What does LLM-Skills do?
Multimodal vision parsing and YOLO dataset generation tool (MS-Qwen-VL), supporting image/video, batch processing, and class-specific detection.
Multimodal vision parsing and YOLO dataset generation tool (MS-Qwen-VL), supporting image/video, batch processing, and class-specific detection.
This skill, WdBlink/LLM-Skills, acts as an advanced multimodal vision parsing and YOLO dataset generation tool powered by MS-Qwen-VL. It is designed to help developers and AI users parse images and videos using large vision-language models and automatically generate YOLO-format annotation datasets for custom object detection tasks. The skill supports batch processing, allowing you to process multiple files efficiently, and can filter detections to only include specific object classes. It is useful for quickly creating training data for computer vision models without manual annotation, and integrates seamlessly with AI agent platforms like Claude Code, Cursor, and Codex by leveraging natural language instructions to control the vision parsing pipeline.
npx skills add WdBlink/LLM-SkillsInstalled? Explore more Coding & Development skills: steipete/bluebubbles, steipete/eightctl, steipete/blucli · View all 6 →
Multimodal vision parsing and YOLO dataset generation tool (MS-Qwen-VL), supporting image/video, batch processing, and class-specific detection.
Send and manage iMessages via BlueBubbles, including attachments, tapbacks, edits, replies, and groups.
Control Eight Sleep pods (status, temperature, alarms, schedules).
BluOS CLI (blu) for discovery, playback, grouping, and volume.
Create, search, and manage Bear notes via grizzly CLI.
Capture frames or clips from RTSP/ONVIF cameras.
Search GIF providers with CLI/TUI, download results, and extract stills/sheets.