Multi-agent orchestration system sử dụng Claude subagents thực tế từ thư mục agents/ cho security reviews, code quality analysis, deployment validation, infrastructure checks. Auto-activates với orchestrator-worker pattern và extended thinking mode.
Auto-Claude debugging and troubleshooting guide. Use when fixing installation issues, debugging build failures, resolving agent errors, or diagnosing performance problems.
Canonical Claude Code skill authoring kit covering agent Skills, sub-agent templates, custom slash commands, orchestration patterns, hooks, memory, settings, and IAM permission rules aligned with official documentation.
Agent-to-Agent (A2A) server configuration patterns for HTTP, STDIO, SSE, and WebSocket transports. Use when building A2A servers, configuring MCP transports, setting up server endpoints, or when user mentions A2A configuration, server transport, MCP server setup, or agent communication protocols.
This skill guides connecting MCP servers to Claude Code plugins for external service integration. Use when configuring MCP servers, setting up authentication, or integrating external tools.
Interactive mode features including keyboard shortcuts, vim mode, command history, and background tasks. Use when user asks about REPL, keyboard shortcuts, interactive features, or vim mode.
Guides creation of custom subagents with YAML frontmatter, system prompts, tool restrictions, and permission modes. Use when creating or configuring subagents.
Automatically manage agent lifecycle, proposals, and registry.
Behavioral workflows and collaboration patterns for code review, agent coordination, and branch management. Use this skill when coordinating multi-agent work, managing code review processes, completing feature branches, or resolving productive disagreements between valid approaches.
Creates skills for installing software and configuring computers. Use when asked to create a new skill for machine setup, software installation, update or removal, or system configuration.
State checkpointing, divergence detection, and confidence tracking for Hopper/Hardin doctrine compliance. Use PROACTIVELY when performing multi-step reasoning, external actions, or any task requiring error recovery capability. Provides checkpoint_create, checkpoint_list, checkpoint_taint, and confidence_calculate tools.
Expert in Lighthouse Journey Timeline backend architecture, service patterns, testing, and API development using Express.js, TypeScript, and Drizzle ORM. Use when implementing backend services, APIs, controllers, database queries, authentication, permissions, error handling, testing server code, or writing migrations.
Generate Mission Control ScrapeConfig YAML from natural language. Use when users ask to build a scraper, create a config scraper, or want YAML to scrape Kubernetes/AWS/GCP/Azure/SQL/HTTP/File/Exec/Logs/Slack/GitHub Actions/Trivy/Terraform sources.
Demonstrates how skills can include executable scripts for automation, calculations, transformations, or system interactions. Use when needing to execute Python, Bash, Node.js, or other scripts.
Use when configuring, maintaining, troubleshooting, or optimizing Claude Code extensions including skills, commands, hooks, MCP servers, or agents. Provides best practices and prevents common mistakes.
Orchestrates complex tasks by automatically spawning specialist subagents in parallel. Use proactively when detecting complex multi-domain tasks, large refactors, comprehensive reviews, or when task complexity exceeds thresholds. Analyzes tasks and routes to appropriate agents.
Guide creation of Claude Code Commands with step-by-step workflows, argument handling, frontmatter configuration, and testing. Ensures Commands follow best practices and correct YAML structure. Use when creating Commands, building slash commands, making user-triggered workflows, or when users want explicit command execution.
Canonical Claude Code skill authoring kit covering agent Skills, sub-agent templates, custom slash commands, orchestration patterns, hooks, memory, settings, and IAM permission rules aligned with official documentation.
AI operational modes (brainstorm, implement, debug, review, teach, ship, orchestrate). Use to adapt behavior based on task type.
