Official agent skill

Adk Unit Design

by google in google/adk-python

Writes an as-built architecture document for one ADK code unit — purpose, execution flow, data flow, cross-class dependencies, extension points, and the parts that must not change — to…

OfficialApache-2.0Auto-check passedAgent Workflows

Install Adk Unit Design

skills CLI
$ npx skills add google/adk-python --skill adk-unit-design -a claude-code

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

GitHub CLI
$ gh skill install google/adk-python adk-unit-design --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-unit-design .claude/skills/adk-unit-design && 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-unit-design
GitHub stars
22k
Token cost
~759 tokens
SKILL.md length
285 words
Files
2 (incl. references)
Skills in repo
13
Repo updated
First seen
Licence
Apache-2.0

At a glance

Writes an as-built architecture document for one ADK code unit — purpose, execution flow, data flow, cross-class dependencies, extension points, and the parts that must not change — to…

  • Asked to write a design doc for {file}
  • SKILL.md covers Inputs, Analyse before writing, Where the document goes and Link to GitHub, not to local…, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Document the architecture of {class}

What it does

Adk Unit Design is an agent skill from google/adk-python, published by the product's own GitHub organization. Writes an as-built architecture document for one ADK code unit — purpose, execution flow, data flow, cross-class dependencies, extension points, and the parts that must not change — to docs/design/{topic}/{unit}/index.md. It describes the code as implemented, not a proposed design, and its reader is a developer about to change or extend that unit. Use when asked to "write a design doc for {file}", "document the architecture of {class}", "document the extension points of {unit}", or after adding a core class, node…

Its SKILL.md is about 760 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/design-template.md`).

It sits in Agent Workflows, covering Architecture decision records. 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

  • Asked to write a design doc for {file}
  • Document the architecture of {class}
  • Document the extension points of {unit}
  • After adding a core class

Example prompts

  • “write a design doc for {file}”
  • “document the architecture of {class}”
  • “document the extension points of {unit}”
  • “/adk-unit-design”

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.

    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 Unit Design loads about 759 tokens when it runs, and up to ~1.1k if it reads all its reference files. Until then it costs about 208 tokens; SKILL.md has 285 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~208
When it runs · the whole SKILL.md, loaded when a task matches
~759
With references · SKILL.md plus every file in references/, read only if the agent opens them
~1.1k

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). 285 words, ~759 tokens.

Download SKILL.mdSave it as .claude/skills/adk-unit-design/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
adk-unit-design
description
Writes an as-built architecture document for one ADK code unit — purpose, execution flow, data flow, cross-class dependencies, extension points, and the parts that must not change — to `docs/design/{topic}/{unit}/index.md`. It describes the code as implemented, not a proposed design, and its reader is a developer about to change or extend that unit. Use when asked to "write a design doc for {file}", "document the architecture of {class}", "document the extension points of {unit}", or after adding a core class, node type, or plugin base. Don't use for documentation aimed at developers who only call the unit from their own application — that is a usage guide with runnable examples under `docs/guides/` (use `adk-unit-guide`). Don't use to answer a framework-wide architecture question (use `adk-architecture`).

ADK code unit design

A unit design documents a code unit as implemented, the way a unit test exercises it as implemented. Nothing proposed or aspirational belongs in one. The reader is deciding what they may safely change, so answer "what breaks if I touch this?" — not "how do I call this?".

Inputs

Require the source file, or a class or method named inside it. Also read, when they exist: the base classes and interfaces the unit implements, its unit tests (the best evidence of intended behaviour), and example usage.

Analyse before writing

Answer each of these from the source. Anything the code does not show stays out of the document — do not infer a design intent from a name.

  • Purpose and intended use of the unit.
  • Execution flow, and the data that flows in and out.
  • Upstream dependencies, and which classes depend on this unit.
  • Extension surfaces: abstract methods, hooks, callbacks, configurable fields.
  • Constraints — what a subclass or caller must not change, and why.
  • Operational limitations.

Where the document goes

Mirror the source path under docs/design/, one directory per unit, document named index.md. Drop the leading underscore of a private module:

SourceDesign document
src/google/adk/workflow/_function_node.pydocs/design/workflow/function_node/index.md
src/google/adk/events/event.pydocs/design/events/event/index.md

If a document already exists at that path, update it in place and keep the existing wording wherever the code has not changed, so the diff shows only what the change actually altered.

docs/design/ does not exist in this repository yet — the first design document creates it. docs/guides/ is the established sibling tree; match its directory shape.

