research

Conduct structured multi-source research using Context7 and Tavily.

Updated Jan 29, 2026
One-click install
npx skills add https://github.com/benjgrad/clawdbot --skill research-benjgrad
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research
Source: https://github.com/benjgrad/clawdbot/tree/main/skills/research
Command: npx skills add https://github.com/benjgrad/clawdbot --skill research-benjgrad

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the process of conducting in-depth research on various topics, technologies, or patterns, providing a structured and sourced summary with actionable recommendations.

Core Features & Use Cases

  • Multi-source Information Gathering: Integrates with tools like Context7, Tavily, and web fetching to gather data from diverse sources.
  • Phased Research Pipeline: Follows a structured 4-phase process: Scope, Gather, Synthesize, and Output.
  • Checkpoint-driven Workflow: Ensures user alignment and feedback at critical stages of the research process.
  • Use Case: When you need to understand the best practices for a new technology stack before starting a project, or compare different architectural patterns for a specific problem.

Quick Start

Use the research skill to investigate the best way to handle file uploads in my Supabase + Next.js app.

Frequently Asked Questions about research

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

FAQPage Schema
How do I conduct structured multi-source research on a new technology stack?

Structured multi-source research automates gathering data from diverse sources like Context7 and Tavily into a phased pipeline. It follows Scope, Gather, Synthesize, and Output phases with forced checkpoints, ensuring user alignment before delivering actionable recommendations.

What is the best way to compare architectural patterns before starting a project?

Comparing architectural patterns requires a checkpoint-driven workflow that synthesizes documentation and web search data. This approach forces user alignment at critical stages to provide structured, sourced summaries and actionable recommendations for your project.

How do I investigate and synthesize information from different documentation sources?

Investigating and synthesizing information involves orchestrating Context7 for documentation, Tavily for web search, and code reading. This multi-source information gathering integrates diverse data into a unified synthesis phase to produce structured, actionable summaries.

Can I integrate web search and documentation reading into a single research workflow?

Yes, you can integrate web search and documentation reading into a single research workflow. The pipeline combines Tavily for web search, Context7 for documentation, and code reading, orchestrating these tools into a phased process with forced checkpoints for user alignment.

When do I need a checkpoint-driven workflow for information gathering?

A checkpoint-driven workflow for information gathering is needed when you must ensure user alignment and feedback at critical stages of the research process. It is essential for complex investigations requiring scoped synthesis before outputting final actionable recommendations.