Drive changes with Red→Green→Refactor; ensure behavior is verifiable and regression-safe.
Scanned 9/2/2026
Install to Claude Code
npx -y skills add KbWen/agent-virtual-office --skill test-driven-development --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Test Driven Development?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/kbwen-test-driven-development)More formats (shields.io, HTML) on the badges page.
---
name: test-driven-development
description: Drive changes with Red→Green→Refactor; ensure behavior is verifiable and regression-safe.
---
# Test-Driven Development
## Overview
TDD uses the **Red → Green → Refactor** micro-cycle. First, define expected behavior. Next, use a minimal implementation to pass the test. Finally, organize the code structure.
## When to Use
- Adding or modifying core logic.
- Fixing bugs and needing regression protection.
- Requirements can be written as explicit input/output acceptance tests.
## Workflow
1. **Red**: Write a failing test describing the expected behavior.
2. **Green**: Write the minimal code to make the test pass.
3. **Refactor**: Clean up naming, structure, and duplication.
4. Repeat the cycle until acceptance criteria are met.
## Ironclad Rules
- Do NOT write massive amounts of features before writing tests.
- Focus on one small goal per cycle.
- All tests MUST pass after refactoring.
Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.
No comments yet. Be the first to comment!
Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...