generating-unit-tests
About
This skill automatically generates comprehensive unit tests from source code when developers request test creation. It supports multiple testing frameworks like Jest, pytest, and JUnit, intelligently detecting the appropriate one or using a specified framework. Use it when asking to "generate tests," "create unit tests," or using the "gut" shortcut with file paths.
Documentation
Overview
This skill empowers Claude to rapidly create robust unit tests, saving developers time and ensuring code quality. It analyzes source code, identifies key functionalities, and generates test cases covering various scenarios, including happy paths, edge cases, and error conditions.
How It Works
- Analyze Source Code: The skill analyzes the provided source code file to understand its functionality, inputs, and outputs.
- Determine Testing Framework: The skill either detects the appropriate testing framework based on the file type and project structure or uses the framework specified by the user.
- Generate Test Cases: The skill generates comprehensive test cases, including tests for valid inputs, invalid inputs, boundary conditions, and error scenarios.
- Create Mock Dependencies: The skill automatically creates mocks and stubs for external dependencies to isolate the code being tested.
- Output Test File: The skill outputs a new test file containing the generated test cases, imports, setup, and assertions.
When to Use This Skill
This skill activates when you need to:
- Create unit tests for a specific file or code snippet.
- Generate test cases for a function, class, or module.
- Quickly add test coverage to existing code.
- Ensure code quality and prevent regressions.
Examples
Example 1: Generating Tests for a JavaScript Utility Function
User request: "generate tests src/utils/validator.js"
The skill will:
- Analyze the
validator.jsfile to understand its functions and dependencies. - Detect that the file is JavaScript and default to Jest.
- Generate a
validator.test.jsfile with test cases covering various validation scenarios.
Example 2: Generating Tests for a Python API Endpoint using pytest
User request: "generate tests --framework pytest src/api/users.py"
The skill will:
- Analyze the
users.pyfile to understand its API endpoints and dependencies. - Use pytest as the testing framework, as specified by the user.
- Generate a
test_users.pyfile with test cases covering various API scenarios, including successful requests, error handling, and authentication.
Best Practices
- Framework Specification: Explicitly specify the testing framework when the default is not desired or ambiguous.
- File Granularity: Generate tests for individual files or modules to maintain focus and testability.
- Review and Refine: Always review and refine the generated tests to ensure they accurately reflect the desired behavior and coverage.
Integration
This skill can be used in conjunction with other code analysis and refactoring tools to improve code quality and maintainability. It also integrates with CI/CD pipelines to automatically run tests and prevent regressions.
Quick Install
/plugin add https://github.com/jeremylongshore/claude-code-plugins-plus/tree/main/unit-test-generatorCopy and paste this command in Claude Code to install this skill
GitHub 仓库
Related Skills
llamaguard
OtherLlamaGuard is Meta's 7-8B parameter model for moderating LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and can be deployed using vLLM, Hugging Face, or Amazon SageMaker. Use this skill to easily integrate content filtering and safety guardrails into your AI applications.
sglang
MetaSGLang is a high-performance LLM serving framework that specializes in fast, structured generation for JSON, regex, and agentic workflows using its RadixAttention prefix caching. It delivers significantly faster inference, especially for tasks with repeated prefixes, making it ideal for complex, structured outputs and multi-turn conversations. Choose SGLang over alternatives like vLLM when you need constrained decoding or are building applications with extensive prefix sharing.
evaluating-llms-harness
TestingThis Claude Skill runs the lm-evaluation-harness to benchmark LLMs across 60+ standardized academic tasks like MMLU and GSM8K. It's designed for developers to compare model quality, track training progress, or report academic results. The tool supports various backends including HuggingFace and vLLM models.
langchain
MetaLangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.
