Research Review

Sends your research work to an external AI reviewer (GPT-5.5 by default via Codex MCP, or manual review backend) and runs a multi-round critical dialogue at maximum reasoning depth. It compiles your project context, asks for NeurIPS-level feedback on claims and methodology, then iterates on weaknesses until you have a concrete experiment plan and claims matrix. Best when you need honest criticism before you burn GPU weeks or submit to a venue. The workflow saves full conversation traces and produces a standalone review document with actionable TODOs ranked by acceptance lift per compute hour. You can push back on criticisms in follow-up rounds, which is the point: it's a conversation, not a one-shot roast.

Install to Claude Code

npx -y skills add wanshuiyin/auto-claude-code-research-in-sleep --skill research-review --agent claude-code