Official agent skill

Adk Sample Creator

by google in google/adk-python

Creates a new sample agent in the ADK Python repository — the sample directory, its agent.py, and its README.md — following the conventions the existing samples already use.

OfficialApache-2.0Auto-check passedDevelopment

Install Adk Sample Creator

skills CLI
$ npx skills add google/adk-python --skill adk-sample-creator -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install google/adk-python adk-sample-creator --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/google/adk-python.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/adk-sample-creator .claude/skills/adk-sample-creator && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
adk-sample-creator
GitHub stars
22k
Token cost
~1.3k tokens
SKILL.md length
462 words
Files
2 (incl. references)
Skills in repo
13
Repo updated
First seen
Licence
Apache-2.0

At a glance

Creates a new sample agent in the ADK Python repository — the sample directory, its agent.py, and its README.md — following the conventions the existing samples already use.

  • Works in 3 steps: Pick the category directory → Write agent.py → Write README.md
  • The user wants to add a sample
  • SKILL.md covers 1. Pick the category directory, 2. Write agent.py, 3. Write README.md and Worked examples
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Adk Sample Creator is an agent skill from google/adk-python, published by the product's own GitHub organization. Creates a new sample agent in the ADK Python repository — the sample directory, its agent.py, and its README.md — following the conventions the existing samples already use. Use when the user wants to add a sample or example demonstrating a feature or agent pattern (dynamic nodes, fan-out/fan-in, a standalone tool-using agent), asks where a new sample belongs under contributing/samples/, or wants an existing sample's README brought up to the standard structure. Don't use for building a real working agent for the…

Its SKILL.md is about 1.3k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/readme-template.md`).

It sits in Development, covering Technical documentation and Building AI agents. It works with Python. The repository describes itself as: An open-source, code-first Python toolkit for building, evaluating, and deploying sophisticated AI agents with flexibility and control. The licence is Apache-2.0.

When your agent uses it

  • The user wants to add a sample
  • Example demonstrating a feature
  • Agent pattern (dynamic nodes
  • A standalone tool-using agent)

Example prompts

  • “s README brought up to the standard structure. Don”
  • “Use the adk-sample-creator skill to create a new sample agent in the ADK Python repository — the sample directory, its agent.py, and its README.md —…”
  • “/adk-sample-creator”

Requirements

  • Python 3

Workflow steps

3 steps, taken from the step headings in SKILL.md.

  1. Pick the category directory
  2. Write agent.py
  3. Write README.md

What it can do on your machine

Read from SKILL.md and the folder at commit 666c26d. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md (its code samples are python and bash).

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Adk Sample Creator loads about 1.3k tokens when it runs, and up to ~1.8k if it reads all its reference files. Until then it costs about 171 tokens; SKILL.md has 462 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~171
When it runs · the whole SKILL.md, loaded when a task matches
~1.3k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.8k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from google/adk-python at commit 666c26d, republished under its Apache-2.0 licence (© google). 462 words, ~1,323 tokens.

Download SKILL.mdSave it as .claude/skills/adk-sample-creator/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
adk-sample-creator
description
Creates a new sample agent in the ADK Python repository — the sample directory, its `agent.py`, and its `README.md` — following the conventions the existing samples already use. Use when the user wants to add a sample or example demonstrating a feature or agent pattern (dynamic nodes, fan-out/fan-in, a standalone tool-using agent), asks where a new sample belongs under `contributing/samples/`, or wants an existing sample's README brought up to the standard structure. Don't use for building a real working agent for the user's own project (use `adk-agent-builder`), or for checking whether the Python blocks in a Markdown file run (use `adk-verify-snippets`).

ADK Sample Creator

Creates samples under contributing/samples/. These are deliberately minimal agents that each exercise one or two features — distinct from the adk-samples repository, which hosts full end-to-end applications.

Read the adk-style skill first for ADK 2.0 conventions if you have not already.

1. Pick the category directory

Almost every sample lives at contributing/samples/{category}/{sample_name}/. List the categories and confirm with the user which one the sample belongs in before creating anything — a workflow sample landing outside workflows/ is the usual mistake.

bash
ls contributing/samples/

Categories include workflows, patterns, core, multi_agent, tools, models, live, mcp, a2a, evaluation, and plugins. A handful of samples nest one level further when a single feature needs several variants, as plugins/plugin_reflect_tool_retry/basic/ does.

Name the sample directory in snake_case after the feature it demonstrates: dynamic_nodes, fan_out_fan_in, streaming_tool_events.

Do not add an _agent suffix, and do not repeat the category as a prefix — every sample is an agent, and the category is already in the path. Many existing directories still carry both; do not copy them.

