Backend

Remote control tmux sessions for interactive CLIs (python, gdb, etc.) by sending keystrokes and scraping pane output. Use when debugging applications, running interactive REPLs (Python, gdb, ipdb, psql, mysql, node), automating terminal workflows, or when user mentions tmux, debugging, or interactive shells.

API Key、JWT、OAuth 2.0、mTLS などの認証方式を比較し、適切なフロー設計と実装方針を整理するスキル。方式選定、トークン管理、署名戦略、セキュリティ対策を一貫して設計します。Anchors:• Web Application Security / 適用: 脅威整理 / 目的: 認証フローのリスク把握• OWASP Authentication Cheat Sheet / 適用: 実装ベストプラクティス / 目的: 安全な実装指針• RFC 6749 & RFC 7519 / 適用: OAuth/JWT仕様 / 目的: 標準準拠の設計Trigger:Use when selecting authentication flows (API Key/JWT/OAuth/mTLS), designing token strategy, or validating auth configuration.

Look up examples and patterns from the official Anthropic Claude Cookbooks repository. Use when you need reference implementations, code examples, or best practices for Claude integrations, tool use, agents, prompting techniques, or API usage.

Domain specialist for infrastructure, CI/CD, containers, observability, and DevOps operations. Scope: CI/CD pipelines, containerization, infrastructure as code, monitoring and observability, container security, release strategies, infrastructure reliability patterns. Excludes: code-level security, application architecture, database design, API design, performance profiling. Triggers: "CI/CD", "Docker", "Kubernetes", "K8s", "deployment", "pipeline", "monitoring", "observability", "Terraform", "Ansible", "infrastructure".

Validates that a skill or MCP implementation matches its manifest by running Codex-powered semantic comparisons across descriptions, preconditions, effects, and API surface.

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.

Use when creating API services for backend communication with proper patterns for caching, error handling, and type safety.

Apply structured logging best practices using Pino for Node.js applications: JSON output, log levels, context, redaction, correlation IDs, and centralization. Use when implementing logging, reviewing log statements, or discussing observability.

GitHub Actions の条件付き実行を設計し、if 条件とイベントフィルタの運用を支援するスキル。条件式の整理、イベント別の分岐、検証と記録の流れを体系化する。Anchors:• The Pragmatic Programmer（Andrew Hunt, David Thomas）/ 適用: 条件分岐による品質管理 / 目的: 実践的な流れ制御パターンを参照• Continuous Delivery（Jez Humble）/ 適用: パイプラインの段階的実行制御 / 目的: 効率的な実行制御• GitHub Actions / 適用: if 条件・event filters・status functions / 目的: 標準構文の準拠Trigger:Use when designing conditional execution in GitHub Actions workflows, handling if expressions, or applying event filters and status functions.conditional execution, github actions, if conditions, event filters, status functions

統合テストの設計・実装・実行スキル。複数コンポーネント間の相互作用を検証し、エンドツーエンドのワークフローが正しく機能することを確認します。Anchors:• Growing Object-Oriented Software, Guided by Tests (Freeman) / 適用: 境界テスト設計 / 目的: 契約ベースのテスト• Continuous Delivery (Humble) / 適用: パイプライン統合 / 目的: 早期フィードバック• Testing Microservices with Mountebank (Byars) / 適用: サービス仮想化 / 目的: 分散システムテスト効率化Trigger:Use when testing component interactions, database integration, external API connections, or E2E workflows.integration testing, database testing, api testing, contract testing, test isolation

Implement security best practices including authentication, authorization, and protection against common vulnerabilities. Use when implementing user authentication, access control, or securing application endpoints.

Design REST and GraphQL APIs. Use when creating backend APIs, defining API contracts, or integrating third-party services. Covers endpoint design, authentication, versioning, documentation, and best practices.

This skill enables Claude to detect potential memory leaks and analyze memory usage patterns in code. It is triggered when the user requests "detect memory leaks", "analyze memory usage", or similar phrases related to memory leak detection and performance analysis. The skill identifies potential issues such as unremoved event listeners, closures preventing garbage collection, uncancelled timers, unbounded cache growth, circular references, detached DOM nodes, and unnecessary global state accumulation. It then provides detailed fix recommendations. Use this skill to proactively identify and resolve memory leaks, improving application performance and stability.

Manage Temporal workflows: server lifecycle, worker processes, workflow execution, monitoring, and troubleshooting for Python SDK with temporal server start-dev.

Multi-language backend development skill for Node.js, Python, and Go applications.This skill should be used when: designing RESTful/GraphQL APIs, optimizing database queries,implementing authentication/authorization, reviewing API security, or building microservices.

This skill enables Claude to detect potential memory leaks and analyze memory usage patterns in code. It is triggered when the user requests "detect memory leaks", "analyze memory usage", or similar phrases related to memory leak detection and performance analysis. The skill identifies potential issues such as unremoved event listeners, closures preventing garbage collection, uncancelled timers, unbounded cache growth, circular references, detached DOM nodes, and unnecessary global state accumulation. It then provides detailed fix recommendations. Use this skill to proactively identify and resolve memory leaks, improving application performance and stability.

Generates CRUD REST API endpoints with request validation, TypeScript types, consistent response formats, error handling, and documentation. Includes route handlers, validation schemas (Zod/Joi), typed responses, and usage examples. Use when building "REST API", "CRUD endpoints", "API routes", or "backend endpoints".

Comprehensive stack health audit for codebase and infrastructure. Runs 10 health checks covering frontend, backend, migrations, Docker, API integrity, and backup status. Use routinely to prevent "time loops" from accumulated issues.

This skill automates the setup of machine learning experiment tracking using tools like MLflow or Weights & Biases (W&B). It is triggered when the user requests to "track experiments", "setup experiment tracking", "initialize MLflow", or "integrate W&B". The skill configures the necessary environment, initializes the tracking server (if needed), and provides code snippets for logging experiment parameters, metrics, and artifacts. It helps ensure reproducibility and simplifies the comparison of different model runs.

Kubernetes node autoscaling with Karpenter for efficient cluster scaling. Use when implementing node provisioning, consolidation, spot instance handling, or optimizing compute costs. Triggers: karpenter, node autoscaling, provisioner, nodepool, spot instances, cluster autoscaling, node consolidation.