Skip to content
Get packs

Research Review via External Reviewer

Gets a multi-round, adversarial critical review of your research from an external AI reviewer (Codex by default).

Source Download skill
Repository
wanshuiyin/Auto-claude-code-research-in-sleep
Stars
18,482
Licence
MIT
Files
1 file

What it does

When installed, the agent gathers your research notes, drafts and results into a briefing file, then sends it to a separate AI reviewer (by default OpenAI Codex, or Gemini, Grok, Claude Code or a manual route you choose). The reviewer is told to act like a strict ML conference reviewer and look for logical gaps, missing experiments, weak narrative and whether the contribution is strong enough for a top venue. The agent can continue the same review thread across rounds.

Great for

  • Researchers who want a harsh second opinion on a paper draft or experimental results before submission
  • Teams that want a cross-model review rather than relying on a single AI's judgement

Skip it if

  • Quick proofreading or grammar checks, since it is aimed at deep methodological critique and is slow and token-expensive
  • Confidential or unpublished work you do not want sent to a third-party AI service, because the briefing is transmitted to the chosen reviewer backend

Try asking

  • “Review my research and tell me where the logic is weakest”
  • “Get external review of my experimental results before I submit to NeurIPS”
  • “Help me review this research idea and list missing experiments”
Step-by-step guide: how to use Research Review via External ReviewerInstall, first run, examples, tips and FAQs

Install in 3 steps

  1. 1

    Download the skill

    The ZIP contains the 1 original files, the MIT licence and an attribution note.

    research-review.zip
  2. 2

    Add it to your agent

    Claude Code (all projects)

    mkdir -p ~/.claude/skills && unzip research-review.zip -d ~/.claude/skills/

    Claude Code / Agent SDK (this project only)

    mkdir -p .claude/skills && unzip research-review.zip -d .claude/skills/

    Claude apps (web/desktop): Settings → Capabilities → Skills → Upload skill, and choose the ZIP.

  3. 3

    Ask for the task

    No special command needed — the agent reads the skill's description and loads it when your request matches. Try one of the prompts above.

Get better results

  • Put your key narrative documents and notes in the project before running it, so the briefing is complete
  • Keep the same review thread for follow-up rounds rather than starting over, to preserve reviewer memory
  • Do not schedule it with /loop or cron; run it once work is ready, as the skill itself instructs

What's inside

  • SKILL.md

Redistributed unmodified from wanshuiyin/Auto-claude-code-research-in-sleep under the MIT licence. The assessment was drafted with AI from the skill's files on 2026-10-29. Skills can instruct your agent to run code — read SKILL.md and any scripts before installing.