OpenParable
Skip to content
← Back to skills

Generate Tests

Testing & Quality
generate-tests

Generate Tests is an Agent Skill for testing & quality published in the FlorianBruniaux/claude-code-ultimate-guide repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.

Generate comprehensive tests for specified code

View on GitHub ↗
QUICK START

How to use this skill

Bring this guide into your coding agent with a prompt tailored to the tool you use.

  1. Open your project in Codex.
  2. Copy and paste the prompt below.
  3. Review files and risks before approving any action.
Prompt to paste
Inspect the Agent Skill at https://github.com/FlorianBruniaux/claude-code-ultimate-guide/blob/HEAD/examples/skills/generate-tests/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/generate-tests, but wait for my approval before writing files or running scripts.

Copying this prompt does not install or run the skill. Review third-party files before use.

Generate Tests

Generate comprehensive tests for specified code.

Instructions

  1. Read the target file(s)
  2. Identify testable units (functions, classes, methods)
  3. Generate tests following project conventions
  4. Ensure high coverage of edge cases

Test Generation Process

1. Analyze Target

  • Identify public interfaces
  • Understand dependencies
  • Note edge cases and boundaries

2. Detect Test Framework

Check for:

  • jest.config.js → Jest
  • vitest.config.ts → Vitest
  • pytest.ini → pytest
  • mocha in package.json → Mocha

3. Generate Tests

Follow the detected framework conventions.

Test Categories

Happy Path

Normal expected behavior with valid input.

Edge Cases

  • Empty inputs
  • Null/undefined values
  • Boundary values (0, -1, MAX_INT)
  • Single item vs multiple items

Error Cases

  • Invalid input types
  • Missing required parameters
  • Network/IO failures
  • Timeout scenarios

Integration Points

  • Database interactions
  • External API calls
  • File system operations

Output Format

describe('[ComponentName]', () => {
  describe('[methodName]', () => {
    // Happy path
    it('should [expected behavior] when [condition]', () => {
      // Arrange
      // Act
      // Assert
    });

    // Edge cases
    it('should handle empty input', () => {});
    it('should handle null values', () => {});

    // Error cases
    it('should throw when [invalid condition]', () => {});
  });
});

Conventions

  • One assertion per test (when practical)
  • Descriptive test names
  • AAA pattern (Arrange-Act-Assert)
  • No test interdependence
  • Mock external dependencies

Usage

/generate-tests src/utils/calculator.ts
/generate-tests src/services/

$ARGUMENTS