novelty-check
Verify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.
Profile →npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill novelty-check --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
# Novelty Check Skill Check whether a proposed method/idea has already been done in the literature: **$ARGUMENTS** ## Constants - **External cross-model verifier (Codex / `mcp__codex__codex`) is UNAVAILABLE** in this environment — persistent `401 Unauthorized` (no OpenAI bearer). Do **not** block on it and do **not** silently skip verification when it fails. - **EVALUATOR = Claude itself**, acting as an impartial, adversarial referee (Phase C). If Codex ever comes back, it may serve as an optional *second* opinion only. - Scoring is anchored to the **calibration rubric in Phase D.0** to prevent the score inflation observed when the Codex backend was down (2026-05: several econfin ideas were rated "9" but on rigorous re-check were 5–7.5). ## Instructions Given a method description, systematically verify its novelty: ### Phase A: Extract Key Claims 1. Read the user's method description 2. Identify 3-5 core technical claims that would need to be novel: - What is the method? - What problem does it solve? - What is the mechanism? - What makes it different from obvious baselines? ### Phase B: Multi-Source Literature Search For EACH core claim, search with ALL relevant sources — **adapt t
- Constants
- Instructions
- Phase A: Extract Key Claims
- Phase B: Multi-Source Literature Search
- Phase C: Adversarial Self-Verification (impartial referee)
- Phase D.0: Score Calibration (anchor EVERY score here — prevents inflation)
- Phase D: Novelty Report
- Important Rules
What does the novelty-check skill do?
Verify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.
How do I install it?
Run `npx skills add brycewang-stanford/Auto-Empirical-Research-Skills --skill novelty-check --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From brycewang-stanford/Auto-Empirical-Research-Skills, a repository with 3,244 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.