Kosmos E2E Testing Skill

Automate end-to-end testing for the Kosmos AI scientist project.

Updated Aug 23, 2026

Search Tags:#automation #testing #e2e #llm #docker #kosmos

Ready to run

npx skills add https://github.com/Zehong-Wang/Kosmos --skill kosmos-e2e-testing-skill-zehong-wang

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: Kosmos E2E Testing Skill
Source: https://github.com/Zehong-Wang/Kosmos/tree/main/.claude/skills/kosmos-e2e-testing
Command: npx skills add https://github.com/Zehong-Wang/Kosmos --skill kosmos-e2e-testing-skill-zehong-wang

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) and examples (resource) and lib (resource) components.

What problem does it solve?

This Skill automates the comprehensive end-to-end testing of the Kosmos autonomous AI scientist project, ensuring its reliability and functionality across various environments and configurations.

Core Features & Use Cases

Multi-Provider Support: Tests can be run using local models (Ollama), external APIs (Anthropic, OpenAI), or mock services.
Environment Validation: Checks for the availability and proper setup of dependencies like Docker, Ollama, and API keys.
Tiered Testing: Supports different test suites from quick sanity checks to full E2E validation.
Use Case: Before deploying a new version of Kosmos, run the full E2E test suite with the anthropic provider to ensure all components integrate correctly and meet production standards.

Quick Start

Run the sanity tests using the auto-detected provider.

Frequently Asked Questions about Kosmos E2E Testing Skill

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate end-to-end testing for an autonomous AI scientist project?▼

End-to-end testing for an autonomous AI scientist project is automated by validating core research workflows, gap implementations, and provider configurations through a tiered testing approach using pytest. This ensures component reliability and functional integration across different environments.

Can I run E2E tests using local LLM providers like Ollama?▼

Yes, E2E tests support local LLM providers like Ollama, external APIs such as Anthropic and OpenAI, or mock services. The testing framework auto-detects configured providers to validate research workflows across your chosen environment.

Do I need Docker to validate research workflows with E2E testing?▼

Docker is required for full E2E testing functionality to enable database integrations and sandboxing. The environment validation feature checks for the availability and proper setup of Docker, Ollama, and API keys before running tests.

What is a tiered testing approach for LLM applications?▼

A tiered testing approach for LLM applications supports different test suites ranging from quick sanity checks to full E2E validation. This allows you to run fast sanity tests using auto-detected providers or comprehensive checks before deployment.

How do I validate environment dependencies before running E2E tests?▼

Environment validation checks for the availability and proper setup of dependencies like Docker, Ollama, and API keys before executing tests. This ensures your local and external LLM provider configurations are correctly established for accurate E2E testing.

What are the limitations of automated E2E testing with mock LLM services?▼

Using mock services for E2E testing validates workflow integration without actual LLM generation, limiting the verification of provider-specific configurations and research quality. Full functionality requires pytest, Docker, and configured LLM access.