47 skills · sorted by relevance
How to swap the VLM in the VSS Alerts Blueprint — covers RTVI-VLM microservice deployment methods, all three VLM consumers (rtvi-vlm, vlm-as-verifier, vss-agent), and health checks.
The English summary is being prepared. Showing the original description.
Configure supervised fine-tuning for models that process images and text. Define which components remain unchanged, set LoRA adapters for updating selected model weights, choose image resolution limits, and investigate training runs whose evaluation results fail to improve.
Use this skill when building, deploying, evaluating, debugging, or measuring latency for the DeepStream SOP Inference Microservice — a GPU-accelerated FastAPI service that detects whether operators perform assembly-line steps in order via event boundary detection (GEBD) plus VLM classification. Trigger even if the user does not name it: verify operator step sequence, detect missing or out-of-order SOP steps, score factory/work-cell video for procedure compliance, run VLM-based SOP checking on industrial cameras, or call /v1/chat/completions with a file, RTSP, or Basler camera. Also trigger for its internals: SOPVideoProcessor, DeepStream GEBD model (e.g. DDM) via Triton CAPI, nvds_custom_postprocess, Cosmos Reason 1/2 vLLM, SSE streaming, Kafka NvProto/JSON output, Basler/Pylon camera + emulation, Docker compose, chunk-level latency. Do NOT trigger for generic DeepStream pipelines, object detection/tracking, NIM imports, or video summarization.
The English summary is being prepared. Showing the original description.
Runs the GPU part of a vlm-ocr pipeline on Leiden University's ALICE cluster. Decides whether a corpus needs ALICE, picks a GPU partition for the model, sets up storage, a pinned vLLM environment and offline weights, ships code and scans, runs a gate job and chained bulk jobs with the bundled SLURM template, and brings the page records home for post-processing. Use with vlm-ocr when OCRing scans on ALICE or deciding whether to.
The English summary is being prepared. Showing the original description.
Run the GPU part of a $vlm-ocr pipeline on Leiden University's ALICE cluster: decide whether a corpus needs ALICE, pick a GPU partition for the model, set up storage, a pinned vLLM environment and offline weights, ship code and scans, run a gate job and chained bulk jobs with the bundled SLURM template, and bring the page records home for post-processing. Use with $vlm-ocr when OCRing scans on ALICE or deciding whether to.
The English summary is being prepared. Showing the original description.
Fine-tune LLMs and VLMs using Unsloth on HF Jobs (Hugging Face on-demand cloud GPUs). Use when users want to fine-tune language models, train VLMs (Vision Language Models), do continued pretraining, domain adaptation, or run UV scripts on HF Jobs. Triggers on requests involving Unsloth training, HF Jobs GPU training, Qwen3-VL fine-tuning, Gemma VLM training, or LoRA fine-tuning on cloud GPUs.
The English summary is being prepared. Showing the original description.
Measure the colors and shot lengths of reference videos to build a reusable style pack. Outputs include a LUT, a color conversion table, plus still frames, overlay assets, and a generation specification grounded in the measured footage.
Extract text from images and PDFs, including handwriting, tables, invoices, and receipts. Return plain text, Markdown tables, or structured JSON fields, with options to select a recognition provider and specific PDF pages.
Provide other skills with tools for generating and editing images, analyzing image content, and improving text through external APIs. This foundation passes inputs to backend services without preprocessing and returns results as text or JSON.
Practical guidance for training MoE VLMs in Megatron Bridge. Compares FSDP and 3D-parallel approaches, using rounded lessons from Qwen3-VL, Qwen3-Next, and other multimodal experiments.
The English summary is being prepared. Showing the original description.
把视频分析为结构化理解索引：场景检测、ASR 转写、逐场景 VLM 观察、静音窗口、融合时间线和写作 brief。 用于理解、索引或总结视频，也作为后续创作前的分析阶段。输入视频文件；输出 scenes.json、 asr_result.json、vlm_analysis.json、silence_periods.json、timeline_fusion.json、agent_narration_brief.md。 触发词：视频理解、视频分析、视频索引、video understanding、analyze video、看懂视频。
The English summary is being prepared. Showing the original description.
