What problem does it solve? Before investing months into a research project, you need to know whether your proposed method has already been published. This Skill systematically checks a research idea against recent literature so you avoid duplicating existing work or making false novelty claims that reviewers will reject. ## Core Features & Use Cases - Claim Extraction: Breaks a method description into 3-5 core technical claims that each need independent novelty verification. - Multi-Source Literature Search: Searches arXiv, Google Scholar, Semantic Scholar, and top venues (ICLR, NeurIPS, ICML) with multiple query formulations and 2024-2026 year filters. - Cross-Model Verification: Sends the method and all found papers to an OpenAI reviewer model via Codex MCP with high reasoning effort for an independent novelty judgment. - Structured Novelty Report: Produces a per-claim novelty rating, closest prior work table, an overall score out of 10, a PROCEED / PROCEED WITH CAUTION / ABANDON recommendation, and suggested positioning. - Use Case: You have an idea for a teacher-aware neural video codec. Run a novelty check to discover the closest prior work, identify your actual delta, and learn how a reviewer would attack your novelty claim before writing the paper. ## Quick Start Ask the assistant to run a novelty check on your method description, for example by saying "check novelty of my idea: using teacher-aware distillation in neural video compression for machine-oriented codecs".
