tavily-research

Generates cited research reports from web sources via the Tavily CLI.

Updated Mar 4, 2026
One-click install
npx skills add https://github.com/chisuhua/home --skill tavily-research-chisuhua
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: tavily-research
Source: https://github.com/chisuhua/home/tree/main/.agents/skills.disabled/tavily-research
Command: npx skills add https://github.com/chisuhua/home --skill tavily-research-chisuhua

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Deep research questions—market analyses, comparisons, literature reviews—require gathering and synthesizing many web sources with citations, which is slow and error-prone when done manually or with single-shot searches. ## Core Features & Use Cases - Deep Research Reports: Runs multi-source research through the Tavily CLI and returns a structured report grounded in cited web sources. - Model and Output Control: Choose mini, pro, or auto models, stream progress, define a JSON output schema, and pick citation formats like MLA or APA. - Async Workflow: Start long-running research with a request ID, poll for status, and save results to a file. - Use Case: Ask for a comparison of AI agent frameworks and receive a cited report in 30-120 seconds, saved directly to a Markdown file. ## Quick Start Ask the assistant to research the competitive landscape of AI code assistants and produce a cited report using the Tavily research command.

Frequently Asked Questions about tavily-research

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I run deep web research with citations using Tavily?▼

Run tvly research followed by your query, for example tvly research "electric vehicle market analysis" --model pro. The command gathers web sources, synthesizes them, and returns a cited report in 30-120 seconds.

What is the difference between tavily research and tavily search?▼

Tavily search handles quick fact-finding and simple lookups, while tavily research performs deep multi-source synthesis with citations. Use research for comparisons, market reports, and literature reviews; use search for single quick answers.

Which Tavily research model should I use, mini or pro?▼

Use mini for single-topic targeted research taking about 30 seconds, and pro for comprehensive multi-angle analysis taking 60-120 seconds. The auto model lets the API choose based on query complexity.

Can I run Tavily research asynchronously and poll for results?▼

Yes, start with tvly research "topic" --no-wait --json to get a request_id, then check progress with tvly research status or wait using tvly research poll with the request ID.

What should I do if the tvly command is not found?▼

Install the Tavily CLI first by running curl -fsSL https://cli.tavily.com/install.sh | bash followed by tvly login. Do not fall back to other tools, as the skill depends on the tvly CLI being on PATH.