MCPInstall

adk-setup

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 run. Runs only when explicitly requested, never on its own. Use when asked to set up, bootstrap, or repair a development checkout, install project dependencies, fix a missing or broken .venv, or prepare a machine for contributing a pull request. Don't use for debugging a running agent (use adk-debug), for commit and pull-request mechanics (use adk-git), or for re-running formatters on a checkout that is already set up (pre-commit run --all-files).

Installs
97
Last 24h
—
Trending rank
—
Security
Not audited

Install

Works with every agent the skills CLI supports.

npx skills add https://github.com/google/adk-python --skill adk-setup
  1. 01

    Install

    Run the command in your project. The CLI asks which agents to install for.

  2. 02

    Describe the task

    Ask your agent for something this skill covers. It loads adk-setup automatically when relevant.

  3. 03

    Review the result

    The agent follows the SKILL.md steps, scripts and references bundled with the skill.

SKILL.md

The instructions your agent reads when the skill is triggered.

ADK Python Development Setup

Set up a working adk-python checkout: a uv-managed virtual environment with every dependency extra, pre-commit hooks, and a green unit-test run.

Prerequisites

  1. Python. ADK supports 3.11 through 3.15 (requires-python = ">=3.11" in pyproject.toml). These steps use 3.11, the version the repo's own tooling defaults to.

    python3 --version
    
  2. uv. Dependencies are declared in pyproject.toml. The uv sync step below creates a local uv.lock, which this repository ignores. Run that step before tox, whose lock runner requires the file.

    uv --version
    

    Install it if missing:

    curl -LsSf https://astral.sh/uv/install.sh | sh
    

Setup

Run these from the repository root.

  1. Create and activate the virtual environment:

    uv venv --python "python3.11" ".venv"
    source .venv/bin/activate
    
  2. Install every dependency extra:

    uv sync --all-extras
    

    --all-extras is what pulls in the test and dev extras. Syncing only the default dependencies leaves pytest and the linters uninstalled.

  3. Install pre-commit and tox as standalone tools:

    uv tool install pre-commit
    uv tool install tox --with tox-uv
    

    Both are also in the dev extra; installing them as uv tools puts them on PATH so the git hook and multi-version test runs work without an activated venv.

  4. Install addlicense (optional, requires Go):

    go install github.com/google/addlicense@latest
    

    Without it the pre-commit hook prints Warning: addlicense not installed, skipping and passes, so a missing Go toolchain does not block setup — CI catches missing license headers instead.

  5. Install the git hooks:

    pre-commit install
    

    On each commit the hooks auto-format with isort, pyink, and mdformat, then run ruff, addlicense, codespell, and the repo's own compliance checks.

  6. Verify the environment:

    pytest tests/unittests -n auto
    

    A green run here is the success criterion for setup. -n auto needs pytest-xdist, which arrives with the test extra in step 2.

Key commands

TaskCommand
Run unit testspytest tests/unittests
Run unit tests in parallelpytest tests/unittests -n auto
Run one test filepytest tests/unittests/agents/test_base_agent.py
Run tests on every supported Pythontox (uv downloads any missing interpreters)
Format and lint everythingpre-commit run --all-files
Launch the web UIadk web {agents_dir}
Run an agent from the CLIadk run {agent_dir}
Build the wheeluv build

FAQ

What does the adk-setup skill do?

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 run. Runs only when explicitly requested, never on its own. Use when asked to set up, bootstrap, or repair a development checkout, install project dependencies, fix a missing or broken .venv, or prepare a machine for contributing a pull request. Don't use for debugging a running agent (use adk-debug), for commit and pull-request mechanics (use adk-git), or for re-running formatters on a checkout that is already set up (pre-commit run --all-files).

How do I install adk-setup?

Run npx skills add https://github.com/google/adk-python --skill adk-setup in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/adk-setup/ (personal) or .claude/skills/adk-setup/ (project).

Which AI agents can use adk-setup?

Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.

Is adk-setup safe to install?

No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.

Who maintains adk-setup?

It is published by google in google/adk-python. It has 97 recorded installs.

More from google/adk-python

View all →

adk-agent-builder

google/adk-python

Open the skill to read its SKILL.md instructions.

440 installs

adk-debug

google/adk-python

Diagnoses misbehaving ADK agents by inspecting sessions, events, tool calls, and the exact request that reached the model. Covers the adk run CLI and the adk web dev server with its session, trace, and debug HTTP endpoints. Use when an agent returns the wrong answer, ignores a tool or swallows a tool error, hangs, loops, emits raw JSON instead of calling tools, is not discovered by adk web, when a sub-agent cannot see the parent conversation, or when you need the LLM request/response, token counts, or logs for a run. Don't use for how ADK is designed internally (use adk-architecture), for building a new agent or workflow (use adk-agent-builder), for environment or dependency setup failures (use adk-setup), or for lint and style nits (use adk-style).

adk-architecture

google/adk-python

Open the skill to read its SKILL.md instructions.

adk-style

google/adk-python

Open the skill to read its SKILL.md instructions.

106 installs

adk-sample-creator

google/adk-python

Open the skill to read its SKILL.md instructions.

91 installs

adk-git

google/adk-python

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 testing-plan sections the PR template requires. Use when writing or rewording a commit message, squashing commits before a pull request, drafting a PR description, or checking that a change is shaped to land. Don't use for generic git mechanics such as rebasing, resolving conflicts, cherry-picking, or branch surgery; those need no skill. Don't use to judge the content of a change (use adk-review) or for code style and naming (use adk-style).

Popular code quality & workflow skills

View category →

grill-me

mattpocock/skills

A relentless interview to sharpen a plan or design.

Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.

handoff

mattpocock/skills

Compact the current conversation into a handoff document for another agent to pick up.

domain-modeling

mattpocock/skills

Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.

codebase-design

mattpocock/skills

Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.

diagnosing-bugs

mattpocock/skills

Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.