gemini-adk-skills

ADK Agent-to-Agent (A2A) protocol integration. Use when building remote agent communication — exposing ADK agents as A2A servers or connecting to external A2A agents as clients.

ADK App pattern with plugins, event compaction, and resumability. Use when you need plugins (context filtering, debug logging), event summarization, or resumable long-running operations.

ADK artifact services for file storage. Use when agents need to save/load files, images, or binary data — InMemory, File, and GCS artifact backends.

ADK authentication and credentials. Use when adding auth to tools — API keys, bearer tokens, OAuth2 flows, OpenID Connect, service accounts, and credential storage services.

Catalog of all ADK built-in tools. Use when looking for pre-built tools to add to agents — search, memory, artifacts, transfer, grounding, and user interaction tools.

Implement ADK agent and tool callbacks. Use when adding lifecycle hooks — before/after agent execution, before/after tool calls, for logging, validation, conditional execution, or response modification.

ADK code execution backends. Use when agents need to write and run Python code — BuiltIn, Container, VertexAI, GKE, or local executors.

Deploy ADK agents to Cloud Run, Vertex AI Agent Engine, or GKE. Use when containerizing and deploying agents for production — covers Dockerfile, adk deploy CLI, and service configuration.

ADK evaluation framework. Use when writing eval sets, running agent evaluations with `adk eval`, or setting up automated quality checks for agent responses.

Create custom function tools for ADK agents. Use when writing Python functions that agents can call — covers docstring conventions, ToolContext, FunctionTool, async tools, and state manipulation via tools.

Create Google ADK LlmAgent (also aliased as Agent). Use when building a single AI agent with model, instruction, tools, and configuration. Covers all LlmAgent parameters, instruction providers, output schemas, and include_contents options.

Integrate MCP (Model Context Protocol) tools into ADK agents. Use when connecting agents to MCP servers — stdio transport, SSE transport, MCPToolset configuration, and tool filtering.

ADK long-term memory with MemoryService. Use when implementing cross-session recall — InMemoryMemoryService for dev, Vertex AI RAG for production. Covers memory tools (load_memory, preload_memory) and custom memory services.

Use non-Gemini models with ADK agents via LiteLLM or Anthropic. Use when wiring Claude, GPT-4, Llama, Mistral, or any LiteLLM-supported provider into an ADK agent.

Build ADK multi-agent systems with sub_agents, transfer_to_agent, and agent hierarchies. Use when creating coordinator/worker patterns, triage agents, or any system with multiple collaborating agents.

Create ADK tools from OpenAPI specs. Use when connecting agents to REST APIs defined by OpenAPI/Swagger specs — auto-generates tools from endpoints with auth support.

Scaffold a new Google ADK (Agent Development Kit) Python project. Use when creating a new ADK agent project from scratch — sets up directory structure, __init__.py, agent.py, pyproject.toml, and .env template.

ADK session management and state. Use when working with conversation state, session services (InMemory, SQLite, Database, Vertex AI), or persisting data across agent invocations.

ADK bidi-streaming / Live API. Use when building real-time audio/video streaming agents — WebSocket connections, run_live, audio transcription, and streaming tools.

Create ADK workflow agents: LoopAgent, ParallelAgent, SequentialAgent. Use when orchestrating deterministic multi-step workflows — sequential pipelines, parallel fan-out, or iterative loops with exit conditions.