SaaS app
Tavily agent skills for Claude Code, Codex and other agents.
- skills
- 84
- official
- 3
- Type
- SaaS app
- Website
- tavily.com
- Official GitHub
- tavily-ai
- Reviews
- See Tavily on Enlisted
Tavily skills, ranked
Ranked by score. Sort bymost stars,trending,newest,recently updated
Official (3 skills)
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 1 | AI-powered web search and content extraction. An agent skill from aws-samples/sample-strands-agent-with-agentcore. | aws-samples/ | 194 | — | ~463 | Automated safety check: Pass | MIT | yesterday |
| 2 | Scaffold a minimal local Deep Agent in Python by following the official quickstart, using provider-native web search instead of Tavily. | langchain-ai/ | 1.3k | — | ~549 | Automated safety check: Notes | MIT | yesterday |
| 3 | Scaffold a minimal local Deep Agent in TypeScript by following the official quickstart, using provider-native web search instead of Tavily. | langchain-ai/ | 1.3k | — | ~548 | Automated safety check: Notes | MIT | yesterday |
Community
| # | Skill | Repository | Stars | Used in | Tokens | Auto-check | Licence | Updated |
|---|---|---|---|---|---|---|---|---|
| 4 | Searches the web through the Tavily API with LLM-friendly output: clean structured results, optional AI-written answers, domain filters, news mode, images and raw content. | allenpeng0705/ | 3.1k | 4 repos | ~2.5k | Automated safety check: Notes | No licence | 6 days ago |
| 5 | Guides building Tavily integrations for web search, URL extraction, site crawling and AI-assisted research in Python or JavaScript agent and RAG projects. | andrewyng/ | 14k | — | ~1.1k | Automated safety check: Pass | MIT | 4 mo ago |
| 6 | A Chinese-language guide and reference for building agents with LangGraph 1.0, from a first ReAct agent through middleware, memory, MCP, RAG and web search. | luochang212/ | 457 | — | ~837 | Automated safety check: Notes | Unknown | 26 days ago |
| 7 | A skill your agent uses when the user wants to fact-check an article or verify factual claims in a document. | MigoXLab/ | 757 | — | ~833 | Automated safety check: Pass | Apache-2.0 | 9 days ago |
| 8 | Web search and content extraction with Tavily and Exa via inference.sh CLI. | EXboys/ | 170 | 3 repos | ~1k | Automated safety check: Pass | MIT | 12 days ago |
| 9 | 9.Osint Conduct deep OSINT research on individuals. An agent skill from smixs/osint-skill. | smixs/ | 140 | — | ~5.5k | Automated safety check: Pass | MIT | 7 mo ago |
| 10 | Builds a cited research base on normal system behavior and adversary abuse patterns before a threat hunt hypothesis gets written. | OTRF/ | 4.7k | — | ~1.3k | Automated safety check: Pass | MIT | 8 mo ago |
| 11 | 双引擎网络搜索：Grok AI 搜索（实时联网+AI分析）+ Tavily 搜索（结构化结果+网页抓取）. An agent skill from ckckck/UltimateSearchSkill. | ckckck/ | 289 | — | ~944 | Automated safety check: Notes | MIT | 6 mo ago |
| 12 | 12.Mysearch DEFAULT search skill for OpenClaw. An agent skill from skernelx/MySearch-Proxy. | skernelx/ | 159 | — | ~1.4k | Automated safety check: Notes | MIT | 6 mo ago |
| 13 | Fetches a web page through a 9Router server's web fetch endpoint and returns it as markdown, plain text or HTML, using one of several extraction providers. | decolua/ | 30k | — | ~941 | Automated safety check: Pass | MIT | 6 days ago |
| 14 | 14.Mysearch Install, verify, debug, and use MySearch MCP/Skill. An agent skill from skernelx/MySearch-Proxy. | skernelx/ | 159 | — | ~3k | Automated safety check: Notes | No licence | 6 mo ago |
| 15 | 股票智能分析技能。输入股票代码（A股/港股/美股），自动完成： 1. An agent skill from liusai0820/Stock-Analysis-Skill. | liusai0820/ | 142 | — | ~904 | Automated safety check: Notes | No licence | 7 mo ago |
| 16 | Runs web, news and public X searches through a 9Router gateway's search endpoint, choosing among providers such as Tavily, Exa, Brave and Perplexity. | decolua/ | 30k | — | ~1k | Automated safety check: Pass | MIT | 6 days ago |
