When the agent reaches for it
The agent keeps every installed skill's description in view and loads the full instructions when a request matches. This is the description it reads:
Use when creating new skills, editing existing skills, or verifying skills work before deployment
What the instructions cover
The sections of its SKILL.md, in order.
- Overview
- What is a Skill?
- TDD Mapping for Skills
- When to Create a Skill
- Skill Types
- Directory Structure
- SKILL.md Structure
- Skill Discovery Optimization (SDO)
- Flowchart Usage
- Code Examples
- File Organization
- The Iron Law (Same as TDD)
- Testing All Skill Types
- Common Rationalizations for Skipping Testing
- Match the Form to the Failure
- Bulletproofing Skills Against Rationalization
- RED-GREEN-REFACTOR for Skills
- Anti-Patterns
- STOP: Before Moving to Next Skill
- Skill Creation Checklist (TDD Adapted)
- Discovery Workflow
What ships with it
Besides SKILL.md, the folder carries these. The agent opens them only when a step in the instructions calls for one.
-
examples/ -
anthropic-best-practices.md -
graphviz-conventions.dot -
persuasion-principles.md -
render-graphs.js -
testing-skills-with-subagents.md
Install the skill writing skill
In Claude Code, run this in a session. It comes from the publisher's own instructions.
/plugin install superpowers@claude-plugins-official License: MIT.
In Longwave, add Superpowers from the marketplace. It installs all 14 of its skills, and your Claude Code, Codex and OpenCode threads can use them.