767 skills · sorted by relevance
Configures, optimizes, and troubleshoots GKE ComputeClasses. Use when configuring Spot VMs with on-demand fallback, targeting specific accelerators (GPUs/TPUs) or machine families, restricting ComputeClass access, or debugging pending pods related to node pool auto-creation. Do not use for cluster-level Node Auto Provisioning configuration or general GKE cluster creation.
The English summary is being prepared. Showing the original description.
Optimizes GKE costs, rightsizes workloads, and configures Spot VMs, CUDs, cost allocation, and resource quotas. Use when optimizing GKE cluster or workload costs, configuring GKE cost allocation or quotas, rightsizing CPU/memory requests, or selecting Spot VMs and machine types. Don't use for general compute class provisioning or GPU Selection (use gke-compute-classes instead).
The English summary is being prepared. Showing the original description.
Plans and executes GKE cluster creation, provisioning, and production readiness audits using pre-defined templates (Autopilot, Standard Regional, GPU/AI Inference, AI Hypercompute). Use when creating GKE clusters, provisioning GKE environments, selecting cluster modes, or auditing GKE clusters. Don't use for application onboarding or deployment configuration (use gke-app-onboarding instead).
The English summary is being prepared. Showing the original description.
Access ENCODE uniform analysis pipelines, generate user-specific Nextflow/WDL pipelines, manage compute resources, and integrate with cloud platforms. Use when the user wants to understand ENCODE pipelines, run pipelines on their own data, generate custom Nextflow workflows from ENCODE pipeline code, check compute requirements (CPU/GPU/memory), run pipelines in background, or integrate with Google Cloud, AWS, or other cloud platforms. Also use when the user asks about ENCODE pipeline outputs, processing standards, software versions, or wants to replicate ENCODE processing. Covers local execution, HPC, and cloud deployment with resource-aware scheduling. Use this skill for ANY pipeline execution, workflow generation, or compute resource management task involving ENCODE data.
The English summary is being prepared. Showing the original description.
Set up and run local LLMs with Harbor. Use when the user wants to run models locally, install Harbor, start Open WebUI, llama.cpp, Ollama, vLLM, Docker Model Runner, MLX, or oMLX, pull GGUF or HuggingFace models, add SearXNG web search, Speaches TTS/STT, or Open Terminal code execution, launch Codex/Claude/Grok/OpenCode against a Harbor backend, or troubleshoot GPU, VRAM, and service startup.
The English summary is being prepared. Showing the original description.
Web browser game development principles. Framework selection, WebGPU, optimization, PWA.
The English summary is being prepared. Showing the original description.
Work with Runpod GPU infrastructure and documentation. Use when Codex needs to create, deploy, manage, debug, or review Runpod Pods, Serverless workers/endpoints, templates, network volumes, Public Endpoints, Flash apps, runpodctl commands, Runpod Python SDK usage, REST/GraphQL API usage, Runpod MCP setup, Docker images for Runpod, endpoint request payloads, logs, billing/cost checks, or Runpod deployment troubleshooting.
The English summary is being prepared. Showing the original description.
Iterate on a GenAI notebook against the self-hosted stack via the genai-stack CLI (config dirs, auth, subdomains, quantization, GPU/VRAM). Arguments: <notebook|service> [--service comfyui|forge|vllm] [--quant int4|fp8] [--validate] [--bg]
The English summary is being prepared. Showing the original description.
Validate the GenAI stack (services, authentication, models, notebooks, GPU). Arguments: [all|services|auth|models|notebooks|vram] [--full] [--auth-only] [--nodes-only] [--notebooks]
The English summary is being prepared. Showing the original description.
Train an ML model in the QuantConnect ML-Training-Pipeline with thermal-safe GPU usage and rigorous validation. Arguments: <architecture|script> [--dry-run] [--seeds 0,1,7,42,99] [--folds 5] [--bg]
The English summary is being prepared. Showing the original description.
Advanced CV for infrastructure inspection including forest fire detection, wildfire precondition assessment, roof inspection, hail damage analysis, thermal imaging, and 3D Gaussian Splatting reconstruction. Expert in multi-modal detection, insurance risk modeling, and reinsurance data pipelines. Activate on "fire detection", "wildfire risk", "roof inspection", "hail damage", "thermal analysis", "Gaussian Splatting", "3DGS", "insurance inspection", "defensible space", "property assessment", "catastrophe modeling", "NDVI", "fuel load". NOT for general drone flight control, SLAM, path planning, or sensor fusion (use drone-cv-expert), GPU shader development (use metal-shader-expert), or generic object detection without inspection context (use clip-aware-embeddings).
The English summary is being prepared. Showing the original description.
Expert in drone systems, computer vision, and autonomous navigation. Specializes in flight control, SLAM, object detection, sensor fusion, and path planning. Activate on "drone", "UAV", "SLAM", "visual odometry", "PID control", "MAVLink", "Pixhawk", "path planning", "A*", "RRT", "EKF", "sensor fusion", "optical flow", "ByteTrack". NOT for domain-specific inspection tasks like fire detection, roof damage assessment, or thermal analysis (use drone-inspection-specialist), GPU shader optimization (use metal-shader-expert), or general image classification without drone context (use clip-aware-embeddings).
The English summary is being prepared. Showing the original description.
