obra/superpowers@writing-skills

Apply test-driven development cycles to author and verify agent skill documentation.

9|2|Updated Mar 18, 2026
One-click install
npx skills add https://github.com/AllBeingsFuture/AllBeingsFuture --skill obra-superpowers-writing-skills-allbeingsfuture
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: obra/superpowers@writing-skills
Source: https://github.com/AllBeingsFuture/AllBeingsFuture/tree/main/electron/embedded-assets/skills/superpowers-writing-skills
Command: npx skills add https://github.com/AllBeingsFuture/AllBeingsFuture --skill obra-superpowers-writing-skills-allbeingsfuture

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Provides a repeatable, test-driven process for authoring and verifying agent Skills so documentation reliably changes agent behavior and resists rationalizations under pressure.

Core Features & Use Cases

  • TDD for documentation: Maps RED-GREEN-REFACTOR to skill creation and edits so authors witness failures before prescribing fixes.
  • Pressure scenario testing: Designs realistic multi-pressure scenarios and captures verbatim rationalizations to close loopholes.
  • Discovery and CSO guidance: Teaches concise frontmatter, search-optimized descriptions, and token-efficient writing to improve Skill discoverability.
  • Use Cases: Creating new skills, editing existing skills for discipline enforcement, and running pre-deployment verification campaigns with subagents.

Quick Start

Run a realistic failing pressure scenario without the skill, document exact agent rationalizations, update the skill to address those failures, and re-run the scenario until the agent complies.

Frequently Asked Questions about obra/superpowers@writing-skills

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

FAQPage Schema
How do I use test-driven development for agent skill documentation?

Test-driven development for agent skills applies RED-GREEN-REFACTOR cycles to documentation, requiring you to define failing pressure scenarios first, then iterate skill content until the agent complies with documented rules.

What are pressure scenarios in agent testing?

Pressure scenarios are realistic multi-agent testing situations designed to make agents fail and rationalize against documented rules, allowing you to capture verbatim rationalizations and close documentation loopholes.

How do I verify agent skills resist rationalization in multi-agent workflows?

You verify agent skills by running pre-deployment verification campaigns with subagents, applying pressure scenarios that force rationalizations, and iterating documentation until the agent fully complies under pressure.

Can I apply red-green-refactor cycles to editing existing agent skills?

Yes, red-green-refactor cycles apply to both creating new skills and editing existing ones for discipline enforcement, allowing you to witness documentation failures before prescribing fixes.

What is the best way to improve agent skill discoverability and search optimization?

The best way to improve discoverability is writing concise frontmatter, search-optimized descriptions, and token-efficient content, guided by discovery and CSO principles integrated into the skill authoring process.

When should I not use TDD for skill authoring?

TDD for skill authoring is not suitable when you cannot construct realistic failing pressure scenarios or when multi-agent verification workflows are unavailable to test compliance under pressure.