# paper-review-pipeline

paper-review-pipeline is a Claude Code skill that reviews near-final ML conference papers section by section, prioritizes issues from P0 to P2, and drafts rebuttal responses.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf (Devin Desktop), Claude.ai · ★ 475 repo stars
- Author: cnfjlhj
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/cnfjlhj/ai-collab-playbook/tree/HEAD/skills/full/paper-review-pipeline/SKILL.md
- Updated: 2026-10-13
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/paper-review-pipeline

## What it does

The skill runs a two-sided review of an almost-finished paper aimed at venues like ICML, ICLR, NeurIPS or AAAI. One pass goes section by section — Abstract, Introduction, Method, Experiments and onward — with concrete edit suggestions. The other builds a prioritized issue list grouped by category: narrative, evidence, experimental design, statistics, reproducibility, citations, formatting. Each entry gets a P0, P1 or P2 tag, a section anchor and a proposed fix.

A separate track handles reviewer feedback: it parses comments, sorts them by type and drafts a point-by-point rebuttal within a stated word or page limit. Citations that can't be verified get flagged as `[CITATION NEEDED]` rather than invented. When touching LaTeX source, the skill avoids breaking `\cite{}`, `\ref{}`, `\label{}` or math environments.

For a near-final PDF, the skill finishes its own review first and only then asks whether to hand off to the external `paperreview` service — it won't submit anything on its own.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add cnfjlhj/ai-collab-playbook --skill paper-review-pipeline -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/paper-review-pipeline/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/paper-review-pipeline/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add cnfjlhj/ai-collab-playbook --skill paper-review-pipeline -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/paper-review-pipeline/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add cnfjlhj/ai-collab-playbook --skill paper-review-pipeline -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/paper-review-pipeline/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install cnfjlhj/ai-collab-playbook skills/full/paper-review-pipeline
```

2. **Manually: put the files in place**
- File: `.github/skills/paper-review-pipeline/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add cnfjlhj/ai-collab-playbook --skill paper-review-pipeline -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/cnfjlhj/ai-collab-playbook --path skills/full/paper-review-pipeline
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/paper-review-pipeline/SKILL.md` — The legacy .windsurf/skills/ path still works

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/cnfjlhj/ai-collab-playbook/tree/HEAD/skills/full/paper-review-pipeline/SKILL.md

## When to use it
- break a paper down by section and flag weak spots
- build a P0–P2 issue list sorted by category
- catch citations that don't match the claims they support
- draft a point-by-point rebuttal to reviewer comments
- run a pre-submission check before sharing with an advisor

## Example prompts
- Run paper-review-pipeline on my ICLR draft and list the P0 issues
- Parse these reviewer comments and help me draft a rebuttal
- Check the Experiments section for missing baselines and stats reporting

## Similar
- [paper-write](https://affpapa.org/en/nevibecode/skills/paper-write.md) — skill · 596 installs
- [paper-audit](https://affpapa.org/en/nevibecode/skills/paper-audit.md) — skill · 3600 installs
- [paper-revision](https://affpapa.org/en/nevibecode/skills/paper-revision.md) — skill · 1900 installs
- [paper-editor](https://affpapa.org/en/nevibecode/skills/paper-editor.md) — skill · ★ 165 repo stars
- [revise-paper](https://affpapa.org/en/nevibecode/skills/revise-paper.md) — skill · ★ 240 repo stars
- [paper-review](https://affpapa.org/en/nevibecode/skills/evoscientist-paper-review.md) — skill · 530 installs

From the same set: [cnfjlhj/ai-collab-playbook](https://affpapa.org/en/nevibecode/by/cnfjlhj/ai-collab-playbook.md) — 18 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
