Skill UI

Automates generating TorchServe deployment configurations with guided best practices for model serving, MLOps pipelines, inference, and production monitoring so ML deployment workflows stay consistent and reliable.

Automates Triton inference config guidance for ML deployment, covering serving, MLOps pipelines, monitoring, and production-ready configurations aligned with best practices.

Assesses Vertex AI Agent Engine deployments for production readiness by evaluating security, monitoring, performance, compliance, and best practices before go-live and recommending fixes with weighted scores.

Guides using verl (Volcano Engine RL) to train large LLMs via PPO, GRPO, and related algorithms, covering backend swapping, rollout setup, reward design, and production-scale orchestration and monitoring.

Automates Vertex AI deployment tasks, offering step-by-step guidance, production-ready code, and validation for model serving, MLOps pipelines, monitoring, and optimization when you mention Vertex AI Deployer.

Curates Claude Code’s auto-memory by reviewing MEMORY.md, promoting reliable patterns into CLAUDE.md or scoped rules, extracting repeat solutions into skills, and monitoring memory health so teams can operationalize lessons learned and keep Claude’s knowledge base tidy.