Tavily Research

1---2name: tavily-research3description: |4  Conduct comprehensive AI-powered research with citations via the Tavily CLI. Use this skill when the user wants deep research, a detailed report, a comparison, market analysis, literature review, or says "research", "investigate", "analyze in depth", "compare X vs Y", "what does the market look like for", or needs multi-source synthesis with explicit citations. Returns a structured report grounded in web sources. Takes 30-120 seconds. For quick fact-finding, use tavily-search instead.5allowed-tools: Bash(tvly *)6---7 8# tavily research9 10AI-powered deep research that gathers sources, analyzes them, and produces a cited report. Takes 30-120 seconds.11 12## Before running any command13 14If `tvly` is not found on PATH, install it first:15 16```bash17curl -fsSL https://cli.tavily.com/install.sh | bash && tvly login18```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 use25 26- You need comprehensive, multi-source analysis27- The user wants a comparison, market report, or literature review28- Quick searches aren't enough — you need synthesis with citations29- Step 5 in the [workflow](../tavily-cli/SKILL.md): search → extract → map → crawl → **research**30 31## Quick start32 33```bash34# Basic research (waits for completion)35tvly research "competitive landscape of AI code assistants"36 37# Pro model for comprehensive analysis38tvly research "electric vehicle market analysis" --model pro39 40# Stream results in real-time41tvly research "AI agent frameworks comparison" --stream42 43# Save report to file44tvly research "fintech trends 2025" --model pro -o fintech-report.md45 46# JSON output for agents47tvly research "quantum computing breakthroughs" --json48```49 50## Options51 52| Option | Description |53|--------|-------------|54| `--model` | `mini`, `pro`, or `auto` (default) |55| `--stream` | Stream results in real-time |56| `--no-wait` | Return request_id immediately (async) |57| `--output-schema` | Path to JSON schema for structured output |58| `--citation-format` | `numbered`, `mla`, `apa`, `chicago` |59| `--poll-interval` | Seconds between checks (default: 10) |60| `--timeout` | Max wait seconds (default: 600) |61| `-o, --output` | Save output to file |62| `--json` | Structured JSON output |63 64## Model selection65 66| Model | Use for | Speed |67|-------|---------|-------|68| `mini` | Single-topic, targeted research | ~30s |69| `pro` | Comprehensive multi-angle analysis | ~60-120s |70| `auto` | API chooses based on complexity | Varies |71 72**Rule of thumb:** "What does X do?" → mini. "X vs Y vs Z" or "best way to..." → pro.73 74## Async workflow75 76For long-running research, you can start and poll separately:77 78```bash79# Start without waiting80tvly research "topic" --no-wait --json    # returns request_id81 82# Check status83tvly research status <request_id> --json84 85# Wait for completion86tvly research poll <request_id> --json -o result.json87```88 89## Tips90 91- **Research takes 30-120 seconds** — use `--stream` to see progress in real-time.92- **Use `--model pro`** for complex comparisons or multi-faceted topics.93- **Use `--output-schema`** to get structured JSON output matching a custom schema.94- **For quick facts**, use `tvly search` instead — research is for deep synthesis.95- Read from stdin: `echo "query" | tvly research - --json`96 97## See also98 99- [tavily-search](../tavily-search/SKILL.md) — quick web search for simple lookups100- [tavily-crawl](../tavily-crawl/SKILL.md) — bulk extract from a site for your own analysis