| 17 | Unified web search, page fetching and evidence checking across hundreds of sources, with result verification, a research-dossier mode and vertical search engines. | taxueseek/ | 184 | — | ~1.2k | Automated safety check: Pass | MIT | yesterday |
| 18 | Looks up current company registration rules, industry licences and compliance obligations in China through live web search, tailored to the business profile. | Serein-81/ | 148 | — | ~1.6k | Automated safety check: Notes | No licence | 4 mo ago |
| 19 | 19.Omk Research Multi-level research: built-in knowledge → web search → Tavily deep research API. | KaimingWan/ | 107 | — | ~827 | Automated safety check: Pass | MIT | 6 mo ago |
| 20 | OpenClaw plugin for source-only Routing v2 multi-provider search, completion-order Research with quality quorum and attributed provenance, heading-aware extraction spans, Tavily-first extraction… | robbyczgw-cla/ | 101 | — | ~1.9k | Automated safety check: Notes | MIT | 13 days ago |
| 21 | Guide agents to use Tavily Hikari safely through tvly-hikari. | IvanLi-CN/ | 362 | — | ~287 | Automated safety check: Pass | MIT | today |
| 22 | Wire AG2 beta's shipped tools into an Agent — both provider-native server-side tools (web search, web fetch, code execution, MCP, image generation, memory) and locally-executed common toolkits… | ag2ai/ | 252 | — | ~1.3k | Automated safety check: Pass | Apache-2.0 | 1 mo ago |
| 23 | Searches current Chinese tax laws, rates and policy changes with Tavily web search, prioritizing government sources and flagging outdated or conflicting results. | Serein-81/ | 148 | — | ~997 | Automated safety check: Notes | No licence | 4 mo ago |
| 24 | Runs headless web searches and single-page extraction through the Tavily API from a Python script, returning cited, summarized results without a browser. | LichAmnesia/ | 234 | — | ~1k | Automated safety check: Notes | MIT | 3 mo ago |
| 25 | Run Tavily CLI workflows through a configured Tavily Hikari deployment. | IvanLi-CN/ | 362 | — | ~285 | Automated safety check: Pass | MIT | today |
| 26 | 26.Search Web search with automatic provider fallback (Tavily → DuckDuckGo) | QuantClaw/ | 214 | — | ~308 | Automated safety check: Pass | Apache-2.0 | 2 mo ago |
| 27 | Portable multi-source research with cross-source validation and an offline evidence ledger. | sandbaseai/ | 201 | — | ~1.6k | Automated safety check: Pass | Apache-2.0 | 11 days ago |
| 28 | Crawl bounded sites through Tavily Hikari with tvly-hikari. An agent skill from IvanLi-CN/tavily-hikari. | IvanLi-CN/ | 362 | — | ~200 | Automated safety check: Pass | MIT | today |
| 29 | Guides a policy notification agent through crawling government policy sources, saving them locally, matching them to enterprise profiles and generating notifications. | Serein-81/ | 148 | — | ~1.4k | Automated safety check: Notes | No licence | 4 mo ago |
| 30 | 多源内容采集专家。能从网页、RSS、Tavily搜索、Twitter抓取内容。适用于：信息收集、竞品监控、行业动态追踪。 | charlie-chann/ | 114 | — | ~233 | Automated safety check: Pass | No licence | 24 days ago |
| 31 | Extract URL content through Tavily Hikari with tvly-hikari. An agent skill from IvanLi-CN/tavily-hikari. | IvanLi-CN/ | 362 | — | ~216 | Automated safety check: Pass | MIT | today |
| 32 | 32.Module 1 This skill should be used when a learner is working through Module 1 ("Build an Agent") of the Build-an-Agent workshop and wants help understanding the concepts, notebooks, or code — e.g. | brevdev/ | 143 | — | ~2.7k | Automated safety check: Pass | Apache-2.0 | today |
| 33 | Registers Tavily's keyless remote MCP server, search and extract, for selected NanoClaw agent groups by pinning an mcp-remote bridge and running it through an approval-gated config step. | nanocoai/ | 31k | — | ~1.7k | Automated safety check: Pass | MIT | yesterday |
| 34 | Discover site URLs through Tavily Hikari with tvly-hikari. An agent skill from IvanLi-CN/tavily-hikari. | IvanLi-CN/ | 362 | — | ~199 | Automated safety check: Pass | MIT | today |
