Explorar skills

Retrieve new cryptocurrency listings from the past 7 days and upcoming listings in the next 7 days across major exchanges. Trigger on requests about recently listed or soon-to-be-listed cryptocurrencies and verify current listings data before responding.

Deploy and configure Proxmox LXC containers for self-hosted services. Always trigger immediately when Mick asks to deploy, set up, or configure a new service on Proxmox, mentions spinning up a container, or needs a systemd service, Cloudflare Tunnel entry, or UniFi static IP assignment. Generate the full stack including the pct create command, container config, apt setup, systemd unit file, and Cl

Write or update content for Mick Pletcher's personal website. Trigger when Mick asks to write, rewrite, or update any section of his personal site including About, Projects, Skills, Blog integration, AI and homelab showcase, health and sports, contact copy, landing page sections, SEO descriptions, or project writeups. Tone is polished and professional, closer to LinkedIn than the blog, but still f

Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).

Testing and evaluation framework for LLM prompts and applications -- promptfooconfig.yaml, assertions, model-graded evals, red teaming, CI/CD integration, custom providers, and comparative evaluation

Design backends that survive redeploys, server reboots, and modest scaling. Covers stateless application servers, state placement (object storage, managed databases, Redis), immutable deploy artifacts, health checks, graceful shutdown, database migrations that don't lock the world, and the twelve-factor baseline. Invoke when designing a new backend, when uploads disappear after a redeploy, or when

Karpathy 风格 LLM Wiki / markdown knowledge base 工作流。用于 ingest、query、lint 持久化知识库；先做 orientation，再按 analysis -> generation 维护 wiki。

TRL: SFT, DPO, PPO, GRPO, reward modeling for LLM RLHF.

Use when managing the pynchy service on the server — deploying changes, observing logs, checking service status, restarting the service, setting up GitHub auth, rebuilding the agent container, or running any commands on pynchy-server via SSH. Also use when interacting with the LiteLLM proxy — investigating failed requests, model routing errors, spend tracking, health checks, API gateway diagnostic

Guide for llama.cpp, the C/C++ LLM inference framework by ggml-org. Covers the C API (llama.h), GGUF format, quantization (Q4_K_M, Q8_0, IQ4_XS), CMake builds, GPU backends (CUDA, Vulkan, Metal, ROCm), HTTP server with OpenAI-compatible API, embeddings, grammar constraints, function calling, LoRA, speculative decoding, multimodal, and UE5 integration. Use when: llama.cpp, GGUF models, local LLM in

Uma biblioteca de arquivos de direção de design de UI que fornecem diretrizes de estilo para a construção de interfaces elegantes e consistentes. Use ao construir qualquer UI — selecione um estilo ou deixe a IA recomendar um com base no contexto do projeto.

lm-eval-harness: benchmark LLMs (MMLU, GSM8K, etc.).