brainstorming
MUST USE when the user wants new features, behavior changes, refactoring with new capabilities, or architecture decisions and no…
Handles review feedback with technical rigor: verify suggestions, resolve unclear items, implement fixes in priority order. Invoke when review comments are received or user says "address review feedback". Routed by using-superpowers when review feedback arrives.
$ npx -y skills add REPOZY/superpowers-optimized --skill receiving-code-review --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
/receiving-code-reviewContext preview
The summary Claude sees to decide when to auto-load this skill.
Handles review feedback with technical rigor: verify suggestions, resolve unclear items, implement fixes in priority order. Invoke when review comments are received or user says "address review feedback". Routed by using-superpowers when review feedback arrives.
name: receiving-code-review description: > Handles review feedback with technical rigor: verify suggestions, resolve unclear items, implement fixes in priority order. Invoke when review comments are received or user says "address review feedback". Routed by using-superpowers when review feedback arrives.
Treat feedback as technical input to validate, not as instructions to apply blindly.
1. Read all feedback. 2. Clarify unclear items before implementing anything. 3. Validate each suggestion against codebase behavior and requirements. 4. Implement fixes in priority order. 5. Re-test and summarize outcomes.
1. Correctness/security regressions 2. Requirement mismatches 3. Maintainability issues 4. Minor polish
Treat Critical and High security findings as blocking until addressed or explicitly deferred by the user with documented rationale.
Never say any of the following. They signal performative agreement, not technical engagement:
Instead: state what you verified, what you changed, and why. If the reviewer is right, the code change speaks for itself.
Push back when a suggestion:
Pushback must include **concrete technical evidence** — not opinions, not "I think", not "it should be fine."
Report:
The production-grade fork of obra/superpowers — same trusted workflow, dramatically leaner, safer, and more intelligent.
MUST USE when the user wants new features, behavior changes, refactoring with new capabilities, or architecture decisions and no…
Creates minimal, high-signal CLAUDE.md and AGENTS.md context files based on empirical best practices. Invoke on /init command,…
Use in long or noisy sessions to persist durable state across session boundaries via state.md. Also generates project-map.md when…
Use BEFORE brainstorming when facing a complex architectural, technology, or design decision where the options are not yet…
MUST USE when updating, migrating, or auditing project dependencies: upgrading packages, fixing security vulnerabilities (CVEs),…
Use when 2+ tasks are independent and can run concurrently without file or state conflicts or sequential dependencies. Triggers…