context-aware-ops
Intelligent resource management with size checking and filtering to preserve context window
Найдите подходящую возможность для вашего агента.
Intelligent resource management with size checking and filtering to preserve context window
AI-powered systematic codebase analysis. Combines mechanical structure extraction with Claude's semantic understanding to produce documentation that captures not just WHAT code does, but WHY it exists and HOW it fits into the system. Includes pattern recognition, red flag detection, flow tracing, and quality assessment. Use for codebase analysis, documentation generation, architecture understanding, or code review.
Use when exploring Context level impact during scoping - system boundaries, actors, cross-container interactions, and high-level concerns
Analyze existing PHPUnit test failure logs without running tests. Use when: - User says "fix the test failures" (after manually running tests) - User says "what tests are failing?" - User points to specific log file - Tests were run outside Claude's context Delegates to fixer agent (sonnet) to find logs, parse failures, and implement fixes. Does NOT execute tests - use phpunit-runner for that.
Comprehensive DevOps skill for CI/CD, infrastructure automation, containerization, and cloud platforms (AWS, GCP, Azure). Includes pipeline setup, infrastructure as code, deployment automation, and monitoring. Use when setting up pipelines, deploying applications, managing infrastructure, implementing monitoring, or optimizing deployment processes.
Comprehensive DevOps skill for CI/CD, infrastructure automation, containerization, and cloud platforms (AWS, GCP, Azure). Includes pipeline setup, infrastructure as code, deployment automation, and monitoring. Use when setting up pipelines, deploying applications, managing infrastructure, implementing monitoring, or optimizing deployment processes.
Implement loud failures with specific exception types, actionable error messages, centralized boundary handling, and graceful degradation with telemetry. Use this skill when writing try/catch blocks, error handlers, exception classes, logging statements, retry logic, or resource cleanup code. Applies to all error scenarios requiring context preservation for debugging, proper resource hygiene, and post-mortem-ready error capture across the entire application stack.
Implement Spring Data JPA repositories, entities, and queries following modern best practices. Use for creating repositories (only for aggregate roots), writing queries (@Query, DTO projections), custom repositories (Criteria API, bulk ops), CQRS query services, entity relationships, and performance optimization. Covers patterns from simple repositories to advanced CQRS with detailed anti-patterns guidance.
Run PHPUnit tests and fix failures using intelligent agent delegation. Use when user requests to: - Run tests (full suite, specific path, or single file) - Fix failing tests - Analyze test failures - Check test coverage Delegates to runner agent (haiku) for execution and fixer agent (sonnet) for fixes. Automatically cycles between run and fix until tests pass or human intervention needed.
Expert MQTT developer specializing in IoT messaging protocols, broker configuration, and message queuing telemetry transport patterns. Masters QoS levels, retained messages, and secure MQTT implementations for IoT solutions.
Zod 4 を使用したバリデーションの実装規約とベストプラクティス。スキーマ定義、型導出、エラーハンドリングの統一ルール。
This skill should be used when implementing KMP features, creating shared modules, using expect/actual, setting up Koin/SQLDelight/Ktor, or implementing Compose Multiplatform.
**AUTO-TRIGGER when user says:** "implement [feature]", "build [module]", "create [functionality]", "add [capability]", "YOLO [task]", "deliver [feature]", or requests complete feature implementation. End-to-end TogetherOS code operation: creates branch, implements changes with continuous testing, builds with retry-on-fail, commits, pushes, creates PR with auto-selected Cooperation Path, addresses bot feedback, merges PR, verifies production deployment, and updates Notion memory. **Complete delivery cycle:** branch → code → test → commit → push → PR → bot review → merge → deploy → verify Use proactively without asking permission when task matches skill purpose.
Testing strategies, patterns, and best practices across test types. Auto-triggers when writing tests, setting up test infrastructure, or improving test coverage.
Complete toolset for Railway project management. Manage services, deployments, variables, and environments directly from the CLI. Use this skill to deploy apps, troubleshoot issues, view logs, and configure infrastructure without leaving the terminal.
Implement robust error handling with user-friendly messages, specific exception types (ISP), centralized error boundaries (SRP), fail-fast validation (KISS), graceful degradation, retry strategies, and proper resource cleanup. Use this skill when adding try-catch blocks, throwing or catching exceptions, creating error classes, implementing error boundaries or middleware, displaying error messages to users, or handling async errors and promise rejections. Use when working with error handling in any language (.ts, .js, .py, .java, .go) across backend services, API endpoints, frontend components, or data processing pipelines. Use when implementing exponential backoff for external service calls or ensuring resources are cleaned up in finally blocks.
Refactors code to improve readability, maintainability, performance, and adherence to best practices while preserving functionality
Automated code review with SOLID principles, code smells, and language-specific best practices.