663 skills · sorted by relevance
Run model training, fine-tuning, inference, and batch jobs on Modal’s cloud GPUs. Estimate hardware needs and cost, generate Python launch scripts, run or deploy workloads, monitor logs, and retrieve results without managing remote servers.
Build Python workloads on Modal for cloud execution, including GPU model training and inference, web APIs, scheduled jobs, and parallel batch processing. Configure container environments, persistent storage, and automatic scaling through the Modal SDK.
Run machine learning workloads on Modal's cloud GPUs without managing servers. Guides Python configuration for training, inference, batch processing, and API deployment, including automatic scaling, persistent storage, scheduled jobs, and troubleshooting.
Launch machine learning experiments on local GPUs, remote servers, Vast.ai, or Modal. It checks the configured environment, deploys code, saves logs, and verifies startup, with optional W&B metric logging and automatic Vast.ai result collection and instance cleanup.
Run machine learning workloads on Modal's cloud GPUs without managing servers. Guides Python configuration for training, inference, batch processing, and API deployment, including automatic scaling, persistent storage, scheduled jobs, and troubleshooting.
Review modal dialogs for keyboard and screen reader accessibility. The skill checks dialog roles, title labels, focus movement within the modal, Escape dismissal, and focus returning to the opening control, then identifies issues and ways to verify fixes.
Launch machine learning training jobs on local or remote GPUs. The skill checks available GPU memory, synchronizes code, saves logs, and verifies startup, with optional experiment tracking and support for Vast.ai and Modal.
Run machine learning training and predictions on cloud GPUs, then publish models as APIs that other applications can call. The skill guides Python-based setup, automatic scaling, persistent storage, parallel processing, and scheduled jobs.
Draft or revise technical documentation in a direct, friendly style based on Modal's documentation. Lead with the concept or benefit, place a runnable example near the top, and reduce jargon and vague promotional wording.
Add animations to React and Next.js interfaces, including buttons, modals, notifications, page transitions, and scrolling content. Uses shared motion settings and reusable patterns for elements entering, leaving, moving, or changing size.
Review pop-ups, modals, and banners that obscure page content. Identify mobile usability and search visibility concerns, then improve dismissal controls and keyboard focus, the element currently receiving keyboard input.
Check running experiments, collect logs and result metrics, and summarize progress alongside baseline comparisons. It supports SSH servers, Vast.ai, and Modal, with optional Weights & Biases metrics and cost reporting for the supported compute services.
Build or update Figma pages, modals, and other composed views from code or descriptions. Reuse existing components, shared color and spacing values, and styles, assembling and checking the design section by section.
Add CSS animations to web interfaces using ready-made patterns for menus, modals, loading states, text changes, and more. It selects a suitable pattern, connects markup and any required JavaScript, and preserves reduced-motion support.
Use when the user asks to run heavy or GPU work on Modal (the cloud compute platform) — writing a Modal function in the workspace, running it with the user's own `modal` CLI + token, and bringing results back. Data-to-compute for jobs too big for the laptop, without a Slurm cluster.
The English summary is being prepared. Showing the original description.
Multi-modal single-cell analysis with muon/MuData. Joint RNA+ATAC (10x Multiome), CITE-seq (RNA+protein), other multi-omics. MuData holds per-modality AnnData with shared obs. WNN joint embedding, per-modality preprocessing, MOFA factor analysis. Use scanpy-scrna-seq for single-modality RNA; use muon when combining 2+ omics from the same cells.
The English summary is being prepared. Showing the original description.
Compose or analyze sacred music in Hildegard von Bingen's distinctive modal style. Covers modal selection, melodic contour (wide-range melodies), text-setting (syllabic and melismatic), neumatic notation, and liturgical context for antiphons, sequences, and responsories. Use when composing a new piece in Hildegardian style, analyzing an existing chant for structure and mode, researching medieval modal music, preparing to perform or teach Hildegard's music, or setting Latin sacred texts.
The English summary is being prepared. Showing the original description.
Registers a custom WooCommerce shipping method with explicit control over which fields appear in the per-zone settings modal — extend WC_Shipping_Method, declare your fields in init_form_fields (and ONLY those fields, no unset / DOM hacks / CSS hides), set the $supports array to control whether the modal opens (omit 'instance-settings' to suppress it entirely), register via the woocommerce_shipping_methods filter, load the class on woocommerce_shipping_init. Corrects the "this is React, removing fields is hard" misconception — the zone-method modal is Backbone with a PHP-rendered settings_html string; the field list is wholly PHP-controlled. Use when scaffolding a shipping method or when you want a feature-flag-only modal without WC defaults. Triggers on WC_Shipping_Method, woocommerce_shipping_methods, woocommerce_shipping_init, init_form_fields with shipping context, $supports shipping-zones, calculate_shipping, add_rate, or "remove default fields from shipping method".
The English summary is being prepared. Showing the original description.
Create short video clips from text or still images with LTX-2.3 22B. Generate supporting footage, animated backgrounds, or moving portraits while specifying camera motion, lighting, dimensions, and duration, with clips around five seconds by default.
Build image classification and search workflows by comparing images with text descriptions. Covers classification without additional training, similarity scoring, batch processing, and storing image representations in a vector database for retrieval.
Build React interfaces with HeroUI v3, including buttons, forms, cards, and modals. The skill guides installation, component documentation lookup, and light or dark theme configuration using Tailwind CSS v4 and reusable interface components.
Build and update Kortix web screens with established interface components and reference layouts. Guides component selection for forms, lists, modals, loading states, and notifications, including replacements for deprecated components and consistent responsive page structure.
Guides image classification and search with OpenAI's CLIP by comparing images with text descriptions, without additional training. Includes batch processing, image-text matching, and category-based checks for potentially inappropriate images.
Get guidance on adapting LLMs through additional training with LLaMA-Factory. The skill covers a visual interface requiring no code, LoRA and QLoRA training methods, and documentation-based help with implementation, features, and debugging.