Adk Agent Builder
Published by google in adk-python
Review recommended88 installs
What this skill does
>-
Add Adk Agent Builder to your agent
Review the source and files first. When you are ready, copy the prompt instruction or use the CLI command supported by your environment.
Install with a prompt
Paste this into a compatible coding agent:
add this skill "adk-agent-builder" from https://github.com/google/adk-pythonInstall with the CLI
Run this command in a controlled environment after reviewing the repository:
npx skills add https://github.com/google/adk-python --skill adk-agent-builderSkill instructions
ADK Agent Builder
Read only the reference that matches the task. Loading the whole tree costs context and buries the part that matters.
Every API below was checked against google-adk 2.6.2. If a symbol is missing
at runtime, read the source under src/google/adk/ rather than guessing a
neighbouring name.
Start here
| Task | Reference |
|---|---|
First agent, environment, adk CLI | getting-started.md |
| Which import path is the canonical one | import-paths.md |
| The rules that cause most runtime failures | best-practices.md |
Building blocks
- tool-catalog.md — function tools, MCP, OpenAPI,
Google API toolsets, built-in tools, custom
BaseToolandBaseToolset. - function-nodes.md — plain functions as nodes:
parameter resolution, generators,
node_inputtyping rules. - llm-agent-nodes.md — an
LlmAgentused as a workflow node: output types, instruction templates,output_schema, auto-wrapping behavior. - task-mode.md —
mode='task'andmode='single_turn'delegation with schema-validated input and output.
Graph orchestration
- routing-and-conditions.md — routed edges, dict routing maps, default routes, self-loops, revision loops.
- parallel-and-fanout.md — fan-out edges,
JoinNodefan-in,parallel_worker=Truelist processing. - dynamic-nodes.md — scheduling nodes at runtime
with
ctx.run_node()and imperative workflow construction. - human-in-the-loop.md —
RequestInput, resume behavior, resumable vs replayed sessions. - advanced-patterns.md — nested workflows,
retries, custom
BaseNodesubclasses, graph validation rules. - multi-agent.md — chat-transfer hierarchies, and
the deprecated
SequentialAgent/LoopAgent/ParallelAgentshells thatWorkflowreplaces.
Runtime and verification
- state-and-events.md — the
Contextobject,Eventfields, and how state flows between nodes. - session-and-state.md — session services, artifacts, memory, and state key scoping.
- callbacks-and-plugins.md — the six agent callbacks and app-level plugins.
- testing.md —
pytestwithInMemoryRunner, faking a model, asserting on node output.
Files included
- references/advanced-patterns.md
- references/best-practices.md
- references/callbacks-and-plugins.md
- references/dynamic-nodes.md
- references/function-nodes.md
- references/getting-started.md
- references/human-in-the-loop.md
- references/import-paths.md
- references/llm-agent-nodes.md
- references/multi-agent.md
- references/parallel-and-fanout.md
- references/routing-and-conditions.md
- references/session-and-state.md
- references/state-and-events.md
- references/task-mode.md
- references/testing.md
- references/tool-catalog.md
- SKILL.md

