# scholar-evaluation

The scholar-evaluation skill reviews papers, literature reviews, and research methods against structured criteria. Use it when you need a reasoned academic assessment or revision notes.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 1 install · ★ 607 repo stars
- Author: jimmc414
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/jimmc414/Kosmos/tree/HEAD/kosmos-claude-scientific-skills/scientific-skills/scholar-evaluation/SKILL.md
- Updated: 2026-10-09
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/jimmc414-scholar-evaluation

## What it does

scholar-evaluation breaks scholarly work into review areas such as research questions, prior work, study design, data, analysis, findings, writing, and references. For each relevant area, the agent records strengths, weaknesses, critical issues, and optional scores on a 1–5 scale.

It covers research papers, proposals, protocols, literature reviews, dissertation chapters, conference abstracts, and short papers. The package includes `references/evaluation_framework.md` with rubrics and assessment criteria. If the requested scope is unclear, the skill asks the user to define it first. Aggregate scoring can use `scripts/calculate_scores.py`.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add jimmc414/Kosmos --skill scholar-evaluation -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add jimmc414/Kosmos --skill scholar-evaluation -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add jimmc414/Kosmos --skill scholar-evaluation -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install jimmc414/Kosmos kosmos-claude-scientific-skills/scientific-skills/scholar-evaluation
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add jimmc414/Kosmos --skill scholar-evaluation -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/jimmc414/Kosmos --path kosmos-claude-scientific-skills/scientific-skills/scholar-evaluation
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add jimmc414/Kosmos --skill scholar-evaluation -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/jimmc414/Kosmos/tree/HEAD/kosmos-claude-scientific-skills/scientific-skills/scholar-evaluation/SKILL.md

## When to use it
- review a research paper against explicit criteria
- inspect a study design for methodological issues
- assess the coverage and synthesis of a literature review
- check whether findings support the claims
- turn review findings into ranked revision actions

## Example prompts
- Evaluate this research paper across all ScholarEval dimensions and list the main issues.
- Review the literature review and methodology in `paper.md`, then score each area from 1 to 5.
- Write a structured assessment with strengths, critical weaknesses, and prioritized changes.

## Similar
- [research-craft](https://affpapa.org/en/nevibecode/skills/research-craft.md) — skill · 153 installs
- [Academic Research MCP — ArXiv & Google Scholar](https://affpapa.org/en/nevibecode/mcp/academic-research-mcp-arxiv-google-scholar.md) — MCP server · 6779 installs
- [research-expert](https://affpapa.org/en/nevibecode/skills/research-expert.md) — skill · 256 installs
- [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
- [thesis-advisor](https://affpapa.org/en/nevibecode/skills/thesis-advisor.md) — skill · ★ 12746 repo stars

## Other versions with the same name
- [scholar-evaluation · k-dense-ai](https://affpapa.org/en/nevibecode/skills/k-dense-ai-scholar-evaluation.md) — 2300 installs

From the same set: [jimmc414/kosmos](https://affpapa.org/en/nevibecode/by/jimmc414/kosmos.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
