Test Driven Development logo

Test Driven Development

Community
fdhhhdjd
Test-Driven Development

Write tests before code using RED-GREEN-REFACTOR cycle

Overview

Publisherfdhhhdjd
RepositoryClass-AI-Agent
Skill nameTest-Driven Development
Stars
268
Forks
168
Bundled files
Instructions only
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 fdhhhdjd on GitHub. Read the source before you install it.

Installation

Install the Test Driven Development 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.
    https://github.com/fdhhhdjd/Class-AI-Agent/tree/main/.claude/skills/tdd
  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/fdhhhdjd/Class-AI-Agent.git /tmp/Class-AI-Agent
mkdir -p .claude/skills
cp -r /tmp/Class-AI-Agent/.claude/skills/tdd .claude/skills/fdhhhdjd-test-driven-development
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Test Driven Development 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 Driven Development 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 Driven Development 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-Driven Development Skill

Overview

TDD transforms testing from an afterthought into the foundation of development. Tests are proof that code works correctly.

When to Invoke

  • Writing new features
  • Fixing bugs (Prove-It pattern)
  • When asked to write tests
  • Before any implementation work

Core Cycle: RED-GREEN-REFACTOR

RED Phase

Write a test that describes expected behavior. It must fail.

javascript
describe('calculateDiscount', () => {
  it('should apply 10% discount for orders over $100', () => {
    const result = calculateDiscount(150);
    expect(result).toBe(15);
  });
});

Run: npm test → Should FAIL

GREEN Phase

Write minimal code to pass the test. No extras.

javascript
function calculateDiscount(amount) {
  if (amount > 100) return amount * 0.1;
  return 0;
}

Run: npm test → Should PASS

REFACTOR Phase

Improve code while keeping tests green.

javascript
const DISCOUNT_THRESHOLD = 100;
const DISCOUNT_RATE = 0.1;

function calculateDiscount(amount) {
  if (amount <= DISCOUNT_THRESHOLD) return 0;
  return amount * DISCOUNT_RATE;
}

Run: npm test → Should still PASS


Prove-It Pattern (Bug Fixes)

Step 1: Write Failing Test

javascript
it('should handle empty cart without error (bug #456)', () => {
  const cart = new Cart([]);
  expect(() => cart.getTotal()).not.toThrow();
  expect(cart.getTotal()).toBe(0);
});

Step 2: Verify Failure

Run test → Confirms bug exists

Step 3: Fix Bug

javascript
getTotal() {
  if (this.items.length === 0) return 0;  // Fix
  return this.items.reduce((sum, item) => sum + item.price, 0);
}

Step 4: Verify Pass

Run test → Confirms fix works

Step 5: Run Full Suite

bash
npm test  # No regressions

Test Pyramid

         ┌─────────┐
         │   E2E   │  5%  — Critical user flows
         │  Tests  │       Full system, minutes
         ├─────────┤
         │ Integr. │  15% — API + DB interactions
         │  Tests  │       Seconds
         ├─────────┤
         │  Unit   │  80% — Pure logic
         │  Tests  │       Milliseconds
         └─────────┘

Test Structure: AAA Pattern

javascript
it('should calculate tax for California', () => {
  // Arrange — Setup
  const order = createOrder({ state: 'CA', subtotal: 100 });
  
  // Act — Execute
  const tax = calculateTax(order);
  
  // Assert — Verify
  expect(tax).toBe(7.25);
});

DAMP > DRY in Tests

Tests should be Descriptive And Meaningful Phrases.

javascript
// ✅ DAMP — Self-contained and clear
it('should reject password without uppercase letter', () => {
  const result = validatePassword('lowercase123!');
  
  expect(result.valid).toBe(false);
  expect(result.errors).toContain('Must contain uppercase letter');
});

// ❌ Too DRY — Requires reading shared context
it('should reject invalid password', () => {
  expect(validate(INVALID_PASSWORD_NO_UPPER)).toBe(false);
});

Test Doubles (Preference Order)

  1. Real implementations — Best, but may be slow
  2. Fakes — In-memory DB, simplified implementations
  3. Stubs — Return canned responses
  4. Mocks — Verify interactions (use sparingly)
javascript
// ✅ Prefer: Real or fake
const db = createTestDatabase();
const user = await userService.create(db, userData);

// ⚠️ Use sparingly: Mocks
const mockDb = { create: vi.fn().mockResolvedValue(user) };

Naming Conventions

javascript
// Pattern: should [expected behavior] when [condition]

// ✅ Good
'should return empty array when no users exist'
'should throw ValidationError when email is invalid'
'should send welcome email after registration'

// ❌ Bad
'works correctly'
'test user creation'
'handles error'

Anti-Patterns

PatternProblemSolution
Testing internalsBreaks on refactorTest behavior, not implementation
Flaky testsErodes trustUse deterministic data
Over-mockingFalse confidencePrefer real implementations
Snapshot abuseLarge diffs ignoredUse sparingly
Shared mutable stateTests affect each otherReset in beforeEach
Testing frameworksWasted effortOnly test your code

Verification Checklist

  • All new code has tests
  • Bug fixes have reproduction tests
  • Tests describe behavior (readable names)
  • No skipped tests
  • Coverage maintained/improved
  • Full suite passes

Frequently asked questions

What does the Test Driven Development AI skill do?

Write tests before code using RED-GREEN-REFACTOR cycle

Why use Test Driven Development on TypingMind?

Because you install it once and use it with any model. Test Driven Development 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 Driven Development in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/fdhhhdjd/Class-AI-Agent/tree/main/.claude/skills/tdd. TypingMind reads its SKILL.md and installs it as a skill you can enable per chat.

Which AI models can use Test Driven Development?

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 Driven Development?

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

Is the Test Driven Development AI skill free?

It is published on GitHub by fdhhhdjd. Check the repository for licensing terms. 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 👇