# literature-review

Walks the agent through a research review: database search, screening, synthesis, citation formatting and a PRISMA diagram.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 342 installs · ★ 7
- Author: eyadsibai
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/eyadsibai/ltk/tree/HEAD/plugins/ltk-product/skills/literature-review/SKILL.md
- Updated: 2026-01-15
- HTML: https://affpapa.org/en/nevibecode/skills/eyadsibai-literature-review

## What it does

The skill breaks a review into five phases. It starts with the research question — PICO for clinical work — and the review type: narrative, systematic or scoping. Then comes the search strategy: key terms, synonyms, Boolean operators, with syntax notes per database.

A table lists PubMed, arXiv, Semantic Scholar, Google Scholar and Web of Science. Screening runs twice, first on titles and abstracts, then on full text, and exclusion reasons get recorded. Synthesis is organized by theme, with a comparison table for methods, sample and findings. Citation templates cover APA 7, Nature and Vancouver; Zotero, Mendeley and EndNote are named as managers.

Quality assessment is split by study design: Cochrane Risk of Bias for RCTs, Newcastle-Ottawa for observational work, CASP for qualitative. There is a PRISMA flow diagram and a section on common pitfalls — publication bias, English-only searches, searches left stale before submission. If you want a review someone else can reproduce, that last point is the one to watch.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add eyadsibai/ltk --skill literature-review -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add eyadsibai/ltk --skill literature-review -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add eyadsibai/ltk --skill literature-review -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install eyadsibai/ltk literature-review
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add eyadsibai/ltk --skill literature-review -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/eyadsibai/ltk --path plugins/ltk-product/skills/literature-review
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add eyadsibai/ltk --skill literature-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/eyadsibai/ltk/tree/HEAD/plugins/ltk-product/skills/literature-review/SKILL.md

## When to use it
- frame a research question with the PICO framework
- build a Boolean search strategy for a specific database
- screen papers against inclusion criteria and log exclusions
- group findings into a thematic synthesis
- format a bibliography in APA 7, Nature or Vancouver

## Example prompts
- Run a systematic review on this topic: build the search strategy and query PubMed and Semantic Scholar
- Synthesize the papers you found by theme and point out the research gaps
- Format the source list in APA 7 and draw a PRISMA diagram from the screening counts

## Similar
- [tooluniverse-literature-deep-research](https://affpapa.org/en/nevibecode/skills/tooluniverse-literature-deep-research.md) — skill · 664 installs
- [systematic-literature-review](https://affpapa.org/en/nevibecode/skills/systematic-literature-review.md) — skill · 2500 installs
- [medical-imaging-review](https://affpapa.org/en/nevibecode/skills/medical-imaging-review.md) — skill · 691 installs
- [lit-review](https://affpapa.org/en/nevibecode/skills/lit-review.md) — skill · ★ 1668
- [research-survey](https://affpapa.org/en/nevibecode/skills/research-survey.md) — skill · 300 installs
- [obsidian-literature-workflow](https://affpapa.org/en/nevibecode/skills/obsidian-literature-workflow.md) — skill · 408 installs

## Other versions with the same name
- [literature-review · k-dense-ai](https://affpapa.org/en/nevibecode/skills/k-dense-ai-literature-review.md) — 2300 installs
- [literature-review · lingzhi227](https://affpapa.org/en/nevibecode/skills/lingzhi227-literature-review.md) — 4000 installs
- [literature-review · collaborative-deep-research](https://affpapa.org/en/nevibecode/skills/collaborative-deep-research-literature-review.md) — 732 installs

From the same set: [eyadsibai/ltk](https://affpapa.org/en/nevibecode/by/eyadsibai/ltk.md) — 2 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