Machine Learning

Compares old vs new prompts across test cases with diff summaries, stability metrics, breakage analysis, and fix suggestions. Use for "prompt testing", "A/B testing prompts", "prompt versioning", or "quality regression".

高质量前端界面设计指南。当用户要求构建 Web 组件、页面、仪表板、React/Vue 组件、HTML/CSS 布局，或对任何 Web UI 进行样式美化时使用。生成富有创意、精美的代码和 UI 设计，避免通用的 AI 美学。

GitHub Actions の Composite Actions 設計と実装を支援するスキル。action.yml の構造、入出力設計、再利用性、検証手順を整理する。Anchors:• 『The Pragmatic Programmer』（Andrew Hunt, David Thomas） / 適用: 自動化設計 / 目的: 再利用可能な処理の整理• 『GitHub Actions公式ドキュメント』 / 適用: Composite Actions 実装 / 目的: 構文仕様の準拠• 『The Twelve-Factor App』 / 適用: 設定と可搬性 / 目的: アクションの独立性確保• 『Release It!』（Michael Nygard） / 適用: エラーハンドリング / 目的: 安定運用の設計Trigger:Use when designing composite actions, validating action.yml structure, or integrating reusable GitHub Actions steps.composite actions, action.yml, reusable action, inputs outputs, github actions

This skill enables Claude to manage and update snapshot tests using intelligent diff analysis and selective updates. It is triggered when the user asks to analyze snapshot failures, update snapshots, or manage snapshot tests in general. It helps distinguish intentional changes from regressions, selectively update snapshots, and validate snapshot integrity. Use this when the user mentions "snapshot tests", "update snapshots", "snapshot failures", or requests to run "/snapshot-manager" or "/sm". It supports Jest, Vitest, Playwright, and Storybook frameworks.

Swagger UI を用いた OpenAPI ドキュメントの公開・統合を支援するスキル。静的HTML/React/Next.js/サーバー埋め込みの構成を整理し、安全なAPI Explorerを構築する。Anchors:• OpenAPI Specification / 適用: API仕様互換 / 目的: 定義の一貫性確保• Swagger UI Documentation / 適用: UI構成 / 目的: 設定項目の正確な適用• OWASP ASVS / 適用: 公開・認証設計 / 目的: セキュリティ要件の確認Trigger:Use when embedding or publishing Swagger UI, configuring OpenAPI docs, or securing API explorer access.swagger ui, openapi docs, api explorer, swagger config, authentication

Maintain consistent code structure and naming patterns across JavaScript modules, CSS, and HTML files in this static website. Use this skill when establishing or following project-wide conventions for file organization, naming, and code structure.

Standardize markdown document creation and updates with proper headers and footers. Use when creating OR updating any markdown file that is NOT a subagent, command, or skill definition. Ensures consistent metadata, classification, and change tracking.

This skill enables Claude to manage environment configurations and secrets across different deployments using the environment-config-manager plugin. It is invoked when the user needs to generate, update, or retrieve configuration settings for various environments (e.g., development, staging, production). Use this skill when the user explicitly mentions "environment configuration," "secrets management," "deployment configuration," or asks to "generate config files". It helps streamline DevOps workflows by providing production-ready configurations based on best practices.

This skill enables Claude to automatically generate comprehensive documentation for existing database schemas using the database-documentation-gen plugin. It is triggered when the user requests database documentation, ERD diagrams, or a data dictionary. The plugin supports multiple database engines and generates documentation that includes ERD diagrams, table relationships, column descriptions, indexes, triggers, stored procedures, and interactive HTML documentation. Use this skill when you need to document existing database schemas for team onboarding, architectural reviews, or data governance purposes. The trigger terms include "database documentation", "ERD diagram", "data dictionary", and `/db-docs`.

Extract specific fields from YAML files efficiently using qq instead of reading entire files, saving 80-95% context.

This skill enables Claude to validate application performance against defined budgets. It's useful for identifying performance regressions early in the development lifecycle. The skill is triggered when the user mentions "performance budget", "validate budget", "performance regression", or requests a check against performance metrics like "page load times", "bundle sizes", "API response times", or "Lighthouse scores". The plugin validates against predefined thresholds and alerts on violations. It is especially helpful in CI/CD pipelines to prevent performance degradation in production.

