# chair

The chair Claude Code prompt combines independent reviews of a research proposal into one meta-review. It checks overlap claims against supplied papers and picks an initial experiment.

- prompt · `type=prompt` · Claude Code, ChatGPT · ★ 159 repo stars
- Author: saideao
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/saideao/research-idea-review/tree/HEAD/src/idea_review/prompts/en/chair.md
- Updated: 2026-11-02
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/prompts/chair

## What it does

The prompt turns reviewer feedback into a JSON meta-review. It merges duplicate concerns, records which reviewers raised each issue, and orders them by severity. For overlap claims, it compares the reviewers’ statements with supplied reading notes and paper excerpts, cites page numbers, and labels judgments as paper-based or inferred.

The result also covers reviewer disagreements, questions for the author, and an experiment to test the idea first. That experiment includes a comparison, a metric, stop and continue criteria, and a duration in days. Supply the proposal, reviewers’ JSON meta-reviews, notes on related papers, and full-text excerpts of cited or overlapping papers. Work outside those materials is marked as unverifiable.

## Install

### Claude Code (native platform)

**Manually: put the files in place**
- File: `.claude/commands/chair.md`

### ChatGPT

**How to use**
- Paste the text at the start of a chat or into project instructions

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/saideao/research-idea-review/tree/HEAD/src/idea_review/prompts/en/chair.md

## When to use it
- combine repeated concerns from multiple reviewers
- check claims that a related paper already covers the proposal
- identify conflicting reviewer judgments
- choose an early experiment that could falsify the idea

## Example prompts
- Combine these reviews into one meta-review and check the overlap claims against the attached papers.
- Compare the reviewers’ judgments, list their disagreements, and select an experiment to test the proposal first.
- Extract the main risks, questions for the author, and claims that need checking against the full texts.

## Similar
- [academic-research-suite](https://affpapa.org/en/nevibecode/skills/academic-research-suite.md) — skill · 2200 installs
- [academic-research](https://affpapa.org/en/nevibecode/skills/academic-research.md) — skill · 148 installs
- [paper-reading-problem-reality-check](https://affpapa.org/en/nevibecode/skills/paper-reading-problem-reality-check.md) — skill · ★ 240 repo stars
- [research-co-pilot](https://affpapa.org/en/nevibecode/plugins/research-co-pilot.md) — plugin · ★ 15 repo stars
- [academic-researcher](https://affpapa.org/en/nevibecode/agents/academic-researcher.md) — subagent · 1855 installs
- [peer-review](https://affpapa.org/en/nevibecode/skills/poemswe-peer-review.md) — skill · 247 installs

From the same set: [saideao/research-idea-review](https://affpapa.org/en/nevibecode/by/saideao/research-idea-review.md) — 8 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
