superpowers-writing-skills

Coordinate RED-GREEN-REFACTOR testing and documentation of skills using subagents.

Updated Apr 23, 2026

Search Tags:#tdd #documentation #subagents #quality-assurance #skill-writing #rationalizations

Ready to run

npx skills add https://github.com/qq824045252-ship-it/erp --skill superpowers-writing-skills-qq824045252-ship-it

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: superpowers-writing-skills
Source: https://github.com/qq824045252-ship-it/erp/tree/main/.agents/skills/superpowers-writing-skills
Command: npx skills add https://github.com/qq824045252-ship-it/erp --skill superpowers-writing-skills-qq824045252-ship-it

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill guides teams to codify tacit knowledge into reusable process instructions by applying a disciplined RED-GREEN-REFACTOR workflow to skill writing and validation.

Core Features & Use Cases

Red-flag rationalization capture: baseline failure documentation and explicit counters to prevent shortcuts.
GREEN/REFACTOR cycles: iterative refinement of skills with real-time feedback and regression testing.
Progressive disclosure: organizes large reference content for efficient discovery and loading.
Cross-skill references: supports linking to other skills and external guidance to improve reuse and discovery.

Quick Start

Start by drafting a minimal skill, run it against a baseline RED test, then iteratively perform GREEN and REFACTOR cycles until the agent consistently complies.

Frequently Asked Questions about superpowers-writing-skills

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

FAQPage Schema

How do I apply TDD to AI agent skill writing?▼

TDD for skill writing uses a RED-GREEN-REFACTOR cycle to validate agent instructions. You draft a minimal skill, run it against a baseline RED test to capture failures, then iteratively refine and regression test until the agent consistently complies.

What are rationalization tables in skill testing?▼

Rationalization tables document baseline failures and explicit counters to prevent agents from taking shortcuts during skill execution. They surface rationalizations, enforcing disciplined skill creation by requiring structured reviews and test-first validation.

Can I use subagents to validate skill documentation?▼

Yes, subagents coordinate the testing and documentation of skills by running RED-GREEN-REFACTOR cycles. They surface rationalizations and provide real-time feedback during iterative refinement, ensuring deployment-ready documentation.

What's the best way to structure large reference content for agent skills?▼

Progressive disclosure organizes large reference content within skills for efficient discovery and loading. This approach supports cross-skill references, linking to other skills and external guidance to improve reuse and discovery.

How do I prevent agents from taking shortcuts when executing skills?▼

To prevent shortcuts, use red-flag rationalization capture with baseline failure documentation and explicit counters. This enforces disciplined skill creation by requiring test-first validation and structured reviews before deployment.