What problem does it solve? Before investing months into a research project, you need to know whether your method or idea has already been published. This Skill systematically checks a proposed research idea against recent literature so you avoid both false novelty claims and prematurely abandoning viable ideas. ## Core Features & Use Cases - Claim Extraction: Breaks a method description into 3-5 core technical claims that carry the claimed contribution. - Multi-Source Literature Search: Searches arXiv, Google Scholar, Semantic Scholar, and recent conference proceedings (ICLR, NeurIPS, ICML) with multiple query formulations per claim. - Cross-Model Verification: Sends a dossier of claims and candidate papers to a reviewer model via Codex MCP for an independent novelty judgment under calibrated verdict limits. - Structured Report: Produces a novelty report with closest prior work, a 1-10 score, and a PROCEED / PROCEED WITH CAUTION / ABANDON recommendation. - Use Case: You have an idea for a new attention mechanism. Run this Skill to find the closest 2024-2026 papers, verify each citation, and get a defensible positioning statement before writing any code. ## Quick Start Ask the assistant to run a novelty check on your research idea, for example by saying "check novelty of my method that combines sparse attention with curriculum learning for long-document summarization".
