skills.rest
drillan
drillanCOMMUNITY
Explore all skills by this author →
WebsiteGitHub

research

Automate sourced, cited research with structured JSON outputs via the Tavily CLI script.

Updated Feb 2, 2026
Search Tags:#API#research#CLI#json#citations#structured-output#web-sourcing
One-click install
npx skills add https://github.com/drillan/marketschema --skill research-drillan
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: research
Source: https://github.com/drillan/marketschema/tree/main/.claude/skills/research
Command: npx skills add https://github.com/drillan/marketschema --skill research-drillan

SYSTEM DOCUMENTATION & REQUIREMENTS

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

What problem does it solve?

Conduct comprehensive, citation-backed research directly from the terminal, reducing manual sourcing and enabling repeatable, auditable workflows.

Core Features & Use Cases

  • Automated source gathering: collect, analyze, and cite sources for any topic.
  • Structured outputs: returns JSON-ready results suitable for pipelines and dashboards.
  • CLI-first workflow: run research tasks from the scripts/research.sh script in your shell or CI.
  • Use Case: market intelligence, technology trends, literature reviews, and competitive analyses.

Quick Start

Use the research script to run queries without writing code. Examples below show how to invoke the script, generate a pro-level analysis, or save results to a file.

Using the Script .claude/skills/research/scripts/research.sh '{"input": "quantum computing trends"}'

Examples:

  • Basic research .claude/skills/research/scripts/research.sh '{"input": "quantum computing trends"}'

  • With pro model for comprehensive analysis .claude/skills/research/scripts/research.sh '{"input": "AI agents comparison", "model": "pro"}'

  • Save to file .claude/skills/research/scripts/research.sh '{"input": "market analysis for EVs", "model": "pro"}' ./ev-report.md

  • With custom citation format .claude/skills/research/scripts/research.sh '{"input": "climate change impacts", "model": "mini", "citation_format": "apa"}'

  • With structured output schema .claude/skills/research/scripts/research.sh '{"input": "fintech startups 2025", "model": "pro", "output_schema": {"properties": {"summary": {"type": "string"}, "companies": {"type": "array", "items": {"type": "string"}}}, "required": ["summary"]}}'

Frequently Asked Questions about research

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

FAQPage Schema
How do I automate web research with citations directly from the terminal?▼

Automate web research with citations by running the research script in your shell, which uses the Tavily API to gather sources, analyze topics, and return structured results. You pass a JSON input with your query to the script to execute the task.

Can I output structured JSON from a CLI research script for data pipelines?▼

Yes, you can output structured JSON from this CLI research script by defining an output_schema in your input JSON. This formats the synthesized research and citations into JSON-ready results suitable for pipelines and dashboards.

Do I need a Tavily API key to run terminal-based AI research?▼

Yes, you need a Tavily API key to run terminal-based AI research because the script relies on the Tavily API for web sourcing and automated source gathering. You must configure this key in your environment before executing queries.

What is the best way to generate a market analysis report in the terminal?▼

The best way to generate a market analysis report in the terminal is using the research script with the pro model option. This performs comprehensive AI-synthesized research and allows you to save the cited analysis directly to a markdown file.

Does the CLI research tool support custom citation formats like APA?▼

Yes, the CLI research tool supports custom citation formats like APA. You can specify your desired citation_format within the JSON input payload passed to the research script to format the gathered sources accordingly.

Why does the research script require jq as a dependency?▼

The research script requires jq as a dependency to parse and process the JSON inputs and structured outputs. This ensures the CLI can correctly handle JSON-ready results and pass parameters to the Tavily API during execution.

Related Skills

Explore More Education & Research Skills→
466852675466852675

tavily

Perform real-time web searches using the Tavily API.

Community
Basic
BekaChkhiroBekaChkhiro
1

planExportJson

Export PROJECT_PLAN.md into structured JSON with phases and tasks.

Community
Basic
pradyumnasagarpradyumnasagar
6

agent-handoff

Automate inter-skill data transfer and provenance capture via JSON Material Passports.

Community
Advanced
matt-fell-aimatt-fell-ai
1

research

Gather and synthesize information from multiple web sources.

Community
Intermediate