code-reviewer
Expert code review specialist. Reviews code for quality, security, and maintainability. Use immediately after writing or modifying code, or when you need thorough code quality assessment.
Найдите подходящую возможность для вашего агента.
Expert code review specialist. Reviews code for quality, security, and maintainability. Use immediately after writing or modifying code, or when you need thorough code quality assessment.
This skill should be used when the user asks to "analyze a specification", "break down a spec", "create tasks from a PRD", "decompose requirements", "generate a task list from a design document", or mentions working from specification documents. Provides comprehensive guidance for transforming specifications into structured, actionable task lists optimized for AI coding agents.
Workflow-first design through collaborative dialogue. Use before creating features, building components, or modifying behavior.
Plan implementation changes before coding. Use when the user requests a new feature, modification, or asks for a plan. Ensures full understanding, discovers existing code, creates detailed file/folder structure with contracts and tests, and gets user approval before implementation.
Maintains continuity across long-running tasks that span multiple agent sessions. Use when starting or resuming a complex project that spans multiple sessions, or for tasks with many discrete features requiring iterative development.
Role-based multi-agent workflow built on tmux-workflow/twf. Use when you want to run a PM/Architect/Product/Dev/QA/Ops/Coordinator/Liaison “AI team” as multiple Codex tmux workers, keep a shared responsibilities registry, route internal questions via Coordinator, and escalate user-facing questions via Liaison.
Manage GitHub issues - fetch details, update descriptions, add comments, close issues. Use when working with GitHub issues, reviewing issue status, or tracking implementation progress.
Generates weekly release cycle reports for the team. - preview: What's shipping (run Sunday after release train) - retro: What happened (run Tuesday after prod stabilizes)
タスク開始フローのエントリーポイント。prompt-analyzer の分析結果を受け取り、pm SubAgent に委譲する。
UE (user experience engineering) skill for defining end-to-end user experience behavior and interaction logic. Use for tasks like flow design, interaction models, state machines, error recovery, input validation, usability heuristics, accessibility, and turning UX intent into testable acceptance criteria for implementation.
Generate enterprise-grade web applications using Backstage Design System. Create admin dashboards, developer tools, and internal applications with modern React components, dark/light themes, and responsive design patterns based on Radix UI and Tailwind CSS.
Execute 1-2+ hour tasks autonomously with minimal supervision. Requires Task Contract (OUTCOME, EXCLUSIONS, DURATION, GUARDRAILS) upfront, then executes with clarification → plan → autonomous work → session report.
Use this agent when a PR touches production data, migrations, or any behavior that could silently discard or duplicate records. Produces a concrete pre/post-deploy checklist with SQL verification queries, rollback procedures, and monitoring plans. Essential for risky data changes where you need a Go/No-Go decision. <example>Context: The user has a PR that modifies how emails are classified. user: "This PR changes the classification logic, can you create a deployment checklist?" assistant: "I'll use the deployment-verification-agent to create a Go/No-Go checklist with verification queries" <commentary>Since the PR affects production data behavior, use deployment-verification-agent to create concrete verification and rollback plans.</commentary></example> <example>Context: The user is deploying a migration that backfills data. user: "We're about to deploy the user status backfill" assistant: "Let me create a deployment verification checklist with pre/post-deploy checks" <commentary>Backfills are high-risk deplo
Systematically gather, organize, and act on user feedback
Reviews existing repository issues, code structure, and domain to create or refresh a semantic label system with appropriate colors aligned to the repository's specific context and needs. Use for initial setup or periodic maintenance (every 6-12 months) when users mention "labels", "label organization", "repository cleanup", "label system", or when detecting labeling inconsistencies.
Master use case development with actors, scenarios, preconditions, postconditions, and detailed specifications for comprehensive requirements.
Create diagrams with Mermaid.js v11 syntax. Use for flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, state diagrams, architecture diagrams, timelines, user journeys.
This skill should be used when breaking down frontend feature requirements into parallelizable work items (API clients, UI components, and integration tasks) with clear dependencies. Particularly useful for creating structured work breakdowns with Mermaid diagrams and organizing tasks for team development.