Test-driven development. Write tests FIRST, then implement. Use for core logic, state machines, data transformations.
Scanned 9/2/2026
Install to Claude Code
npx -y skills add imoonkey/yaco --skill tdd --agent claude-codeInstalls into .claude/skills of the current project.
Are you the author of Tdd?
Add the live security badge to your README — it updates automatically with every re-scan.
[](https://www.skillsdirectory.com/skills/imoonkey-tdd)More formats (shields.io, HTML) on the badges page.
---
name: tdd
description: Test-driven development. Write tests FIRST, then implement. Use for core logic, state machines, data transformations.
---
# TDD
Write tests before implementation, using the project's test framework. RED (failing test) -> GREEN (minimal code to pass) -> REFACTOR (improve, keep green).
## When to Use
| Use for | Skip for |
|---------|----------|
| State machines, orchestration | UI/browser automation (use e2e) |
| Data transformations, parsing | Simple CRUD / glue code |
| Protocol implementations | One-off scripts |
| Pure utility functions | |
## Cycle
1. Define the interface and result types first.
2. **RED** — write a failing test, run it targeted at the unit under development, confirm it fails.
3. **GREEN** — minimal code to pass.
4. **REFACTOR** — improve, keep green.
## Judgment
Tests are not equal in value — a test that mocks away the logic it claims to cover proves nothing. Aim for robustness, not a coverage number; test observable behavior, not implementation. Where a part doesn't fit TDD, don't force it.
Floor for core logic: ~80% coverage — run a coverage report and check against it.
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', ...