office-to-md — Claude Code skill: what it does, how to install
office-to-md turns Office documents and PDFs into Markdown files while keeping tables and images. Ideal when an agent needs to read spreadsheets, slide decks, or text files.
no license 1 installs ★ 277 updated 2026-06-20
npx skills add shuyu-labs/WebCode --skill office-to-md -a claude-codeWhat office-to-md does
The skill uses Python scripts to translate DOCX, XLSX, PPTX, and PDF files into structured Markdown. It recognizes heading hierarchies, extracts inline pictures, and formats spreadsheet grids into Markdown tables. You can serve extracted graphics via a local directory or a custom URL.
Processing legacy DOC files strictly requires a working LibreOffice installation on your machine. Without LibreOffice, the companion script doc_converter.py fails immediately. Table parsing in PDF files offers two approaches: fast boundary detection with lines or precise detection based on text coordinates.
The parser handles individual files up to 160MB in size.
What it helps with
- turn spreadsheet sheets from Excel into Markdown tables
- extract text and graphics from PowerPoint presentations
- convert complex PDF documents while preserving headings
- transform legacy Word DOC files into clean text
Example prompts for the agent
- Convert
specification.docxinto Markdown and export its images - Transform the
budget.xlsxsheets into Markdown tables - Parse
deck.pptxinto Markdown while keeping slide order
How to install office-to-md
1Skills CLI (Vercel)
npx skills add shuyu-labs/WebCode --skill office-to-md -a claude-code2Manually: put the files in place
~/.claude/skills/office-to-md/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/office-to-md/
1Skills CLI (Vercel)
npx skills add shuyu-labs/WebCode --skill office-to-md -a codex2Manually: put the files in place
.agents/skills/office-to-md/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add shuyu-labs/WebCode --skill office-to-md -a cursor2Manually: put the files in place
.cursor/skills/office-to-md/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install shuyu-labs/WebCode skills/claude/office-to-md2Manually: put the files in place
.github/skills/office-to-md/SKILL.md1Skills CLI (Vercel)
npx skills add shuyu-labs/WebCode --skill office-to-md -a gemini-cli2Platform CLI
gemini skills install https://github.com/shuyu-labs/WebCode --path skills/claude/office-to-mdManually: put the files in place
.devin/skills/office-to-md/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add shuyu-labs/WebCode --skill office-to-md -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about office-to-md
How to install office-to-md in Claude Code?
Run npx skills add shuyu-labs/WebCode --skill office-to-md -a claude-code. The skill definition will be added to ~/.claude/skills/office-to-md/SKILL.md.
Which file formats are supported?
It parses DOCX, DOC, PDF, XLSX, XLS, and PPTX files with sizes up to 160MB.
Why is LibreOffice required?
LibreOffice is needed specifically to transform legacy DOC files before parsing them with enhanced_parser.py.