Join a video meeting as an AI bot with voice, avatar, and screenshare across four operating modes.
Coding
Tavily Search
Try itSearch the public web via Tavily and get structured results with titles, URLs, and snippets.
What it does
Calls the Tavily API to search the public web and returns results in three formats. The default output is raw JSON with the query string, an optional short answer, and a results list containing title, URL, and content. A `brave` format uses a web_search-style schema with `snippet` fields, and a Markdown format produces a compact human-readable list. Requires a TAVILY_API_KEY supplied via environment variable or the `~/.openclaw/.env` file.
When to use it
- Looking up a current fact or topic from the open web
- Gathering candidate sources (titles and URLs) for further reading
- Getting a short synthesized answer alongside supporting links
- Rendering search hits as a human-readable Markdown list
The skill document
Tavily Search
Use the bundled script to search the web with Tavily.
Requirements
- Provide API key via either:
- environment variable:
TAVILY_API_KEY, or ~/.openclaw/.envline:TAVILY_API_KEY=...
- environment variable:
Commands
Run from the OpenClaw workspace:
# raw JSON (default)
python3 {baseDir}/scripts/tavily_search.py --query "..." --max-results 5
# include short answer (if available)
python3 {baseDir}/scripts/tavily_search.py --query "..." --max-results 5 --include-answer
# stable schema (closer to web_search): {query, results:[{title,url,snippet}], answer?}
python3 {baseDir}/scripts/tavily_search.py --query "..." --max-results 5 --format brave
# human-readable Markdown list
python3 {baseDir}/scripts/tavily_search.py --query "..." --max-results 5 --format md
Output
raw (default)
- JSON:
query, optionalanswer,results: [{title,url,content}]
brave
- JSON:
query, optionalanswer,results: [{title,url,snippet}]
md
- A compact Markdown list with title/url/snippet.
Notes
- Keep
max-resultssmall by default (3–5) to reduce token/reading load. - Prefer returning URLs + snippets; fetch full pages only when needed.
Related skills
Generate and edit Draw.io, Mermaid, and Excalidraw diagrams from natural language using a structured JSON spec.
Stores durable facts in a categorized, plain-markdown vault on disk, alongside your agent's built-in memory.
Save, search, and manage personal notes and knowledge bases in Get笔记 on explicit request.
Site audit, content writing, and competitor analysis for organic search rankings.
Fetch raw ad creative, app, ranking, and revenue data from AdMapix as structured JSON.