orchestrating-test-workflows
About
This skill enables Claude to orchestrate complex test workflows using a dedicated plugin. It allows defining test execution graphs with dependencies, running tests in parallel, and intelligently selecting tests based on code changes. Use it for managing test orchestration, dependency management, parallel execution, and smart test selection in CI/CD pipelines.
Documentation
Overview
This skill empowers Claude to manage and execute complex test suites efficiently. It leverages the test-orchestrator plugin to handle test dependencies, parallel execution, and intelligent test selection, resulting in faster and more reliable testing processes.
How It Works
- Workflow Definition: Claude uses the plugin to define the test workflow, specifying dependencies between tests.
- Parallelization: The plugin identifies independent tests and executes them in parallel to reduce overall execution time.
- Smart Selection: Based on code changes, the plugin selects only the affected tests to run, minimizing unnecessary execution.
When to Use This Skill
This skill activates when you need to:
- Optimize test execution time.
- Manage dependencies between tests.
- Run only relevant tests after code changes.
Examples
Example 1: Optimizing Regression Testing
User request: "Orchestrate the regression tests for the user authentication module after the recent code changes."
The skill will:
- Use the test-orchestrator plugin to identify the tests affected by the changes in the user authentication module.
- Execute those tests in parallel, respecting any dependencies.
Example 2: Setting up a CI/CD Pipeline
User request: "Set up a test workflow for the CI/CD pipeline that runs unit tests, integration tests, and end-to-end tests with appropriate dependencies."
The skill will:
- Define a test workflow using the test-orchestrator plugin, specifying the order and dependencies between the different test suites (unit, integration, end-to-end).
- Configure the pipeline to trigger the orchestrated test execution upon code commits.
Best Practices
- Dependency Mapping: Clearly define dependencies between tests to ensure correct execution order.
- Granularity: Break down large test suites into smaller, more manageable units for better parallelization.
- Change Tracking: Integrate the test-orchestrator with version control to accurately identify affected tests.
Integration
This skill integrates with the test-orchestrator plugin and can be incorporated into CI/CD pipelines. It can also be used in conjunction with other code analysis tools to further refine test selection.
Quick Install
/plugin add https://github.com/jeremylongshore/claude-code-plugins-plus/tree/main/test-orchestratorCopy and paste this command in Claude Code to install this skill
GitHub 仓库
Related Skills
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.
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.
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.
