Total 50,674 skills
Showing 12 of 50674 skills
AGENTS.md 거버넌스 시스템을 분석·생성하는 마스터 프롬프트. 현재 프로젝트를 분석하여 루트 AGENTS.md와 하위 AGENTS.md를 즉시 생성하고, CLAUDE.md에 @AGENTS.md 링크를 추가한다. "AGENTS.md 만들어줘", "에이전트 규칙 만들어줘", "/agents-md" 호출 시 반드시 실행하라.
Clone the latest NVIDIA Holoscan Sensor Bridge repo, ask which supported devkit is being used, configure the host per platform, build the correct demo container, run it, and verify HSB connectivity by pinging 192.168.0.2. Use for Holoscan Sensor Bridge setup, build, container launch, and first-connectivity bring-up.
Run the full DEFT AOI improvement loop for NVIDIA TAO VisualChangeNet / ChangeNet PCB inspection models: baseline evaluate, RCA, ingestion of customer-supplied pre-generated AnomalyGen images, k-NN mining, retraining, and deployment gating until FAR / recall KPI targets are met. EA variant — does not run AnomalyGen inline; the customer pre-generates synthetic NG/OK pairs out-of-band and the loop ingests them. Use for prompts like "run the DEFT loop", "fine-tune until FAR below 0.1% at recall=100%", or "improve my AOI ChangeNet model with RCA and pre-generated synthetic defects"; do not use for standalone TAO training, one-off inference, generic anomaly generation, or RCA-only analysis.
Interact with Litefuse and access its documentation. Use when needing to (1) query or modify Litefuse data programmatically via the CLI — traces, prompts, datasets, scores, sessions, and any other API resource, (2) look up Litefuse documentation, concepts, integration guides, or SDK usage, or (3) understand how any Litefuse feature works. This skill covers CLI-based API access (via npx) and multiple documentation retrieval methods.
Use this skill when a content-complete website has missing/placeholder images and needs visual assets — scenario illustrations, tool screenshots, instructor cards, conceptual diagrams, classroom location maps, QR codes. Triggers on phrases like "插圖", "工具截圖", "QR", "講師卡", "地圖", "示意圖", "Playwright 爬蟲", "AI 生圖", "visual assets", "screenshots", "illustrations", "QR codes", "instructor cards". This skill covers the four asset sources (scraping, AI generation, hand-drawn SVG, generated codes), the PNG-first + SVG-fallback render pattern, and verification scripts. Usually invoked AFTER interactions are wired (so missing images are visible), but can be invoked earlier if assets are pre-planned.
Use this skill as the main entry point whenever the user wants to build, plan, or evolve an interactive teaching website / course microsite / workshop landing page — from a blank slate, from existing course materials, or any state in between. Triggers on broad phrases like "做課程網站", "做教學網頁", "做工作坊網站", "把講義變網頁", "course microsite", "workshop site", "interactive lesson page", "multi-day curriculum website", "做一套課程". This skill is the router for the whole teaching-site pipeline (outline → content → SPA → interactions → visuals → corporate / ebook) and dispatches to the 10 specialised sub-skills as needed. Prefer this when the user's request is broad or unclear about which stage they're at — sub-skills (e.g. `course-ebook-publishing`) are still triggerable directly for stage-specific requests.
Measure and improve the quality of AI models and agents on Google Cloud using the Eval Quality Flywheel methodology. Use when evaluating an agent or model, building an eval dataset, picking or writing evaluation metrics, analyzing failures, comparing results before and after a fix, or when guidance is needed on Agent Platform eval methodology — including dataset schema, LLM-as-judge scoring, and common failure causes. For fine-tuning, use agent-platform-tuning. For deployment, use agent-platform-deploy.
Use when the user wants to orchestrate defect image generation, run associated setup, or handle outputs on OSMO. The Day 0 path handles cold-start with USD-to-ROI, image-edit augmentation, and AnomalyGen to create initial PCBA datasets. The Day 1 path performs inference and labeling on real images. This skill helps with first-time asset setup, creation of finetuning checkpoints, and configuring deployment. Trigger keywords: defect image generation, dig workflow, dig pipeline, defect image detection workflow, aoi pipeline, aoi anomalygen, usd2roi anomalygen, day 0 pcba, day 1 pcba, day 1 real-photo alignment, day 1 manual roi, metal surface anomaly, glass defect, anomalygen finetune, setup_pcb, setup_metal, setup_glass, setup_pretrained, dig setup, dig datasets, dig pretrained checkpoint, dig image-edit endpoint.
Deploy and operate the RTVI-CV-3D stack (also known as MV3DT, Multi-View 3D Tracking, or RTVI-CV-MV3DT) — per-camera DeepStream perception plus BEV Fusion over multiple calibrated cameras. Use when the user says "deploy RTVI-CV-3D", "deploy rtvi-cv-3d", "deploy MV3DT", "deploy multi-view 3D tracking", "deploy rtvi-cv-mv3dt", "enable multi-camera tracking", "enable multi camera tracking", "set up multi-camera tracking", "multi-camera tracking", "run RTVI-CV-3D on my videos", "run MV3DT on my videos", "run RTVI-CV-3D / MV3DT on RTSP", "run on the sample dataset", "set up 3D tracking", or provides a 4-camera warehouse video/RTSP set. Routes between sample-data, custom-videos, and custom-RTSP flows; auto-chains to `vss-generate-video-calibration` when calibration data is missing.
Linting and formatting for Megatron-LM. Covers running autoformat.sh, tools (ruff, black, isort, pylint, mypy), and code style rules.
Use this skill when deploying standalone RT-VLM dense captioning or calling its REST API (uploads, captions, streams, chat-completions, Kafka). Not for VSS profile deploy or video-search ingestion.
Use for VSS alert workflows — real-time monitoring, Alert-Bridge subscriptions, Slack notifications, incident queries, camera onboarding. Not for non-alert analytics.