Loading...
Loading...
Found 55 Skills
Masked Auto-Encoder (MAE) for self-supervised pretraining and fine-tuning. Masks random patches and reconstructs them to learn visual representations; supports pretrain and finetune stages. Use when training, evaluating, exporting, or running inference for a TAO MAE backbone. Trigger phrases include "pretrain MAE", "self-supervised vision pretraining", "Masked Autoencoder", "Mask Auto-Encoder", "MAE fine-tune".
Translate designs and UI requirements into robust, extensible implementations. Apply when converting designs to code, implementing components, fixing broken UI, or handling responsive layouts.
Use when the workflow is too slow, too expensive, or both and needs latency, cost, or token usage optimization.
Deploy prompt-based Azure AI agents from YAML definitions to Azure AI Foundry projects. Use when users want to (1) create and deploy Azure AI agents, (2) set up Azure AI infrastructure, (3) deploy AI models to Azure, or (4) test deployed agents interactively. Handles authentication, RBAC, quotas, and deployment complexities automatically.
Evaluate UI/flows from cognitive load, error prevention, and accessibility perspectives. Apply when reviewing UX, discussing user confusion, high drop-off, or form usability issues.
Use when the workflow feels over-engineered, has premature optimizations, unnecessary abstraction layers, or complexity beyond actual requirements.
Design UI as information architecture + interaction + visual tone, then translate into implementable specs. Apply when discussing screen design, component design, design systems, or visual hierarchy.
Receive context from parent, child, or sibling session
Use when porting a workflow to a different AI provider, deployment environment, model tier, or organizational context.
Use when the workflow works but needs polish, or as the final step in a diagnose → fix → refine cycle before shipping.
Extract frames from video files using ffmpeg for AI/LLM analysis. Use when (1) the user asks to analyze, describe, or summarize a video file, (2) the user wants to extract frames or screenshots from a video, (3) the user provides a video file (.mp4, .mov, .avi, .mkv, .webm, etc.) and asks questions about its visual content, (4) the user wants to identify scenes, objects, or events in a video, (5) the user wants timestamps overlaid on extracted frames for temporal reference. Converts video into JPEG frames that can be attached to LLM prompts as images. Requires ffmpeg on PATH. Supports scene-change detection, model-aware optimization (Claude/OpenAI/Gemini), quality presets (efficient/balanced/detailed/ocr), grayscale and high-contrast OCR mode, and automatic FPS calculation via --max-frames.
Use the `date` command via Bash tool whenever you or the user mention time, dates, or temporal concepts. Verify current date/time before ANY temporal response, as environment context may be outdated. Parse expressions like "tomorrow", "next week", "3 days", "in 2 weeks", "next Monday at 3pm". Proactively invoke for deadlines, schedules, time-sensitive tasks, week numbers, or any date/time reference.