research

Orchestrates parallel AI agents to decompose, execute, verify, and synthesize research workflows.

6|1|Updated May 9, 2022
One-click install
npx skills add https://github.com/mazenyassergithub/oh-my-claudecode --skill research-mazenyassergithub
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research
Source: https://github.com/mazenyassergithub/oh-my-claudecode/tree/main/skills/research
Command: npx skills add https://github.com/mazenyassergithub/oh-my-claudecode --skill research-mazenyassergithub

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill automates complex research tasks by orchestrating multiple AI agents to analyze codebases, identify patterns, and synthesize findings into comprehensive reports.

Core Features & Use Cases

  • Automated Research Workflows: Decomposes research goals into stages, executes them in parallel, and verifies results.
  • Intelligent Agent Orchestration: Utilizes different AI scientist agents (low, medium, high complexity) with smart model routing (Haiku, Sonnet, Opus).
  • AUTO Mode: Enables fully autonomous research execution.
  • Use Case: Automatically analyze the security vulnerabilities of an entire codebase by breaking down the task into file enumeration, token handling analysis, session management review, and vulnerability pattern identification.

Quick Start

Initiate a fully autonomous security analysis of the authentication system by typing /research AUTO: Comprehensive security analysis of the authentication system.

Frequently Asked Questions about research

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

FAQPage Schema
How do I automate code analysis across an entire codebase using AI agents?

You can automate code analysis by orchestrating parallel AI scientist agents that decompose research goals into stages, execute tasks in parallel, verify results, and synthesize findings into comprehensive reports.

What is the best way to run a fully autonomous security analysis of my authentication system?

The best way to run fully autonomous security analysis is using AUTO mode, which independently manages session tracking, evidence extraction, and model routing to identify vulnerability patterns without manual intervention.

How does parallel AI agent orchestration work for complex code research workflows?

Parallel AI agent orchestration works by decomposing research goals into distinct stages, routing tasks to different AI scientist agents based on complexity, and executing them concurrently before synthesizing the verified findings.

Can I use different AI models for varying complexity levels in automated research workflows?

Yes, smart model routing automatically assigns low, medium, and high complexity tasks to appropriate AI models like Haiku, Sonnet, and Opus to optimize code analysis and problem-solving workflows.

Does automated code research provide state tracking and session management for long-running workflows?

Yes, automated code research provides detailed session management and state tracking throughout the workflow, ensuring robust evidence extraction, verification, and reporting across all research stages.

When should I not use fully autonomous AI research modes for codebase analysis?

You should avoid fully autonomous modes when you need granular control over individual research stages, preferring standard mode to manually guide the decomposition, execution, and verification phases of your code analysis.