DevOps and Cloud

This skill defines prompt-based rules only . No setup scripts. Use it to configure and remind the agent (e.g. OpenClaw/Claw) how to work with CloudBase.

High-performance serving framework for LLMs and VLMs with RadixAttention for automatic prefix caching.

Comprehensive guide to running ML workloads across clouds with automatic cost optimization using SkyPilot.

Generate professional clinical decision support (CDS) documents for pharmaceutical companies, clinical researchers, and medical decision-makers. This skill specializes in analytical, evidence-based documents that inform treatment strategies and drug development:

Source details, install context, and public review data are available on the full page.

File Organization : This skill uses split structure. See references/ for advanced patterns and security examples.

Source details, install context, and public review data are available on the full page.

Systematic improvement of existing agents through performance analysis, prompt engineering, and continuous iteration.

Remotion renderer that converts JSON timeline specs into video compositions.

Design offline-first mobile applications that provide seamless user experience regardless of connectivity.

This skill covers using LM Studio as the embedding provider for GrepAI, offering a user-friendly GUI for managing local models.

This skill covers using PostgreSQL with the pgvector extension as the storage backend for GrepAI.

Pre-built shadcn/ui component definitions and implementations for json-render. Provides 36 components built on Radix UI + Tailwind CSS.

Implement robust database migration systems with version control, rollback capabilities, and data transformation strategies. Includes migration frameworks and production deployment patterns.

Safe migrations for frameworks, languages, and infrastructure.

Comprehensive guide for building modern full-stack web applications using Next.js, Turborepo, and RemixIcon.

AWS development with infrastructure automation and cloud architecture patterns

Source details, install context, and public review data are available on the full page.

Comprehensive guide to running ML workloads on Lambda Labs GPU cloud with on-demand instances and 1-Click Clusters.

NeMo Guardrails adds programmable safety rails to LLM applications at runtime.

bitsandbytes reduces LLM memory by 50% (8-bit) or 75% (4-bit) with <1% accuracy loss.

When implementing SDK features or debugging provider-specific issues, check reference implementations.

Load with: base.md + [typescript.md | python.md]

LitGPT provides 20+ pretrained LLM implementations with clean, readable code and production-ready training workflows.