tdd

Plan and execute feature work using red-green-refactor and eval-driven loops.

Updated Apr 7, 2026
One-click install
npx skills add https://github.com/Alfie728/my-skills --skill tdd-alfie728
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: tdd
Source: https://github.com/Alfie728/my-skills/tree/main/tdd
Command: npx skills add https://github.com/Alfie728/my-skills --skill tdd-alfie728

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This skill provides a disciplined workflow for building features and fixing bugs by applying a red-green-refactor loop for deterministic code, alongside an eval-driven loop to safely develop and test agents and LLM features.

Core Features & Use Cases

  • Red-Green-Refactor: end-to-end workflow for small vertical slices that keeps risks low and tests green quickly.
  • Eval-Driven Development: a structured process to test non-deterministic components, including error analysis, failure taxonomy, and a dataset-driven harness.
  • Linear Issue Bootstrapping: fetch acceptance criteria from Linear issues to bootstrap planning when an issue ID is provided; otherwise starts from user requests.

Quick Start

Provide a Linear issue ID to seed acceptance criteria and begin the red-green-refactor loop, or proceed from the user request if no issue ID is supplied.

Frequently Asked Questions about tdd

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I apply test-driven development to non-deterministic LLM agents?

You can bootstrap TDD planning by providing a Linear issue ID, which extracts acceptance criteria, file paths, and epic context. If no issue ID is supplied, the workflow proceeds directly from your text request.

What is eval-driven development for LLM features?

You can bootstrap TDD planning by providing a Linear issue ID, which extracts acceptance criteria, file paths, and epic context. If no issue ID is supplied, the workflow proceeds directly from your text request.

How do I bootstrap feature planning from a Linear issue ID?

You can bootstrap TDD planning by providing a Linear issue ID, which extracts acceptance criteria, file paths, and epic context. If no issue ID is supplied, the workflow proceeds directly from your text request.

Does test-driven development work for both deterministic code and LLM agents?

You can bootstrap TDD planning by providing a Linear issue ID, which extracts acceptance criteria, file paths, and epic context. If no issue ID is supplied, the workflow proceeds directly from your text request.

What's the best way to manage risk when building small vertical slices of code?

You can bootstrap TDD planning by providing a Linear issue ID, which extracts acceptance criteria, file paths, and epic context. If no issue ID is supplied, the workflow proceeds directly from your text request.

When should I use an eval-driven loop instead of red-green-refactor?

You can bootstrap TDD planning by providing a Linear issue ID, which extracts acceptance criteria, file paths, and epic context. If no issue ID is supplied, the workflow proceeds directly from your text request.