Skills
.Work. You
Rest

research-novelty-audit

Community

Evaluate AI idea novelty with reviewer critique.

Education & Research#ai#critical-thinking#peer-review#novelty#framing#prior-work
AuthorOcean326
Version1.0.0
Installs0

System Documentation

What problem does it solve?

评估 AI、深度学习和序列表征学习 idea 或 draft 的新颖性与竞争定位。当 Codex 需要对比 prior work、压力测试贡献主张、提前暴露 reviewer 质疑，或判断一个想法是否值得继续做实验时使用。

Core Features & Use Cases

  • 用于系统地拆分新颖性要素：objective、architecture、data or augmentation、training recipe、evaluation setting。
  • 对每个部分评估它是“真正新”、“旧元素重组”、“调参优化”还是“当前任务设定下才算新”，并输出最终结论。
  • 针对 AI 工作，重点关注缺少强基线、基准 cherry-pick、算力变化对新颖性的影响、以及新颖性是否主要来自规模化等问题。
  • 输出包括：最强的 prior-work 冲突点、以 reviewer 风格提出的质疑，以及最小且有效的增强改动。
  • 输出格式便于后续进入 paper-production-pipeline 或实验设计阶段。

Quick Start

Submit a concise description of your AI idea and any cited prior work, and run this skill to generate a formal novelty audit.

Dependency Matrix

Required Modules

None required

Components

references

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: research-novelty-audit
Download link: https://github.com/Ocean326/Agents/archive/main.zip#research-novelty-audit

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.