Markit Markdown Converter
Convert PDFs, Office files, URLs, and media into clean markdown via markit-ai CLI or TypeScript SDK for docs and agent context.
Overview
Markit Markdown Converter is an agent skill most often used in Build (also Idea research, Grow content) that documents markit-ai CLI and SDK flows to convert files, URLs, and media into markdown.
Install
npx skills add https://github.com/aradotso/trending-skills --skill markit-markdown-converterWhat is this skill?
- CLI and TypeScript/Node library (markit-ai) with pluggable converters
- Formats: PDF, DOCX, PPTX, XLSX, HTML, EPUB, Jupyter, CSV, JSON, YAML, ZIP, URLs, Wikipedia
- Media path: images (EXIF + AI description) and audio (metadata + AI transcription) with LLM API keys
- OpenAI, Anthropic, and OpenAI-compatible LLM hooks for AI enrichment
- Triggers cover install, plugin authoring, and in-project SDK usage
Adoption & trust: 751 installs on skills.sh; 31 GitHub stars; 1/3 security scanners passed (skills.sh audits).
What problem does it solve?
You have PDFs, decks, URLs, or recordings stuck outside your markdown repo and manually copying text wastes hours.
Who is it for?
Indie builders building doc sites, agent knowledge bases, or content pipelines from mixed file types.
Skip if: Builders who only need in-IDE markdown preview with no batch conversion, or air-gapped workflows that cannot use network or LLM APIs for media.
When should I use this skill?
convert PDF to markdown, turn a DOCX into markdown, extract markdown from a URL, convert images or audio to markdown with AI, use markit to convert files, install markit CLI, write a markit plugin, or use markit as a lib
What do I get? / Deliverables
You produce consistent markdown files or strings via markit commands or TypeScript APIs, optionally enriched with LLM summaries or transcripts.
- Markdown output files or strings from CLI conversion
- TypeScript SDK integration snippets for custom plugins
- Normalized text from URLs and office formats for downstream agents
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Build docs is where raw assets become repo-ready markdown; markit is the ingestion bridge for solo builders. Docs subphase captures file-to-markdown pipelines that feed READMEs, knowledge bases, and RAG corpora—not live app code.
Where it fits
Pull a competitor landing page and a Wikipedia article into markdown for positioning notes.
Convert a customer PDF spec and Jupyter notebook into repo docs before implementation.
Transcribe a podcast MP3 to markdown draft for your newsletter using an Anthropic or OpenAI key.
How it compares
Focused markit-ai integration skill—not a general document editor or Obsidian plugin guide.
Common Questions / FAQ
Who is markit-markdown-converter for?
Solo developers and content-heavy products using Claude Code or Cursor who want repeatable PDF, URL, and media-to-markdown conversion with markit-ai.
When should I use markit-markdown-converter?
In Build docs when ingesting specs; in Idea research when archiving competitor URLs; in Grow content when turning webinars or audio into editable posts.
Is markit-markdown-converter safe to install?
Review the Security Audits panel on this page and treat LLM-backed conversion as sending document excerpts to configured API providers.
SKILL.md
READMESKILL.md - Markit Markdown Converter
# markit-markdown-converter > Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection. markit converts almost anything to markdown: PDFs, Word docs, PowerPoint, Excel, HTML, EPUB, Jupyter notebooks, RSS feeds, CSV, JSON, YAML, images (with EXIF + AI description), audio (with metadata + AI transcription), ZIP archives, URLs, Wikipedia pages, and source code files. It works as a CLI tool and as a TypeScript/Node.js library, supports pluggable converters, and integrates with OpenAI, Anthropic, and any OpenAI-compatible LLM API. --- ## Installation ```bash # Global CLI npm install -g markit-ai # Or as a project dependency npm install markit-ai # bun add markit-ai # pnpm add markit-ai ``` --- ## CLI Quick Reference ```bash # Convert a file markit report.pdf markit document.docx markit slides.pptx markit data.xlsx markit notebook.ipynb # Convert a URL markit https://example.com/article markit https://en.wikipedia.org/wiki/Markdown # Convert media (requires LLM API key for AI features) markit photo.jpg markit recording.mp3 markit diagram.png -p "Describe the architecture and data flow" markit receipt.jpg -p "List all line items with prices as a table" # Output options markit report.pdf -o report.md # Write to file markit report.pdf -q # Raw markdown only (great for piping) markit report.pdf --json # Structured JSON output # Read from stdin cat file.pdf | markit - # Pipe output markit report.pdf | pbcopy markit data.xlsx -q | some-other-tool # List supported formats markit formats # Configuration markit init # Create .markit/config.json markit config show # Show resolved config markit config get llm.model markit config set llm.provider anthropic markit config set llm.model claude-haiku-4-5 # Plugins markit plugin install npm:markit-plugin-dwg markit plugin install git:github.com/user/markit-plugin-ocr markit plugin install ./my-plugin.ts markit plugin list markit plugin remove dwg # Agent integration markit onboard # Adds usage instructions to CLAUDE.md ``` --- ## AI / LLM Configuration Images and audio always get free metadata extraction. AI-powered description and transcription requires an API key. ```bash # OpenAI (default) export OPENAI_API_KEY=sk-... markit photo.jpg # Anthropic export ANTHROPIC_API_KEY=sk-ant-... markit config set llm.provider anthropic markit photo.jpg # OpenAI-compatible APIs (Ollama, Groq, Together, etc.) markit config set llm.apiBase http://localhost:11434/v1 markit config set llm.model llama3.2-vision markit photo.jpg ``` `.markit/config.json` (created by `markit init`): ```json { "llm": { "provider": "openai", "apiBase": "https://api.openai.com/v1", "model": "gpt-4.1-nano", "transcriptionModel": "gpt-4o-mini-transcribe" } } ``` Environment variables always override config file values. Never store API keys in the config file — use env vars. | Provider | Env Vars | Default Vision Model | |-------------|---------------------------------------|-----------------------| | `openai` | `OPENAI_API_KEY`, `MARKIT_API_KEY` | `gpt-4.1-nano` | | `anthropic` | `ANTHROPIC_API_KEY`, `MARKIT_API_KEY` | `claude-haiku-4-5` | --- ## SDK Usage ### Basic File and URL Conversion ```typescript import { Markit } from "markit-ai"; const markit = new Markit(); // Convert a file by path const { markdown } = await markit.convertFile("report.pdf"); console.log(markdown); //