2. Write agent.py

Contents of a sample directory:

FileRequiredPurpose
agent.pyyesThe agent or workflow. Must expose root_agent.
README.mdyesSee readme-template.md.
__init__.pysometimesPresent when the sample is imported as a package.
tests/*.jsonnoRecorded sessions used as eval sets.

Use absolute imports so the file can be run and imported directly.

Do not set model= on Agent instances. Samples inherit the system-configured model, which keeps them working when the default model changes; hardcoding model="gemini-2.5-flash" pins the sample to a model that will be retired. Set it only when the user explicitly asks for a specific model.

Then pick one of the two shapes.

Show full SKILL.md (190 more words)Show less
Pattern A — Workflow, for multi-step graphs

Use when the sample needs multiple nodes, routing, or parallel execution.

python
from google.adk import Agent
from google.adk import Context
from google.adk import Event
from google.adk import Workflow
from google.adk.workflow import JoinNode
from google.adk.workflow import node

Import Workflow from google.adk, not from a private google.adk.workflow._* module.

python
my_agent = Agent(name="my_agent", instruction="...")


@node()
async def my_node(node_input: str) -> str:
  return "result"


root_agent = Workflow(
    name="root_agent",
    edges=[("START", my_node)],
)

A plain function can be used as a node directly in edges; reach for the @node(...) decorator when you need one of its options, such as rerun_on_resume=True for a node that calls ctx.run_node.

Pattern B — Standalone agent, for single-agent or simple tool use

Use when there is no graph and the agent drives its own loop.

python
from google.adk import Agent
from google.adk.tools import google_search

root_agent = Agent(
    name="standalone_assistant",
    instruction="You are a helpful assistant.",
    description="An assistant that can help with queries.",
    tools=[google_search],
)

3. Write README.md

Follow readme-template.md — section order, prompt formatting, the Mermaid topology rules, and the relative link depth for docs/guides/.

Worked examples

Read these two before writing a new Pattern A sample — one dynamic graph, one static one.

  • contributing/samples/workflows/dynamic_nodes/agent.py — a Python node driving a while loop with ctx.run_node, so the number of agent calls is decided at runtime rather than by the edges.

    python
    @node(rerun_on_resume=True)
    async def orchestrate(ctx: Context, node_input: str) -> str:
      yield Event(state={"topic": node_input})
    
      while True:
        headline = await ctx.run_node(generate_headline)
        # ...
  • contributing/samples/workflows/fan_out_fan_in/agent.py — three functions run in parallel from START, collected by a JoinNode, then aggregated.

    python
    join_node = JoinNode(name="join_for_results")
    
    root_agent = Workflow(
        name="root_agent",
        edges=[(
            "START",
            (make_uppercase, count_characters, reverse_string),
            join_node,
            aggregate,
        )],
    )

© google, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in .agents/skills/adk-sample-creator of google/adk-python.

  • SKILL.md
  • references/readme-template.md

Open the folder on GitHubat commit 666c26d

Compare with similar skills

Adk Sample Creator next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Adk Sample Creator compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Adk Sample Creator this skillgoogle/adk-python22k—~1.3kAutomated safety check: PassApache-2.0
A2ui Python Developmenta2ui-project/a2ui17k—~2.4kAutomated safety check: PassApache-2.0
Glossarylightly-ai/lightly-studio896—~482Automated safety check: PassApache-2.0
Docstring Deep Divealbumentations-team/AlbumentationsX566—~534Automated safety check: PassAGPL-3.0
Swarmauri Add Community Standaloneswarmauri/swarmauri-sdk104—~387Automated safety check: PassApache-2.0
Phoenix Docs Gap AuditArize-ai/phoenix12k—~4.8kAutomated safety check: PassCustom licence

Similar skills

  • A2ui Python Development

    a2ui-project/a2ui

    Grounding, architectural standards, Python best practices, package facade conventions, testing, and verification workflows for developing any Python code across the entire A2UI repository (core…

    17k GitHub stars~2.4k tokensUpdated today
    DevelopmentAuto-check passed
  • Glossary

    lightly-ai/lightly-studio

    Read when naming anything user-facing - GUI text, docs, public Python API names, arguments, docstrings, or error messages.

    896 GitHub stars~482 tokensUpdated today
    DevelopmentAuto-check passed
  • Docstring Deep Dive

    albumentations-team/AlbumentationsX

    Review public AlbumentationsX docstrings for useful descriptions, runnable examples, parameter semantics, and related transforms.

    566 GitHub stars~534 tokensUpdated today
    DevelopmentAuto-check passed
  • Swarmauri Add Community Standalone

    swarmauri/swarmauri-sdk

    Add a second-class standalone Swarmauri package under pkgs/community.

