A powerful toolset for AI agents to perform real-time web searches, extract structured content, and execute deep research tasks with source citations.
Install & Download
1. ClawHub CLI
The fastest way to install a skill directly from the registry.
npx clawhub@latest install tavily-web
2. Manual Installation
Copy the skill folder to one of these locations
~/.openclaw/skills/ <project>/skills/ Priority: Workspace > Local > Bundled
3. Prompt Installation
Copy this prompt to OpenClaw to install it automatically.
Help me install tavily-web using Clawhub. If Clawhub is not installed, install it first (npm i -g clawhub).
Prefer to download?
Get the raw skill files in a ZIP archive.
What is Tavily Web Search and Research?
The Tavily skill provides AI agents with sophisticated web intelligence capabilities via the Tavily Search, Extract, and Research APIs. Unlike standard search tools, this skill is specifically optimized for LLMs, allowing for granular control over search depth, topic filtering (general, news, or finance), and content extraction in formats like markdown. By integrating this into Openclaw Skills, developers can equip their agents with the ability to find verified information, generate cited answers, and summarize complex topics with high accuracy while maintaining strict control over context window usage.
Tavily Web Search and Research Use Cases
- Gathering the latest technical documentation or API changes for coding tasks.
- Monitoring real-time news or financial market trends with specific time-range filters.
- Extracting specific data points or pricing information from target URLs without loading entire pages.
- Executing multi-step research tasks that require polling for completion and comprehensive source synthesis.
How Tavily Web Search and Research Works
- The agent receives a user request and reformats it into one or more focused search queries.
- It selects the appropriate topic (general, news, or finance) and search depth based on the required precision and credit cost.
- The skill executes the search via the bundled Python CLI or direct API calls, retrieving a list of URLs and snippets.
- For detailed analysis, the agent uses the extract command to pull specific content chunks from the top results in markdown format.
- The final output is synthesized with proper citations, or for complex queries, a background research task is managed until completion.
Tavily Web Search and Research Setup
To use this within the Openclaw Skills ecosystem, ensure your API key is configured correctly.
# 1. Set your Tavily API Key in your environment
export TAVILY_API_KEY="your_api_key_here"
# 2. Verify installation and check credit limits
python3 SKILL_DIR/scripts/tavily.py usage
Tavily Web Search and Research Data Schema & Taxonomy
The skill organizes web data and metadata to ensure agents can cite sources accurately within Openclaw Skills:
| Attribute | Type | Description |
|---|---|---|
results[].url |
String | The source URL for the search result, used for citations. |
results[].content |
String | Snippet or extracted text from the webpage. |
score |
Number | A relevance score used to filter high-trust results. |
request_id |
String | A unique identifier used for debugging and support. |
usage |
Object | Metadata tracking credit consumption for the specific request. |
Tavily Web Search and Research Advanced Features
- Advanced Search Depth: Toggle high-precision results with multiple chunks per source for deep context analysis.
- Automated Research Tasks: Initiate long-running asynchronous research with specified citation formats (e.g., numbered citations).
- Targeted Content Extraction: Use query-based extraction to pull only the most relevant sections of a webpage into the agent context, saving tokens.
- Topic-Specific Filtering: Specialized filters for finance and news to improve results for niche industry queries.
SKILL.md
Loading
Related Openclaw Skills
apix
A CLI utility that allows developers and agents to discover, inspect, and call REST API endpoints using local markdown documentation.
Security Scanner
A professional security automation toolkit for penetration testing, service discovery, and vulnerability assessment across web apps and infrastructure.
Yanxue Course Manager
An intelligent workstation for generating, managing, and exporting professional K-12 study tour programs.
Charisma Research Loop
A self-improving AI research agent that generates actionable daily insights on charisma, social psychology, and influence.
Agnxi Search
A powerful discovery utility that allows agents to search the Agnxi.com database for curated AI tools and MCP servers.
Agent Team Workflows
A universal orchestration framework for managing 5-agent teams to execute complex, multi-step workflows across software, research, and business domains.