行動開發

Universal design principles for any UI platform. Use when establishing design direction, choosing typography, building color systems, or understanding visual hierarchy. Platform-agnostic theory that applies to web, SwiftUI, and beyond.

This skill automates the setup of synthetic monitoring for applications. It allows Claude to proactively track performance and availability by configuring uptime, transaction, and API monitoring. Use this skill when the user requests to "set up synthetic monitoring", "configure uptime monitoring", "track application performance", or needs help with "proactive performance tracking". The skill helps to identify critical endpoints and user journeys, design monitoring scenarios, and configure alerts and dashboards.

This skill helps to identify Cross-Site Request Forgery (CSRF) vulnerabilities in web applications. It validates the implementation of CSRF protection mechanisms, such as synchronizer tokens, double-submit cookies, SameSite attributes, and origin validation. Use this skill when you need to analyze your application's security posture against CSRF attacks or when asked to "validate csrf", "check for csrf vulnerabilities", or "test csrf protection".

Use when the user needs technical research, architecture validation, documentation generation, or code review. Default is read-only mode, but can enable auto-approve (-y) for code changes.

End-to-end testing patterns and best practices for web applications using Playwright and Cypress. Covers Page Object Model, test fixtures, selector strategies, async handling, visual regression testing, and flaky test prevention. Use when setting up E2E tests, debugging test failures, or improving test reliability. Trigger keywords: e2e testing, end-to-end tests, Playwright, Cypress, Page Object Model, test fixtures, selectors, data-testid, async tests, visual regression, flaky tests, browser testing.

This skill uses the test-doubles-generator plugin to automatically create mocks, stubs, spies, and fakes for unit testing. It analyzes dependencies in the code and generates appropriate test doubles based on the chosen testing framework, such as Jest, Sinon, or others. Use this skill when you need to generate test doubles, mocks, stubs, spies, or fakes to isolate units of code during testing. Trigger this skill by requesting test double generation or using the `/gen-doubles` or `/gd` command.

This skill enables Claude to perform comprehensive accessibility audits. It uses the accessibility-test-scanner plugin to identify WCAG 2.1/2.2 compliance issues, validate ARIA attributes, check keyboard navigation, and assess screen reader compatibility. Use this skill when the user requests an accessibility scan, audit, or compliance check, or when terms like "WCAG", "ARIA", "screen reader", "accessibility testing", or "a11y" are mentioned. It provides actionable insights for improving web application accessibility.

Use when creating or editing skills, before deployment, to verify they work under pressure and resist rationalization - applies RED-GREEN-REFACTOR cycle to process documentation by running baseline without skill, writing to address failures, iterating to close loopholes

This skill optimizes deep learning models using various techniques. It is triggered when the user requests improvements to model performance, such as increasing accuracy, reducing training time, or minimizing resource consumption. The skill leverages advanced optimization algorithms like Adam, SGD, and learning rate scheduling. It analyzes the existing model architecture, training data, and performance metrics to identify areas for enhancement. The skill then automatically applies appropriate optimization strategies and generates optimized code. Use this skill when the user mentions "optimize deep learning model", "improve model accuracy", "reduce training time", or "optimize learning rate".

微信小程序分享到朋友圈开发指南。当开发朋友圈分享功能、配置 onShareTimeline、适配单页模式、处理场景值 1154、navigationBarFit 布局调整时使用。

Agent lifecycle management specialist skill. Ensures continuous quality through startup, execution, state management, shutdown, versioning, and maintenance.• The Pragmatic Programmer (Andrew Hunt, David Thomas) / Apply: Lifecycle management and maintenance strategies / Purpose: Practical agent operations and versioning philosophyTrigger: Use when designing agent initialization strategies, implementing agent state management mechanisms, developing agent versioning strategies, planning agent maintenance, implementing agent shutdown and cleanup, coordinating multi-agent system lifecycles. initialization, state management, versioning, maintenance, shutdown, cleanup, monitoring, logging

Automatically generate user-friendly changelogs from git commit history. Use when preparing release notes, documenting changes for stakeholders, or creating app store descriptions.

データベーストランザクション管理の専門スキル。ACID特性、分離レベル、デッドロック回避を提供します。Anchors:• 『Designing Data-Intensive Applications』（Martin Kleppmann）/ 適用: トランザクション設計 / 目的: データ整合性Trigger:トランザクション管理、ACID特性実装、データ整合性保証設計、トランザクション分離レベル決定、ロック戦略検討、ロールバック処理実装時に使用

This skill deploys monitoring stacks, including Prometheus, Grafana, and Datadog. It is used when the user needs to set up or configure monitoring infrastructure for applications or systems. The skill generates production-ready configurations, implements best practices, and supports multi-platform deployments. Use this when the user explicitly requests to deploy a monitoring stack, or mentions Prometheus, Grafana, or Datadog in the context of infrastructure setup.

AIシステムへのプロンプトインジェクション攻撃を防ぎ、入力検証とコンテキスト分離の設計指針を提供するスキル。Anchors:• OWASP LLM Top 10 / 適用: LLMセキュリティ脅威モデリング / 目的: インジェクション攻撃の分類と防御パターン理解• Simon Willison's Prompt Injection Research / 適用: 実攻撃パターン分析 / 目的: 実世界の攻撃事例から防御戦略を導出• Defense in Depth principle / 適用: 多層防御設計 / 目的: 単一障害点の排除Trigger:Use when designing prompt injection defenses, implementing AI security measures, sanitizing user inputs for LLM systems, separating trusted and untrusted contexts, conducting security reviews for LLM applications, mitigating indirect prompt injection risks.

GitOps continuous delivery with Argo CD for Kubernetes deployments. Use when implementing GitOps workflows, application sync, multi-cluster deployments, or progressive delivery. Triggers: argocd, argo cd, gitops, application, applicationset, sync, app of apps, progressive delivery.

アーキテクチャパターン（Hexagonal、Onion、Vertical Sliceなど）の選定・比較・適用と、依存関係の準拠評価を支援するスキル。境界設計、レイヤー責務、移行計画を整理し、設計判断の根拠と実装の一貫性を保ちます。Anchors:• Patterns of Enterprise Application Architecture / 適用: パターン比較と選定 / 目的: トレードオフを整理する• Domain-Driven Design / 適用: ドメイン中心設計 / 目的: 境界と責務の明確化• Clean Architecture / 適用: 依存関係ルール / 目的: レイヤーの一方向性を維持Trigger:Use when selecting architecture patterns, designing system boundaries, comparing Hexagonal/Onion/Vertical Slice approaches, or evaluating dependency compliance in a codebase.

This skill enables Claude to generate end-to-end (E2E) tests for web applications. It leverages Playwright, Cypress, or Selenium to automate browser interactions and validate user workflows. Use this skill when the user requests to "create E2E tests", "generate end-to-end tests", or asks for help with "browser-based testing". The skill is particularly useful for testing user registration, login flows, shopping cart functionality, and other multi-step processes within a web application. It supports cross-browser testing and can be used to verify the responsiveness of web applications on different devices.

Use when implementing any feature or bugfix, adding tests, fixing flaky tests, refactoring, or changing behavior. Default approach for new features, bug fixes. Exceptions only for throwaway prototypes or generated code. Covers TDD workflow (red-green-refactor), condition-based waiting for async tests, and testing anti-patterns to avoid.

Use after research (Z01 files exist) when you need to create implementation plan - wrapper that loads Z01 research context, invokes superpowers:writing-plans, and saves to Z02_{feature}_plan.md in docs/ai/ongoing/