Claude Skills

Use when asked for "deep research", "thorough analysis", "comprehensive report", "investigate", "due diligence", or when multiple sources are needed to answer complex questions. Produces well-sourced research reports through iterative refinement.

This skill should be used when analyzing errors, stack traces, and logs to identify root causes and implement fixes.

This skill should be used when the user asks to initialize tracking, set up reference tracking, enable automatic source tracking, create tracking files, or start using the track plugin for the current project. Creates claude_usage/ directory with sources.md and prompts.md files, configures hooks-based automatic tracking with verbosity settings, and enables PostToolUse and SessionEnd hooks.

Use before workflow execution to discover available agents, skills, and quality commands in the project environment. Use when adapting gh-workflow commands to project-specific tooling.

DEPRECATED in v2.0 - Replaced by hooks-based tracking. This skill is no longer needed. Use /track:init to enable automatic hooks-based tracking instead.

Analyze git changes to determine release scope (marketplace/plugin/variants)

Coordinates parallel multi-expert PR code review. Activates with /zen:pr:review or when user asks for "code review", "PR feedback", "security check", "review my changes", "レビューして", "PRレビュー", "コードチェック", "セキュリティ確認", "変更を確認", "コードレビュー". Spawns specialized reviewers (Security, API, Database, DevOps, Frontend, Test, Dependencies, Prompt Engineer, Tech Writer) based on changed file patterns. Produces unified findings with severity levels.

React Testing Library patterns for component testing

Design and implement wide-event logging with tail sampling for context-rich, queryable observability

Use when researching a specific pillar and need to create traceable evidence objects. Guides creation of YAML evidence files with semantic IDs, confidence scores, and assumptions.

Build AI agents with Cloudflare Agents SDK on Workers + Durable Objects. Provides WebSockets, state persistence, scheduling, and multi-agent coordination. Prevents 23 documented errors. Use when: building WebSocket agents, RAG with Vectorize, MCP servers, or troubleshooting "Agent class must extend", "new_sqlite_classes", binding errors, WebSocket payload limits.

React component patterns, best practices, and architecture guidelines

Cross-platform Mobile-MCP tools for device interaction, screenshots, touch simulation, and UI inspection. Works with iOS Simulator and Android Emulator for any mobile app (Flutter, native, React Native).

Orchestrates development workflow with domain understanding, architecture mapping, and implementation. Use when user says /developer or /dev.

Clean Architecture patterns for Flutter with Riverpod state management. Use when building or reviewing Flutter apps with layered architecture (Domain, Data, Application, Presentation).

GitHub Actions workflow patterns

Test-driven development for Spring Boot using JUnit 5, Mockito, MockMvc, Testcontainers, and JaCoCo. Use when adding features, fixing bugs, or refactoring.

Frontend development patterns for React, Next.js, state management, performance optimization, and UI best practices.