research

Research technical decisions across web and codebase sources into structured reports.

Updated Apr 19, 2026
One-click install
npx skills add https://github.com/mgsystemsdev/POD --skill research-mgsystemsdev
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research
Source: https://github.com/mgsystemsdev/POD/tree/main/agent-system-base/.claude/skills/research
Command: npx skills add https://github.com/mgsystemsdev/POD --skill research-mgsystemsdev

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Deep technical research with parallel discovery across web, codebase, and alternatives. Synthesizes findings into actionable recommendations. Use when the user says "research this", "look into", "compare options for", "what's the best way to", "find out about", or when a technical decision needs evidence before committing.

Core Features & Use Cases

  • Phase 1: Decompose the Question — break the user topic into 3-5 specific sub-questions and confirm with the user before proceeding.
  • Phase 2: Parallel Discovery — search the web, inspect the codebase for patterns, and explore viable alternatives.
  • Phase 3: Cross-Reference — compare findings, flag contradictions, note recency, and differentiate opinions from facts.
  • Phase 4: Synthesize — deliver a structured report with Summary, Evidence, Recommendation, Risks, and Next Steps.

Quick Start

Ask it to research a technical topic using parallel web and codebase sources and produce a structured, evidence-based recommendation.

Frequently Asked Questions about research

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

FAQPage Schema
How do I get evidence-backed recommendations for technical decisions?

You can get evidence-backed recommendations by requesting a cross-source research process that decomposes your question, performs parallel discovery across the web and codebase, and synthesizes a structured report with risks and next steps.

What's the best way to compare technical alternatives and cross-reference sources?

The best way to compare technical alternatives is to run parallel discovery across the web and codebase, then cross-reference findings to flag contradictions, note recency, and differentiate opinions from facts before synthesizing an actionable recommendation.

How does cross-source technical research handle codebase analysis?

Cross-source technical research handles codebase analysis by inspecting the codebase for patterns during the parallel discovery phase, comparing those findings against web sources and alternatives to generate evidence-backed recommendations.

Can I use automated research to find out about and compare options for a new technology?

Yes, you can use automated research to find out about and compare options for a new technology by breaking the topic into sub-questions, exploring viable alternatives, and cross-referencing multiple sources to deliver a structured recommendation.

What is included in a structured technical research report?

A structured technical research report includes a summary, evidence, recommendation, risks, and next steps, generated by cross-referencing multiple sources and synthesizing findings from web, codebase, and alternative analyses.

When do I need cross-source research instead of a simple web search?

You need cross-source research instead of a simple web search when a technical decision requires parallel discovery across the web and codebase, cross-referencing to flag contradictions, and an actionable, evidence-backed recommendation before committing.