deep-research

Synthesize sourced information into structured research reports with validation.

109|17|Updated Mar 14, 2026
One-click install
npx skills add https://github.com/312362115/claude --skill deep-research-312362115
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: deep-research
Source: https://github.com/312362115/claude/tree/main/skills/deep-research
Command: npx skills add https://github.com/312362115/claude --skill deep-research-312362115

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires numpy, matplotlib, and includes scripts (resource) and references (resource) components.

What problem does it solve?

Deep Research enables teams to systematically understand complex propositions and produce professional, evidence-backed reports that withstand scrutiny and support decision-making.

Core Features & Use Cases

  • Structured, hypothesis-driven research that combines internal data with curated external sources.
  • Multi-hop information gathering and cross-source validation, with confidence levels and source provenance.
  • Automatic generation of charts and diagrams through Diagram Bridge to illustrate findings.
  • End-to-end workflow support from understanding the proposition to delivering a final report, including quality self-checks.
  • Reusable templates and templates for different research domains (technical, market, product/industry).

Quick Start

Start by defining your research proposition, setting the scope and required data sources, and invoking the six-step deep-research workflow to produce a structured report.

Frequently Asked Questions about deep-research

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

FAQPage Schema
How do I generate an evidence-based research report with source provenance?

To generate an evidence-based research report, define a proposition and invoke the six-step workflow to synthesize structured information with explicit data provenance, confidence levels, and multi-layer validation.

What is the best way to structure a competitive benchmarking analysis?

The best way to structure competitive benchmarking is using hypothesis-driven investigations with iterative search depth, cross-source validation, and automatic chart generation to produce defensible, professional reports.

How do I visualize research findings using matplotlib for market analysis?

You visualize research findings for market analysis by running the workflow's Diagram Bridge, which leverages matplotlib and numpy dependencies to automatically generate charts and diagrams illustrating your synthesized data.

Can I use structured analysis frameworks for technology strategy decisions?

Yes, you can use structured analysis frameworks for technology strategy by applying reusable domain templates that combine internal data with curated external sources to support evidence-backed product decisions.

Does the deep research workflow support multi-hop information gathering?

Yes, the deep research workflow supports multi-hop information gathering by cross-validating multiple sources, tracing evidence, and assigning confidence levels to ensure the final output meets strict sourcing requirements.