Tailwind CSS v4.1 best practices with WCAG 2.1 AA accessibility, theming, and dark mode support. Use when working with HTML, CSS, styling components, accessibility (a11y), WCAG compliance, color contrast, focus states, screen readers, theming, light mode, dark mode, or building accessible UI patterns like buttons, forms, cards, and navigation. Complements the angular-best-practices skill for Angular frontends.

This skill enables Claude to validate the ethical implications and fairness of AI/ML models and datasets. It is triggered when the user requests an ethics review, fairness assessment, or bias detection for an AI system. The skill uses the ai-ethics-validator plugin to analyze models, datasets, and code for potential biases and ethical concerns. It provides reports and recommendations for mitigating identified issues, ensuring responsible AI development and deployment. Use this skill when the user mentions "ethics validation", "fairness assessment", "bias detection", "responsible AI", or related terms in the context of AI/ML.

This skill enables Claude to automatically scan for XSS (Cross-Site Scripting) vulnerabilities in code. It is triggered when the user requests to "scan for XSS vulnerabilities", "check for XSS", or uses the command "/xss". The skill identifies reflected, stored, and DOM-based XSS vulnerabilities. It analyzes HTML, JavaScript, CSS, and URL contexts to detect potential exploits and suggests safe proof-of-concept payloads. This skill is best used during code review, security audits, and before deploying web applications to production.

This skill enables Claude to track and manage AI/ML model versions using the model-versioning-tracker plugin. It should be used when the user asks to manage model versions, track model lineage, log model performance, or implement version control for AI/ML models. Use this skill when the user mentions "track versions", "model registry", "MLflow", or requests assistance with AI/ML model deployment and management. This skill facilitates the implementation of best practices for model versioning, automation of model workflows, and performance optimization.

ロックファイル整合性と依存関係再現性の専門スキル。pnpm-lock.yaml、package-lock.json、yarn.lockを管理し、一貫性のあるビルド、マージコンフリクト解決、CI/CD最適化を実現。Anchors:• The Pragmatic Programmer / 適用: 依存関係管理 / 目的: 再現可能なビルドTrigger:Use when managing lock files, resolving merge conflicts, verifying integrity, or optimizing CI/CD caching.

This skill assists with SOC2 audit preparation by automating tasks related to evidence gathering and documentation. It leverages the soc2-audit-helper plugin to generate reports, identify potential compliance gaps, and suggest remediation steps. Use this skill when the user requests help with "SOC2 audit", "compliance check", "security controls", "audit preparation", or "evidence gathering" related to SOC2. It streamlines the initial stages of SOC2 compliance, focusing on automated data collection and preliminary analysis.

This skill enables Claude to generate Kubernetes deployment manifests, services, and related configurations following best practices. It should be used when the user asks to create a new Kubernetes deployment, service, ingress, or other related resources. Claude will generate YAML files for Deployments, Services, ConfigMaps, Secrets, Ingress, and Horizontal Pod Autoscalers. Use this skill when the user mentions "Kubernetes deployment", "K8s deployment", "create service", "define ingress", or asks for a manifest for any K8s resource.

This skill generates comprehensive test reports with coverage metrics, trends, and stakeholder-friendly formats (HTML, PDF, JSON). It aggregates test results from various frameworks, calculates key metrics (coverage, pass rate, duration), and performs trend analysis. Use this skill when the user requests a test report, coverage analysis, failure analysis, or historical comparisons of test runs. Trigger terms include "test report", "coverage report", "testing trends", "failure analysis", and "historical test data".

GitHub Actionsワークフローの構文とイベントトリガー、ジョブ定義、ステップ実行、パーミッション管理、環境変数設定について実装指針を提供する。CI/CDパイプラインの構築と管理を支援。Anchors:• GitHub Actions Workflow Syntax / 適用: ワークフロー構造設計 / 目的: 公式構文に準拠した実装• YAML 1.2 Specification / 適用: 構文検証・パース / 目的: 正確なYAML記述• 12-Factor App (Config) / 適用: 環境変数設計 / 目的: 環境非依存の設定管理Trigger:Use when creating or editing GitHub Actions workflow files, troubleshooting syntax errors, configuring event triggers, setting up job dependencies and matrix strategies, or managing permissions and environment variables.github actions, workflow syntax, yaml, event trigger, jobs, steps, permissions, environment variables