    104 GitHub stars~387 tokensUpdated 1 mo ago
    DevelopmentAuto-check passed
  • Phoenix Docs Gap Audit

    Arize-ai/phoenix

    Audit documentation gaps across the Phoenix repo by analyzing recent commits to main (default: last 7 days).

    12k GitHub stars~4.8k tokensUpdated today
    DevelopmentAuto-check passed
  • Add an experimental standalone Swarmauri package under pkgs/experimental.

    104 GitHub stars~457 tokensUpdated 1 mo ago
    DevelopmentAuto-check passed

More from google/adk-python

All 13 skills in this repo
  • Adk Verify Snippets

    google/adk-python

    Official

    Checks that every Python code block in a Markdown file actually compiles and runs, by extracting each block to a temporary file, executing it in an isolated subprocess, and writing a pass/fail…

    22k GitHub stars~1.4k tokensUpdated today
    Auto-check passed
  • Adk Unit Guide

    google/adk-python

    Official

    Writes a hands-on developer guide for one ADK code unit — a minimal runnable example, how it works, a configuration-option table, advanced uses, limitations, and links to related samples — to…

    22k GitHub stars~2.6k tokensUpdated today
    Auto-check passed
  • Adk Git

    google/adk-python

    Official

    Writes commit messages and pull request descriptions for the adk-python repository: Conventional Commits types and scopes, subject lines that say why a change was made, and the linked-issue and…

    22k GitHub stars~1.3k tokensUpdated today
    Auto-check passed
  • Adk Setup

    google/adk-python

    Official

    Sets up a local ADK Python development environment in a git clone of the open-source adk-python repository: a uv virtual environment, all dependency extras, pre-commit hooks, and a first unit-test…

    22k GitHub stars~993 tokensUpdated today
    Auto-check: notes
  • Adk Agent Builder

    google/adk-python

    Official

    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…

    22k GitHub stars~879 tokensUpdated today
    Auto-check passed
  • Adk Architecture

    google/adk-python

    Official

    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.

    22k GitHub stars~1.2k tokensUpdated today
    Auto-check passed

Works with

Questions about Adk Sample Creator

What does Adk Sample Creator do?

Creates a new sample agent in the ADK Python repository — the sample directory, its agent.py, and its README.md — following the conventions the existing samples already use. Adk Sample Creator is an agent skill from google/adk-python, published by the product's own GitHub organization.md — following the conventions the existing samples already use.

When should I use Adk Sample Creator?

Adk Sample Creator fits situations like: the user wants to add a sample; example demonstrating a feature; agent pattern (dynamic nodes; A standalone tool-using agent).

How do I install Adk Sample Creator in Claude Code?

Run `npx skills add google/adk-python --skill adk-sample-creator -a claude-code`. Or copy the skill folder (.agents/skills/adk-sample-creator in google/adk-python) into .claude/skills/adk-sample-creator in your project. Claude Code loads it when a task matches its description.

How do I install Adk Sample Creator in Codex?

Run `npx skills add google/adk-python --skill adk-sample-creator -a codex`. Or copy the skill folder (.agents/skills/adk-sample-creator in google/adk-python) into .agents/skills/adk-sample-creator in your project. Codex loads it when a task matches its description.

Can I use Adk Sample Creator in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add google/adk-python --skill adk-sample-creator -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/adk-sample-creator, .gemini/skills/adk-sample-creator, .github/skills/adk-sample-creator and .opencode/skills/adk-sample-creator in your project.

What does Adk Sample Creator need to run?

SKILL.md names no scripts, command-line tools or credentials: Adk Sample Creator is instructions for the agent only. Our summary lists: Python 3.

Does Adk Sample Creator access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Adk Sample Creator safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Adk Sample Creator use?

Adk Sample Creator is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Adk Sample Creator use?

About 1.3k tokens (SKILL.md is roughly 5.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 497 tokens, read only when the agent opens those files.

What are the alternatives to Adk Sample Creator?

Skills that share tags, products or a category with Adk Sample Creator: A2ui Python Development (a2ui-project/a2ui, 17k stars), Glossary (lightly-ai/lightly-studio, 896 stars), Docstring Deep Dive (albumentations-team/AlbumentationsX, 566 stars) and Swarmauri Add Community Standalone (swarmauri/swarmauri-sdk, 104 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Adk Sample Creator?

google (a GitHub organization, an official publisher) maintains it in google/adk-python, which has 21,729 GitHub stars. The repository holds 13 skills in this directory. The repository was last updated on October 7, 2026.

Source: google/adk-python on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.