Loading...
Loading...
Found 38 Skills
Summarize a video by calling the VLM NIM or the Long Video Summarization (LVS) microservice directly. For short videos (under 60s) call the VLM's OpenAI-compatible chat completions endpoint; for long videos (60s or longer) call the LVS microservice. Use when asked to summarize a video, describe what happens in a video, analyze a recording, call or debug LVS summarize/model/health/recommended-config/metrics endpoints, or configure and troubleshoot the LVS service that backs long-video summarization.
Manage and monitor VSS alerts after the alerts profile is deployed. The deployment's mode (CV vs VLM real-time) is fixed at deploy time and determines the workflow — start/stop real-time alerts via the VSS Agent on a VLM deployment, onboard CV alerts by adding RTSP streams to VIOS on a CV deployment, query incidents, customize verifier prompts. Use when asked to start/stop a real-time alert, check or list alerts, add a camera, use a sample video for alerts, customize alert prompts, or view verdicts.
Creative-mode PPT pipeline. One full-page 16:9 PNG per slide. LLM / VLM calls go through sn-ppt-standard/lib/model_client.py (shared thin client). Text-to-image (the actual png rendering) goes through sn-image-base/scripts/sn_agent_runner.py. Expects task_pack.json + info_pack.json already written by sn-ppt-entry.
Return public original model architecture diagrams for user-specified LLM, VLM, MoE, diffusion, OCR, and SGLang/sgl-cookbook model families. Use when the user asks for a model structure chart, architecture diagram, or rendered image link for a specific model such as DeepSeek, GLM, Qwen, Kimi, MiniMax, Step, Hunyuan, or Qwen3-VL.
Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns from DSV3, Qwen3, Qwen3-Next, and VLM bring-up work.
Two-step image grounding pipeline: extracts referring expressions from (image, caption) pairs and grounds them to pixel-space bounding boxes via a VLM. Use when the user wants to ground captions to bboxes, generate phrase-grounded annotations, auto-label images for grounding, or run the image_grounding pipeline. Triggers include 'image grounding', 'phrase grounding', 'ground captions', 'auto-label image grounding', 'image_grounding'.
Guide for adding support for new LLM or VLM models in Megatron-Bridge. Covers bridge, provider, recipe, tests, docs, and examples.
Validate and use packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs, and applying the right CP constraints.
Multi-step video annotation pipeline that turns raw videos into Chain-of-Thought training data — multi-level captions, structured descriptions, and QA pairs (MCQ, binary, open-ended) with reasoning traces, via VLM/LLM distillation. Use when the user wants to "create video training data", "generate video QA datasets", "build CoT reasoning traces from videos", "auto-label videos", or run the video_reasoning_annotation pipeline. Triggers include "video annotation", "video CoT", "video QA", "chain-of-thought", "video captioning pipeline", "video distillation".
Validate and use packed sequences and long-context training in Megatron-Bridge, distinguishing offline packed SFT for LLMs from in-batch packing for VLMs, and applying the right CP constraints.
Use the mm CLI to index, explore, query, and extract content from multimodal directories containing images, videos, PDFs, code, and other files. Triggers: exploring a directory's contents, listing/finding files by type or size, extracting text from PDFs, getting image metadata, searching across file contents, counting tokens, viewing directory trees, extracting PDF page mosaics, video keyframe extraction, 'what files are in this folder', 'find all images', 'show me the PDFs', 'how much storage do videos use', 'extract text from this PDF', 'search documents for X', 'analyze this directory', 'how many tokens', 'show the tree'.
Choose the right MoE token dispatcher (`alltoall`, DeepEP, or HybridEP) for the hardware, EP degree, and optimization stage. Summarizes patterns from DSV3, Qwen3, Qwen3-Next, and VLM bring-up work.