Loading...
Loading...
Found 104 Skills
Company newsletter and content roundup creation with consistent formatting, content curation, and audience segmentation. Use when creating internal newsletters, external digests, or content summaries.
Implement computer vision features including text recognition (OCR), face detection, barcode scanning, image segmentation, object tracking, and document scanning in iOS apps. Covers both the modern Swift-native Vision API (iOS 16+) and legacy VNRequest patterns, VisionKit DataScannerViewController for live camera scanning, and VNCoreMLRequest for custom model inference. Use when adding OCR, barcode scanning, face detection, or custom Core ML model inference with Vision.
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.
Perform RFM (Recency, Frequency, Monetary) customer segmentation from transaction data. Use this skill when the user needs to segment customers by purchase behavior, identify high-value buyers, design retention campaigns, or prioritize marketing spend by customer value — even if they say 'who are our best customers', 'which customers are at risk of churning', or 'how do we target our marketing'.
Guides cybersecurity isolation controls using MITRE D3FEND—access mediation, content filtering, execution isolation, and network segmentation. Covers access policies, permissions, content validation, process isolation, allowlisting, and traffic filtering. Use when segmenting networks, restricting access, filtering content, or isolating execution—not for detection (d3fend-detect), hardening (d3fend-harden), or deception (d3fend-deceive).
Create short-video subtitles with Luma / 拾光 / 拾光工具. Use ASR, segmentation, styling, and burn-in as composable steps; keep editorial decisions in the agent instructions.
Foundation model for image segmentation with zero-shot transfer. Use when you need to segment any object in images using points, boxes, or masks as prompts, or automatically generate all object masks in an image.
Computer vision engineering skill for object detection, image segmentation, and visual AI systems. Covers CNN and Vision Transformer architectures, YOLO/Faster R-CNN/DETR detection, Mask R-CNN/SAM segmentation, and production deployment with ONNX/TensorRT. Includes PyTorch, torchvision, Ultralytics, Detectron2, and MMDetection frameworks. Use when building detection pipelines, training custom models, optimizing inference, or deploying vision systems.
Process and generate multimedia content using Google Gemini API for better vision capabilities. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (better image analysis than Claude models, captioning, reasoning, object detection, design extraction, OCR, visual Q&A, segmentation, handle multiple images), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image with Imagen 4, editing, composition, refinement), generate videos (text-to-video with Veo 3, 8-second clips with native audio). Use when working with audio/video files, analyzing images or screenshots (instead of default vision capabilities of Claude, only fallback to Claude's vision capabilities if needed), processing PDF documents, extracting structured data from media, creating images/videos from text prompts, or implementing multimodal AI features. Supports Gemini 3/2.5, Imagen 4, and Veo 3 models with context windows up to 2M tokens.
E-commerce email marketing system builder. Creates complete email automation flows with full copywriting, subject lines, ESP setup instructions, segmentation rules, and annual campaign calendars. Generates copy-paste-ready email sequences for Klaviyo, Omnisend, Mailchimp, or any ESP. Covers welcome series, cart abandonment, browse abandonment, post-purchase, review requests, cross-sell, win-back, VIP/loyalty, replenishment, and sunset flows. Includes A/B test subject line variants, send timing, trigger conditions, branching logic, and seasonal campaign calendar. No API key required. Use when: (1) setting up email marketing for an e-commerce store, (2) writing email sequences and flows, (3) planning seasonal email campaigns.
Braze platform help — Canvas Flow journey orchestration, email/push/in-app/SMS/WhatsApp/Content Cards campaigns, BrazeAI (predictive, generative, agentic), Braze Data Platform (CDI, Currents), real-time segmentation, Catalogs, Feature Flags, transactional email API, Liquid templating, Connected Content, Braze Alloys integrations, SCIM, REST API. Use when asking 'how do I do X in Braze', configuring Canvas flows, building segments, setting up Currents data streaming, using the Braze API, or migrating from Appboy. Do NOT use for building prospect lists (use /sales-prospect-list), designing outbound cadence strategy (use /sales-cadence), cross-platform deliverability (use /sales-deliverability), transactional email strategy (use /sales-transactional-email), push notification strategy (use /sales-push-notification), in-app messaging strategy (use /sales-in-app-messaging), or email marketing strategy (use /sales-email-marketing).
Brand Tailored Promotions — audience targeting, discount tiers, customer segmentation, repeat purchase incentives