skills.rest
MattMagg
MattMaggCOMMUNITY
Explore all skills by this author →
GitHub

ADK Behavior

Configures ADK agents with callbacks, memory, and grounding for Python environments.

3|Updated Jan 9, 2026
Search Tags:#memory#grounding#events#callbacks#human-in-the-loop#adk
One-click install
npx skills add https://github.com/MattMagg/agentic-plugins --skill adk-behavior
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: ADK Behavior
Source: https://github.com/MattMagg/agentic-plugins/tree/main/plugins/adk-builder/skills/adk-behavior
Command: npx skills add https://github.com/MattMagg/agentic-plugins --skill adk-behavior

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

Customizes ADK agent behavior by providing structured access to callbacks, memory, events, and grounding, enabling interceptable and persistent agent workflows.

Core Features & Use Cases

  • Exposes agent, model, and tool callbacks to adapt execution flow.
  • Enables session and long-term memory integration with memory services and tools.
  • Supports grounding against external knowledge sources (RAG, search, and databases) and human-in-the-loop workflows.

Quick Start

Configure an LlmAgent with callbacks, memory, and grounding tools to tailor its behavior for your workflow.

Frequently Asked Questions about ADK Behavior

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I configure ADK agent behavior with callbacks and memory?▼

Configure ADK agent behavior by exposing agent, model, and tool callbacks alongside memory services to adapt execution flow and persist session data within your Python environment.

What is grounding in ADK and how does it work with external knowledge?▼

Grounding in ADK anchors agent responses by integrating external knowledge sources like RAG, search, and databases, ensuring customized agent workflows retrieve verified information.

Can I implement human-in-the-loop workflows using ADK callbacks?▼

Yes, you can implement human-in-the-loop workflows by configuring LlmAgent callbacks to intercept execution flow, enabling manual review and approval steps during agent processing.

Does ADK behavior customization require Vertex AI or Google Cloud services?▼

ADK behavior customization requires a Python-based ADK environment with callback, memory, and grounding components, but may leverage Vertex AI or Google Cloud services for advanced memory capabilities.

What's the best way to persist long-term memory for ADK agents?▼

Persist long-term memory for ADK agents by integrating memory services and tools directly into your LlmAgent configuration, enabling structured retention of session data across workflows.

When do I need to intercept execution flow in ADK agent workflows?▼

Intercept execution flow in ADK agent workflows when you need to adapt behavior dynamically, validate tool outputs, or inject human-in-the-loop approval steps before completing agent tasks.

Related Skills

Explore More Software Engineering Skills→
AgentientAgentient
2

adk-fundamentals

Scaffold ADK agent projects with uv and Vertex AI configuration.

Official
Intermediate
hoanghd218hoanghd218

google-adk-python

Automates AI agent development with Google ADK Python.

Community
Advanced
redis-developerredis-developer
29

adk-redis

Integrate Redis with Google ADK for persistent sessions and semantic caching.

Official
Advanced
DektoraDektora

rotation-handoff

Generate and read structured DekSpec session handoff records in dekspec/.scratch/rotation-handoff/.

Official
Advanced