# scientific-manuscript-review

A skill that walks a scientific manuscript through eight review passes: structure, sections, claim clarity, language and journal formatting.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 479 installs · ★ 186
- Author: lyndonkl
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/lyndonkl/claude/tree/HEAD/skills/scientific-manuscript-review/SKILL.md
- Updated: 2026-09-01
- HTML: https://affpapa.org/en/nevibecode/skills/scientific-manuscript-review

## What it does

The skill works through a manuscript step by step. It first pins down the document type and the one message readers should keep, then maps the overall organization against IMRaD, then reviews the introduction, results and discussion one at a time. After that comes a scientific clarity check — are claims backed by data, are statistics and controls described — and a language pass that also covers journal compliance.

Inside is an eight-step checklist you can copy and tick off as you go. The introduction gets a funnel pattern: broad context, narrowing to the topic, the knowledge gap, the hypothesis. Results get their own frame per figure or experiment: question, approach, finding with numbers, short interpretation. A rubric at `resources/evaluators/rubric_scientific_manuscript.json` sets a minimum average score of 3.5.

The skill reads text, not data. It will not recheck your calculations or match numbers against source tables. If the paper is already accepted and edits are frozen, eight passes is more than you need. The same author ships `grant-proposal-assistant` for grant applications and `academic-letter-architect` for recommendation letters.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill scientific-manuscript-review -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill scientific-manuscript-review -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill scientific-manuscript-review -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install lyndonkl/claude scientific-manuscript-review
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill scientific-manuscript-review -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/lyndonkl/claude --path skills/scientific-manuscript-review
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill scientific-manuscript-review -a opencode
```

### 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/lyndonkl/claude/tree/HEAD/skills/scientific-manuscript-review/SKILL.md

## When to use it
- map a manuscript into structural blocks and spot gaps between them
- state the knowledge gap explicitly in the introduction
- add interpretation to each figure instead of bare numbers
- separate data interpretation from speculation in the discussion
- make abbreviations and terminology consistent across the text

## Example prompts
- run my manuscript through the scientific-manuscript-review checklist
- go through the introduction and flag where the knowledge gap stays implicit
- do a results pass: every figure needs question, approach, finding and interpretation

## Similar
- [scientific-writing](https://affpapa.org/en/nevibecode/skills/k-dense-ai-scientific-writing.md) — skill · 2400 installs
- [academic-paper-review](https://affpapa.org/en/nevibecode/skills/academic-paper-review.md) — skill · 2700 installs
- [nature-writing](https://affpapa.org/en/nevibecode/skills/nature-writing.md) — skill · 15700 installs
- [scientific-toolkit-skill](https://affpapa.org/en/nevibecode/skills/scientific-toolkit-skill.md) — skill · 816 installs
- [scientific-critical-thinking](https://affpapa.org/en/nevibecode/skills/scientific-critical-thinking.md) — skill · 644 installs
- [Scientific Data Visualizer](https://affpapa.org/en/nevibecode/prompts/scientific-data-visualizer.md) — prompt · ★ 174597

From the same set: [lyndonkl/claude](https://affpapa.org/en/nevibecode/by/lyndonkl/claude.md) — 5 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