Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

requesting-code-review

Prepare code for review: self-review, test coverage, and pull request description

subagent-driven-development

Orchestrate specialized subagents for different parts of a task

systematic-debugging

Hypothesis-driven debugging loop: observe, hypothesize, test, verify

test-driven-development

TDD loop: write the failing test first, implement the minimal change, verify, then refactor

using-git-worktrees

Use git worktrees to run parallel agent sessions on separate branches

using-superpowers

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

verification-before-completion

Force a verification pass before any task is marked done

writing-plans

Write structured implementation plans before starting complex tasks

writing-skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

obra/superpowers

Ask in your favorite AI

ドキュメント