deep-research

Produces multi-phase research reports with sourced, scored evidence and recommendations.

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

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill addresses complex decision problems that require multi-source investigation, careful source evaluation, and a clear, evidence-backed synthesis rather than a quick or shallow answer.

Core Features & Use Cases

  • Structured research workflow: Frames questions, builds research plans, layers discovery and source inspection, and pressures opposing views.
  • Source scoring and ledger: Evaluates each relied-on source with freshness, bias, quality score, and caveats to support defensible conclusions.
  • Actionable deliverables: Produces scoped research objectives, findings by theme, option comparisons, conflicts and gaps, and a recommendation with confidence levels.
  • Use Case: Vendor comparisons, market scans, technical tradeoffs, policy investigations, and decision memos that require primary-source grounding and explicit uncertainty.

Quick Start

Request a deep research brief that defines scope and assumptions, gathers and scores primary and secondary sources, seeks disconfirming evidence, and delivers a clear recommendation with confidence levels.

Frequently Asked Questions about deep-research

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

FAQPage Schema
How do I conduct evidence-backed research for a complex vendor comparison?

To produce an evidence-backed research brief, frame your question, build a research plan, gather and score primary sources, seek disconfirming evidence, and deliver a structured recommendation with confidence levels.

What is a source ledger and how does it help with multi-source investigations?

A source ledger evaluates each relied-on source with freshness, bias, quality score, and caveats, ensuring your multi-source investigation produces defensible conclusions and explicit uncertainty tracking.

How do I create a decision memo with explicit assumptions and confidence levels?

Create a decision memo by defining scoped research objectives, synthesizing findings by theme, comparing options, identifying conflicts, and delivering a recommendation with explicit confidence levels and assumptions.

Can I use deep research for technical tradeoff analysis requiring disconfirming evidence?

Yes, deep research applies to technical tradeoffs by layering source discovery, inspecting evidence, and pressuring opposing views to deliver a recommendation with explicit confidence levels for high-stakes decisions.

What is the best way to structure a market scan with source evaluation?

The best way to structure a market scan is to establish a source ledger, score each source on bias and freshness, and synthesize the evaluated evidence into a comparative analysis with confidence levels.