New to Claude Skills? Learn how to install them →

Testing skills

Free agent skills tagged testing, ready to install into any SKILL.md-compatible agent.

E

Eval-Driven Development

github

Automate evaluation for Python LLM applications.

Developer ToolsintermediatePython · Shell37.7k repo

Validate BSP Image

nvidia

Ensure your Jetson BSP image is correctly deployed and functional.

Developer ToolsintermediatePython · Shell2.8k repo

Mcore Testing

nvidia

Streamline testing for Megatron-LM systems.

Developer ToolsintermediatePython · Shell2.8k repo

Web Application Testing

anthropics

Automate and debug local web apps with Playwright.

Developer ToolsintermediatePython · Node · Shell167.6k repo

LangSmith Observability

davila7

Monitor and debug your LLM applications effectively.

Developer ToolsintermediatePython · Shell30.2k repo
P

Prowler MCP Testing

prowler-cloud

Streamlined testing for Prowler MCP Server components.

Developer ToolsintermediatePython · Shell14.6k repo

Mem0 Test Integration

mem0ai

Verify your Mem0 integrations with automated testing.

Developer ToolsintermediatePython · Node63k repo
B

Browser Harness

browser-use

Control browsers for automation, scraping, and testing tasks.

Developer ToolsintermediatePython · Shell16.6k repo

Audit Tests

jeremylongshore

Comprehensive diagnostic tool for test quality auditing.

Developer ToolsintermediatePython · Node · Shell2.6k repo
T

ToolUniverse Tool Creator

mims-harvard

Efficiently create scientific tools for the ToolUniverse framework.

Developer ToolsintermediatePython · Shell1.6k repo
T

ToolUniverse Self-Evolution

mims-harvard

Automate the development lifecycle for tool improvement.

Developer ToolsintermediatePython · Shell1.6k repo

Behavioral X-Ray

sickn33

Probe AI models for hidden behavioral patterns.

AI & AgentsintermediatePython · Shell44.7k repo

Promptfoo Evaluation

daymade

Efficiently evaluate LLM outputs with Promptfoo.

AI & AgentsintermediatePython · Node · Shell1.3k repo