tavily-weblisted
Install: claude install-skill Lu1sDV/skillsmd
# Tavily Web Search & Research
CLI-based web search, extraction, crawling, and research via `curl`. No SDK installation required.
## Prerequisites
- `TAVILY_API_KEY` set in environment
- Never hardcode or paste API keys into chat
## Choosing the Right Method
| Need | Method | Cost | Latency |
|------|--------|------|---------|
| Web search results | `search` | 1-2 credits | Fast |
| Content from specific URLs | `extract` | 1+ credits | Fast |
| Content from entire site | `crawl` | Variable | Slow |
| URL discovery from a site | `map` | 1 credit | Fast |
| End-to-end research with AI synthesis | `research` | Higher | Minutes |
## Quick Reference
### search — Web Search
```bash
curl -s "https://api.tavily.com/search" \
-H "Authorization: Bearer $TAVILY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"query": "your search query here",
"max_results": 5,
"search_depth": "basic",
"topic": "general"
}'
```
**Key parameters:**
| Parameter | Values | Notes |
|-----------|--------|-------|
| `query` | string (max 400 chars) | Keep focused; split complex questions into sub-queries |
| `max_results` | 1-20 (default 5) | Start small, increase if needed |
| `search_depth` | `basic` (1 credit) / `advanced` (2 credits) | Use basic unless you need precision |
| `topic` | `general` / `news` / `finance` | Determines ranking algorithm |
| `time_range` | `day` / `week` / `month` / `year` | Filter by recency |
| `include_answer` | `true` / `"basic"` / `"adv