1---
2name: tavily-search
3description: |
4  Search the web with LLM-optimized results via the Tavily CLI. Use this skill when the user wants to search the web, find articles, look up information, get recent news, discover sources, or says "search for", "find me", "look up", "what's the latest on", "find articles about", or needs current information from the internet. Returns relevant results with content snippets, relevance scores, and metadata — optimized for LLM consumption. Supports domain filtering, time ranges, and multiple search depths.
5allowed-tools: Bash(tvly *)
6---
7 
8# tavily search
9 
10Web search returning LLM-optimized results with content snippets and relevance scores.
11 
12## Before running any command
13 
14If `tvly` is not found on PATH, install it first:
15 
16```bash
17curl -fsSL https://cli.tavily.com/install.sh | bash && tvly login
18```
19 
20Do not skip this step or fall back to other tools.
21 
22See [tavily-cli](../tavily-cli/SKILL.md) for alternative install methods and auth options.
23 
24## When to use
25 
26- You need to find information on any topic
27- You don't have a specific URL yet
28- First step in the [workflow](../tavily-cli/SKILL.md): **search** → extract → map → crawl → research
29 
30## Quick start
31 
32```bash
33# Basic search
34tvly search "your query" --json
35 
36# Advanced search with more results
37tvly search "quantum computing" --depth advanced --max-results 10 --json
38 
39# Recent news
40tvly search "AI news" --time-range week --topic news --json
41 
42# Domain-filtered
43tvly search "SEC filings" --include-domains sec.gov,reuters.com --json
44 
45# Include full page content in results
46tvly search "react hooks tutorial" --include-raw-content --max-results 3 --json
47```
48 
49## Options
50 
51| Option | Description |
52|--------|-------------|
53| `--depth` | `ultra-fast`, `fast`, `basic` (default), `advanced` |
54| `--max-results` | Max results, 0-20 (default: 5) |
55| `--topic` | `general` (default), `news`, `finance` |
56| `--time-range` | `day`, `week`, `month`, `year` |
57| `--start-date` | Results after date (YYYY-MM-DD) |
58| `--end-date` | Results before date (YYYY-MM-DD) |
59| `--include-domains` | Comma-separated domains to include |
60| `--exclude-domains` | Comma-separated domains to exclude |
61| `--country` | Boost results from country |
62| `--include-answer` | Include AI answer (`basic` or `advanced`) |
63| `--include-raw-content` | Include full page content (`markdown` or `text`) |
64| `--include-images` | Include image results |
65| `--include-image-descriptions` | Include AI image descriptions |
66| `--chunks-per-source` | Chunks per source (advanced/fast depth only) |
67| `-o, --output` | Save output to file |
68| `--json` | Structured JSON output |
69 
70## Search depth
71 
72| Depth | Speed | Relevance | Best for |
73|-------|-------|-----------|----------|
74| `ultra-fast` | Fastest | Lower | Real-time chat, autocomplete |
75| `fast` | Fast | Good | Need chunks, latency matters |
76| `basic` | Medium | High | General-purpose (default) |
77| `advanced` | Slower | Highest | Precision, specific facts |
78 
79## Tips
80 
81- **Keep queries under 400 characters** — think search query, not prompt.
82- **Break complex queries into sub-queries** for better results.
83- **Use `--include-raw-content`** when you need full page text (saves a separate extract call).
84- **Use `--include-domains`** to focus on trusted sources.
85- **Use `--time-range`** for recent information.
86- Read from stdin: `echo "query" | tvly search - --json`
87 
88## See also
89 
90- [tavily-extract](../tavily-extract/SKILL.md) — extract content from specific URLs
91- [tavily-research](../tavily-research/SKILL.md) — comprehensive multi-source research
92