skills/jb-markit/SKILL.md
Use when converting PDFs, Office/iWork docs, webpages, feeds, spreadsheets, JSON/YAML, GitHub pages, images, audio, archives, or stdin to markdown.
npx skillsauth add bjesuiter/skills jb-markitInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Use markit to convert almost anything into markdown.
Tested and adjusted against
markit 0.5.0.
bun add -g markit-ai
markit <source> -q → raw markdown onlymarkit <source> --json → structured output for parsingmarkit <source> -o output.md → write markdown to a filemarkit <source> -i extracted-images/ → save extracted images to a directorycat file.pdf | markit - → read from stdin# Documents
markit report.pdf
markit document.docx
markit slides.pptx
markit data.xlsx
markit proposal.pages
markit deck.key
markit budget.numbers
# Web
markit https://example.com/article
markit https://en.wikipedia.org/wiki/Markdown
markit https://github.com/user/repo
markit https://gist.github.com/user/abcdef
# Data / config
markit data.csv
markit config.json
markit schema.yaml
# Raw markdown or JSON
markit report.pdf -q
markit report.pdf --json
# Save output
markit report.pdf -o report.md
Images and audio include metadata extraction by default. AI descriptions/transcriptions require an API key.
# OpenAI (default)
export OPENAI_API_KEY=sk-...
markit photo.jpg
markit recording.mp3
# Anthropic
markit config set llm.provider anthropic
export ANTHROPIC_API_KEY=sk-ant-...
markit photo.jpg
# Focus image description / extraction
markit receipt.jpg -p "List all line items with prices as a table"
markit whiteboard.jpg -p "Extract all text verbatim"
markit diagram.png -p "Describe the architecture and data flow"
# Save extracted images alongside markdown output
markit report.pdf -i ./report-images -o report.md
markit supports PDFs, DOCX, PPTX, XLSX, HTML, EPUB, Jupyter notebooks, RSS/Atom, CSV/TSV, JSON, YAML, XML/SVG, Pages, Keynote, Numbers, plain text, many code files, images, audio, ZIP archives, GitHub URLs, Wikipedia pages, and general URLs.
Use markit formats to see what the installed version supports.
markit init
markit config show
markit config get llm.model
markit config set llm.provider anthropic
markit config set llm.apiBase http://localhost:11434/v1
Config file: .markit/config.json
Env vars override config. Common keys:
OPENAI_API_KEYANTHROPIC_API_KEYMARKIT_API_KEYmarkit onboard
Adds markit usage instructions to CLAUDE.md or AGENTS.md.
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
Plugin converters run before built-ins, so plugins can add new formats or override existing converters.
-q when you want clean markdown in pipelines.--json when another tool or agent will parse the result.-p to constrain image description/extraction to the exact task.-i when you want extracted images written to a durable folder.-o when the conversion should become a durable artifact in the repo.testing
Use when the user mentions Clawpatch/clawpatch.ai, semantic feature review, repo-wide AI audit, persistent findings, or clawpatch init/map/review/report/fix/revalidate.
development
Use when the user asks for autoreview, Codex/Claude second-model review, or final review of dirty changes, a branch, commit, or PR before ship.
testing
Use when the user asks to cut, prepare, publish, tag, or verify a release, especially npm/package releases.
tools
Use when adding, writing, fixing, or exposing a script for the Tuna macOS launcher.