research

Synthesize multi-source research into a Markdown report with sources and confidence assessment.

Updated Feb 27, 2026
One-click install
npx skills add https://github.com/Crispy13/copilot-directions --skill research-crispy13
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research
Source: https://github.com/Crispy13/copilot-directions/tree/main/.github/skills/research
Command: npx skills add https://github.com/Crispy13/copilot-directions --skill research-crispy13

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Deep research and investigation that produces a comprehensive Markdown report. Use for architecture analysis, technology comparisons, API deep-dives, implementation pattern discovery, and other multi-source questions a single search cannot answer. Triggers on "research this", "investigate", "deep dive into", "how does X work", or "compare approaches for". Also use when the user requests committee or multi-model research, or when planning stalls on unknowns.

Core Features & Use Cases

  • Autonomous deep-research workflow that curates evidence from multiple sources into a single, shareable Markdown report.
  • Generates a comprehensive report with a clear confidence assessment, open questions, and actionable findings.
  • Useful for architecture analyses, technology comparisons, API deep-dives, and multi-source investigations.

Quick Start

Provide a topic and let the system produce a comprehensive, source-backed Markdown research report.

Frequently Asked Questions about research

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

FAQPage Schema
How do I generate a research report from multiple sources?

To generate a multi-source research report, provide a topic and the system synthesizes evidence from various references into a single Markdown report. It returns complete findings, a confidence assessment, and open questions with minimal prompting.

When do I need multi-source research synthesis for architecture analysis?

Multi-source research synthesis is needed for architecture analysis, technology comparisons, or API deep-dives where a single search cannot answer. It combines evidence from various sources into one comprehensive Markdown report.

Can I use this for technology comparisons and API deep-dives?

Yes, you can use it for technology comparisons and API deep-dives. It performs autonomous investigations to synthesize evidence into a source-backed Markdown report with actionable findings and a confidence assessment.

How do I investigate vague topics with minimal prompting?

To investigate vague topics with minimal prompting, trigger the system with phrases like "research this" or "deep dive into". It autonomously sharpens vague research questions before generating the final evidence-backed report.

Does the research report include a confidence assessment and sources?

Yes, the research report includes a confidence assessment and sources. It curates evidence from multiple references to produce a complete Markdown document featuring actionable findings, open questions, and source citations.

What are the limitations of autonomous deep-research workflows?

Autonomous deep-research workflows rely on synthesizing available references, meaning output quality depends on source evidence. While it sharpens vague topics, it may still leave open questions when investigating highly novel or undocumented technologies.