inno-idea-eval

Evaluate research ideas across five dimensions with three reviewer personas.

708|51|Updated Mar 10, 2026
One-click install
npx skills add https://github.com/LigphiDonk/Oh-my--paper --skill inno-idea-eval-ligphidonk
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: inno-idea-eval
Source: https://github.com/LigphiDonk/Oh-my--paper/tree/main/src-tauri/resources/skills/inno-idea-eval
Command: npx skills add https://github.com/LigphiDonk/Oh-my--paper --skill inno-idea-eval-ligphidonk

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Provides a structured, multi-perspective evaluation workflow to assess research ideas with a quality gate, ensuring rigorous critique from diverse expert viewpoints and a coherent Area Chair synthesis.

Core Features & Use Cases

  • Independent persona reviews (Senior ML Researcher, Domain Expert, Methods Specialist) with a unified meta-review.
  • Integrated Active Novelty Verification and evidence-based scoring across five dimensions.
  • Comprehensive outputs including per-dimension scores, aggregated decision, and actionable refinement guidance.

Quick Start

Run the evaluation workflow on your current idea to obtain a complete area-chair synthesis and decision.

Frequently Asked Questions about inno-idea-eval

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

FAQPage Schema
How do I run a multi-persona idea evaluation for a research proposal?

Multi-persona idea evaluation uses three independent reviewer personas to assess research ideas across five dimensions. It generates per-dimension scores, a novelty grounding report, and an area-chair meta-review to produce an aggregated decision and actionable feedback.

What is an area-chair meta-review in research idea evaluation?

An area-chair meta-review synthesizes independent critiques from multiple reviewer personas into a single coherent evaluation. It integrates per-dimension scores and novelty verification to produce a final aggregated decision and refinement guidance for the research idea.

Can I use evidence blocks to score research ideas across multiple dimensions?

Yes, evidence blocks serve as inputs alongside the idea text and pipeline state to score research ideas. The evaluation workflow processes these inputs to generate per-dimension scores, a novelty grounding report, and actionable refinement guidance.

What's the best way to verify novelty and get expert feedback on a research idea?

The best way to verify novelty is through an integrated evaluation pipeline featuring a Senior ML Researcher, Domain Expert, and Methods Specialist. This multi-persona workflow generates a novelty grounding report and an area-chair synthesis with actionable feedback.

Does the idea evaluation workflow require a specific pipeline state to function?

The idea evaluation workflow requires the idea text, evidence blocks, and the current pipeline state as inputs. Processing these elements allows the workflow to generate per-dimension scores, a final decision, and refined guidance.

Why use multiple reviewer personas instead of a single critique for idea evaluation?

Using multiple reviewer personas ensures rigorous critique from diverse expert viewpoints, such as a Domain Expert and a Methods Specialist. This multi-perspective approach provides a comprehensive quality gate before the area-chair meta-review synthesizes the final decision.