Tdd

A proper TDD cycle implementation that won't let you cheat. It enforces five distinct phases: RED (failing test), DOMAIN review (no primitive obsession), GREEN (minimal fix), another DOMAIN pass, then COMMIT. The cycle adapts to your environment, either spawning focused subagents for each phase or falling back to sequential role-switching when delegation isn't available. The domain review step has veto power, which means you'll actually debate whether that string should be a value object instead of rubber-stamping everything. Hard gate on commits: working tree must be clean before starting the next test. If you've been doing "test after" or skipping the refactor step, this will feel constraining at first, which is the point.

skills.sh installs: 195
GitHub stars: 5
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add jwilger/agent-skills --skill tdd --agent claude-code

Installs into .claude/skills of the current project.

Files

TDD

Value: Feedback -- short cycles with verifiable evidence keep AI-generated code honest and the human in control. Tests express intent; evidence confirms progress.

Purpose

Teaches a five-step TDD cycle (RED, DOMAIN, GREEN, DOMAIN, COMMIT) that adapts to whatever harness runs it. Detects available delegation primitives and routes to guided mode (human drives each phase) or automated mode (system orchestrates phases). Prevents primitive obsession, skipped reviews, and untested complexity regardless of mode.

Practices

The Five-Step Cycle

Every feature is built by repeating: RED -> DOMAIN -> GREEN -> DOMAIN -> COMMIT.

RED -- Write one failing test with one assertion. Only edit test files. Write the code you wish you had -- reference types and functions that do not exist yet. Run the test. Paste the failure output. Stop. Done when: tests run and FAIL (compilation error OR assertion failure).

SKILL.md on GitHub