Fast, clean web research: search with an AI answer and cited sources. Trigger phrases: research this, web search, look up, tavily, find sources.
npx skills add https://github.com/Anil-matcha/awesome-muse-connectors --skill tavily
Give any Muse fast, clean web research: one call returns an AI-generated answer plus ranked sources with snippets. Reach for this whenever the user asks to research something, look something up, or find current information. It beats raw browsing for quick factual grounding.
All commands go through bin/tavily.py:
bin/tavily.py search --query "who won the 2026 supernova challenge" --max-results 5
Output is the AI answer first, then per-result title, URL, and a content snippet.
tavily (credential is collected as custom.tavily)credentials.request_api_access): a Tavily API key (tavily.com), pasted once into the hosted formapi.tavily.combin/tavily.py search --query "test" --max-results 1 (must return an answer and results)max-results small (default 5); each result costs tokens twice (fetch + read).bin/tavily.py). Do not print, log, or transmit the token value.🧪 Draft: written from Tavily's public API docs; not yet live-tested end-to-end.
Take anil-matcha/tavily from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.