test-generator — Claude Code skill: what it does, how to install
test-generator produces initial unit test scaffolding for new functions and UI components across popular testing libraries.
MIT ★ 788 updated 2026-07-03
npx skills add alirezarezvani/claude-code-tresor --skill test-generator -a claude-codeWhat test-generator does
The skill triggers whenever new functions or components appear in the codebase, or when you explicitly ask for tests. It generates baseline test suites containing primary success scenarios, error handling, and null input checks, alongside TODO reminders for complex edge cases. Operating entirely on local files, it relies on read and write permissions without network calls.
Testing libraries are detected automatically through dependency manifests and existing imports: Jest, Vitest, Mocha, pytest, unittest, JUnit, and Go testing package are supported out of the box.
Integration suites and end-to-end workflows remain out of scope for this skill because it only handles quick scaffolding.
What it helps with
- scaffold unit tests for newly written functions
- generate component tests with React Testing Library
- cover edge cases for null and invalid inputs
- identify existing test frameworks across project files
Example prompts for the agent
- Generate unit tests for calculateDiscount in utils.js
- Create test scaffolding for the UserCard component
- Add pytest cases for this python module
How to install test-generator
1Skills CLI (Vercel)
npx skills add alirezarezvani/claude-code-tresor --skill test-generator -a claude-code2Manually: put the files in place
~/.claude/skills/test-generator/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/test-generator/
1Skills CLI (Vercel)
npx skills add alirezarezvani/claude-code-tresor --skill test-generator -a codex2Manually: put the files in place
.agents/skills/test-generator/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add alirezarezvani/claude-code-tresor --skill test-generator -a cursor2Manually: put the files in place
.cursor/skills/test-generator/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install alirezarezvani/claude-code-tresor skills/development/test-generator2Manually: put the files in place
.github/skills/test-generator/SKILL.md1Skills CLI (Vercel)
npx skills add alirezarezvani/claude-code-tresor --skill test-generator -a gemini-cli2Platform CLI
gemini skills install https://github.com/alirezarezvani/claude-code-tresor --path skills/development/test-generatorManually: put the files in place
.devin/skills/test-generator/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about test-generator
How to install test-generator in Claude Code?
Run npx skills add alirezarezvani/claude-code-tresor --skill test-generator -a claude-code in your terminal.
What test runners does test-generator support?
It detects and writes tests for Jest, Vitest, Mocha, pytest, unittest, JUnit, and standard Go testing.
Does test-generator produce full integration test suites?
No, it focuses strictly on basic scaffolding, happy paths, and initial edge cases.
Source text
SKILL.md · MIT
---
name: test-generator
description: Automatically suggest tests for new functions and components. Use when new code is written, functions added, or user mentions testing. Creates test scaffolding with Jest, Vitest, Pytest patterns. Triggers on new functions, components, test requests, testing mentions.
allowed-tools: Read, Write, Edit
---
# Test Generator Skill
Auto-suggest tests when you write new code.
## When I Activate
- ✅ New function created
- ✅ New component added
- ✅ User mentions testing or tests
- ✅ Test file missing for implementation
- ✅ User asks "can you test this?"
## What I Generate
### Quick Test Scaffolding
- Basic happy path tests
- Null/undefined edge cases
- Simple error scenarios
- Framework-appropriate syntax (Jest/Vitest/Pytest)
### What I Don't Do
- Comprehensive test suites → Use **@test-engineer** sub-agent
- Integration tests → Use **@test-engineer** sub-agent
- E2E test design → Use **@test-engineer** sub-agent
- Test strategy planning → Use **@test-engineer** sub-agent
## Relationship with @test-engineer Sub-Agent
**Me (Skill):** Quick test scaffolding
**@test-engineer (Sub-Agent):** Comprehensive testing strategy
### Workflow
1. You write a function
2. I auto-generate basic test structure
3. You want full suite → Invoke **@test-engineer** sub-agent
4. Sub-agent creates comprehensive tests
## Examples
### JavaScript Function
```javascript
// You write:
function calculateDiscount(price, percentage) {
if (price <= 0) throw new Error('Invalid price');
