google-agents-cli-adk-code

SKILL.md

Quick reference for ADK Python patterns: agents, tools, callbacks, and state management.

Covers agent creation with model and instruction configuration, basic tool definition via FunctionTool, and callback patterns for state initialization and lifecycle hooks

Includes built-in tool imports, agent orchestration (SequentialAgent, ParallelAgent, LoopAgent), and state management through CallbackContext

ADK 2.0 Workflow API available as opt-in experimental feature for graph-based pipelines with conditional routing and parallel processing; requires Python 3.11+ and explicit user consent before use

Requires an existing scaffolded project; use agents-cli scaffold create or scaffold enhance before writing agent code

ADK Code Reference

Activate /google-agents-cli-workflow first for required development phases and scaffolding steps.

1. Study Recipes (No Project Needed)

Read the topic index in references/samples.md before answering "how do I build X". Worked implementations exist for: sandboxed/per-user code execution, agent-loadable SKILL.md skills, cross-session memory, approval gates before risky actions, tool guardrails, per-user credentials, and scheduled/event-driven runs.

The index only gives you a name; the recipe is the code. Clone it and read its AGENTS.md before you implement anything it covers. Hand-writing a Docker or E2B sandbox wrapper, a skill loader, a moderation callback or a memory store — for a capability the index lists — means you stopped at the name.

2. Prerequisites for Writing Code

Do NOT write agent code until a project is scaffolded.

Verify project: run agents-cli info (proceed if config exists).

New project: run agents-cli scaffold create <name>.

Existing code: run agents-cli scaffold enhance ..

Language Support: This reference covers the Python ADK SDK. Support for other languages coming soon.