Google ADK Python Implementation

Verified API patterns for building production-grade multi-agent systems using Google's Agent Development Kit (ADK) for Python.

triggers:google adkadk pythonmulti-agent workflowagent development kitadk 2.0

GitHub SKILL.md

What it does

Equips the agent with comprehensive, verified implementation patterns for the Google Agent Development Kit (ADK) in Python. It covers both stable 1.x patterns and 2.0 Beta graph-based workflows, enabling the construction of complex multi-agent systems.

When to use it

Use this skill when designing, coding, or debugging agents built with Google ADK. Specifically for implementing LlmAgent, SequentialAgent, LoopAgent, and the new declarative Workflow graphs, as well as managing session state and context compaction.

What's included

Instructions: Detailed code snippets for agent types, graph routing, Human-in-the-Loop (HITL) flows, and MCP toolset integration.
Technical Guides: Guidance on context compaction, callback hooks, and migration paths from ADK 1.x to 2.0.

Compatible agents

Any agent capable of writing and reviewing Python code, specifically those targeting Gemini-powered ecosystems or general AI agent architectures.

Not yet audited

This skill has not been reviewed by our automated audit pipeline yet.

Information

Repository: k3-agentic-skills
Stars: 26

More from k3-agentic-skills

Git Push Workflow

Automates the process of staging changes, creating conventional commit messages, and pushing to a remote repository.

Related Skills

Extract Circuit Netlist Edge Features

Extract structured edge features from a bipartite circuit netlist (NetworkX MultiGraph), normalizing device/net ordering, mapping terminal colors, and detecting

Markdrop

Convert PDFs to structured Markdown or interactive HTML and generate AI-powered descriptions for images and tables using multiple LLM providers.

FastAPI Project Templates

Creates production-ready FastAPI project scaffolds with async patterns, DI, middleware, and testing best practices for high-performance APIs.

Unitree Robot Controller

Control and command Unitree robots (GO1/GO2/G1/H1) via OpenClaw: initialization, basic motion commands, and sensor integrations.

Alpha Forge Pre-Ship Quality Gates

Pre-merge quality gates for PRs that validate RNG determinism, forked URLs, runtime parameter ranges, and manifest synchronization to reduce review cycles.

Ip2Location IO Automation (Composio)

Automate Ip2location IO tasks via Composio's Rube MCP toolkit — discover tools, verify connections, and execute schema-compliant workflows safely.

Plotly (Interactive Python Visualizations)

Interactive Python visualization skill for building hoverable, zoomable, and embeddable charts (Plotly Express + Graph Objects) for EDA, dashboards, and present

Dr. Manhattan - Prediction Market Trading

Unified CCXT-style API and tools for discovering, analyzing, and trading prediction markets across Polymarket, Kalshi, Opinion, Limitless, and Predict.fun; incl

MCP App Store

Google ADK Python Implementation

What it does

When to use it

What's included

Compatible agents