Agent Skills: tavily-search
使用Tavily API进行网络搜索，获取实时信息、回答问题或研究主题
ID: aiskillstore/marketplace/tavily-search
42745
Install this agent skill to your local
Skill Files
The files that make up tavily-search.
Loading file tree…
More agent skills
- hermes-learns-manimOperate Math-To-Manim with Hermes: inspect artifacts, run deterministic checks, use Codex-backed codegen, render/review Manim outputs, and avoid committing generated media.
- vercel-sandboxRun agent-browser + Chrome inside Vercel Sandbox microVMs for browser automation from any Vercel-deployed app. Use when the user needs browser automation in a Vercel app (Next.js, SvelteKit, Nuxt, Remix, Astro, etc.), wants to run headless Chrome without binary size limits, needs persistent browser sessions across commands, or wants ephemeral isolated browser environments. Triggers include "Vercel Sandbox browser", "microVM Chrome", "agent-browser in sandbox", "browser automation on Vercel", or any task requiring Chrome in a Vercel Sandbox.
- wox-i18nAdd a new Wox language or complete and improve an existing Wox translation. Use for Wox-owned locale registration, translation parity, wording quality, and placeholder-safe updates based on wox.core/resource/lang/en_US.json.
- upgradeIntelligently upgrade claudesidian with new features while preserving user customizations using AI-powered semantic analysis. Use when the user wants to upgrade claudesidian, pull in upstream changes, or update their installation.
- crypto-protocol-diagramExtracts protocol message flow from source code, RFCs, academic papers, pseudocode, informal prose, ProVerif (.pv), or Tamarin (.spthy) models and generates Mermaid sequenceDiagrams with cryptographic annotations. Use when diagramming a crypto protocol, visualizing a handshake or key exchange flow, extracting message flow from a spec or RFC, diagramming a ProVerif or Tamarin model, or drawing sequence diagrams for TLS, Noise, Signal, X3DH, Double Ratchet, FROST, DH, or ECDH protocols.
- create-atomic-toolBuild a `BaseTool[InSchema, OutSchema]` subclass — input/output schemas, `BaseToolConfig`, `run()` (and optional `run_async()`), env-driven secrets, typed failure outputs. Use when the user asks to "add a tool", "create a tool", "wrap an API as a tool", "build a `BaseTool`", "make a calculator/search/weather tool", or runs `/atomic-agents:create-atomic-tool`.