AI Skill Authoring (TDD) FAQs

Question 1

What is the Red-Green-Refactor workflow for skills?

Accepted Answer

It is an adaptation of software testing where you first observe an agent fail a task (Red), write a skill to fix the failure (Green), and then refine the instructions to close any remaining loopholes (Refactor).

Question 2

What is the 'Iron Law' of skill writing?

Accepted Answer

The Iron Law states: 'No skill without a failing test first.' This ensures that every instruction added to your library is necessary and addresses a verified performance gap.

Question 3

When should I create a skill versus updating CLAUDE.md?

Accepted Answer

Create a skill for broad, reusable patterns or techniques that apply across multiple projects. Use CLAUDE.md for project-specific conventions and one-off solutions.

Question 4

Why should I test skills with subagents?

Accepted Answer

Testing with subagents allows you to simulate high-pressure scenarios to ensure your documentation is robust and that the AI follows instructions even in complex edge cases.

Question 5

Where are Claude Code skills stored locally?

Accepted Answer

Personal skills for Claude Code are typically stored in the ~/.claude/skills directory, while Codex-specific skills reside in ~/.codex/skills.

AI Skill Authoring (TDD)

Acerca de

Características Principales

Casos de Uso

AI Skill Authoring (TDD)

Acerca de

Características Principales

Casos de Uso