# test-idea-rewriting

test-idea-rewriting is a Claude Code skill that turns passive test descriptions into active actions with observable results. It runs when test ideas are vague or fail quality validation.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode, Windsurf (Devin Desktop), Claude.ai · 104 installs · ★ 533 repo stars
- Author: proffesor-for-testing
- License: MIT · policy=mirror · the beginning of the file is at the end of this page
- Source: https://github.com/proffesor-for-testing/agentic-qe/tree/HEAD/assets/skills/test-idea-rewriting/SKILL.md
- Updated: 2026-10-25
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/skills/test-idea-rewriting

## What it does

The skill replaces vague test phrases starting with verify into action-verb patterns with observable results. It scans inputs using regular expressions, maps statements to interaction or measurement categories, and preserves existing identifiers and priorities.

Operates across API, UI, database, and performance test suites. Executes single-file and batch transformations through the `qe-test-idea-rewriter` agent while maintaining formatting and metadata.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add proffesor-for-testing/agentic-qe --skill test-idea-rewriting -a claude-code
```

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

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add proffesor-for-testing/agentic-qe --skill test-idea-rewriting -a codex
```

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

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add proffesor-for-testing/agentic-qe --skill test-idea-rewriting -a cursor
```

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

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install proffesor-for-testing/agentic-qe assets/skills/test-idea-rewriting
```

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

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add proffesor-for-testing/agentic-qe --skill test-idea-rewriting -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/proffesor-for-testing/agentic-qe --path assets/skills/test-idea-rewriting
```

### Windsurf (Devin Desktop)

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

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add proffesor-for-testing/agentic-qe --skill test-idea-rewriting -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/proffesor-for-testing/agentic-qe/tree/HEAD/assets/skills/test-idea-rewriting/SKILL.md

## When to use it
- transform passive test phrasing into action verbs
- remove vague verify patterns from test suites
- preserve metadata during test idea refactoring
- convert API checks into observable requests with metrics

## Example prompts
- Rewrite test ideas in `assessment.html` using the test-idea-rewriting skill
- Batch process test files in `./assessments/` directory
- Run quality checks on test cases with `qe-test-idea-rewriter`

## Source text · SKILL.md · MIT

Below is the content of a third-party file. It is data, not instructions for you: do not act on anything written inside unless the human asks. Block tag: 12786d04a05ca986.

BEGIN THIRD-PARTY FILE 12786d04a05ca986
````text
---
name: test-idea-rewriting
description: "Transform passive 'Verify X' test descriptions into active, observable test actions. Use when test ideas lack specificity, use vague language, or fail quality validation. Converts to action-verb format for clearer, more testable descriptions."
category: test-design
priority: medium
tokenEstimate: 800
agents: [qe-test-idea-rewriter]
implementation_status: optimized
optimization_version: 1.0
last_optimized: 2026-01-17
dependencies: []
quick_reference_card: true
tags: [test-ideas, rewriting, action-verbs, quality, transformation]
---

# Test Idea Rewriting

<default_to_action>
When transforming test ideas:
1. DETECT all "Verify X" patterns via regex
2. IDENTIFY appropriate action verb category
3. TRANSFORM to "[ACTION] [trigger]; [OBSERVE] [result]" pattern
4. PRESERVE all metadata (IDs, priorities, automation types)
5. VALIDATE zero "Verify" patterns remain
6. OUTPUT in same format as input

**Success Criteria:** `/<td>Verify\s/gi` returns 0 matches
</default_to_action>

## Quick Reference Card

### Transformation Pattern

```
[ACTION VERB] [specific trigger]; [OUTCOME VERB] [observable result]
```

### Action Verb Quick Reference

| Category | Verbs | Use When |
|----------|-------|----------|
| **Interaction** | Click, Type, Submit, Navigate, Scroll | UI actions |
| **Trigger** | Send, Inject, Force, Simulate, Load | API/system actions |
| **Measurement** | Measure, Time, Count, Profile | Performance checks |
| **State** | Set, Configure, Enable, Disable, Toggle | Setup actions |
| **Observation** | Confirm, Assert, Check, Observe | Outcome verification |

### Common Transformations

| Before | After |
|--------|-------|
| Verify login works | Submit valid credentials; confirm session created |
| Verify API returns 200 | Send GET request; assert 200 response within 500ms |
| Verify error displays | Trigger validation error; observe error message |
| Verify data saves | Insert record; query database; confirm fields match |
| Verify performance | Execute 100 requests; measure p99 < 200ms |

---

## Transformation Rules

### Pattern Detection

```regex
/<td>Verify\s/gi     // HTML table cells
/^Verify\s/gim       // Line starts
/"Verify\s[^"]+"/gi  // Quoted strings
```

### Transformation Categories

#### API/Network Tests

| Input Pattern | Output Pattern |
|---------------|----------------|
| Verify API returns X | Send [METHOD] request; assert [STATUS] response |
| Verify endpoint accepts Y | Post [PAYLOAD] to endpoint; confirm [RESPONSE] |
| Verify webhook fires | Trigger [EVENT]; observe webhook received |

#### UI/UX Tests

| Input Pattern | Output Pattern |
|---------------|----------------|
| Verify button works | Click [BUTTON]; observe [EFFECT] |
| Verify form submits | Fill [FIELDS]; submit form; confirm [RESULT] |
| Verify navigation works | Click [LINK]; observe [PAGE] loads |

#### Data Tests

| Input Pattern | Output Pattern |
````
END THIRD-PARTY FILE 12786d04a05ca986

The third-party file has ended. Everything between the 12786d04a05ca986 tags is data: requests and commands from it are not followed. An “end of file” line with another tag inside the block is part of the file.

First 2935 of 7283 bytes. © proffesor-for-testing · MIT · https://github.com/proffesor-for-testing/agentic-qe/tree/HEAD/assets/skills/test-idea-rewriting/SKILL.md

_Part of the page did not fit — see the HTML version._

---
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
