Loading...
Loading...
Found 440 Skills
Evaluates future GPU and TPU reservation feasibility and calendar-mode booking options in Google Compute Engine (GCE). Use when planning future AI/ML training runs, checking reservation availability windows, verifying accelerator cluster topologies, or assessing future capacity lead times. Don't use for active on-demand reservations (use compute-on-demand-reservations), immediate Spot capacity queries (use compute-spot-capacity-advice), or Standard Future Reservations (--reservation-mode=DEFAULT).
Use when an Unreal Engine 5.8 project misses its frame rate or stutters: "optimize to 60 fps", "we run at 38 fps", CPU or GPU bound, game or render thread too long, hitches, traversal or shader stutter (PSO), GC spikes, camera-cut spikes, Lumen, Nanite, VSM, ray tracing, foliage, crowds or Niagara too expensive, async compute, stat unit, ProfileGPU, Unreal Insights, TraceQuery, snapshothitches, scalability and device profiles, dynamic resolution and TSR, streaming budgets, or proving a fix with before and after captures.
Create, verify by read-back, and manage the lifecycle of Runpod's reusable plumbing (templates, network and global volumes, container registry credentials, account secrets, the account's SSH public keys, and Instant Clusters), the account's audit trail and organization members (reads), plus staging large model files on a volume and diagnosing a private-image pull failure. Use when the user wants one of those resources created, changed, inspected or removed through the Runpod MCP tools, or asks where a volume should live so a GPU can mount it. Also use for an account cleanup request: only what this conversation created may be removed; everything else is reported for the user to decide.
Databricks AI Runtime, the `databricks air` CLI commands for submitting and managing GPU training workloads on Databricks serverless compute. Use for: writing and submitting `databricks air` workload YAML, choosing an accelerator type and Python environment, passing hyperparameters and secrets, configuring retries, checking run status, listing/cancelling runs, streaming a run's logs and watching its progress, debugging failed runs, GPU pools, multi-container workloads, custom Docker image setup, and converting a workload to a Databricks Asset Bundle.
This skill should be used when the user asks about "electrobun WebGPU", "GpuWindow", "WGPUView", "WGSL shaders", "KEEPALIVE pattern", "electrobun GPU", render loops in electrobun, FFI pointer management, or GPU buffer serialization.
Provision a Runpod Pod for interactive, development or training use and tell the user exactly how to connect to it. Reads stock before creating, picks the image and GPU class from the catalog reads, exposes only the ports the workload needs, hands back the working proxy URL or SSH address, and for training co-locates a network volume so checkpoints outlive the Pod. Also covers creating a Pod and stopping it immediately, so that only its disk bills until the user comes back. Use when the user wants a GPU or CPU machine of their own (a web app, Jupyter, SSH, a training box) rather than a Serverless endpoint, through the Runpod MCP tools.
Bring any source (a HuggingFace repo, a ComfyUI workflow, a Hub release, a custom container image, a GGUF repo, a Civitai asset, or a community template) to a proven Runpod Serverless endpoint: pick the engine for the modality and model format, size the GPU from the model's real metadata, provision, warm, prove it with one real job, and hand back the URL with what it bills. Deploys an existing source through the Runpod MCP tools; code-first Python deploys (the Flash dev loop) are out of scope. Use when the user wants a model or worker served on Runpod Serverless, whatever the modality: text generation, speech-to-text or text-to-speech, image or video generation, embeddings, document processing, or their own handler image.
Understand WebGL rendering architecture, GPU resources, textures, buffers, shaders, and performance constraints for interactive graphics.
Move a workload from another cloud or GPU platform to Runpod: Vast.ai, Lambda, CoreWeave, Paperspace, Modal, Replicate, Baseten, Together AI, Fireworks AI, fal, Hugging Face Inference Endpoints, AWS, Google Cloud or Azure. Inventories what the project uses, maps it to Runpod, plans, then migrates one workload at a time with verification. To move Runpod code between Runpod API versions, use runpod-migrate instead.
Diagnoses, mitigates, and prevents Google Compute Engine resource availability and capacity stockout errors (ZONE_RESOURCE_POOL_EXHAUSTED, ZONE_RESOURCE_POOL_EXHAUSTED_WITH_DETAILS, and machine type or accelerator unavailable in zone). Use ONLY when VM creation, Managed Instance Group (MIG) scale-out, or stopped instance startup fails due to regional or zonal hardware capacity exhaustion for GPUs, TPUs, or specific CPU shapes. DO NOT read or use for IAM permission errors, project quota limit increases without stockouts, general greenfield VM creation, or unexpected host reboots on already-running VMs.
Debug TensorFlow and Keras issues systematically. This skill helps diagnose and resolve machine learning problems including tensor shape mismatches, GPU/CUDA detection failures, out-of-memory errors, NaN/Inf values in loss functions, vanishing/exploding gradients, SavedModel loading errors, and data pipeline bottlenecks. Provides tf.debugging assertions, TensorBoard profiling, eager execution debugging, and version compatibility guidance.
Render framefields projects on framefields cloud GPUs (api.framefields.dev) or a self-hosted render worker. Use when running `framefields render --cloud`, calling `renderCloud` from `framefields/cloud`, planning cost and workers, splitting a long film across several GPUs, starting renders from the framefields dashboard, getting a project render-ready (push, lockfile, pinned assets, private repos), or fixing a cloud render error code such as ASSET_NOT_FOUND or LOCKFILE_MISSING.