skill CX Codex

tavily-search · veithly — Claude Code skill: what it does, how to install

Q: How to install tavily-search in Claude Code?

Install it by running `npx skills add veithly/tavily-search --skill tavily-search -a claude-code`. This adds the definition to `~/.claude/skills/tavily-search/SKILL.md`.

Q: What does the tavily-search skill do?

It queries the Tavily search API through `scripts/search ` to gather real-time web results prepared for AI contexts.

Q: What environment variables are required for tavily-search?

You must set `export TAVILY_API_KEY="your-api-key"`. You can generate this key on tavily.com.

Connects Tavily AI search API to fetch fresh web information and real-time facts. Helpful whenever an agent needs recent updates from outside its training data.

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓

npx skills add veithly/tavily-search --skill tavily-search -a claude-code

Open on GitHub

What tavily-search does

This skill brings Tavily search directly to agent workflows. Instead of browsing raw web pages, the agent runs queries through scripts/search <query> to retrieve focused text context.

The repository includes the scripts/search script with an optional --format json parameter for structured payloads. It will not work without an active TAVILY_API_KEY exported in the shell environment. That key must be generated at tavily.com beforehand.

What it helps with

retrieve recent facts and news from the web
receive structured JSON search responses with --format json
fetch current technical updates without scraping HTML manually

Example prompts for the agent

Search for the latest Node.js release notes using tavily-search
Run scripts/search with the --format json flag to look up recent SQLite developments
Find up-to-date documentation changes for Vite via Tavily

How to install tavily-search

1Skills CLI (Vercel)

npx skills add veithly/tavily-search --skill tavily-search -a claude-code

2Manually: put the files in place

~/.claude/skills/tavily-search/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/tavily-search/

1Skills CLI (Vercel)

npx skills add veithly/tavily-search --skill tavily-search -a codex

2Manually: put the files in place

.agents/skills/tavily-search/SKILL.md

For all projects use ~/.agents/skills/

1Skills CLI (Vercel)

npx skills add veithly/tavily-search --skill tavily-search -a cursor

2Manually: put the files in place

.cursor/skills/tavily-search/SKILL.md

Cursor also reads .agents/skills/ and .claude/skills/

1GitHub CLI

gh skill install veithly/tavily-search tavily-search

2Manually: put the files in place

.github/skills/tavily-search/SKILL.md

1Skills CLI (Vercel)

npx skills add veithly/tavily-search --skill tavily-search -a gemini-cli

2Platform CLI

gemini skills install https://github.com/veithly/tavily-search --path skills/tavily-search

Manually: put the files in place

.devin/skills/tavily-search/SKILL.md

The legacy .windsurf/skills/ path still works

Skills CLI (Vercel)

npx skills add veithly/tavily-search --skill tavily-search -a opencode

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about tavily-search

How to install tavily-search in Claude Code?

Install it by running npx skills add veithly/tavily-search --skill tavily-search -a claude-code. This adds the definition to ~/.claude/skills/tavily-search/SKILL.md.

What does the tavily-search skill do?

It queries the Tavily search API through scripts/search <query> to gather real-time web results prepared for AI contexts.

What environment variables are required for tavily-search?

You must set export TAVILY_API_KEY="your-api-key". You can generate this key on tavily.com.

tavily-search by other authors comes first.

tavily-search tavily-ai Runs web searches via the tvly CLI and returns LLM-tailored snippets with relevance scores. Use it when your agent needs fresh web sources without an exact URL. CX Codex +1 36,100installs tavily-search framix-team Integrates Tavily API into your coding agent for web search, text extraction, site crawling, and research reports. Works as an AI-oriented search replacement. CX Codex +1 840installs tavily-dynamic-search tavily-ai Tavily search skill with context isolation. Saves large web payloads to local disk and filters them before sending snippets into the agent context. CX Codex +1 13,500installs web-search-tavily agent-skills A skill that runs web searches through the Tavily API and returns structured results with relevance scores. Useful when the agent needs current data from the web. CX Codex +1 1,100installs tavily intellectronica Searches the web, extracts page content, maps domains, and runs deep research tasks through Tavily's REST API. CX Codex +1 627installs tavily-best-practices tavily-ai This skill gives an agent guidance for Tavily web search, content extraction, site crawling, and research. Use it when adding current web data to an agent workflow or RAG system. CX Codex +1 20,700installs tavily-usage fcakyon Guides coding agents to run web searches and extract page content via Tavily MCP tools. Requires a Tavily API key. CX Codex +1 758installs web-search 101-skills This skill gives your agent web search and content extraction through Tavily and Exa. Useful for research, fact-checking and RAG pipelines. CX Codex +1 110,000installs