# paperreview

Uploads a paper PDF to paperreview.ai over HTTP and fetches the finished review by token. No browser in the loop.

- 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/paperreview/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/paperreview

## What it does

The skill follows the site's own three steps: it asks for a temporary upload link, pushes the PDF into S3, then confirms so processing starts and a token is issued. A small Python script, `scripts/submit_http.py`, does the work, so nothing opens a browser.

\`--submit` is the point of no return. It files a real submission and returns a token you cannot regenerate later. Run `--dry-run` first to see what the script validates without any network call. Your email is not baked in anywhere, so pass it with `--email` and set the venue with `--venue`. After a successful submit the token is written beside the PDF as `<pdf>.paperreview.token.txt` unless you add `--no-token-file`.

\`scripts/watch_review.py` polls `GET /api/review/<token>` every 10 minutes for up to 48 hours. A 202 means the job is still running, 200 means the review is ready; you get a timestamped raw JSON dump and a readable Markdown copy next to the PDF. `--once` does a single check for debugging or cron.

## Install

### Claude Code (native platform)

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

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

### Codex

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

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

### Cursor

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

2. **Manually: put the files in place**
- File: `.cursor/skills/paperreview/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/paperreview
```

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

### Gemini CLI

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

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

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/paperreview/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/paperreview/SKILL.md

## When to use it
- Send a near-final PDF out for an outside review without a browser
- See what the script checks before anything leaves your machine
- Pull the finished review by token and keep it beside the paper
- Poll the review endpoint on a schedule without losing the result
- Keep your email address out of repo defaults

## Example prompts
- Dry-run `paper.pdf` first and show me what the script checked, without submitting anything.
- Submit `paper.pdf` to paperreview.ai for the ICLR venue; I'll give you the email address to use.
- Start `scripts/watch_review.py` on `paper.pdf` and tell me when the review files appear.

## Similar
- [idea-discovery](https://affpapa.org/en/nevibecode/skills/idea-discovery.md) — skill · 639 installs
- [research-refine](https://affpapa.org/en/nevibecode/skills/research-refine.md) — skill · 584 installs
- [ccf-paper-reviewer](https://affpapa.org/en/nevibecode/skills/ccf-paper-reviewer.md) — skill · 2300 installs
- [research-writing-skill](https://affpapa.org/en/nevibecode/skills/research-writing-skill.md) — skill · 979 installs
- [pre-submission-reviewer](https://affpapa.org/en/nevibecode/skills/pre-submission-reviewer.md) — skill · 931 installs
- [paper-self-review](https://affpapa.org/en/nevibecode/skills/paper-self-review.md) — skill · 702 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
