How do I install the Adk Agent Builder skill?

Run npx skillmds@latest add google/adk-agent-builder in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

Is Adk Agent Builder safe to use?

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Adk Agent Builder?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Adk Agent Builder free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Adk Agent Builder?

Google (@google) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Adk Agent Builder by google — Agent Skill

Name: Adk Agent Builder
Rating: 4.2 (5 reviews)
Author: Google

Adk Agent Builder

Builds ADK (Agent Development Kit) Python agents: LLM agents with tools, graph workflows of function and agent nodes, conditional routing, fan-out and join, schema-validated delegation between agents, human-in-the-loop pauses, and pytest coverage for all of it. Use when asked to create an agent or a workflow, add a tool to one, branch or loop between nodes, run steps in parallel, pause for user approval, or test an agent. Don't use for explaining how ADK works internally or designing its core components (use `adk-architecture`), for an agent that already runs but misbehaves (use `adk-debug`), for authoring a sample under `contributing/` (use `adk-sample-creator`), or for naming, typing, and formatting conventions (use `adk-style`).

Google Updated Sep 9, 2026 14.4k repo stars

File contents

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 BaseTool and BaseToolset.
function-nodes.md — plain functions as nodes: parameter resolution, generators, node_input typing rules.
llm-agent-nodes.md — an LlmAgent used as a workflow node: output types, instruction templates, output_schema, auto-wrapping behavior.
task-mode.md — mode='task' and mode='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, JoinNode fan-in, parallel_worker=True list 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 BaseNode subclasses, graph validation rules.
multi-agent.md — chat-transfer hierarchies, and the deprecated SequentialAgent / LoopAgent / ParallelAgent shells that Workflow replaces.

Runtime and verification

state-and-events.md — the Context object, Event fields, 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 — pytest with InMemoryRunner, faking a model, asserting on node output.

---name: adk-agent-builderdescription: Builds ADK (Agent Development Kit) Python agents: LLM agents with tools, graph workflows of function and agent nodes, conditional routing, fan-out and join, schema-validated delegation between agents, human-in-the-loop pauses, and pytest coverage for all of it. Use when asked to create an agent or a workflow, add a tool to one, branch or loop between nodes, run steps in parallel, pause for user approval, or test an agent. Don't use for explaining how ADK works internally or designing its core components (use `adk-architecture`), for an agent that already runs but misbehaves (use `adk-debug`), for authoring a sample under `contributing/` (use `adk-sample-creator`), or for naming, typing, and formatting conventions (use `adk-style`).--- # 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](references/getting-started.md) | | Which import path is the canonical one | [import-paths.md](references/import-paths.md) | | The rules that cause most runtime failures | [best-practices.md](references/best-practices.md) | ## Building blocks - [tool-catalog.md](references/tool-catalog.md) — function tools, MCP, OpenAPI, Google API toolsets, built-in tools, custom `BaseTool` and `BaseToolset`. - [function-nodes.md](references/function-nodes.md) — plain functions as nodes: parameter resolution, generators, `node_input` typing rules. - [llm-agent-nodes.md](references/llm-agent-nodes.md) — an `LlmAgent` used as a workflow node: output types, instruction templates, `output_schema`, auto-wrapping behavior. - [task-mode.md](references/task-mode.md) — `mode='task'` and `mode='single_turn'` delegation with schema-validated input and output. ## Graph orchestration - [routing-and-conditions.md](references/routing-and-conditions.md) — routed edges, dict routing maps, default routes, self-loops, revision loops. - [parallel-and-fanout.md](references/parallel-and-fanout.md) — fan-out edges, `JoinNode` fan-in, `parallel_worker=True` list processing. - [dynamic-nodes.md](references/dynamic-nodes.md) — scheduling nodes at runtime with `ctx.run_node()` and imperative workflow construction. - [human-in-the-loop.md](references/human-in-the-loop.md) — `RequestInput`, resume behavior, resumable vs replayed sessions. - [advanced-patterns.md](references/advanced-patterns.md) — nested workflows, retries, custom `BaseNode` subclasses, graph validation rules. - [multi-agent.md](references/multi-agent.md) — chat-transfer hierarchies, and the deprecated `SequentialAgent` / `LoopAgent` / `ParallelAgent` shells that `Workflow` replaces. ## Runtime and verification - [state-and-events.md](references/state-and-events.md) — the `Context` object, `Event` fields, and how state flows between nodes. - [session-and-state.md](references/session-and-state.md) — session services, artifacts, memory, and state key scoping. - [callbacks-and-plugins.md](references/callbacks-and-plugins.md) — the six agent callbacks and app-level plugins. - [testing.md](references/testing.md) — `pytest` with `InMemoryRunner`, faking a model, asserting on node output.

Frequently asked questions