MattMagg

This skill should be used when the user asks about "visual builder", "no-code agent builder", "drag and drop", "ThinkingConfig", "extended thinking", "chain of thought", "reasoning", or needs guidance on using ADK's visual development tools or configuring advanced reasoning capabilities.

This skill should be used when the user asks about "callbacks", "lifecycle hooks", "before_model_call", "after_tool_call", "plugins", "session state", "state management", "artifacts", "file uploads", "events", "EventActions", "human-in-the-loop", "confirmation", "memory", "MemoryService", "long-term memory", "remember across sessions", "RAG", "retrieval augmented generation", "grounding", "knowledge base", "vector search", or needs guidance on customizing agent behavior, intercepting execution, managing state across turns, implementing approval workflows, or implementing persistent memory or grounding agent responses in external knowledge.

This skill should be used when the user asks about "creating a new ADK project", "initializing ADK", "setting up Google ADK", "adk create command", "ADK project structure", "YAML agent configuration", "creating an agent", "LlmAgent", "BaseAgent", "custom agent", "agent with different model", "Claude with ADK", "OpenAI with ADK", "LiteLLM", "multi-model agent", or needs guidance on bootstrapping an ADK development environment, authentication setup, choosing between Python code and YAML-based agent definitions, agent configuration, model selection, system instructions, or extending the base agent class for non-LLM logic.

This skill should be used when the user asks about "multi-agent systems", "sub-agents", "delegation", "agent routing", "orchestration", "SequentialAgent", "ParallelAgent", "LoopAgent", "agent-to-agent", "A2A protocol", "agent hierarchy", "streaming", "real-time responses", "SSE", "server-sent events", "websocket", "bidirectional", "Live API", "voice", "audio", "video", "multimodal streaming", or needs guidance on building systems with multiple specialized agents working together or implementing real-time communication patterns.

This skill should be used when the user asks about "deploying", "production", "Agent Engine", "Vertex AI", "Cloud Run", "GKE", "Kubernetes", "hosting", "scaling", "guardrails", "safety", "content filtering", "input validation", "output validation", "authentication", "OAuth", "API keys", "credentials", "security plugins", "testing agents", "evaluation", "evals", "benchmarks", "tracing", "Cloud Trace", "logging", "observability", "AgentOps", "LangSmith", "user simulation", or needs guidance on deploying ADK agents to production environments, implementing safety measures, access control, secure authentication, testing, debugging, monitoring, or evaluating ADK agent quality.

This skill should be used when the user asks about "adding a tool", "FunctionTool", "creating tools", "MCP integration", "OpenAPI tools", "built-in tools", "google_search tool", "code_execution tool", "long-running tools", "async tools", "third-party tools", "LangChain tools", "computer use", or needs guidance on extending agent capabilities with custom functions, API integrations, or external tool frameworks.

Workflow patterns and gotchas for Google Agent Development Kit. Directs to RAG for implementation.

Workflow patterns and gotchas for Anthropic/Claude agents. Directs to RAG for implementation.

Use when any Mister Smith request touches Linear, GitHub PR flow, packet slicing, review state, workspace hygiene, or bootstrap readiness and needs the correct Smith MCP route first.

Use after a Mister Smith SpecKit packet has been created and needs post-spec closure: packet verification, git closure, Linear materialization, honest execution-lane preparation, and follow-on execution readiness without implementation unless explicitly requested.

Use when the user wants a complete Mister Smith live runtime session or workflow evaluation with real execution, durable evidence capture, and honest task/session/autonomy proof instead of mock-only validation.

Use when Mister Smith needs spec-only frontier packet work: turning current repo truth or a pre-SpecKit primer into a new product-side SpecKit packet, or running the full local SpecKit authoring chain for an already chosen packet. Trigger for requests to create or extend a Mister Smith packet spec, pre-SpecKit primer, specify-init prompt, or full spec bundle without implementation.

Use when a Mister Smith SpecKit phase or tasks pack needs to be turned into deterministic Linear slices, blocker chains, prep-slice opportunities, and direct-execution-ready work.

Legacy-named skill for Mister Smith tasks that span Linear control-plane state, GitHub PR flow, local repo truth, lifecycle recovery, or workspace hygiene.

Legacy-named skill for Mister Smith Human Review handoff, review triage, and merge readiness through Smith MCP.

Use when a Mister Smith phase, issue, PR, or design decision needs a frontier-legitimacy judgment about supervised autonomy, scope drift, or security-versus-autonomy balance.

Use when a user has a rough prompt that needs a staged prompt-improvement workflow for `$ralph-wiggum-codex`, with saved draft/final files and explicit review checkpoints.

Use when a coding task needs an objective-first long-running loop with fresh-context work and review phases, explicit acceptance criteria, resumable state, and real blocked handling.

Create or optimize agent prompts and workflows with structured analysis and improvement