Test Hardening logo

Test Hardening

Organization
WellApp-ai
test-hardening

Convert passed QA Contract criteria to automated tests

Overview

PublisherWellApp-ai
RepositoryWell
Skill nametest-hardening
Stars
342
Forks
48
Bundled files
Instructions only
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • Self-contained

    Everything the model needs lives in the instructions — no extra files to sync.

  • Open source

    Published by WellApp-ai on GitHub. Read the source before you install it.

Installation

Install the Test Hardening AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/WellApp-ai/Well.git /tmp/Well
mkdir -p .claude/skills
cp -r /tmp/Well/cursor-rules/skills/test-hardening .claude/skills/test-hardening
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Test Hardening in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Test Hardening on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Test Hardening is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Test Hardening Skill

Convert verified QA Contract criteria (G#N, AC#N) into permanent automated tests. Ensures passing scenarios become regression tests.

When to Use

  • After qa-commit returns GREEN for a commit
  • After debug skill fixes an issue (Phase 7: Harden)
  • Before pushing PR (ensure all criteria have tests)
  • Manually with "use test-hardening skill"

Input: Verification Report

From qa-commit's Verification Report:

  • List of passed G#N (Gherkin scenarios)
  • List of passed AC#N (acceptance criteria)

Phase 1: Analyze Criteria

1.1 Categorize by Test Type

Criteria TypeTest FrameworkLocation
G#N (Backend)Jestapps/api/**/*.test.ts
AC#N (UI State)Storybook**/*.stories.tsx
AC#N (Interaction)Playwrighttests/e2e/**/*.spec.ts

1.2 Check Existing Tests

Grep: "G#[N]" or "[scenario name]" in test files

Skip if test already exists.

Phase 2: Generate Backend Tests (G#N)

For each passed G#N without existing test:

2.1 Template

typescript
// apps/api/src/[feature]/__tests__/[feature].test.ts

describe('[Feature Name]', () => {
  // G#1: [Scenario name]
  it('should [expected behavior]', async () => {
    // Arrange
    const input = { /* test data */ };
    
    // Act
    const response = await request(app)
      .[method]('[endpoint]')
      .send(input);
    
    // Assert
    expect(response.status).toBe([status]);
    expect(response.body).toMatchObject({ /* expected */ });
  });

  // G#2: [Scenario name]
  it('should return [error] when [condition]', async () => {
    // Test implementation
  });
});

2.2 Generate Test

  1. Extract endpoint, method, expected response from G#N
  2. Create test file if not exists
  3. Add test case with G#N reference in comment
  4. Run test to verify it passes
bash
npm run test -- --grep "[scenario name]"

Phase 3: Generate Storybook Stories (AC#N - States)

For state-based AC#N:

3.1 Template

typescript
// apps/web/src/[component]/[Component].stories.tsx

import type { Meta, StoryObj } from '@storybook/react';
import { Component } from './Component';

const meta: Meta<typeof Component> = {
  title: 'Features/[Feature]/[Component]',
  component: Component,
};

export default meta;
type Story = StoryObj<typeof Component>;

// AC#1: Renders without error
export const Default: Story = {
  args: { /* default props */ },
};

// AC#2: Shows loading state
export const Loading: Story = {
  args: { isLoading: true },
};

// AC#3: Shows error state
export const Error: Story = {
  args: { error: 'Something went wrong' },
};

// AC#4: Shows empty state
export const Empty: Story = {
  args: { data: [] },
};

3.2 Generate Story

  1. Check if stories file exists
  2. Add missing story variants for each AC#N
  3. Run Storybook to verify renders
bash
npm run storybook -- --smoke-test

Phase 4: Generate E2E Tests (AC#N - Interactions)

For interaction-based AC#N:

4.1 Template

typescript
// tests/e2e/[feature].spec.ts

import { test, expect } from '@playwright/test';

test.describe('[Feature Name]', () => {
  // AC#5: User can submit form
  test('should allow form submission', async ({ page }) => {
    await page.goto('/[route]');
    
    await page.fill('[name="field"]', 'value');
    await page.click('[type="submit"]');
    
    await expect(page.locator('.success')).toBeVisible();
  });

  // AC#6: Keyboard navigation works
  test('should support keyboard navigation', async ({ page }) => {
    await page.goto('/[route]');
    
    await page.keyboard.press('Tab');
    await expect(page.locator(':focus')).toHaveAttribute('name', 'first-field');
  });
});

4.2 Generate Test

  1. Check if E2E test file exists
  2. Add test case for each interaction AC#N
  3. Run Playwright to verify
bash
npx playwright test [feature].spec.ts

Phase 5: Verify Tests Pass

Run all generated tests:

bash
# Backend
npm run test

# Storybook
npm run storybook -- --smoke-test

# E2E (if applicable)
npx playwright test

Phase 6: Update Test Summary

markdown
## Test Hardening Report

### Generated Tests

| Criteria | Type | File | Status |
|----------|------|------|--------|
| G#1 | Jest | `[path]` | CREATED/EXISTS |
| G#2 | Jest | `[path]` | CREATED/EXISTS |
| AC#1 | Storybook | `[path]` | CREATED/EXISTS |
| AC#3 | Playwright | `[path]` | CREATED/EXISTS |

### Test Results

| Suite | Total | Passed | Failed |
|-------|-------|--------|--------|
| Jest | [N] | [N] | 0 |
| Storybook | [N] | [N] | 0 |
| Playwright | [N] | [N] | 0 |

### Coverage Update

- Backend: [N]% → [N]%
- Frontend: [N]% → [N]%

Integration with Debug

When invoked from debug skill Phase 7 (Harden):

  1. Receive the reproduction steps from debug
  2. Create regression test to prevent recurrence
  3. Add test with reference to original issue
typescript
// Regression test for [issue description]
// Debug session: [date]
it('should not [bug behavior] when [condition]', async () => {
  // Reproduction steps from debug
});

Invocation

Invoked by:

  • qa-commit - After GREEN verdict
  • debug - Phase 7 Harden
  • Push-pr mode - Pre-push verification

Or manually with "use test-hardening skill".

Frequently asked questions

What does the Test Hardening AI skill do?

Convert passed QA Contract criteria to automated tests

Why use Test Hardening on TypingMind?

Because you install it once and use it with any model. Test Hardening is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Test Hardening in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/WellApp-ai/Well/tree/main/cursor-rules/skills/test-hardening. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Test Hardening?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Test Hardening?

As many as you like. As long as a model supports skills, you can use Test Hardening with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Test Hardening AI skill free?

Yes. It is published on GitHub by WellApp-ai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