Expert in script-to-video production pipelines for Apple Silicon Macs. Specializes in hybrid local/cloud workflows, LoRA training for character consistency, motion graphics generation, and artist commissioning. Activate on 'AI video production', 'script to video', 'video generation pipeline', 'character consistency', 'LoRA training', 'cloud GPU', 'motion graphics', 'Wan I2V', 'InVideo alternative'. NOT for real-time video editing, video compositing (use DaVinci/Premiere), audio production, or 3D modeling (use Blender/Maya).
The English summary is being prepared. Showing the original description.
Safely auto-detect the current machine's hardware (GPU, VRAM, system RAM, OS) with read-only commands, then recommend the top 3 local AI models to run — most powerful that fits, best for coding, and best small-and-fast — each with download links. Use when someone asks "what AI models can my computer run" or "what's the best local model for my rig".
The English summary is being prepared. Showing the original description.
Add p-value brackets, significance asterisks, and effect-size annotations to distribution plots using ggpubr, ggsignif, and statannotations with correct test selection (parametric vs non-parametric vs paired), multiple-testing adjustment, and rendering of negative results. Use when a boxplot/violin/raincloud needs in-figure statistical comparisons between groups.
The English summary is being prepared. Showing the original description.
Own the lifecycle of short-lived paid CPU/GPU hosts and attached resources, from bounded provisioning through verified permanent deletion. Use when renting, extending, retiring, or recovering billable remote resources; campaign scheduling belongs to run-ephemeral-hosts.
The English summary is being prepared. Showing the original description.
Up-to-date Zig programming language patterns for version 0.17.0-dev (0.16.0 stable APIs plus the 0.17 deltas). Use when writing, reviewing, or debugging Zig code, working with build.zig and build.zig.zon files, or using comptime metaprogramming. Critical for avoiding outdated patterns from training data - especially std.net→std.Io.net (requires Io instance), std.time timestamps removed (use clock_gettime), std.Thread.Mutex/Condition/sleep removed (use pthreads), std.crypto.random removed, build system APIs (root_module, Compile methods→Module methods), I/O APIs (buffered writer pattern), container initialization (.empty/.init), allocator selection (DebugAllocator), ArrayList now unmanaged by default, @typeInfo lowercase fields (.@"struct" not .Struct), and removed language features (async/await, usingnamespace). Also covers 0.17.0-dev deltas: b.args→run_cmd.addPassthruArgs(), std.gpu→std.spirv, @bitCast logical-bit (endian-agnostic) semantics, build configurer/maker split, and the zig-pkg/ package directory. Also covers quality tooling Zig does not ship: coverage with kcov (and why in-file tests wreck the denominator), detecting unused private functions (neither the compiler nor zlint's unused-decls finds them), duplicate detection with jscpd, zlint (NOT the same-named X.509 linter in Homebrew), and the built-in fuzzer whose testOne now takes *std.testing.Smith rather than []const u8.
The English summary is being prepared. Showing the original description.
Expert-level computer graphics covering the rendering pipeline, rasterization, ray tracing, shaders, transformations, lighting models, and GPU programming.
The English summary is being prepared. Showing the original description.
Framework de segurança em runtime da NVIDIA para aplicações LLM. Com detecção de jailbreak, validação de entrada/saída, verificação de fatos, detecção de alucinações, filtragem de PII, detecção de toxicidade. Usa DSL Colang 2.0 para rails programáveis. Pronto para produção, executa em GPU T4.
The English summary is being prepared. Showing the original description.
Framework RLHF de alta performance com aceleração Ray+vLLM. Use para treinamento PPO, GRPO, RLOO, DPO de modelos grandes (7B-70B+). Construído em Ray, vLLM, ZeRO-3. 2× mais rápido que DeepSpeedChat com arquitetura distribuída e compartilhamento de recursos GPU.
The English summary is being prepared. Showing the original description.
Otimiza atenção em transformers com Flash Attention para ganho de 2-4x em velocidade e redução de 10-20x em memória. Use ao treinar/executar transformers com sequências longas (>512 tokens), ao encontrar problemas de memória GPU com atenção, ou quando precisa de inferência mais rápida. Suporta SDPA nativo do PyTorch, biblioteca flash-attn, H100 FP8 e sliding window attention.
The English summary is being prepared. Showing the original description.
Fornece orientação para interpretar e manipular internals de redes neurais usando nnsight com execução remota NDIF opcional. Use quando precisar executar experimentos de interpretabilidade em modelos massivos (70B+) sem recursos locais de GPU, ou ao trabalhar com qualquer arquitetura PyTorch.
The English summary is being prepared. Showing the original description.
Geração estruturada rápida e serving para LLMs com RadixAttention para cache de prefixos. Use para saídas JSON/regex, decodificação restrita, workflows com agentes que fazem chamadas de ferramentas, ou quando você precisa de 5× mais rápido que vLLM com compartilhamento de prefixos. Alimenta 300.000+ GPUs na xAI, AMD, NVIDIA e LinkedIn.
The English summary is being prepared. Showing the original description.
Implementação educacional do GPT em ~300 linhas. Reproduz o GPT-2 (124M) em OpenWebText. Código limpo e hackeável para aprender transformers. Por Andrej Karpathy. Perfeito para entender a arquitetura do GPT do zero. Treine em Shakespeare (CPU) ou OpenWebText (multi-GPU).
The English summary is being prepared. Showing the original description.