Loading...
Loading...
Found 173 Skills
Trains and fine-tunes vision models for object detection (D-FINE, RT-DETR v2, DETR, YOLOS), image classification (timm models — MobileNetV3, MobileViT, ResNet, ViT/DINOv3 — plus any Transformers classifier), and SAM/SAM2 segmentation using Hugging Face Transformers on Hugging Face Jobs cloud GPUs. Covers COCO-format dataset preparation, Albumentations augmentation, mAP/mAR evaluation, accuracy metrics, SAM segmentation with bbox/point prompts, DiceCE loss, hardware selection, cost estimation, Trackio monitoring, and Hub persistence. Use when users mention training object detection, image classification, SAM, SAM2, segmentation, image matting, DETR, D-FINE, RT-DETR, ViT, timm, MobileNet, ResNet, bounding box models, or fine-tuning vision models on Hugging Face Jobs.
Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container. Use when the user wants to fine-tune a HuggingFace model (full or LoRA), train a vision / VLM / LLM model end-to-end, generate a reproducible HF training pipeline, smoke-test a HuggingFace model locally before scale-up, push a fine-tuned model to the HF Hub with a model card, or emit a self-contained rerun skill for an existing HuggingFace finetune. Supports image classification, object detection, semantic / instance / panoptic segmentation, depth estimation, image-text-to-text VLM (SFT / LoRA), and LLM SFT / DPO / GRPO. Six-step workflow: inspect and qualify, hardware and NGC image, research, generate and smoke, train + eval + infer, push and emit rerun skill.
OpenAI's model connecting vision and language. Enables zero-shot image classification, image-text matching, and cross-modal retrieval. Trained on 400M image-text pairs. Use for image search, content moderation, or vision-language tasks without fine-tuning. Best for general-purpose image understanding.
Data classification framework including sensitivity levels, handling requirements, labeling, and data lifecycle management
Design and operate privacy and data security programs for SEC-registered firms under Reg S-P, Reg S-ID, and SEC cybersecurity expectations. Use when the user asks about privacy notices, the Safeguards Rule, identity theft prevention programs, breach notification obligations, vendor security due diligence, incident response planning, data classification, or state privacy law compliance. Also trigger when users mention 'customer data was exposed', 'do we need to notify clients of a breach', 'cybersecurity exam prep', 'cloud vendor risk assessment', 'encrypting client data', 'BYOD security policy', 'Red Flags Rule', 'NY DFS 500 requirements', or ask how to handle a cybersecurity incident.
Calculate import tariffs, duties, and landed cost for products imported to sell on Amazon. Covers HS code classification, duty rates, additional tariffs, freight and customs fees, and the true per-unit landed cost. Use when a user asks about import tariffs, customs duty, landed cost, HS codes, import taxes, duty rates, or the cost of importing a product. Trigger phrases: "tariff", "import duty", "customs", "landed cost", "HS code", "import tax", "duty rate", "cost to import". Works with zero tools. the user provides the product, the route, and the costs.
Analyze emotion — mood classification, energy, valence, genre detection
Industry-standard gradient boosting libraries for tabular data and structured datasets. XGBoost and LightGBM excel at classification and regression tasks on tables, CSVs, and databases. Use when working with tabular machine learning, gradient boosting trees, Kaggle competitions, feature importance analysis, hyperparameter tuning, or when you need state-of-the-art performance on structured data.
Customer query skill. Suitable for requirements such as searching customer lists by keywords and obtaining customer GTMs classifications. This skill is used when users need to: (1) Search for customers by keyword, (2) Obtain the list of GTM business lines.
Behavioral classification, performance analysis, and trading style detection for Solana wallets
CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX export, and TensorRT deployment. Use when fine-tuning or training CLIP, running zero-shot classification, computing image embeddings, or deploying CLIP to ONNX/TensorRT.
SAP HANA Machine Learning Python Client (hana-ml) development skill. Use when: Building ML solutions with SAP HANA's in-database machine learning using Python hana-ml library for PAL/APL algorithms, DataFrame operations, AutoML, model persistence, and visualization. Keywords: hana-ml, SAP HANA, machine learning, PAL, APL, predictive analytics, HANA DataFrame, ConnectionContext, classification, regression, clustering, time series, ARIMA, gradient boosting, AutoML, SHAP, model storage