Tavily Search
- 51 installs
- 186 repo stars
- Updated August 4, 2026
- aws-samples/sample-strands-agent-with-agentcore
tavily-search is a Claude skill that runs AI-powered web search and extracts clean readable content from URLs with cited claims.
About
This skill gives an agent Tavily's AI-powered web search plus a content-extraction tool. tavily_search returns summarized results with tunable depth and topic, and tavily_extract pulls clean readable content from specific URLs. A developer uses it when an assistant needs AI-curated search or time-sensitive news lookups. It requires wrapping factual claims in cite tags.
- AI-powered web search that returns relevant, summarized results
- tavily_extract pulls clean readable content from one or more URLs
- Search depth and topic (general/news/research) are tunable; excels at recent information
Tavily Search by the numbers
- 51 all-time installs (skills.sh)
- Ranked #7,162 of 16,546 AI & Agent Building skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
tavily-search capabilities & compatibility
- Capabilities
- web search · content extraction
- Use cases
- web search · research · web scraping
- Pricing
- Bring your own API key
What tavily-search says it does
AI-powered web search and content extraction
Tavily excels at recent information and news — prefer it for time-sensitive queries.
npx skills add https://github.com/aws-samples/sample-strands-agent-with-agentcore --skill tavily-searchAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 51 |
|---|---|
| repo stars | ★ 186 |
| Last updated | August 4, 2026 |
| Repository | aws-samples/sample-strands-agent-with-agentcore ↗ |
What it does
Let an agent run Tavily AI web search and extract clean content from URLs, with cited claims.
Who is it for?
AI-curated web research and time-sensitive news, plus extracting full content from specific URLs.
Skip if: Non-web tasks or deep multi-source report writing.
When should I use this skill?
The agent needs AI-curated search results or to extract content from a URL.
What you get
Summarized Tavily search results and extracted page content, with each factual claim cited.
By the numbers
- 2 tools (search and extract)
- 3 topic modes: general/news/research
Files
Tavily AI Search
Available Tools
- tavily_search(query, search_depth?, topic?): AI-powered web search that returns relevant, summarized results.
query(string, required): Search querysearch_depth(string, optional, default: "basic"): "basic" for quick lookups, "advanced" for comprehensive researchtopic(string, optional, default: "general"): "general", "news", or "research"
- tavily_extract(urls, extract_depth?): Extract clean, readable content from one or more web URLs.
urls(string, required): Comma-separated URLs to extract content fromextract_depth(string, optional, default: "basic"): "basic" or "advanced"
Usage Guidelines
- Use
tavily_searchfor research queries that benefit from AI-curated results. - Set
search_depthto "advanced" for comprehensive research, "basic" for quick lookups. - Set
topicto "news" for recent events, "research" for academic/technical topics. - Use
tavily_extractto get full page content from specific URLs found in search results. - Tavily excels at recent information and news — prefer it for time-sensitive queries.
Citation Format
When presenting information from search results, wrap every specific claim in <cite> tags:
<cite source="SOURCE_TITLE" url="URL">claim text</cite>Rules:
- Cite factual claims, statistics, quotes, and specific information from search results.
- The
sourceattribute should contain the title or name of the source. - The
urlattribute should contain the source URL when available. - Do NOT cite your own reasoning or general knowledge.
- If search results don't contain relevant information, inform the user rather than guessing.
- Use the minimum number of citations necessary to support claims.
Related skills
Setup Matt Pocock SkillsScaffold the per-repo configuration that Matt Pocock’s engineering agent skills rely on so they understand the issue tracker, triage labels, and domain documentation la495k196k
Lark AppsConnect Claude, Cursor or custom agents directly to Lark (Feishu) for messaging, document automation, approval workflows and enterprise data access.402k
CavemanSlash token usage by roughly 75% while keeping every technical detail intact when working with Claude Code, Cursor or similar agents.391k94.7k
Lark Skill MakerQuickly turn any Lark/Feishu OpenAPI call or multi-step workflow into a reusable agent skill with its own SKILL.md.386k16k
Running Claude Code Via Litellm CopilotRun Claude Code at a fraction of the cost by routing requests through LiteLLM to the GitHub Copilot Chat API.270k72
Codex PetGenerate a complete Codex Pet spritesheet and metadata from one reference image without needing an OpenAI key or Codex Pro.246k10FAQ
What is tavily_extract for?
It extracts clean, readable content from one or more web URLs, useful for pages found in search results.
How do I tune the search?
Set search_depth to basic or advanced and topic to general, news, or research.