Outils

Converts PDF, Word, Excel, PowerPoint, HTML, images, audio and more into Markdown that keeps headings, lists and tables, ready for LLMs to read and analyze. Maintained by Microsoft; requires Python 3.10+.

From Microsoft: converts PDF, Word, Excel, PowerPoint, HTML and other files or URLs to Markdown so agents can read and search them. A single convert_to_markdown tool over STDIO or local HTTP.

Anthropic's document skills, the implementation behind Claude's file features: create, edit and analyze Word, Excel, PowerPoint and PDF files, including tracked changes, comments, formulas and form filling. Source-available, not under an open-source license.

From Firecrawl: converts Word, PowerPoint, Excel, PDF, EPUB, RTF and more into clean Markdown locally in milliseconds, keeping headings, tables, footnotes and formulas so agents can read attachments. Needs Node.js; optional Firecrawl cloud OCR for scans uploads the whole file.

MiniMax's official skill plugin with dev guides for frontend, full-stack, Android, iOS, Flutter, React Native and GLSL shaders, plus PDF, PowerPoint, Excel and Word document skills and image, video and music generation. Media skills need a MiniMax API key. Still in beta.

Open-source PDF table extraction with a camelot CLI: exports tables from financial reports, bank statements and statistical reports to Excel, CSV or Markdown, with an accuracy score. Needs Python 3.10+; handles text-based PDFs by default, scans need the ml and ocr extras. Double-check results.

Local LLM-powered document translator for PDF, Word, Excel, EPUB, SRT subtitles and more; Word and Excel keep their formatting, glossaries can be built automatically, and agents can submit jobs via MCP. Needs uv and an OpenAI-compatible API key; translated PDFs lose the original layout.

Converts PDF, Word, PowerPoint, Excel, EPUB, web pages and images to clean Markdown locally, keeping page anchors, tables and two-column reading order, with full-text search across folders. Formerly pdf-reader-mcp; no uploads, no API key. Needs Node.js 18+; OCR for scans needs tesseract.

Runs LibreOffice as a persistent server so unoconvert can batch-convert Word, Excel, PowerPoint, ODF and PDF, handling about 2-4x as many documents in the same time as cold-starting LibreOffice each time. Install LibreOffice first and use its bundled Python; officially tested on Linux only.

130+ office skills for contract review, NDAs, job descriptions, offer letters, invoices and expenses, meeting notes, email, and Excel, PowerPoint and PDF work. Writing skills work as-is; Airtable, Slack and other automations need those services. Legal and finance output needs expert review.

DeepL's official CLI: translate text and PDF, Word, PowerPoint and Excel documents while keeping formatting, with glossaries and translation memory. Needs a DeepL API key (free plan available); install from source with Node.js 24.15+. Have legal translations reviewed.