research

Query Tavily's API to obtain structured, citation-backed research results.

Updated Dec 1, 2025
One-click install
npx skills add https://github.com/stevessr/dotsfiles --skill research-stevessr
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research
Source: https://github.com/stevessr/dotsfiles/tree/main/dot_agents/skills/research
Command: npx skills add https://github.com/stevessr/dotsfiles --skill research-stevessr

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires jq, curl, and includes scripts (resource) components.

What problem does it solve?

Quickly obtain AI-synthesized research with citations directly in your terminal, enabling repeatable, citation-backed insights for decision making.

Core Features & Use Cases

  • Automatic topic research with source gathering and citations
  • Structured JSON output suitable for pipelines and dashboards
  • Background-friendly execution with a clear usage path for quick topic exploration

Quick Start

Run the research script with a JSON payload describing your topic to fetch structured results.

Frequently Asked Questions about research

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

FAQPage Schema
How do I get AI-backed research with citations directly in my terminal?

You can get AI-backed research with citations by posting a research query as a JSON payload to the Tavily API. The script returns structured JSON containing AI-synthesized content, source links, and response time metrics.

What do I need to run a script that fetches AI-synthesized research results?

To fetch AI-synthesized research results, you need the TAVILY_API_KEY environment variable configured, along with jq and curl installed. You provide a JSON payload describing your topic to execute the research script.

Can I customize the JSON output format when gathering research sources?

Yes, you can customize the JSON output format when gathering research sources by passing optional parameters. The script accepts output_schema and citation_format inputs alongside your query and chosen model to tailor the response.

Does the research pipeline support multiple AI models for topic exploration?

The research pipeline supports multiple AI models for topic exploration. You specify your preferred model in the input JSON payload alongside your research query to obtain structured, citation-backed results from the API.

What is the best way to use structured research JSON in automated dashboards?

The best way to use structured research JSON in automated dashboards is leveraging the script's background-friendly execution. It outputs clean JSON with content, sources, and response_time fields, making it suitable for pipeline integration and dashboard rendering.