Research Review

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

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.

skills.sh installs: 595
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 research-review --agent claude-code

Installs into .claude/skills of the current project.

Files

Research Review via External Reviewer Backend (ultra reasoning)

🔒 Do not wrap this skill in /loop, /schedule, or CronCreate. It is verdict-bearing — it produces a cross-model review verdict, multi-round with reviewer thread continuity. An external timer re-fires the verdict on wall-clock time and breaks the reviewer's round-to-round memory: zero new signal, full token cost. Schedule the external wait that precedes it (work ready → then review once), not the verdict. See shared-references/external-cadence.md.

Get a multi-round critical review of research work from the selected external reviewer backend with maximum reasoning depth.