Build a regression + eval harness for AI-written code and AI features. Generates characterization tests that lock current behavior before a refactor, scaffolds a Promptfoo eval suite for chatbots/RAG/classifiers, and wires it into the ship-gate. Use when the user wants evals, regression tests for AI code, to stop AI features drifting, or to test an LLM feature.
$npx -y skills add houseofmvps/ultraship --skill evalsInstalls into the current project.
Run `npx skills use "https://github.com/houseofmvps/ultraship" --skill "houseofmvps/ultraship/evals"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/houseofmvps/ultraship" that are relevant to the current task. Run `npx skills add "https://github.com/houseofmvps/ultraship"` and select the relevant skills, then follow their instructions.