These documents render on GitHub, where a local filesystem path is dead. Rewrite {repo_root}/src/google/adk/{topic}/{unit}.py#L93 as https://github.com/google/adk-python/blob/main/src/google/adk/{topic}/{unit}.py#L93.

Structure

Follow references/design-template.md section by section.

© 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-unit-design of google/adk-python.

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

Open the folder on GitHubat commit 666c26d

Compare with similar skills

Adk Unit Design 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 Unit Design compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Adk Unit Design this skillgoogle/adk-python22k—~759Automated safety check: PassApache-2.0
Plan Previewu-ichi/reviewable-html-workbench2981 repos~1.8kAutomated safety check: PassMIT
Deep Divebyungjunjang/jangpm-meta-skills121—~2.5kAutomated safety check: PassNone
Complete SubtaskLog2n-io/Typhon250—~1.5kAutomated safety check: PassCustom licence
MCP Google Map Projectcablate/mcp-google-map466—~774Automated safety check: PassMIT
Comet Designrpamis/comet3.2k—~1.9kAutomated safety check: PassMIT

Similar skills

  • Plan Preview

    u-ichi/reviewable-html-workbench

    Plan Mode の <proposedplan を出す直前に、計画の段階・依存関係・検証観点を一時HTMLで視覚確認したい時に使う agent-internal skill。Use this agent-internal skill to create a temporary HTML preview for a plan just before presenting…

    298 GitHub starsUsed in 1 repo~1.8k tokens
    Agent WorkflowsAuto-check passed
  • Deep Dive

    byungjunjang/jangpm-meta-skills

    Socratic interview skill to deepen a spec or refine an existing agent blueprint.

    121 GitHub stars~2.5k tokensUpdated 2 mo ago
    Agent WorkflowsAuto-check passed
  • Complete Subtask

    Log2n-io/Typhon

    Complete a sub-issue of an umbrella issue - close it, check parent checkbox, update design doc

    250 GitHub stars~1.5k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • MCP Google Map Project

    cablate/mcp-google-map

    Project knowledge for developing and maintaining @cablate/mcp-google-map.

    466 GitHub stars~774 tokensUpdated 10 days ago
    Agent WorkflowsAuto-check passed
  • Comet Design

    rpamis/comet

    A skill your agent uses when full Comet change 已完成 open 阶段但缺少 Superpowers Design Doc,或 design 阶段需要从 OpenSpec 交接包恢复。

    3.2k GitHub stars~1.9k tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Memory

    686f6c61/alfred-dev

    This skill should be used when the user asks to record a design decision, search past project decisions, inspect the Alfred memory timeline, or work with the alfred-memory MCP server.

    117 GitHub stars~601 tokensUpdated 1 mo ago
    Agent WorkflowsAuto-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 Sample Creator

    google/adk-python

    Official

    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.

    22k GitHub stars~1.3k 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

Questions about Adk Unit Design

What does Adk Unit Design do?

Writes an as-built architecture document for one ADK code unit — purpose, execution flow, data flow, cross-class dependencies, extension points, and the parts that must not change — to…. Adk Unit Design is an agent skill from google/adk-python, published by the product's own GitHub organization.md.

When should I use Adk Unit Design?

Adk Unit Design fits situations like: asked to write a design doc for {file}; document the architecture of {class}; document the extension points of {unit}; after adding a core class.

How do I install Adk Unit Design in Claude Code?

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

How do I install Adk Unit Design in Codex?

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

Can I use Adk Unit Design 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-unit-design -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-unit-design, .gemini/skills/adk-unit-design, .github/skills/adk-unit-design and .opencode/skills/adk-unit-design in your project.

What does Adk Unit Design need to run?

SKILL.md names no scripts, command-line tools or credentials: Adk Unit Design is instructions for the agent only.

Does Adk Unit Design 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 Unit Design 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 Unit Design use?

Adk Unit Design 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 Unit Design use?

About 759 tokens (SKILL.md is roughly 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 329 tokens, read only when the agent opens those files.

What are the alternatives to Adk Unit Design?

Skills that share tags, products or a category with Adk Unit Design: Plan Preview (u-ichi/reviewable-html-workbench, 298 stars), Deep Dive (byungjunjang/jangpm-meta-skills, 121 stars), Complete Subtask (Log2n-io/Typhon, 250 stars) and MCP Google Map Project (cablate/mcp-google-map, 466 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Adk Unit Design?

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.