return price * (percentage / 100);
}
// I auto-generate:
describe('calculateDiscount', () => {
it('calculates discount correctly', () => {
expect(calculateDiscount(100, 10)).toBe(10);
});
it('throws error for invalid price', () => {
expect(() => calculateDiscount(0, 10)).toThrow('Invalid price');
});
it('handles zero percentage', () => {
expect(calculateDiscount(100, 0)).toBe(0);
});
// TODO: Add more edge cases
// Consider: negative percentages, decimal values, very large numbers
});
```
### React Component
```jsx
// You write:
function UserCard({ user, onEdit }) {
return (
<div className="user-card">
<h2>{user.name}</h2>
<button onClick={() => onEdit(user.id)}>Edit</button>
</div>
);
}
// I auto-generate:
import { render, screen, fireEvent } from '@testing-library/react';
describe('UserCard', () => {
const mockUser = { id: 1, name: 'John Doe' };
const mockOnEdit = jest.fn();
it('renders user name', () => {
render(<UserCard user={mockUser} onEdit={mockOnEdit} />);
expect(screen.getByText('John Doe')).toBeInTheDocument();
});
it('calls onEdit with user id when button clicked', () => {
render(<UserCard user={mockUser} onEdit={mockOnEdit} />);
fireEvent.click(screen.getByText('Edit'));
expect(mockOnEdit).toHaveBeenCalledWith(1);
});
// TODO: Add tests for edge cases
// - Missing user data
// - Undefined onEdit
// - Long names (UI testing)
});
```
### Python Function
```python
# You write:
def fetch_user_data(user_id: int) -> dict:
if user_id <= 0:
raise ValueError("Invalid user ID")
return db.query("SELECT * FROM users WHERE id = ?", [user_id])
# I auto-generate:
import pytest
def test_fetch_user_data_success():
"""Test successful user data retrieval"""
result = fetch_user_data(1)
assert isinstance(result, dict)
assert 'id' in result
def test_fetch_user_data_invalid_id():
"""Test with invalid user ID"""
with pytest.raises(ValueError, match="Invalid user ID"):
fetch_user_data(0)
def test_fetch_user_data_negative_id():
"""Test with negative ID"""
with pytest.raises(ValueError):
fetch_user_data(-1)
# TODO: Add integration tests with database
# TODO: Test database connection failures
```
## Framework Detection
I automatically detect your testing framework:
- **JavaScript/TypeScript**: Jest, Vitest, Mocha
- **Python**: pytest, unittest
- **Java**: JUnit
- **Go**: testing package
Detection based on:
- package.json dependencies
- requirements.txt
- Existing test files
- Import statements
## Test Patterns
### Unit Tests
```javascript
// Function testing
test('adds numbers correctly', () => {
expect(add(2, 3)).toBe(5);
});
```
### Component Tests
```jsx
// React component testing
test('button click triggers callback', () => {
const onClick = jest.fn();
render(<Button onClick={onClick} />);
fireEvent.click(screen.getByRole('button'));
expect(onClick).toHaveBeenCalled();
});
```
### Edge Cases
```javascript
// Boundary testing
test('handles empty input', () => {
expect(processData([])).toEqual([]);
});
test('handles null input', () => {
expect(processData(null)).toBeNull();
});
```
## When to Use Sub-Agent
Invoke **@test-engineer** for:
- Complete test suites (20+ tests)
- Integration test strategy
- E2E test planning
- Test coverage goals
- Complex mocking scenarios
**Example:**
```
Me: "Generated 3 basic tests for calculateDiscount()"
You: "@test-engineer create comprehensive test suite with all edge cases"
Sub-agent: [Creates 25+ tests covering all scenarios]
```
## Sandboxing Compatibility
**Works without sandboxing:** ✅ Yes
**Works with sandboxing:** ✅ Yes
- **Filesystem**: Writes test files to project
- **Network**: None required
- **Configuration**: None required
## Customization
Edit test templates:
```bash
cp -r ~/.claude/skills/development/test-generator \
~/.claude/skills/development/my-test-generator
# Edit SKILL.md to customize:
# - Test patterns
# - Framework preferences
# - Coverage expectations
```
## Integration with Commands
### /test-gen Command
```bash
/test-gen --file utils.js --framework jest --coverage 90
# Combines:
# 1. My quick scaffolding
# 2. @test-engineer comprehensive tests
# 3. Full test file generation
```
## Tips
1. **Let me scaffold first** - Review before invoking sub-agent
2. **Add TODOs** - I include TODO comments for complex cases
3. **Framework consistency** - I match your project's testing style
4. **Quick iteration** - Regenerate if not satisfied
## Related Tools
- **@test-engineer**: Comprehensive test suite creation
- **code-reviewer skill**: Flags code that needs testing
- **/test-gen command**: Full test generation workflow
© alirezarezvani · MIT · alirezarezvani/claude-code-tresor