rb-research-question-gate

Audits research proposals for novelty and validity before implementation.

Updated Jul 2, 2026
One-click install
npx skills add https://github.com/richardmbailey/rb-skills --skill rb-research-question-gate
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: rb-research-question-gate
Source: https://github.com/richardmbailey/rb-skills/tree/main/rb-research-question-gate
Command: npx skills add https://github.com/richardmbailey/rb-skills --skill rb-research-question-gate

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill prevents wasted engineering effort by rigorously auditing research ideas, scientific hypotheses, and technical novelty claims before any code is written or product plans are finalized.

Core Features & Use Cases

  • Novelty Auditing: Systematically compares proposed ideas against existing literature and prior art to identify duplicates or near-misses.
  • Structured Gatekeeping: Enforces a formal decision-making process (Stop, Revise, or Proceed) based on measurable criteria and falsifiability.
  • Use Case: Use this before starting a new machine learning project to ensure your proposed algorithm is not already a well-documented baseline, saving weeks of potentially redundant development.

Quick Start

Invoke the rb-research-question-gate skill to begin the novelty audit process for your current research hypothesis.

Frequently Asked Questions about rb-research-question-gate

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

FAQPage Schema
How do I validate research novelty before starting development?

To validate research novelty, audit your proposed ideas against existing literature and prior art to identify duplicates or near-misses. This structured gatekeeping process enforces a formal Stop, Revise, or Proceed decision based on measurable criteria and falsifiability before any code is written.

What is a research gap matrix and when do I need it?

A research gap matrix defines technical novelty and scientific validity by mapping problem statements against domain constraints. You need it during the pre-implementation phase to establish falsifiers and determine if your scientific hypothesis is already a well-documented baseline.

How do I audit prior art for a machine learning project?

To audit prior art, input your structured problem statements and domain constraints to systematically compare your proposed algorithm against existing literature. This determines whether to stop, revise, or proceed with development, saving weeks of potentially redundant engineering effort.

Can I use this gatekeeping process for any scientific hypothesis?

Yes, you can use this gatekeeping process for any scientific hypothesis requiring technical novelty auditing. It requires structured input of problem statements and domain constraints to evaluate scientific validity and determine whether to stop, revise, or proceed.

What are the limitations of automated novelty auditing?

Automated novelty auditing limitations depend on the structured input of problem statements and domain constraints provided. It operates strictly within the pre-implementation phase and cannot evaluate post-development results or replace empirical scientific validation of the implemented research.