How do I install the Tdd Workflow skill?

Run npx skillmds@latest add dmitryprg-ai/tdd-workflow-2 in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Tdd Workflow safe to use?

This skill has not completed SkillMD's automated safety review yet. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Tdd Workflow?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Tdd Workflow free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Tdd Workflow?

dmitryprg-ai (@dmitryprg-ai) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Tdd Workflow by dmitryprg-ai — Agent Skill

Name: Tdd Workflow
Rating: 4.2 (5 reviews)
Author: dmitryprg-ai

Tdd Workflow

Test-Driven Development workflow with strict Red-Green-Refactor cycle. Use when developing features with TDD, writing tests before code, or when test-driven approach is needed. MANDATORY order - test cases table BEFORE code, failing tests BEFORE implementation.

dmitryprg-ai Updated Sep 22, 2026

File contents

TDD Workflow

Principle: Red -> Green -> Refactor (STRICT order!)

PHASE 0: Test Planning (FIRST STEP)

Fill test cases table BEFORE any code:

## TEST CASES (fill BEFORE implementation!)

| # | Scenario | Input | Expected Output | Type | Status |
|---|----------|-------|-----------------|------|--------|
| 1 | Happy path | <input> | <expected> | Unit | pending |
| 2 | Edge case: empty | [] | <expected> | Unit | pending |
| 3 | Edge case: null | null | Error | Unit | pending |
| 4 | Integration | <context> | <expected> | Integration | pending |

Coverage categories:

Happy path (main scenario)
Edge cases (empty data, boundaries, null/undefined)
Error cases (invalid input, exceptions)
Integration points (if dependencies exist)

STOP: Do NOT proceed to Phase 1 until table is filled!

PHASE 1: RED -- Write Failing Tests

Create test file (feature.test.ts)
Write tests for ALL cases from Phase 0 table

Run tests -- they MUST FAIL:

npm test -- --grep "feature"
# Expected: FAIL

STOP: Do NOT write implementation until tests fail!

PHASE 2: GREEN -- Minimal Code

Write MINIMAL code to make tests pass
Do NOT optimize, do NOT add "for later"

Run tests:

npm test -- --grep "feature"
# Expected: PASS

Repeat for each test case

STOP: Do NOT refactor until ALL tests are green!

PHASE 3: REFACTOR

All tests green? -> Refactor
Remove duplication, improve readability
After EACH change: npm test (must stay green)

PHASE 4: VERIFY

## TDD VERIFICATION

| Category | Written | Passing | Skipped |
|----------|---------|---------|---------|
| Happy path | X | X | 0 |
| Edge cases | X | X | 0 |
| Error cases | X | X | 0 |
| Integration | X | X | 0 |
| **TOTAL** | X | X | 0 |

FORBIDDEN

Writing code BEFORE test cases table
Writing code BEFORE failing tests
Refactoring with red tests
Skipping checkpoints
"I'll write tests later"

---name: tdd-workflow-2description: Test-Driven Development workflow with strict Red-Green-Refactor cycle. Use when developing features with TDD, writing tests before code, or when test-driven approach is needed. MANDATORY order - test cases table BEFORE code, failing tests BEFORE implementation.---# TDD WorkflowPrinciple: **Red -> Green -> Refactor** (STRICT order!)## PHASE 0: Test Planning (FIRST STEP)Fill test cases table BEFORE any code:```markdown## TEST CASES (fill BEFORE implementation!)| # | Scenario | Input | Expected Output | Type | Status ||---|----------|-------|-----------------|------|--------|| 1 | Happy path | <input> | <expected> | Unit | pending || 2 | Edge case: empty | [] | <expected> | Unit | pending || 3 | Edge case: null | null | Error | Unit | pending || 4 | Integration | <context> | <expected> | Integration | pending |```Coverage categories:- [ ] Happy path (main scenario)- [ ] Edge cases (empty data, boundaries, null/undefined)- [ ] Error cases (invalid input, exceptions)- [ ] Integration points (if dependencies exist)**STOP: Do NOT proceed to Phase 1 until table is filled!**## PHASE 1: RED -- Write Failing Tests1. Create test file (`feature.test.ts`)2. Write tests for ALL cases from Phase 0 table3. Run tests -- they MUST FAIL: ```bash npm test -- --grep "feature" # Expected: FAIL ```**STOP: Do NOT write implementation until tests fail!**## PHASE 2: GREEN -- Minimal Code1. Write MINIMAL code to make tests pass2. Do NOT optimize, do NOT add "for later"3. Run tests: ```bash npm test -- --grep "feature" # Expected: PASS ```4. Repeat for each test case**STOP: Do NOT refactor until ALL tests are green!**## PHASE 3: REFACTOR1. All tests green? -> Refactor2. Remove duplication, improve readability3. After EACH change: `npm test` (must stay green)## PHASE 4: VERIFY```markdown## TDD VERIFICATION| Category | Written | Passing | Skipped ||----------|---------|---------|---------|| Happy path | X | X | 0 || Edge cases | X | X | 0 || Error cases | X | X | 0 || Integration | X | X | 0 || **TOTAL** | X | X | 0 |```## FORBIDDEN- Writing code BEFORE test cases table- Writing code BEFORE failing tests- Refactoring with red tests- Skipping checkpoints- "I'll write tests later"

Frequently asked questions