Skip to content
Skillpedia
Testing48k · #4354

test-driven-development

Helps your agent write tests that guide the development of new features or bug fixes.

What it does

This tool helps you write code more reliably. You write a test that describes what you want the code to do, then make the code work to pass that test.

When to use it

  • ✓When adding a new feature.
  • ✓When fixing a bug.
  • ✓When you want to be sure the code does what it should.

Example of what to ask your AI

“Write a failing test for the login functionality, then create the code to make it pass.”

Want more? Open the sections below.

How to use

The easiest way: copy the message below and paste it into Claude, ChatGPT, Cursor or any AI. It reads the skill and follows the instructions.

Skill link

https://github.com/sickn33/agentic-awesome-skills/blob/main/plugins/agentic-awesome-skills-claude/skills/test-driven-development/SKILL.md

Ready-to-paste message

Use this skill to help me: https://github.com/sickn33/agentic-awesome-skills/blob/main/plugins/agentic-awesome-skills-claude/skills/test-driven-development/SKILL.md Read the SKILL.md file at that link and follow its instructions for my task.
How it works

First, you write a test that you know will fail. Then, you write the minimum code needed for that test to pass. Finally, you can clean up the code without breaking the test.

Installation

Easiest way: copy the skill link and paste it into Claude, ChatGPT or Cursor asking it to follow the instructions.

In the terminal (Claude Code, Codex, Cursor), in your project folder:

npx skills add sickn33/agentic-awesome-skills --skill test-driven-development

Or download just the file:

curl -L https://raw.githubusercontent.com/sickn33/agentic-awesome-skills/main/plugins/agentic-awesome-skills-claude/skills/test-driven-development/SKILL.md -o SKILL.md
Technical content (original SKILL.md)

Original text by the author, straight from GitHub.

Test-Driven Development (TDD)

Overview

Write the test first. Watch it fail. Write minimal code to pass.

Core principle: If you didn't watch the test fail, you don't know if it tests the right thing.

Violating the letter of the rules is violating the spirit of the rules.

When to Use

Use for behavior changes where a repeatable test can demonstrate the requirement or reproduce the bug. Inspect the repository’s test runner and existing coverage first. For copy, generated outputs or low-impact configuration, use the appropriate focused validation rather than manufacturing a unit test.

Preserve existing work

Write the failing regression before the repair when feasible, and verify that it fails for the expected reason. If implementation already exists, preserve it and add characterization/regression tests. Do not delete user work, reset a branch or rewrite working code to reconstruct an ideal test-first history. State honestly whether the test preceded the fix.

Red-Green-Refactor

digraph tdd_cycle {
    rankdir=LR;
    red [label="RED\nWrite failing test", shape=box, style=filled, fillcolor="#ffcccc"];
    verify_red [label="Verify fails\ncorrectly", shape=diamond];
    green [label="GREEN\nMinimal code", shape=box, style=filled, fillcolor="#ccffcc"];
    verify_green [label="Verify passes\nAll green", shape=diamond];
    refactor [label="REFACTOR\nClean up", shape=box, style=filled, fillcolor="#ccccff"];
    next [label="Next", shape=ellipse];

    red -> verify_red;
    verify_red -> green [label="yes"];
    verify_red -> red [label="wrong\nfailure"];
    green -> verify_green;
    verify_green -> refactor [label="yes"];
    verify_green -> green [label="no"];
    refactor -> verify_green [label="stay\ngreen"];
    verify_green -> next;
    next -> red;
}

RED - Write Failing Test

Write one minimal test showing what should happen.

<Good> ```typescript test('succeeds on the third attempt', async () => { let attempts = 0; const operation = async () => { attempts++; if (attempts < 3) throw new Error('fail'); return 'success'; };

const result = await retryOperation(operation);

expect(result).toBe('success'); expect(attempts).toBe(3); });

Clear name, tests real behavior, one thing
</Good>

<Bad>
```typescript
test('retry works', async () => {
  const mock = jest.fn()
    .mockRejectedValueOnce(new Error())
    .mockRejectedValueOnce(new Error())
    .mockResolvedValueOnce('success');
  await retryOperation(mock);
  expect(mock).toHaveBeenCalledTimes(3);
});

Vague name, tests mock not code </Bad>

Requirements:

  • One behavior
  • Clear name
  • Real code (no mocks unless unavoidable)

Verify RED - Watch It Fail

MANDATORY. Never skip.

npm test path/to/test.test.ts

Confirm:

  • Test fails (not errors)
  • Failure message is expected
  • Fails because feature missing (not typos)

Test passes? Determine whether it already characterizes the required behavior. For a regression, prove it detects the defect using the prior revision or an isolated controlled change; do not alter a correct assertion just to force red.

Test errors? Fix error, re-run until it fails correctly.

GREEN - Minimal Code

Write simplest code to pass the test.

<Good> ```typescript async function retryOperation<T>(fn: () => Promise<T>): Promise<T> { for (let i = 0; i < 3; i++) { try { return await fn(); } catch (e) { if (i === 2) throw e; } } throw new Error('unreachable'); } ``` Just enough to pass </Good> <Bad> ```typescript async function retryOperation<T>( fn: () => Promise<T>, options?: { maxRetries?: number; backoff?: 'linear' | 'exponential'; onRetry?: (attempt: number) => void; } ): Promise<T> { // YAGNI } ``` Over-engineered </Bad>

Don't add features, refactor other code, or "improve" beyond the test.

Verify GREEN - Watch It Pass

MANDATORY.

npm test path/to/test.test.ts

Confirm:

  • Test passes
  • Other tests still pass
  • Output pristine (no errors, warnings)

Test fails? Fix code, not test.

Other tests fail? Fix now.

REFACTOR - Clean Up

After green only:

  • Remove duplication
  • Improve names
  • Extract helpers

Keep tests green. Don't add behavior.

Repeat

Next failing test for next feature.

Good Tests

Quality Good Bad

…

FAQ

Why write the test first?

Writing the test first ensures you know exactly what the code needs to do and that the test actually verifies the desired behavior.

What does 'red-green-refactor' mean?

It's a cycle: 'Red' (write a failing test), 'Green' (write minimal code to pass), and 'Refactor' (clean up the code while keeping tests passing).

Can I write the code first?

It's possible, but writing the test first helps prevent errors and ensures the code meets requirements from the start.

Details

Original description by the author

Use a failing behavioral test to guide a feature or bug fix, then implement and refactor with relevant regression checks.

repo: sickn33/agentic-awesome-skills

Popularity

GitHub stars
48k
Ranking position
#4354
License
MIT
Updated
10/15/2026

Is this skill useful?

0

Sign in to vote.

Comments

  • …

More skills from this repository

Similar skills