search
Web search with LLM-optimized results, relevance scoring, and flexible filtering.
What it does
- ultra-fast: Real-time chat, autocomplete
- fast: Need chunks but latency matters
- basic: General-purpose, balanced
- advanced: Precision matters (default recommendation)
- Keep queries under 400 characters - Think search query, not prompt
- Break complex queries into sub-queries - Better results than one massive query
- Use includedomains to focus on trusted sources
Requirements & configuration
- Alternative: API Key
- If you prefer using an API key, get one at https://tavily.com and add to ~/.claude/settings.json:
- fast: Need chunks but latency matters
Configuration: TAVILY_API_KEYYYYY
Derived from the skill's own SKILL.md documentation · extracted 2026-07-23
Web search with LLM-optimized results, relevance scoring, and flexible filtering.
Source
Repository: https://github.com/tavily-ai/skills
search FAQ
What does the search skill do?
Search the web using Tavily's LLM-optimized search API. Returns relevant results with content snippets, scores, and metadata. Use when you need to find web content on any topic without writing code. ultra-fast: Real-time chat, autocomplete fast: Need chunks but latency matters
What does search require?
Alternative: API Key If you prefer using an API key, get one at https://tavily.com and add to ~/.claude/settings.json: fast: Need chunks but latency matters Configuration keys: TAVILY_API_KEY, YYYY.
How do I install search?
Run: npx -y skills add https://github.com/tavily-ai/skills --skill search --agent claude-code — the source lives at github.com/tavily-ai/skills.
Maintain search?
Let people know it's listed here — add the badge (live metrics, light/dark aware) or a plain link to your README or docs.
[](https://getagentictools.com/skills/tavily-ai-skills-search?ref=badge) npx agentictools info skills/tavily-ai-skills-search The second line is the CLI lookup for this page — handy in READMEs and docs.