obra/ superpowers-skills
31 agent skills in one repository, published by obra. One command installs the lot; each skill also has its own page below.
Install
npx skills add obra/superpowers-skills
The repository
The 31 skills
Interactive idea refinement using Socratic method to develop fully-formed designs
- Code Review ReceptionReview & testing
Receive and act on code review feedback with technical rigor, not performative agreement or blind implementation
Force unrelated concepts together to discover emergent properties - "What if we treated X like Y?
Replace arbitrary timeouts with condition polling for reliable async tests
Validate at every layer data passes through to make bugs impossible
Use multiple Claude agents to investigate and fix independent problems concurrently
Execute detailed plans in batches with review checkpoints
Complete feature development with structured options for merge, PR, or cleanup
Maintain skills wiki health - check links, naming, cross-references, and coverage
Skills wiki intro - mandatory workflows, search tool, brainstorming triggers
Flip core assumptions to reveal hidden constraints and alternative approaches - "what if the opposite were true?
Spot patterns appearing in 3+ domains to find universal principles
Recognize when disagreements reveal valuable context, preserve multiple valid approaches instead of forcing premature resolution
Sync local skills repository with upstream changes from obra/superpowers-skills
Search previous Claude Code conversations for facts, patterns, decisions, and context using semantic or text search
- Requesting Code ReviewReview & testing
Dispatch code-reviewer subagent to review implementation against plan or requirements before proceeding
Systematically trace bugs backward through call stack to find original trigger
Test at extremes (1000x bigger/smaller, instant/year-long) to expose fundamental truths hidden at normal scales
Contribute skills back to upstream via branch and PR
Find one insight that eliminates multiple components - "if this is true, we don't need X, Y, or Z
- Subagent-Driven DevelopmentReview & testing
Execute implementation plan by dispatching fresh subagent for each task, with code review between tasks
- Systematic DebuggingReview & testing
Four-phase debugging framework that ensures root cause investigation before attempting fixes. Never jump to solutions.
Write the test first, watch it fail, write minimal code to pass
Never test mock behavior. Never add test-only methods to production classes. Understand dependencies before mocking.
- Testing Skills With SubagentsWriting & docs
RED-GREEN-REFACTOR for process documentation - baseline without skill, write addressing failures, iterate closing loopholes
Understand how ideas evolved over time to find old solutions for new problems and avoid repeating past failures
Create isolated git worktrees with smart directory selection and safety verification
Run verification commands and confirm output before claiming success
Dispatch to the right problem-solving technique based on how you're stuck
Create detailed implementation plans with bite-sized tasks for engineers with zero codebase context
- Writing SkillsWriting & docs
TDD for process documentation - test with subagents before writing, iterate until bulletproof