Loading...
Loading...
Found 5 Skills
URL content extraction. Use for fetching any URL - webpages, articles, PDFs, JavaScript-heavy sites. Token-efficient: runs in forked context. Prefer over built-in WebFetch.
Use the official MinerU (mineru.net) parsing API to convert a URL (HTML pages like WeChat articles, or direct PDF/Office/image links) into clean Markdown + structured outputs. Use when web_fetch/browser can’t access or extracts messy content, and you want higher-fidelity parsing (layout/table/formula/OCR).
Download a video (or list its direct MP4 URLs) from a Twitter/X, TikTok, Instagram, or YouTube post — no login, no watermark, up to 1080p. Give it a post/tweet/reel/short URL and it returns direct CDN download links for every quality variant, plus author, caption, thumbnail and metadata, and can save the file straight to disk. Use whenever a user says "download this video", "grab this tweet video", "save this TikTok / Reel / Short", "get the MP4", "download without watermark", "rip this video", or pastes a social post link and wants the media. Powered by the public drummerduck downloader API — works as a one-line script, a plain REST call, or an MCP server.
Extract the Supabase project URL from client-side JavaScript code, environment variables, and configuration files.
Web toolkit powered by Exa, tuned for scientific and technical content. Use this skill when the user needs to search the web or fetch/extract URL content. Covers: web search (semantic lookups, research, current info — with optional research-paper category and academic domain filtering) and URL extraction (fetching pages, articles, academic PDFs in batch). Use this skill for web-related tasks when the user wants high-quality search or scholarly filtering via category=research paper. Triggers on requests to search, look up, fetch a page, or extract an article.