research-refine

Transforms vague research directions into implementable academic method plans.

2|Updated Aug 12, 2025
One-click install
npx skills add https://github.com/goupup-ai/miccai25 --skill research-refine-goupup-ai
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: research-refine
Source: https://github.com/goupup-ai/miccai25/tree/main/ARIS/skills/research-refine
Command: npx skills add https://github.com/goupup-ai/miccai25 --skill research-refine-goupup-ai

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill solves the common pain point of having a rough, vague research direction but no concrete, implementable, and competitive method plan for top academic venues. It eliminates the risk of unfocused, bloated proposals that fail to meet publication standards by anchoring all work to the core research problem.

Core Features & Use Cases

  • Iterative GPT-5.5 Review: Multiple rounds of AI-powered feedback to sharpen method specificity, contribution quality, and frontier leverage.
  • Problem Anchor Enforcement: Freezes the core research bottleneck to prevent drift and ensure all revisions stay aligned with the original goal.
  • Minimal Contribution Guardrails: Enforces a single dominant contribution plus at most one supporting contribution to avoid unfocused module pile-ups.
  • Use Case: A researcher with a rough idea for a vertebrae segmentation method can use this Skill to turn it into a polished, implementation-ready proposal competitive for MICCAI.

Quick Start

Use the research-refine skill to turn my vague idea for a frequency-enhanced vertebrae segmentation method into a concrete, top-venue ready research plan.

Frequently Asked Questions about research-refine

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

FAQPage Schema
How do I turn a vague machine learning research idea into a top-venue paper proposal?

Refining a vague machine learning idea into a top-venue proposal requires iterative AI review and problem anchoring to enforce minimal contributions and generate implementation-oriented method plans.

What is the best way to prevent problem drift when designing a medical imaging method?

Preventing problem drift in medical imaging method design requires freezing the core research bottleneck to ensure all revisions stay anchored to the original goal and avoid unfocused module pile-ups.

How does iterative review improve academic paper planning for computer vision research?

Iterative review improves academic paper planning by providing multiple rounds of AI-powered feedback to sharpen method specificity, contribution quality, and frontier leverage for computer vision publications.

Can I use this method refinement process for an early-stage medical imaging proposal?

Yes, you can use this method refinement process for early-stage medical imaging proposals to transform rough directions into competitive, implementation-ready roadmaps for top academic venues.

Why does my research plan have unfocused module pile-ups and how do I fix it?

Unfocused module pile-ups occur when proposals lack minimal contribution guardrails; fixing this requires enforcing a single dominant contribution plus at most one supporting contribution.

What is needed to generate a validation sketch for a machine learning research plan?

Generating a validation sketch for a machine learning research plan requires an implementation-oriented method design that transforms your specific problem anchor into a focused, implementable research roadmap.