Novelty Check

wanshuiyin/auto-claude-code-research-in-sleep

Before you sink weeks into a research idea, this skill runs a systematic novelty check against recent literature. It breaks your proposed method into core technical claims, searches across arXiv, Google Scholar, and major venue proceedings, then calls a reasoning model to assess overlap with prior work. You get a brutally honest report scoring each claim, identifying the closest papers, and suggesting how to position the work if it's still viable. The skill enforces strict citation verification to avoid hallucinated references and includes cross-model validation with high reasoning effort. Best used when you have a concrete method description and need to know if someone already published it in the last conference cycle.

skills.sh installs: 588
GitHub stars: 18.9K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add wanshuiyin/auto-claude-code-research-in-sleep --skill novelty-check --agent claude-code

Installs into .claude/skills of the current project.

Files

Novelty Check Skill

Before each reviewer slot, follow Selectable Reviewers: resolve invocation → .aris/reviewer.json → Claude Code default (Codex MCP) with reviewer_route.py through the canonical helper resolver, preserving this slot's tier, fresh contexts, source/image inputs and deterministic gates. Codex examples/pins below apply only to backend=codex; other routes use their own first-call/reply contract. Save the route and actual returned identity; unavailable selections are REVIEW_UNAVAILABLE. Classify acceptance from actual families/completion/scope. Forward invocation reviewer/model/effort overrides to reviewer-bearing children. Generation workers are unchanged.

Check whether a proposed method/idea has already been done in the literature: $ARGUMENTS