Loading...
Loading...
Found 9,086 Skills
Comet Native workflow. Used when the user explicitly calls /comet-native, requests to start or resume a Native change, or the entry route leads to Native.
Official Quark Drive Skill, used for file upload/download (supports resumable uploads), file sharing and saving to personal drive, cloud drive file search, album organization, and AI Assistant (file summarization and knowledge Q&A, supporting up to 10,000 files). It is used when users need to operate Quark Drive files or perform identity verification.
Collect listings from Alibaba — title, price, condition, seller, URL. Use when the user wants to collect product or offer listings.
Collect professional services leads from Google Maps — firm name, specialty, address, phone, website, rating. Use when the user wants to prospect lawyers, accountants, consultants, or other professionals.
Search for candidate leads in LinkedIn Recruiter — name, title, location, skills, contact signals. Use when the user wants to find qualified candidates for a role.
Collect products from Tesco — title, price, specs, images, availability. Use when the user wants to research products or collect catalog data.
Collect listings from AliExpress — title, price, condition, seller, URL. Use when the user wants to collect product or offer listings.
Turn customer feedback (usually an email) into discrete GitHub issues. Checks for duplicates, proposes new issues for approval, creates them, and drafts a reply email.
HTX spot market data — ticker / klines / order book / latest trades / currency and symbol metadata.
Helps users discover and install agentic loops (recurring, scheduled AI agents) when they ask "find a loop for X", "is there a loop that…", "install a recurring agent that does X", "schedule an agent to do X", or want a repeating job run on a timer (a daily digest, a competitor watcher, a triage sweep, an every-morning report) — even if they never say the word "loop". Use this to SEARCH the agenticloops.dev directory and INSTALL an existing loop. This is the loop-level analogue of find-skills. For AUTHORING a new loop when none fits, use the fuller `loops` skill.
Search the web with fastCRW and get titles, URLs, and descriptions. Use when you have a question or topic but not a URL — "search for", "find pages about", "look up", "what is", "who is", "latest news on", "find docs for". Own search backend: self-hosted, no API key, no per-query cost, high recall via meta-search aggregation. Step 1 of the crw workflow ladder.
Scrape a single known URL into clean markdown / HTML / links / structured JSON with fastCRW. Use when you already have the URL and want the page content — "scrape", "grab", "fetch", "pull", "read this page", "get the content of". Handles JavaScript-rendered SPAs automatically. Step 2 of the crw workflow ladder.