rai-research

Frame research prompts requiring triangulated evidence for ADR decisions.

71|8|Updated Feb 13, 2026
One-click install
npx skills add https://github.com/humansys/raise --skill rai-research-humansys
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: rai-research
Source: https://github.com/humansys/raise/tree/main/packages/raise-cli/src/raise_cli/skills_base/rai-research
Command: npx skills add https://github.com/humansys/raise --skill rai-research-humansys

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Research decisions often rely on a single source or intuition, risking biased or incomplete conclusions. This Skill enables epistemologically rigorous, triangulated research to inform ADRs and evaluations.

Core Features & Use Cases

  • Structured evidence catalog creation and maintenance for research topics.
  • Rigorous source evaluation using RaiSE criteria (Very High to Low).
  • Synthesis of findings with explicit confidence, contradictions, and actionable recommendations.
  • Generates outputs: evidence catalog, synthesis document, and recommendations to feed governance artifacts.

Quick Start

Execute a standard-depth topic prompt to produce a complete evidence catalog, synthesis, and recommendations for your ADR.

Frequently Asked Questions about rai-research

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

FAQPage Schema
How do I gather triangulated evidence to justify architecture decisions in an unfamiliar domain?

Triangulated research for ADRs uses structured evidence collection and source evaluation with RaiSE levels to synthesize findings, exposing confidence levels and contradictions to produce actionable governance recommendations.

When should I use multi-source research instead of intuition for high-stakes architecture choices?

Multi-source research replaces intuition for high-stakes architecture choices by applying structured evidence cataloging and RaiSE source evaluation, ensuring decisions are justified by transparent triangulation rather than single-source bias.

How do I evaluate the reliability of sources used for technical decision-making research?

Evaluate source reliability for technical decision-making research using RaiSE criteria, which assigns confidence levels from Very High to Low to structure your evidence catalog and guide transparent triangulation.

What outputs do I need to generate from research to feed into architecture decision records?

To feed architecture decision records, generate an evidence catalog, a synthesis document detailing contradictions and confidence, and actionable recommendations derived from transparent triangulation.

Why does relying on a single source risk biased conclusions for governance evaluations?

Relying on a single source risks biased or incomplete conclusions for governance evaluations because it lacks epistemological rigor, whereas triangulated research synthesizes multiple evaluated sources to justify decisions.

Can I use standard-depth research prompts to produce a complete evidence catalog for ADRs?

Yes, you can execute a standard-depth topic prompt to produce a complete evidence catalog, synthesis document, and actionable recommendations suitable for directly informing your ADRs.