# test-skill

Tests agent skills before deployment using a TDD cycle with pressure scenarios. Reveals when an assistant bypasses rules and invents excuses.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 1200 installs · ★ 1787
- Author: NeoLabHQ
- License: GPL-3.0 · policy=link-only · description only; the file stays with the author
- Source: https://github.com/NeoLabHQ/context-engineering-kit/tree/HEAD/skills/test-skill/SKILL.md
- Updated: 2026-08-26
- HTML: https://affpapa.org/en/nevibecode/skills/test-skill

## What it does

This skill adapts test-driven development to process documentation and instructions. The workflow mirrors the standard red-green-refactor loop. You first put the agent in a high-pressure scenario without the skill. Deadlines, sunk costs, or conflicting instructions force a choice. You record the failures word for word.

Next, you write the minimal rules that address those recorded excuses. Testing pure reference documents like API guides is pointless because the agent has no incentive to bypass them. Run the scenario again with the skill loaded and close any remaining loopholes. Note that this workflow requires familiarity with `superpowers:test-driven-development` to understand the baseline testing cycle.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add NeoLabHQ/context-engineering-kit --skill test-skill -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add NeoLabHQ/context-engineering-kit --skill test-skill -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add NeoLabHQ/context-engineering-kit --skill test-skill -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install NeoLabHQ/context-engineering-kit test-skill
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add NeoLabHQ/context-engineering-kit --skill test-skill -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/NeoLabHQ/context-engineering-kit --path skills/test-skill
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add NeoLabHQ/context-engineering-kit --skill test-skill -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/NeoLabHQ/context-engineering-kit/tree/HEAD/skills/test-skill/SKILL.md

## When to use it
- expose instruction failures under simulated deadline pressure
- capture agent rationalizations before deploying a skill
- plug compliance loopholes in project rules
- apply the TDD cycle to process documentation

## Example prompts
- Run a baseline stress test for this skill without loading it.
- Apply the TDD workflow to verify our code review rules against rationalizations.

## Similar
- [test-driven-development](https://affpapa.org/en/nevibecode/skills/test-driven-development.md) — skill · 259292 installs
- [principle-test-behavior-not-implementation](https://affpapa.org/en/nevibecode/skills/principle-test-behavior-not-implementation.md) — skill · 5200 installs
- [codebase-cleanup-test-automator](https://affpapa.org/en/nevibecode/agents/codebase-cleanup-test-automator.md) — subagent · ★ 41729
- [adding-dbt-unit-test](https://affpapa.org/en/nevibecode/skills/adding-dbt-unit-test.md) — skill · 1100 installs
- [momentic-spec](https://affpapa.org/en/nevibecode/skills/momentic-spec.md) — skill · 28300 installs
- [bmad-agent-dev](https://affpapa.org/en/nevibecode/skills/bmad-agent-dev.md) — skill · 11900 installs

From the same set: [neolabhq/context-engineering-kit](https://affpapa.org/en/nevibecode/by/neolabhq/context-engineering-kit.md) — 64 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