Curated skills for evaluation, observability, and protection — installed in one command, compatible with any agent.
Add Galileo observability and tracing to my Python agent workflow. observability
Evaluate this RAG pipeline with guardrail metrics and score regressions. evaluation
Instrument my TypeScript workflow with Galileo observe and evaluate steps. typescript
Add guardrails and content filtering stages to my production agent. protection
Run experiments, score regressions, and test RAG pipelines against ground truth with built-in metrics and scorers.
Trace workflows end-to-end, log structured spans, and monitor production agents with deep observability.
Add guardrails, content filtering, and safety stages to catch issues before they ever reach your users.
Run npx skills add gyanesh-m/skills in your project. Skills are copied into your agent's skill directory.
When your agent works on a relevant task, it reads the skill reference for API patterns, best practices, and integration details.
Your agent writes instrumented, evaluated, and protected code from the start — no copy-pasting from docs.