superpowers-optimized

Use this agent to review completed implementation work against requirements, correctness, and production readiness.

Use this agent to adversarially attack completed implementation work — find concrete ways to break the code through specific inputs, state sequences, race conditions, assumption violations, and production context mismatches that checklist-based review would miss.

Validates whether proposed or in-progress work should exist before investing in it. Invoke BEFORE designing, planning, or building anything non-trivial — and WHEN new evidence arrives that could change the motivation for existing work. Triggers on: "design a system", "create a plan", "build out the full version", "extend this to handle", architecture proposals, or any moment where test results, research findings, or changed requirements weaken the original reason for doing something. Also triggers when you catch yourself updating a document's facts without reassessing its conclusions.

MUST USE when the user wants new features, behavior changes, refactoring with new capabilities, or architecture decisions and no approved design exists yet. Produces an approved design document before any code is written. Triggers on: "build this", "add a feature", "I want to change", "how should we", "design", "architect", "new project", "refactor", "we need to add/build/create", "implement a new". Routed by using-superpowers, or invoke directly via /brainstorming.

Creates minimal, high-signal CLAUDE.md and AGENTS.md context files based on empirical best practices. Invoke on /init command, "create CLAUDE.md", "update CLAUDE.md", "write AGENTS.md", or "set up Claude Code for this project". Also invoked by brainstorming when repo lacks a context file. tools: Read, Glob, Grep, Bash, Edit

Use in long or noisy sessions to persist durable state across session boundaries via state.md. Also generates project-map.md when asked to map the project. Triggers on: user explicitly asks to "save state", "compress context", "map this project", "generate project map", "create project map", cross-session handoff needed, or repeated failures indicate context is getting stale.

Use BEFORE brainstorming when facing a complex architectural, technology, or design decision where the options are not yet well-defined or the problem itself may need reframing. Assembles named stakeholder perspectives that each speak once without debate, then surfaces where they converge and where real tension remains — without forcing a premature choice. Triggers on: "should we use X or Y", "not sure which approach", "evaluate these options", "what are the trade-offs between", "help me think through this decision", "architecture decision", "technology choice". Routed by using-superpowers before brainstorming when the decision space is unclear.

Use when 2+ tasks are independent and can run concurrently without file or state conflicts or sequential dependencies. Triggers on: "run these in parallel", "do these at the same time", plans with independent tasks, when subagent-driven-development identifies parallelizable work.

Maintains a project-specific known-issues.md mapping recurring errors to their solutions. Consulted automatically by systematic-debugging before investigation. Saves time by avoiding rediscovery of known problems across sessions. Triggers on: "save this fix", "remember this error", "known issues", or automatically when systematic-debugging resolves a recurring error.

MUST USE when a plan.md exists and implementation needs to begin. Executes in controlled batches with verification checkpoints. Triggers on: "execute the plan", "start building", "follow the plan", "go". Routed by using-superpowers or writing-plans handoff.

MUST USE when implementation is verified and you need to choose the branch outcome: merge, PR, keep, or discard. Triggers on: "merge this", "create a PR", "squash and merge", "we're done with this branch", "clean up the branch", "push this", "get it merged", after verification-before-completion passes. Routed by using-superpowers or executing-plans at completion.

MUST USE for any frontend, UI, or web interface implementation. Enforces production-grade visual quality, accessibility, responsive design, and professional polish. Triggers on: "build a UI", "frontend", "website", "landing page", "dashboard", "make it look professional", any React/Vue/Svelte/HTML component work. Routed by using-superpowers, or invoke directly via /frontend-design.

BLOCKING REQUIREMENT — invoke this skill BEFORE writing any code, editing files, debugging, planning, reviewing, or making any technical tool calls beyond reading files. This is the mandatory workflow router for ALL technical tasks. Matches: "implement", "build", "fix", "debug", "refactor", "optimize", "add feature", "change", "update", "create", "develop", "plan", "review", "test", or ANY request that involves code changes. Do NOT skip this skill even if the task seems simple. Invoke FIRST, then follow its routing.

Invoke BEFORE saying "done", "tests pass", "ready to merge", or any completion claim. Requires fresh command output as evidence — no completion without proof. Also routed by using-superpowers at task end.

MUST USE after design approval to decompose requirements into executable task plans with verification commands and TDD ordering. Triggers on: "write a plan", "break this down", "plan the implementation", after brainstorming approval. Routed by brainstorming as the next step.

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.

Structured code review against requirements, quality, and security standards. Invoke after meaningful code changes or before merge. Triggers on: "review my code", "code review", "check this before merge", "security review", "is this secure", "look over my changes", "second pair of eyes", "check the diff". Routed by using-superpowers or executing-plans after implementation.

Internal reasoning technique invoked by systematic-debugging and verification-before-completion for high-stakes multi-step inference. Generates N independent reasoning paths and takes majority vote to surface confident-but-wrong single-chain failures. DO NOT invoke independently — this skill is embedded in the skills that need it.

Executes plans using parallel subagents with per-task implementation and staged review gates. Invoke for parallel plan execution in the current session. Routed by writing-plans handoff or using-superpowers for large plans with independent tasks.

Invoke BEFORE attempting any fix when a bug, test failure, error, warning, unexpected behavior, or performance regression appears. Enforces hypothesis-driven root cause analysis — no fix without evidence. Triggers on: error messages, stack traces, "it's broken", "not working", "bug", test failures, blank/white screens, "works locally but not in production", performance degradation, console warnings, "can't figure out why". Also routed by using-superpowers for debugging tasks.

MUST USE for any behavior change: write failing tests before production code. No exceptions. Triggers on: "TDD", "write tests first", any implementation task, bug fix needing regression tests, behavior changes during execution. Routed by using-superpowers, or invoke directly via /test-driven-development.

Always-on operational standard. Enforces concise responses, parallel tool execution, no redundant work, exploration tracking, and proactive context compression throughout every session. Applied automatically at session start.

Use before implementation when work should be isolated from the current branch. Triggers on: "use a worktree", "isolate this work", "don't touch main", experimental or risky changes that need isolation.

9 hooks across 6 events