Eval Recipes Runner
Run standardized evaluation recipes against LLM prompts, agents, and tool chains to catch regressions, compare model versions, and gate releases with repeatable quality checks.
npx skills add https://github.com/rysweet/amplihack --skill eval-recipes-runner| Installs | 119 |
|---|---|
| Repository | rysweet/amplihack ↗ |
Related skills
Agent BrowserDrive the agent-browser CLI to open local or remote pages, click, fill forms, screenshot, and sanity-check dev servers after npm run dev.404k187
TddRun a red-green-refactor loop while building features or fixing bugs so tests describe behavior through public APIs instead of brittle implementation checks.260k121k
Use My BrowserUse the user live browser session for logged-in flows, DevTools context, and rendered DOM inspection.219k61
Test Driven DevelopmentMake your coding agent follow strict test-first red-green-refactor before any feature, bugfix, or refactor production code.132k221kVerification Before CompletionInstall this when you want your coding agent to prove tests, lint, and builds actually pass before it says a task is done or opens a PR.113k221k
Webapp TestingVerify local web apps with Python Playwright—UI behavior, screenshots, and browser logs—with optional managed dev-server startup.98.2k148k