| 35 | 35.Web Search Search the public web for up-to-date facts. An agent skill from tmustier/pi-for-excel. | tmustier/ | 434 | — | ~410 | Automated safety check: Pass | MIT | today |
| 36 | 36.Module 1 This skill should be used when a learner is working through Module 1 ("Build an Agent") of the Build-an-Agent workshop and wants help understanding the concepts, notebooks, or code — e.g. | brevdev/ | 143 | — | ~2.7k | Automated safety check: Pass | Apache-2.0 | today |
| 37 | Dispatch copy-lead helpers: Tavily, Codex luna/terra, grok/X, OpenCode DeepSeek, Cursor Grok 4.6 medium-fast. | VKirill/ | 122 | — | ~827 | Automated safety check: Pass | MIT | today |
| 38 | Run multi-step Tavily research through Tavily Hikari with tvly-hikari. | IvanLi-CN/ | 362 | — | ~289 | Automated safety check: Pass | MIT | today |
| 39 | Fetch URL → markdown / text / HTML via KeiRouter /v1/web/fetch using Firecrawl / Jina Reader / Tavily Extract / Exa Contents. | mydisha/ | 147 | — | ~741 | Automated safety check: Pass | MIT | 26 days ago |
| 40 | 40.Tavily Web Web search, content extraction, crawling, and research capabilities using Tavily API | davila7/ | 32k | 7 repos | ~227 | Automated safety check: Pass | MIT | today |
| 41 | 41.Hanzi Browse Delegates a browsing task to a sub-agent running in the USER'S OWN Chrome — the browser they have open right now, already signed into everything. | hanzili/ | 177 | — | ~2.4k | Automated safety check: Pass | Unknown | 5 mo ago |
| 42 | Search the web through Tavily Hikari with tvly-hikari. An agent skill from IvanLi-CN/tavily-hikari. | IvanLi-CN/ | 362 | — | ~233 | Automated safety check: Pass | MIT | today |
| 43 | 43.Tavily Tavily web search, content extraction, and research tools. An agent skill from SafeAI-Lab-X/ClawKeeper. | SafeAI-Lab-X/ | 1k | 2 repos | ~1.2k | Automated safety check: Pass | No licence | 1 mo ago |
| 44 | Automate Tavily tasks via Rube MCP (Composio). An agent skill from ComposioHQ/awesome-claude-skills. | ComposioHQ/ | 77k | 3 repos | ~727 | Automated safety check: Pass | No licence | 19 days ago |
| 45 | Web search via KeiRouter /v1/search using Tavily / Exa / Brave / Serper / SearXNG / Google PSE / Perplexity. | mydisha/ | 147 | — | ~771 | Automated safety check: Pass | MIT | 26 days ago |
| 46 | Search biomedical literature and web content using Tavily search engine for research and clinical information. | InternScience/ | 169 | 1 repo | ~598 | Automated safety check: Pass | MIT | 4 mo ago |
| 47 | 47.Search Layer 四源同级：Brave (websearch) + Exa + Tavily + Grok。按意图自动选策略、调权重、做合成。 | aAAaqwq/ | 105 | 1 repo | ~1.9k | Automated safety check: Pass | MIT | 10 days ago |
| 48 | Deep multi-source research using Tavily Research API. An agent skill from initializ/forge. | initializ/ | 223 | — | ~1.1k | Automated safety check: Pass | Apache-2.0 | 6 days ago |
Questions, answered from the data.
What is the best Tavily skill?
Tavily Search (official) from aws-samples/sample-strands-agent-with-agentcore ranks first of the 84 Tavily skills listed here, with the highest score: its repository has 194 GitHub stars, its SKILL.md loads about 463 tokens and it passes the automated safety check with no findings. Next come Deepagents Python Quickstart and Deepagents Typescript Quickstart.
Is there an official Tavily skill?
3 of the 84 Tavily skills are official, published by the vendor's own GitHub organization: Tavily Search, Deepagents Python Quickstart and Deepagents Typescript Quickstart.
How are these skills ranked?
By Skill Navigator score, which combines the GitHub stars of the skill's repository (shared across that repo's skills and discounted for large collections), how many other GitHub owners carry a copy of the skill, and automated SKILL.md quality checks, minus penalties for safety-check warnings and for each further skill from the same repository. Skills that fail the safety check are not listed.