novelty-check

Extract technical claims and search recent literature to verify research novelty.

Updated Apr 21, 2026
One-click install
npx skills add https://github.com/Shallow-W/llm-wiki --skill novelty-check-shallow-w
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: novelty-check
Source: https://github.com/Shallow-W/llm-wiki/tree/main/.claude/skills/novelty-check
Command: npx skills add https://github.com/Shallow-W/llm-wiki --skill novelty-check-shallow-w

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It helps you avoid wasting time by checking whether a proposed research method or idea has already been reported in recent literature.

Core Features & Use Cases

  • Claim-focused novelty checking: Extracts 3–5 core technical claims from your idea and treats each as a separate novelty target.
  • Multi-source literature search: Performs targeted web searches (including arXiv/Scholar-style sources) with multiple query formulations and recent-year filters, then inspects overlapping abstracts.
  • Cross-model verification: Uses a reviewer model (via Codex MCP) to compare your proposal against the found prior work and assess novelty and the closest related papers.
  • Structured novelty reporting: Produces a clear report including core-claim novelty levels, closest prior work, overall score, and recommendations.

Quick Start

Ask to run a novelty check for your idea by saying: "查新:<paste your method or research idea here>".

Frequently Asked Questions about novelty-check

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

FAQPage Schema
How do I check if my research idea has already been published?

To check if a research idea is published, the novelty verification process extracts 3-5 core technical claims from your proposal and searches recent literature across multiple sources. It inspects overlapping abstracts to confirm whether your method has been previously reported.

Can I use arXiv literature to verify research novelty before implementation?

You can verify research novelty against arXiv literature by running targeted web searches with recent-year filters. The system cross-checks your proposed method's core technical claims against found prior work to assess overlap and novelty at the abstract level.

What is the best way to find prior work overlaps for a proposed research method?

The best way to find prior work overlaps is through claim-focused novelty checking, which separates your idea into individual technical targets. A reviewer model then performs comparative judgment against closest related papers to produce a structured novelty report.

Does claim analysis for research novelty require multiple search queries?

Yes, claim analysis requires multiple search query formulations to effectively verify research novelty. Applying 2024-2026 recency filters across multiple sources ensures comprehensive coverage when cross-checking closest prior work and assessing abstract-level overlaps.

How to generate a structured novelty report for experimental settings?

To generate a structured novelty report for experimental settings, the system extracts core technical claims and performs multi-source literature searches. It outputs a clear report including core-claim novelty levels, closest prior work, an overall score, and actionable recommendations.