adk▌

Quick reference for Python ADK API, agent types, tools, orchestration, and state management. \n \n Covers Python ADK SDK only; includes agent definitions, tool patterns, callbacks, plugins, state management, artifacts, and context caching \n Provides a searchable index of all ADK documentation pages with URLs for fetching reference materials \n Intended as a lookup resource while writing or modifying code in existing projects, not for bootstrapping new agents \n Reference files include python.md

This skill provides comprehensive documentation and Python examples for the Google Agent Development Kit (ADK). It maps documentation topics to their corresponding Python code snippets.

Scaffold new ADK agent projects and add deployment, CI/CD, and infrastructure to existing ones. \n \n Provides guided project creation with templates for standard agents, agent-to-agent (A2A) coordination, and RAG with data ingestion \n Supports multiple deployment targets: Agent Engine (managed), Cloud Run (container), GKE (Kubernetes), or prototype-only (code without deployment scaffolding) \n Includes optional CI/CD pipeline setup via GitHub Actions or Google Cloud Build, session storage conf

Comprehensive evaluation methodology guide for ADK agents covering metrics, schemas, and iteration workflows. \n \n Provides eight evaluation criteria (tool trajectory, response matching, rubric-based scoring, hallucination detection, safety) with configurable thresholds and judge model options \n Includes evalset schema documentation with multi-turn conversation support, tool use trajectory specification, and session state initialization patterns \n Outlines the eval-fix loop: start small, run

Comprehensive deployment guide for ADK agents across Google Cloud platforms with CI/CD, infrastructure, and troubleshooting. \n \n Covers three deployment targets (Agent Engine, Cloud Run, GKE) with a decision matrix comparing scaling, networking, session state, and cost models \n Includes quick-deploy CLI commands, scaffolded project workflows with make commands, and full CI/CD pipeline setup via GitHub Actions or Cloud Build with Workload Identity Federation \n Provides platform-specific detai

Essential reference guide for ADK agent development, covering spec-driven workflow, code preservation rules, and operational best practices. \n \n Read DESIGN_SPEC.md first as your primary source of truth; all implementation decisions must align with it \n Follow four mandatory phases: understand spec, build and implement, evaluate (using /adk-eval-guide ), and deploy with human approval \n Preserve all unrelated code when making modifications; only alter explicitly targeted segments and never c

Observability setup guide for ADK agents covering tracing, logging, analytics, and third-party integrations. \n \n Four observability tiers: Cloud Trace (always enabled, distributed tracing), Prompt-Response Logging (GenAI interactions to GCS/BigQuery), BigQuery Agent Analytics (structured agent events), and third-party platforms (AgentOps, Phoenix, MLflow, Weave, Arize, Monocle, Freeplay) \n Cloud Trace automatically configured in scaffolded projects and Agent Engine deployments; captures execu

Use this skill when you've got questions about the Botpress Agent Development Kit (ADK) - like when you're building a feature that involves tables, actions, tools, workflows, conversations, files, knowledge bases, triggers, evals, or Zai.