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`).

Jump to install Review files

Repository: google/adk-python
Last source activity: October 1, 2026 at 21:28
Detected SKILL.md language: English
Stars: 21,709
Forks: 4,101

Install options

The review-first prompt is selected by default. You can switch to a direct command or download a local copy.

Install with an AI assistant

Copy this prompt into the AI assistant you're using.

Follow https://skillsmp.com/skill-install/prompt.md to install only the Agent Skill at https://github.com/google/adk-python/tree/main/.agents/skills/adk-agent-builder.

A direct command skips the review prompt. Inspect the source before running it.

npx skills add https://github.com/google/adk-python --skill adk-agent-builder

The command stays on one line. Scroll horizontally to inspect it before copying.

Prefer a local copy? Download the files currently available to SkillsMP.

Review the source files

Read SKILL.md and any companion files shown by SkillsMP before deciding whether to install.

File Explorer

18 files

SKILL.md

Source instructions · Read-only preview

name: adk-agent-builder
description: 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.

View on GitHub

Back to search Back to installation

adk-review

Reviews the uncommitted changes in an adk-python working tree and reports correctness, design, public-API stability, test, sample and documentation gaps as a prioritized findings report, fixing them only when asked. Use when the user asks to review local changes, wants a self-review before opening a pull request, asks whether a change breaks the public API or needs tests, samples or docs, or asks what is wrong with the current diff. Required for changes to public APIs, core architecture (Runner, Workflow, BaseNode), new features and major refactors. Don't use for a single style nit (use adk-style), for diagnosing a failing test or a misbehaving agent at runtime (use adk-debug), or for wording a commit message or PR description (use adk-git).

2026-10-03

adk-style

Python style and codebase conventions for ADK (Agent Development Kit): private-by-default file visibility, imports, type hints, Pydantic v2 models, formatting, docstrings, logging, async I/O, file and test layout, and unit test structure. Use when writing or editing ADK source or tests, deciding whether a new file or symbol should be public or private, naming or placing a test file, fixing a formatter, linter, or type-check failure (pyink, isort, ruff, mypy, addlicense, compliance-checks), or asking whether code matches house style. Don't use for reviewing a whole changeset (use adk-review), writing a developer guide or design doc for a code unit (use adk-unit-guide or adk-unit-design), building or configuring agents (use adk-agent-builder), or installing the toolchain (use adk-setup).

2026-10-03

adk-architecture

Explains how the ADK runtime fits together: the node and graph execution model, Context and Event flow, checkpoint and resume, tracing, and the rules governing the public API surface. Use when answering "how does X work" about ADK internals, tracing where an event or a piece of state comes from, deciding where a new capability belongs, reviewing a change to BaseNode, Workflow, Runner, Agent, Event or Context, working out why a node re-ran or stayed waiting after a resume, or judging whether a change breaks the public API. Don't use for assembling an agent from existing pieces (use adk-agent-builder), diagnosing one failing run or test (use adk-debug), or formatting and naming conventions (use adk-style).

2026-10-01

View all from this repository

adk-agent-builder

Source facts

Install options

Install with an AI assistant

Review the source files

More from this repository

Install with an AI assistant

More from this repository