Pinned Loading

1. llm-evaluations llm-evaluations Public

   Multi-metric LLM evaluation across providers Ollama, OpenAI, Groq: macro/micro/per-label F1, exact match, LLM-as-a-judge. Benchmarked on a public HuggingFace ABSA dataset.

   Python 1

2. k6-quickpizza-demo k6-quickpizza-demo Public

   k6 load test with staged and constant profiles, SLO thresholds on failure rate, p95 latency, contract checks on API responses.

   JavaScript 2 1

3. playwright-e2e-guidelines playwright-e2e-guidelines Public

   Team Playwright conventions encoded as token-efficient AI instructions applied at code generation and review.

   1