開發

Generate app icon using IconKitchen and place in correct locations

Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.

WHEN: Flutter/Dart code review, Widget patterns, State management checks, BLoC/Provider/Riverpod analysis WHAT: Widget best practices + State management patterns + Performance optimization + Platform channel review WHEN NOT: Native Android → kotlin-android-reviewer, Native iOS → ios-reviewer

This skill should be used when the user asks to "find code", "search codebase", "locate functions", "understand architecture", "find implementations", or needs intelligent code discovery using MorphLLM's AI-powered search tools.

Specialized agent for integrating BarqNet backend with multiple client platforms (Desktop/Electron, iOS/Swift, Android/Kotlin). Handles API contracts, authentication flows, error handling, token management, cross-platform compatibility, and end-to-end data flow validation. Use when connecting backend APIs to client applications or debugging integration issues.

Comprehensive test-driven development for Terraform providers with iterative co-development of tests, generators, and schemas. NEVER skip development or refactoring - always fix root causes in generators, schemas, or test code. Only skip resources requiring external credentials (AWS/Azure/GCP) or premium licensing. Uses terraform-plugin-testing SDK with modern assertion patterns.

Compress, resize, and convert images for web/mobile. Handles PNG, JPG, WebP, SVG optimization. Use when user needs to optimize images for performance or convert formats.

File-to-agent mapping and manifest generation for composite monorepo audits. Provides dynamic discovery of all config agents, generates structured audit manifests with priority-ordered spawn instructions, and handles library vs consumer repo exclusions. Use when performing root-level composite audits that scan repository for all config files and coordinate parallel agent execution across 26+ config domains.

Templates, standards, and structure requirements for generating SDLC approach learning repositories. Use when creating new methodology learning repositories, artifact documentation, or validating repository structure.

Lazy-load access to enterprise_bot codebase. Provides 12 nuclear protocol exports (cfg, CogTwin, auth, memory) and zipped source. Load SKILL.md instead of 60 files. Extract from src.zip on demand.

C# 12 and .NET 8 coding standards including primary constructors, collection expressions, async patterns, null handling, and naming conventions. Use when writing or reviewing .NET 8 code.

DDDアーキテクチャでFastAPIのバックエンドを新規実装または既存コードベースをリファクタリングする際のガイド。レイヤー構成（domain/application/infrastructure/controller）、依存方向、責務境界、pydantic/sqlalchemy(sqlmodel)/alembic/pytestの前提、セッション管理（Dependsで1リクエスト1セッション、必要時UoW）を含む。

TypeScript strictest patterns, type guards, optional properties (exactOptionalPropertyTypes), Drizzle query safety, null checks. Use when fixing type errors, implementing complex types, or when user mentions TypeScript/types/generics.

Implementation agent focused on high-integrity TDD-driven code generation.

Use when the app is slow or when optimizing functions. Enforces profile-first methodology to prevent premature optimization.

Analyze test coverage, identify gaps, suggest strategic test cases. Use when writing features, after bug fixes, or during test reviews. Ensures comprehensive coverage without over-testing.

Enforces security guardrails for Claude Code. Blocks access to secrets, credentials, and sensitive files. Requires confirmation for network requests and infrastructure changes. Use when accessing files, making network requests, or running infrastructure commands.

Validate and manage D&D party configuration files including player names, character mappings, and DM information. Use when creating new party configs, troubleshooting speaker mapping issues, or verifying configuration before session processing.

Delegate complex, multi-step codebase exploration to local Ollama models. Best for analysis, review, and understanding tasks that require reasoning across multiple files.

Select appropriate models (haiku/sonnet/opus) and parallelize tasks. Use at the start of implementation to optimize model selection and identify parallelization opportunities.