# evaluation-rubrics

Builds a rubric with explicit criteria, a scale and level descriptors so the same work gets scored the same way twice.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 784 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/evaluation-rubrics/SKILL.md
- Updated: 2026-09-01
- HTML: https://affpapa.org/en/nevibecode/skills/evaluation-rubrics

## What it does

The skill walks the agent through six steps: define purpose and scope, pick criteria, design the scale, write descriptors for each level, calibrate on sample work, then iterate. Templates for each step sit alongside a methodology file covering scale design and calibration.

Criteria are meant to be observable rather than impressionistic — the test is whether two independent reviewers score the same item the same way. The skill suggests a 1–4 or 1–5 scale, with 4–8 criteria covering the dimensions that matter. Descriptors have to separate adjacent levels concretely, not just say "good" and "very good".

Five patterns are laid out: analytic, holistic, single-point, binary checklist and standards-based. Calibration needs several reviewers on the same samples; if their scores drift apart, the descriptors are the thing to rewrite.

## Install

### Claude Code (native platform)

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

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

### Codex

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

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

### Cursor

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

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install lyndonkl/claude evaluation-rubrics
```

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

### Gemini CLI

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

2. **Platform CLI**
```bash
gemini skills install https://github.com/lyndonkl/claude --path skills/evaluation-rubrics
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add lyndonkl/claude --skill evaluation-rubrics -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/evaluation-rubrics/SKILL.md

## When to use it
- build a rubric for grading articles or code against named criteria
- compare several candidate solutions on one scale
- set an acceptance threshold for a pull request or a draft
- cut the spread between scores from different reviewers
- rewrite level descriptors that read too much alike

## Example prompts
- Build a 1–5 rubric for technical blog posts: accuracy, clarity, practical value, originality
- Score these two architecture options against one rubric and show where they diverge
- Check my code review rubric: are the criteria observable and the levels distinct?

## Similar
- [scholar-evaluation](https://affpapa.org/en/nevibecode/skills/k-dense-ai-scholar-evaluation.md) — skill · 2100 installs
- [agent-evaluation](https://affpapa.org/en/nevibecode/skills/mlflow-agent-evaluation.md) — skill · 1100 installs
- [llm-evaluation](https://affpapa.org/en/nevibecode/skills/llm-evaluation.md) — skill · 12755 installs
- [self-eval](https://affpapa.org/en/nevibecode/skills/self-eval.md) — skill · 575 installs
- [code-review](https://affpapa.org/en/nevibecode/skills/jwynia-code-review.md) — skill · 498 installs
- [code-review-and-quality](https://affpapa.org/en/nevibecode/skills/code-review-and-quality.md) — skill · 73200 installs

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