Backend

Run Python code in the cloud with serverless containers, GPUs, and autoscaling. Use when deploying ML models, running batch jobs, scheduling tasks, serving APIs with GPU acceleration, or scaling compute-intensive workloads. Triggers on requests for serverless GPU infrastructure, LLM inference, model training/fine-tuning, parallel data processing, cron jobs in the cloud, or deploying Python web endpoints.

PHP language specialist for framework-specific patterns, modern PHP features, and PHP best practices. Scope: Laravel patterns, Symfony patterns, Bespoke PHP patterns, modern PHP features, deprecated API replacements, array syntax updates, common PHP mistakes. Triggers: "PHP", "Laravel", "Symfony", "Eloquent", "Blade", "Twig", "composer", "artisan", "type hints", "modern PHP", "PHP 8".

Write a detailed feature specification from requirements. Use after shaping to create spec.md with goals, user stories, requirements, and technical approach.

This skill performs correlation analysis between differential methylation and differential gene expression, identifying genes with coordinated epigenetic regulation. It provides preprocessing and integration workflows, using promoter-level methylation–expression relationships.

This skill automates security vulnerability testing. It is triggered when the user requests security assessments, penetration tests, or vulnerability scans. The skill covers OWASP Top 10 vulnerabilities, SQL injection, XSS, CSRF, authentication issues, and authorization flaws. Use this skill when the user mentions "security test", "vulnerability scan", "OWASP", "SQL injection", "XSS", "CSRF", "authentication", or "authorization" in the context of application or API testing.

Chokidarライブラリを中心としたファイルシステム監視の専門スキル。Observer Patternによる効率的なファイル変更検知、クロスプラットフォーム対応、EventEmitterによる疎結合な通知システムを設計・実装する。Anchors:• Node.js EventEmitter / 適用: イベント駆動設計 / 目的: 疎結合な通知メカニズム• Chokidar Documentation / 適用: ファイル監視設定 / 目的: クロスプラットフォーム監視• Observer Pattern (GoF) / 適用: イベント通知設計 / 目的: 変更検知と通知の分離Trigger:Use when implementing file system watching, Chokidar configuration, file change detection, or event-based file monitoring systems.file watching, chokidar, fs watch, file change, event emitter, observer pattern, hot reload

Implement state machines for managing complex workflows and state transitions. Use when models have distinct states with defined transitions, business rules for state changes, or event-driven workflows.

Node.jsにおけるストリーム処理とバックプレッシャー管理の専門知識。大容量ファイルの効率的処理、メモリ使用量の最適化、Readable/Writable/Transform/Duplexストリームの適切な活用方法を提供。Anchors:• Node.js Streams API Documentation / 適用: ストリームAPI全般 / 目的: 公式APIの正確な使用• Backpressuring in Streams (Node.js official) / 適用: バックプレッシャー管理 / 目的: メモリ効率最適化• The Pragmatic Programmer (Hunt and Thomas) / 適用: 実装品質 / 目的: 保守性とテスタビリティTrigger:Use when implementing stream processing in Node.js, handling large files, managing backpressure, or building data transformation pipelines.nodejs stream, stream processing, backpressure, readable stream, writable stream, transform stream, duplex stream, pipeline, large file

MANDATORY invocation for ALL LLM-related work. Invoke immediately when: - ANY mention of model names, IDs, or versions - ANY configuration of AI providers or APIs - ANY defaults/constants for LLM settings - ANY prompt engineering or modification - ANY discussion of model capabilities or features - ANY changes to AI-related dependencies - Reading/writing .env files with AI config - Modifying aiProviders.ts, prompts.ts, or similar - Reviewing AI-related pull requests - Debugging LLM integration issues CRITICAL: Training data lags reality by months. ALWAYS research first. Use WebSearch, Exa MCP, or Gemini CLI before making ANY LLM decisions.

プロジェクト固有のアーキテクチャ設計原則を統合するスキル。ハイブリッドアーキテクチャ（shared/features）、Clean Architecture依存関係ルール、データベース設計、REST API、テスト戦略、エラーハンドリング、CI/CD原則をエージェント設計に適用する。Anchors:• Clean Architecture / 適用: 依存関係ルールと境界設計 / 目的: アーキテクチャ層の分離と依存方向制御• Hybrid Architecture (shared/features) / 適用: ドメイン分離と再利用設計 / 目的: 循環依存回避と単一責任維持• docs/00-requirements/ / 適用: プロジェクト技術スタック仕様 / 目的: 要求仕様との整合性確保Trigger:Use when designing agents that generate project-specific files, database operations, API integrations, test strategies, error handling, or CI/CD workflows. Apply when determining file placement (shared/ vs features/), enforcing dependency rules, or ensuring architecture compliance.architecture compliance, hybrid structure, shared features, dependency rules, agent file generation, database design, REST API, testing strategy

This skill assists with managing database sharding strategies. It is activated when the user needs to implement horizontal database sharding to scale beyond single-server limitations. The skill supports designing sharding strategies, distributing data across multiple database instances, and implementing consistent hashing, automatic rebalancing, and cross-shard query coordination. Use this skill when the user mentions "database sharding", "sharding implementation", "scale database", or "horizontal partitioning". The plugin helps design and implement sharding for high-scale applications.

Restructures existing code to improve readability, maintainability, and performance without changing external behavior. Trigger keywords: refactor, restructure, clean up, improve code, simplify, extract, modernize.

This skill enables Claude to generate ORM models and database schemas. It is triggered when the user requests the creation of ORM models, database schemas, or wishes to generate code for interacting with databases. The skill supports various ORMs including TypeORM, Prisma, Sequelize, SQLAlchemy, Django ORM, Entity Framework, and Hibernate. Use this skill when the user mentions terms like "ORM model", "database schema", "generate entities", "create migrations", or specifies a particular ORM framework like "TypeORM entities" or "SQLAlchemy models". It facilitates both database-to-code and code-to-database schema generation.

Use when executing implementation plans. Dispatches independent subagents for individual tasks with code review checkpoints between iterations for rapid, controlled development.

Use when creating or modifying domain entities with static expressions, computed properties, field tracking, and validation methods.

Design ActiveRecord models with proper validations, associations, scopes, and domain methods. Use when creating new models, refactoring model structure, or adding model-level business logic.

Implement security best practices across the application stack. Use when securing APIs, implementing authentication, preventing vulnerabilities, or conducting security reviews. Covers OWASP Top 10, auth patterns, input validation, encryption, and security monitoring.

Validates that version strings in Dockerfiles match package.json dependencies and constraints. Use when updating Docker base images, Node.js versions, pnpm versions, turbo versions, or other tool versions in Dockerfiles. Ensures consistency between Dockerfile versions and package.json engines, devDependencies, and packageManager fields. Automatically runs on pre-commit for Dockerfile changes and in CI pipeline. Trigger keywords: Dockerfile, Docker version, Node version, pnpm version, turbo version, version mismatch, version sync, Docker update.

This skill assists with managing database sharding strategies. It is activated when the user needs to implement horizontal database sharding to scale beyond single-server limitations. The skill supports designing sharding strategies, distributing data across multiple database instances, and implementing consistent hashing, automatic rebalancing, and cross-shard query coordination. Use this skill when the user mentions "database sharding", "sharding implementation", "scale database", or "horizontal partitioning". The plugin helps design and implement sharding for high-scale applications.

Use Jina AI APIs for converting URLs to LLM-friendly Markdown (Reader) and searching the web (Search).