Skill UI

Guides Kubernetes operators through workload design, manifest generation, security hardening, networking, storage, GitOps, and multi-cluster operations while ensuring probes, resource limits, and least-privilege policies.

Guide to diagnose and fix LangChain authentication, import, rate limit, parsing, chain, agent, and memory failures, plus debugging tips and tracing resources for integrations.

Step-by-step guidance for benchmarking LangChain apps, enabling caching, batching, streaming, and prompt/model tuning to cut latency, boost throughput, and improve resource use when a pipeline feels slow.

Guides tuning Langfuse integrations for high-throughput apps, covering benchmarking, batching, non-blocking traces, payload trimming, and error handling to minimize latency and resource cost in production workloads.

Guides developers through diagnosing Lindy AI SDK incidents, covering authentication, rate limits, agent, and tool failures, plus checklists and resources for integration troubleshooting.

A comprehensive guide to production-grade patterns for Linkerd, a lightweight, security-first service mesh for Kubernetes. This resource covers essential concepts like automatic mTLS, advanced traffic routing (e.g., canary deployments, A/B testing), service resilience using retries/timeouts, and robust access control policies, enabling reliable microservices architecture deployment.

Provides production-ready bash templates for Linux admins to automate backups, monitor resources, manage users, and handle security tasks across servers and pen-testing setups.

llama.cpp is a pure C/C++ library designed for efficient LLM inference, optimized to run on resource-constrained environments. It excels in scenarios where high-end NVIDIA GPUs (CUDA) are unavailable, making it ideal for Apple Silicon Macs, AMD/Intel GPUs, or edge deployment devices like Raspberry Pi. It supports GGUF quantization formats, enabling significant memory reduction and speed improvements for local, cross-platform AI applications.

Defines MCP server tooling with file search, query execution, resource endpoints, prompt templates, and transport configurations alongside a client setup example for streamlined project automation.

This skill provides a comprehensive set of cross-language patterns and best practices for achieving memory-safe systems programming. It covers fundamental concepts such as RAII, ownership models, smart pointers, and robust resource management. Use this guide when writing low-level or systems code, managing critical resources (files, sockets, memory), or debugging complex memory issues to prevent use-after-free errors and memory leaks.

Automates GCP Memorystore configuration by guiding users through best-practice patterns, generating production-ready resources, and validating outputs whenever the skill detects memorystore config queries.

This skill provides comprehensive guidance on training Mixture of Experts (MoE) models, including architectures like Mixtral and DeepSeek-V3. It details techniques for achieving large-scale model capacity with significantly reduced computational costs (e.g., 5x reduction vs. dense models). Topics covered include top-k routing, load balancing, expert parallelism, and integration with frameworks like DeepSpeed and HuggingFace for efficient, resource-constrained training.