stdout stream from source document
- Agent-ready plain text suitable for summarization and analysis
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Converting source files into Markdown is a core documentation and knowledge-ingest step while you are building—feeding specs, legacy docs, and data exports into agent workflows. The docs subphase is where solo builders normalize heterogeneous files into text agents can index, quote, and transform alongside READMEs and internal guides.
Where it fits
Convert competitor PDF whitepapers and annual reports to Markdown before your agent summarizes positioning and feature gaps.
Turn a stakeholder Word brief into Markdown so you can diff scope changes and feed a prototype checklist to your agent.
Batch-convert internal PowerPoint architecture decks and Excel API matrices into repo docs your coding agent can cite during implementation.
Extract Markdown from webinar slide exports and YouTube-linked sources to draft blog posts or lifecycle emails without retyping slides.
Re-ingest updated PDF runbooks or CSV incident exports as Markdown when you refresh on-call documentation after production changes.
How it compares
Use this skill for one-shot file-to-Markdown conversion via MarkItDown—not as a live MCP document server or a full docs-site generator.
Common Questions / FAQ
Who is markdown-converter for?
Solo and indie builders using Claude Code, Cursor, or Codex who need PDFs, Office files, spreadsheets, and similar assets as Markdown for agents to process.
When should I use markdown-converter?
During Build when normalizing specs and exports into docs; in Idea when turning research PDFs into searchable text; and in Grow when repurposing decks or reports into content workflows—whenever MarkItDown-style conversion beats manual copy-paste.
Is markdown-converter safe to install?
Treat it like any shell-invoking skill: review what files you pass in and check the Security Audits panel on this Prism page before running conversions on sensitive documents.
SKILL.md
READMESKILL.md - Markdown Converter
# Markdown Converter Convert files to Markdown using `uvx markitdown` — no installation required. ## Basic Usage ```bash # Convert to stdout uvx markitdown input.pdf # Save to file uvx markitdown input.pdf -o output.md uvx markitdown input.docx > output.md # From stdin cat input.pdf | uvx markitdown ``` ## Supported Formats - **Documents**: PDF, Word (.docx), PowerPoint (.pptx), Excel (.xlsx, .xls) - **Web/Data**: HTML, CSV, JSON, XML - **Media**: Images (EXIF + OCR), Audio (EXIF + transcription) - **Other**: ZIP (iterates contents), YouTube URLs, EPub ## Options ```bash -o OUTPUT # Output file -x EXTENSION # Hint file extension (for stdin) -m MIME_TYPE # Hint MIME type -c CHARSET # Hint charset (e.g., UTF-8) -d # Use Azure Document Intelligence -e ENDPOINT # Document Intelligence endpoint --use-plugins # Enable 3rd-party plugins --list-plugins # Show installed plugins ``` ## Examples ```bash # Convert Word document uvx markitdown report.docx -o report.md # Convert Excel spreadsheet uvx markitdown data.xlsx > data.md # Convert PowerPoint presentation uvx markitdown slides.pptx -o slides.md # Convert with file type hint (for stdin) cat document | uvx markitdown -x .pdf > output.md # Use Azure Document Intelligence for better PDF extraction uvx markitdown scan.pdf -d -e "https://your-resource.cognitiveservices.azure.com/" ``` ## Notes - Output preserves document structure: headings, tables, lists, links - First run caches dependencies; subsequent runs are faster - For complex PDFs with poor extraction, use `-d` with Azure Document Intelligence