Creates detailed code unit guides for source code documentation.
npx skills add https://github.com/google/adk-python --skill adk-unit-guide
This skill creates a detailed developer guide for new or updated code file or direct code input. The guide it generates is meant to explain the code to a developer who wants to use it in an application, but with a higher level of technical detail than what would appear in published developer documentation. Similar to a *unit test*, a *unit guide* provides generated, granular-level documentation for a unit of code, without worrying about bloating the actual developer documentation with too many details.
/docs/guides/*** directory of this repository./docs/guides/*** directory of this repository, using the relative path of the code unit. For example, if the code unit is called /topic/function/class.ext, create a guide in the location /docs/guides/topic/function/class/index.md./docs/guides/README.md. Ensure the guide is listed under the correct category with a link and a brief summary.Use the following structure and instructions to create the guide for the code unit:
# Title: name of the code file or code unit
- 2-sentence summary of the code unit
## Introduction
- Paragraph(s) explaining:
- The purpose and application of the code unit
- Key classes that depend on this code unit
- Developer problems solved by this code unit
## Get started
- Present a single, minimum implementation of the code unit to demonstrate its use.
- Show enough of the containing classes to make it clear where the code could be used.
- Use unit test code as a starting point for the code example, if available.
- When writing a sample agent, do not set the `model` attribute.
- For workflow node samples, prefer using a simple Python function rather than extending `BaseNode` to demonstrate the node's logic, unless class extension is explicitly required for the use case.
- When wrapping Python functions as workflow nodes, prefer using the `@node` decorator instead of `FunctionNode` directly, whenever possible.
## How it works
- Explain how the code unit accomplishes its purpose or solves a problem.
- Mention key code classes that depend on this code unit.
- Mention code classes that this code unit depends on.
- Explain any cross-class dependencies of the code unit.
## Configuration options
- If the code unit has configuration options (e.g., settings, configuration objects), document them in a table detailing parameters, types, default values, and descriptions.
- **Do NOT** list options inherited from base classes. Focus only on options introduced by the code unit itself.
- Dive into each option to provide detailed description and usage patterns, rather than just repeating the type and a brief description.
- **Do NOT** list references of all attributes or methods of the classes. Exhaustive API references belong in auto-generated reference documentation, not in guides. Guides should focus on how to use the code unit.
## Advanced applications
- Determine if there are advanced use cases for the code unit.
- Add advanced applications of the code unit, including:
- Problem solved
- Implementations for special circumstances
## Limitations
- Mention any limitations of the code unit, if known.
## Related samples
- Link to relevant samples in the `contributing/` directory that demonstrate the use of this code unit.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Automatically creates user-facing changelogs from git commits by analyzing commit history, categorizing changes, and transforming technical commits into clear, customer-friendly release notes. Turns hours of manual changelog writing into minutes of automated generation.
Use when implementation is complete, all tests pass, and you need to decide how to integrate the work - guides completion of development work by presenting structured options for merge, PR, or cleanup
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
React Native and Expo best practices for building performant mobile apps. Use when building React Native components, optimizing list performance, implementing animations, or working with native modules. Triggers on tasks involving React Native, Expo, mobile performance, or native platform APIs.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Next.js best practices - file conventions, RSC boundaries, data patterns, async APIs, metadata, error handling, route handlers, image/font optimization, bundling
Use when starting feature work that needs isolation from current workspace or before executing implementation plans - creates isolated git worktrees with smart directory selection and safety verification
Take google/adk-unit-guide from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.