Results for “code-review”

Interviews the user one question at a time to stress-test a plan or design, exploring the codebase when possible, until reaching a shared understanding.

Agent profile for prioritize product scope, user outcomes, MVP slices, roadmap tradeoffs, and launch criteria. Use when Codex needs a specialist agent perspective for planning, implementation, review, debugging, validation, or handoff in this domain.

Designs the contract for an API change inside one codebase — a component's props, a function surface, URL or query parameters, an event payload, or a module boundary — through a discovery pass, an options document with one recommendation, a question round, and an adversarial validation round, with every element of the contract justified from one stated goal. Use when you want to design, shape, decide, or nail down an interface, contract, signature, or API change for a capability you can already describe, sized for roughly one pull request. Produces a design document and changes no code. Does not specify what a feature should do — use plan-a-feature. Does not plan delivery or sequencing — use plan-implementation. Does not assess the architecture of existing code — use architectural-analysis. Does not write the code — use tdd. Does not restructure existing code — use refactor. Runs its rounds without pausing for review; to review each round as it lands, use pairing.

Survey a codebase's animation and motion code as a senior motion advisor, then produce a prioritized audit and self-contained implementation plans for other agents (or cheaper models) to execute. Read-only on source code — it plans improvements, it does not apply them. Use when the user asks to "improve the animations", "audit the motion", "make this app feel better", or wants a roadmap of animation fixes rather than a review of a single diff. Source: github.com/emilkowalski/skills.

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.

Multi-agent autonomous startup system for Claude Code. Triggers on "Loki Mode". Orchestrates 100+ specialized agents across engineering, QA, DevOps, security, data/ML, business operations, marketing, HR, and customer success. Takes PRD to fully deployed, revenue-generating product with zero human intervention. Features Task tool for subagent dispatch, parallel code review with 3 specialized reviewers, severity-based issue triage, distributed task queue with dead letter handling, automatic deployment to cloud providers, A/B testing, customer feedback loops, incident response, circuit breakers, and self-healing. Handles rate limits via distributed state checkpoints and auto-resume with exponential backoff. Requires --dangerously-skip-permissions flag.

Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says "实现实验", "implement experiments", "bridge", "从计划到跑实验", "deploy the plan", or has an experiment plan ready to execute.

Review an open GitHub issue for a selected repository against the current codebase, then either close it as already implemented with an evidence comment, label it needs clarification with an explanatory comment, or create a fleshed-out Jira story in the requested board/project when the remaining work is clear. Use when triaging GitHub issues into Jira backlog work or closing stale implemented GitHub issues.

Plan-driven implementation in Sage/Acorn — reads docs/plans/ directory, implements components from approved sub-plans, runs scaffold generators (lando acorn acf:block), commits incrementally, auto-invokes block-scaffolding per ACF block, runs lando flush and lando theme-build after changes; full PR workflow with sage-reviewer gate. Invoke for: "/building", "implement from the plan", "implement from the plan", "build from the plan", "execute the plan", "start building", "code this feature". Skip when: there is no approved plan yet — run /architecture-discovery then /plan-generator first.

Create OR review a page-brief — the artifact BETWEEN a wireflow and the full PRD. It turns each unique page/screen of a product into documented requirements TIED TO JOBS: a self-contained board card per page (what the page is accountable for, the job-tagged checklist of what it must let you do, the journeys it appears in, what it connects to, and the acceptance criteria that say how you'd know it's right). It is the "PRD per page", not a sitemap — and it stops ABOVE the screen: no components, no layout, no hierarchy. Use whenever the user wants to "spec the pages", "document each screen", turn a wireflow + live design into per-page requirements, or asks "what does this page need to do / which jobs pass through it" — even if they never say "page-brief". Natural NEXT STEP after the wireflow skill. ALSO use it to REVIEW an existing page-brief / screen catalog. In the A-Team pipeline this is a definition-phase skill: output lands in docs/features/<slug>/briefs/pages/, job codes are the durable [[NN]] ids from doc