# prompt-engineer-toolkit

The prompt-engineer-toolkit Claude Code skill tests production prompts and scores model outputs. Use it to compare revisions, investigate regressions, and gate prompt changes before release.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 106 installs · ★ 1183 repo stars
- Author: borghei
- License: LicenseRef-MIT-Commons-Clause · policy=link-only · description only; the file stays with the author
- Source: https://github.com/borghei/Claude-Skills/tree/HEAD/engineering/prompt-engineer-toolkit/SKILL.md
- Updated: 2026-11-08
- Security check: automated, 2026-11-16 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/borghei-prompt-engineer-toolkit

## What it does

The skill treats prompts as versioned artifacts: build an evaluation suite, inspect prompt text, compare revisions, and score model responses. The toolkit includes `prompt_analyzer.py`, `prompt_diff.py`, and `eval_scorer.py`.

Evaluation cases compare actual outputs with `contains`, `regex`, or `exact` expectations. Set a score threshold with `--fail-under`; the scorer exits with code 1 when results fall below it. The analyzer and diff use text heuristics, so they cannot tell whether a prompt succeeds at its task. The evaluation suite does that.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill prompt-engineer-toolkit -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill prompt-engineer-toolkit -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill prompt-engineer-toolkit -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install borghei/Claude-Skills engineering/prompt-engineer-toolkit/SKILL.md
```

2. **Manually: put the files in place**
- File: `.github/skills/prompt-engineer-toolkit/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill prompt-engineer-toolkit -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/borghei/Claude-Skills --path engineering/prompt-engineer-toolkit
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add borghei/Claude-Skills --skill prompt-engineer-toolkit -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/borghei/Claude-Skills/tree/HEAD/engineering/prompt-engineer-toolkit/SKILL.md

## When to use it
- catch regressions in a revised production prompt
- compare two prompt versions and flag risky edits
- score model outputs against an evaluation suite
- spot vague wording and unnecessary prompt instructions

## Example prompts
- Analyze `assets/prompt_v1.txt` and flag vague wording or unnecessary instructions.
- Compare `assets/prompt_v1.txt` with `assets/prompt_v2.txt` and report risky changes.
- Score the outputs in `assets/sample_eval_suite.json` using `--fail-under 0.9`.

## Similar
- [prompt-engineer](https://affpapa.org/en/nevibecode/skills/httpsgithubcomjeffallan-prompt-engineer.md) — skill · 6100 installs
- [prompt-engineering](https://affpapa.org/en/nevibecode/skills/giuseppe-trisciuoglio-prompt-engineering.md) — skill · 4200 installs
- [prompt-engineering-patterns](https://affpapa.org/en/nevibecode/skills/prompt-engineering-patterns.md) — skill · 23418 installs
- [prompt-governance](https://affpapa.org/en/nevibecode/skills/prompt-governance.md) — skill · 40 installs
- [prompt-optimize](https://affpapa.org/en/nevibecode/commands/prompt-optimize.md) — command · ★ 42780 repo stars
- [senior-prompt-engineer](https://affpapa.org/en/nevibecode/skills/senior-prompt-engineer.md) — skill · 970 installs

## Other versions with the same name
- [prompt-engineer-toolkit · alirezarezvani](https://affpapa.org/en/nevibecode/skills/prompt-engineer-toolkit.md) — 623 installs

From the same set: [borghei/claude-skills](https://affpapa.org/en/nevibecode/by/borghei/claude-skills.md) — 120 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
