|-
Skills(SKILL.md)は、AIエージェント(Claude Code、Cursor、Codexなど)に特定の能力を追加するための設定ファイルです。
詳しく見る →|-
Use when building, improving, or reviewing command-line interfaces for better user experience - before implementing commands/output/errors, when users report confusion or frustration, or when CLI feels hard to use - provides UX principles, visual design techniques, and practical patterns for creating discoverable, delightful CLIs
データベーススキーマ設計と最適化を支援します。正規化戦略、インデックス設計、パフォーマンス最適化を提供します。データモデル設計、データベース構造の最適化が必要な場合に使用してください。
Specialized skill for designing AWS DynamoDB single-table schemas with optimized access patterns. Use when modeling data, designing table structure, or optimizing DynamoDB queries for production applications.
Use when designing, implementing, or modifying UI for GNOME apps; before writing UI code; when reviewing existing UI for HIG compliance; when working with GTK 4/libadwaita or styling Qt/PySide6 for GNOME
Help users design and optimize growth loops. Use when someone is building viral mechanics, designing referral programs, creating product-led acquisition, or figuring out how to make their product grow itself.
Design custom syntax elements with reuse-first approach for workflow orchestration. Use when user needs custom operators, checkpoints, or syntax patterns not available in core syntax.
Guides test strategy, TDD/BDD approaches, test coverage planning, and testing best practices. Use when designing test suites, improving coverage, or choosing testing approaches.
Generate end-to-end tests for the complete Desktop Ethereal application, including UI interactions, system integration, and user workflows. Triggers on E2E testing, Playwright, system testing, or complete application testing requests.
Electron desktop development guide. Use when implementing desktop features, IPC handlers, controllers, preload scripts, window management, menu configuration, or Electron-specific functionality. Triggers on desktop app development, Electron IPC, or desktop local tools implementation.
詳細設計書作成時のテンプレート集(フロントエンド設計書、Issue作成テンプレート等)
基本設計書を入力として、詳細設計書を作成し、モックアップ生成とテスト設計までを一貫して行うワークフロー。
Requires detailed Google-style docstrings for all functions, methods, and classes.
Generates detailed implementation plans from a SINGLE plan-based-page output file. Supports parallel execution - run multiple sessions simultaneously for different pages. Input is ONE file (either _shared-components.md or a specific page like landingpage-page.md). Use when you want to generate implementation plans in parallel across multiple sessions.
Identify code quality issues and anti-patterns. Use when reviewing code for maintainability problems.
Detect project type and configuration for generic application releases
Detects arbitrary read vulnerabilities by identifying unchecked array indexing and out-of-bounds memory access. Use when analyzing array access patterns, pointer arithmetic, or investigating information disclosure vulnerabilities.
>
Create new vision detector plugins following Bob The Skull's detector architecture. Use when adding new detectors like object detection, pose estimation, gesture recognition, or any computer vision detector.
Detects SpecWeave context and provides workflow documentation for available commands. Use when learning SpecWeave commands, understanding available slash commands (/sw:increment, /sw:do, /sw:progress, /sw:done), or getting workflow guidance. Explains command syntax and recommended workflow patterns.
Production-grade API design patterns for REST, GraphQL, gRPC, and tRPC. Covers API architecture, OpenAPI/Swagger specs, versioning/deprecation, authentication/authorization, rate limiting, pagination, error models, contract testing, and developer documentation.
FBX model loading patterns with sequential loading for React Three Fiber. Use when loading multiple FBX character models, implementing sequential loading to prevent memory overload, or creating character model components with proper error handling.
Autonomous development workflow. Generate detailed specs, plans, and tasks for autonomous agent execution with session memory tracking.
Use dev-browser for browser automation on NixOS. Invoke when user asks to test UI, automate browser interactions, take screenshots, or verify web app behavior.
Code Quality Standards. Use it everytime you plan or implement any code.
