# ai-eval-playbook

ai-eval-playbook is a Claude Code skill for assessing AI tools, chatbots, and GenAI products. It comes into play when a team needs evaluation measures or a review of an AI tool proposal.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 118 installs · ★ 3 repo stars
- Author: gasserane
- License: not stated · policy=link-only · description only; the file stays with the author
- Source: https://github.com/gasserane/personal-skills/tree/HEAD/skills/ai-eval-playbook/SKILL.md
- Updated: 2026-10-23
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/ai-eval-playbook

## What it does

The skill frames product evaluation across four levels: model, product, user, and impact. Its scope includes minimum viable evaluations, golden datasets, LLM-as-judge methods, engagement measures, and guardrail metrics.

Before giving a substantive answer, it requires fetching the current playbook from `https://eval.playbook.org.ai/`. The fetch options include `WebFetch` and `ctx_fetch_and_index`, with `claude-in-chrome` as a fallback. It does not cover programme or MEL evaluation design, or AI used as an evaluator’s working tool.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add gasserane/personal-skills --skill ai-eval-playbook -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add gasserane/personal-skills --skill ai-eval-playbook -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add gasserane/personal-skills --skill ai-eval-playbook -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install gasserane/personal-skills skills/ai-eval-playbook
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add gasserane/personal-skills --skill ai-eval-playbook -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/gasserane/personal-skills --path skills/ai-eval-playbook
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add gasserane/personal-skills --skill ai-eval-playbook -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/gasserane/personal-skills/tree/HEAD/skills/ai-eval-playbook/SKILL.md

## When to use it
- choose an evaluation level for an AI product
- select measures for a chatbot evaluation
- appraise an AI tool proposal

## Example prompts
- How should we evaluate this AI tool?
- Which measures should we track for this chatbot?
- Review this partner’s AI tool proposal and outline an evaluation.

## Similar
- [gsd-eval-review](https://affpapa.org/en/nevibecode/skills/gsd-eval-review.md) — skill · 570 installs
- [agent-platform-eval-flywheel](https://affpapa.org/en/nevibecode/skills/agent-platform-eval-flywheel.md) — skill · 8334 installs
- [google-agents-cli-eval](https://affpapa.org/en/nevibecode/skills/google-agents-cli-eval.md) — skill · 586000 installs
- [searching-mlflow-docs](https://affpapa.org/en/nevibecode/skills/searching-mlflow-docs.md) — skill · 1100 installs
- [eval-driven-dev](https://affpapa.org/en/nevibecode/skills/eval-driven-dev.md) — skill · 3900 installs
- [eval-harness-first](https://affpapa.org/en/nevibecode/skills/eval-harness-first.md) — skill · 2600 installs

From the same set: [gasserane/personal-skills](https://affpapa.org/en/nevibecode/by/gasserane/personal-skills.md) — 44 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
