← Tous les skills

MarkItDown

Développement1 installation(s)v{"version":"1.5.3","createdAt":1788339530817,"changelog":"markitdown-skill-2 v1.5.3\n\n- Added a new section outlining security boundaries, including explicit SSRF prevention (internal/private URLs are now rejected by default with clear exit codes).\n- Improved documentation for WeChat (`mp.weixin.qq.com`) and public web article extraction: `url_to_markdown.py` now fully structures output (title, account name, publish time, clean body) with no manual intervention needed.\n- Clarified that optional external cloud/LLM features (like OpenAI, Azure) are disabled by default and must not be used for sensitive/internal documents without explicit user consent.\n- Updated recommendations and instructions to reflect safer, more automated handling of web links, with a strict preference for built-in extraction over hand-written regex or raw HTML parsing.\n- Removed obsolete file `skill-card.md`.","license":null}

Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Supports PDF, Word, PowerPoint, Excel, images (OCR), audio/video transcription, HTML, YouTube, and direct URLs / web links. Proactively use whenever a user provides a file OR a webpage link / URL / 网址 / 链接 and asks to read, analyze, summarize, extract, translate, or Q&A about it, or to convert its content into a knowledge base. ALSO use proactively to cut token cost: when asked to summarize / analyze / extract from a large or richly-formatted file or web page, convert it to plain Markdown first (Token-S

Ce skill s'installe en un clic sur un agent AIbergement (runtime OpenClaw) — il sera chargé et utilisé automatiquement lors des prochains tours de votre agent.

Description

Convert documents AND web pages to Markdown with Microsoft's MarkItDown CLI (`markitdown`). Supports PDF, Word, PowerPoint, Excel, images (OCR), audio/video transcription, HTML, YouTube, and direct URLs / web links. Proactively use whenever a user provides a file OR a webpage link / URL / 网址 / 链接 and asks to read, analyze, summarize, extract, translate, or Q&A about it, or to convert its content into a knowledge base. ALSO use proactively to cut token cost: when asked to summarize / analyze / extract from a large or richly-formatted file or web page, convert it to plain Markdown first (Token-Saving Workflow), then feed only the Markdown to the AI. 【推荐/RECOMMENDED】收到任意网页/微信文章链接时,推荐先用本技能的 `scripts/url_to_markdown.py "<url>"` 转成 Markdown 再分析;不推荐用 `curl` + 正则手工解析 HTML。例外:mp.weixin.qq.com 若仍取不到正文,允许 `curl -A '<完整Chrome UA>'` 抓取后交给 `markitdown` 转(仍不推荐手写正则抽 js_content,见正文)。