Loading...
Loading...
Found 1,617 Skills
Master fine-tuning of large language models for specific domains and tasks. Covers data preparation, training techniques, optimization strategies, and evaluation methods. Use when adapting models for specialized applications, reducing inference costs, or improving domain-specific performance.
Implement real-time streaming UI patterns for AI chat applications. Use when adding response lifecycle handlers, progress indicators, client effects, or thread state synchronization. Covers onResponseStart/End, onEffect, ProgressUpdateEvent, and client tools. NOT when building basic chat without real-time feedback.
Persona + messaging framework for K-12, higher-ed, and workforce enrollment campaigns.
Use when "LLM inference", "serving LLM", "vLLM", "llama.cpp", "GGUF", "text generation", "model serving", "inference optimization", "KV cache", "continuous batching", "speculative decoding", "local LLM", "CPU inference"
Use when "training LLM", "finetuning", "RLHF", "distributed training", "DeepSpeed", "Accelerate", "PyTorch Lightning", "Ray Train", "TRL", "Unsloth", "LoRA training", "flash attention", "gradient checkpointing"
Build LLM applications using Dify's visual workflow platform. Use when creating AI chatbots, implementing RAG pipelines, developing agents with tools, managing knowledge bases, deploying LLM apps, or building workflows with drag-and-drop. Supports hundreds of LLMs, Docker/Kubernetes deployment.
Use Claude Code's full tool system with any OpenAI-compatible LLM — GPT-4o, DeepSeek, Gemini, Ollama, and 200+ models via environment variable configuration.
Best practices for contributing code to TensorRT-LLM. Covers the official contribution process (issue tracking, fork workflow, DCO signing), coding guidelines, implementation workflow, common mistakes, testing strategy, commit hygiene, and review readiness. Incorporates rules from CONTRIBUTING.md and CODING_GUIDELINES.md plus lessons distilled from real PR retrospectives. Use when implementing new features, optimizations, or bug fixes in the TensorRT-LLM codebase.
Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.
Crafting effective prompts for LLMs. Use when designing prompts, improving output quality, structuring complex instructions, or debugging poor model responses.
Genera documentación llms.txt optimizada para LLMs. Usa cuando el usuario diga "crear llms.txt", "documentar para AI", "crear documentación para LLMs", "generar docs para modelos", o quiera hacer el repo legible para Claude/AI.
Scaffolds a personal LLM Wiki from scratch — the Karpathy pattern of incrementally building a persistent, interlinked markdown knowledge base maintained by LLMs. Generates directory structure, schema file, index, log, and workflow conventions. Use when user says "create wiki", "new wiki", "bootstrap wiki", "llm wiki", "knowledge base", "start a wiki", "build a wiki", or wants to set up a structured markdown knowledge base for any domain.