체계적인 디버깅(Systematic Debugging) 절차를 통해 버그의 원인을 찾고 해결합니다. (Source: obra/superpowers)
Context architecture skill for aligning work. Use when starting new features, making architectural decisions, or setting up implementation work. Generates interconnected ADR/Design/Spec/Plan scaffolding that agents can navigate and humans can enrich.
This skill should be used when the user asks to 'debug', 'fix bug', 'investigate error', 'why is it broken', 'trace root cause', 'find the bug', or needs systematic bug investigation and fixing with verification-driven methodology using ralph loops.
Master debugging techniques for Vue.js, Pinia, and cached state issues. Identify reactivity problems, memory leaks, performance bottlenecks, and complex state synchronization issues with systematic troubleshooting approaches.
<!-- SKILL CHAINING: After completing debugging work, Claude MUST invoke related skills -->
Internal skill used by dev-implement during Phase 5 of /dev workflow. NOT user-facing - should only be invoked by dev-ralph-loop inside each implementation iteration. Handles Task agent spawning with TDD enforcement and two-stage review (spec compliance + code quality).
**Announce:** "Using dev-design (Phase 4) to propose implementation approaches and obtain user approval."
Create consistent, reproducible development environments across all machines.
Unified execution engine for all development workflows. Progressive disclosure for phase execution, quick features, story completion, and scaffolding. Integrates with artifact-tracking and meatycapture-capture. Use when running /dev:execute-phase, /dev:quick-feature, /dev:implement-story, /dev:complete-user-story, or /dev:create-feature commands.
REQUIRED Phase 2 of /dev workflow after dev-brainstorm. This skill should be used when the user asks to 'explore the codebase', 'map architecture', 'find similar features', 'discover test infrastructure', 'trace execution paths', 'identify code patterns', or needs to understand WHERE code lives and HOW it works before implementation. Launches parallel explore agents and returns prioritized key files list.
ring:dev-feedback-loop
DEBUG keyboard shortcuts not working, conflicting hotkeys, and event handling issues. Fix when Ctrl+Z, Ctrl+S, or other shortcuts fail. Use for global keyboard handlers, event conflicts, and shortcut key debugging.
MASTER Pinia task store debugging covering synchronization, CRUD operations, state persistence, IndexedDB conflicts, advanced state management, and complex store architecture. Fix when tasks don't save, disappear unexpectedly, don't update in UI, backup systems read wrong data, store actions fail, or advanced performance issues occur. CRITICAL: All store fixes MUST be tested with Playwright before claiming success.
DEBUG Pomodoro timer state issues, incorrect countdown behavior, and timer synchronization problems. Fix when timer won't start, time display is wrong, or timer gets stuck. Use for timer state management, countdown logic, and session persistence.
ring:dev-implementation
개발 환경(폴더 구조, README)을 신속하게 초기화하는 Dev 전용 워크플로우입니다.
dev_invoke_gemini-cli
dev_invoke_kimi-cli
FIX ESLint errors safely without breaking code. Prefix unused variables with `_`, fix no-case-declarations, add default props, and verify builds after each batch. Use when lint cleanup is needed for easier refactoring & faster Claude Code editing.
This skill should be used when testing ScreenGraph end-to-end flows (drift detection, agent runs) while monitoring backend and frontend logs in real-time. Use when the user wants to observe system behavior across services, debug live runs, or verify event streaming.
Review developer meeting notes from the UCEAP IT Software Engineering wiki to process any outstanding action items. Creates Jira tickets, updates meeting notes, and manages the wiki Home page. Use when processing UCEAP meeting followups or planning a dev meeting.
Material selection, shaders, and visual effects for R3F
Per-task ralph loop pattern for implementation and debugging. One loop per task, not one loop per feature.
Analyzes codebase against standards and generates refactoring tasks for ring:dev-cycle.
AUTO-ACTIVATE when working in flow-state-refactor worktree or refactoring large components. MANDATORY port 5550 for refactor worktree. Extract Vue composables, split large files, reduce component size, baseline testing, zero regressions. Triggers on keywords refactor, composable, extract, split component, reduce file size, flow-state-refactor directory.