OCRs scanned or image-only corpora with vision-language models in four phases. Triage inventories the scans, identifies script and language, and shortlists models by script, hardware, and data constraints. Evaluate selects a system by measured CER or WER against ground truth, using born-digital twins, a second reader, and decision rules set in advance. Run builds the production pipeline. Clean removes model artifacts, audits what every cleaning rule deletes, corrects with rule-based and LLM passes, and records provenance. Use when choosing an OCR model for a corpus, measuring OCR accuracy, transcribing scans at scale, or correcting raw OCR. Born-digital documents with text layers go to doc-to-markdown; runs on Leiden's ALICE cluster add vlm-ocr-alice.
The English summary is being prepared. Showing the original description.
OCR scanned or image-only corpora with vision-language models in four phases: `triage` inventories the scans, identifies script and language, and shortlists models by script, hardware, and data constraints; `evaluate` picks a system by measured CER/WER against ground truth, using born-digital twins, a second reader, and decision rules set in advance; `run` builds the production pipeline; and `clean` removes model artifacts, audits what every cleaning rule deletes, corrects with rule-based and LLM passes, and records provenance. Born-digital documents with a text layer go to $doc-to-markdown; runs on Leiden's ALICE cluster add $vlm-ocr-alice.
The English summary is being prepared. Showing the original description.
Local vision-language model for image analysis using SmolVLM-2B
The English summary is being prepared. Showing the original description.
最新AI技術動向のレポート（最新 / 週次 / 月次 / 特定トピック別）を Web 検索・WebFetch・GitHub/Hugging Face MCP で調査して生成し、Yagami360/ai-product-dev-tips リポジトリの GitHub Issue として投稿するスキル。ユーザーが「AI技術のキャッチアップ」「最新AIニュースまとめ」「週次/月次のAI動向レポート」「〇〇（例: AI Agent, RAG, VLM, Physical AI, Claude Code）についての技術調査レポート」「AI Tech Catchup レポートを作って」などを求めたとき、たとえ "skill" や "Issue" という単語が無くても必ずこのスキルを使うこと。直近のAI業界の最新情報を調べてまとめてほしい・GitHub Issue 化してほしいという依頼全般で発動する。AI とは無関係な一般的な技術調査や、このリポジトリへの Tip 追加（ai-product-dev-tips-create スキルの領分）には使わない。
The English summary is being prepared. Showing the original description.
Operational guide for the NV oOS Dictation desktop companion app (Tauri v2 + Rust, examples/nvoos-dictate) — build/run on Windows/MSVC, the local-first engine track (parakeet/whisper/fastconformer/moonshine/silero-vad), the embedded remote-STT fallback, the Stage-2 polish provider track (disabled/openai_compat/nvoos plus local LM Studio and Ollama), the file/media decode seam (Symphonia 0.5), the live camera + local object-detection/tracking track (Proposals 073 + 075) with an opt-in VLM label-polish layer (Proposal 076), the CDP browser-control agent (feature agent) + FastConformer engine + NV oOS multi-SPA hub, model registry + verification harnesses, the plugins.updater boot-crash config rule, and the full test/clippy gate matrix. Use when building, extending, or debugging the dictation app, adding an engine/model, a polish provider, the browser agent, file/video transcription, camera/vision detection, or VLM relabeling.
The English summary is being prepared. Showing the original description.
Prepare GRPO reinforcement learning configurations for tasks with programmatically checkable answers, such as math, code, and structured output. Design and inspect reward functions, then select training variants when runs show instability or exploit flaws in scoring.
Evaluate language models with over 100 benchmark tests covering knowledge, math, coding, safety, and image understanding. Configure runs on Docker, Slurm computing clusters, or cloud infrastructure, compare models, and export results.
Plan and troubleshoot large language and vision model training and inference. This guide uses hardware measurements to identify bottlenecks, address memory shortages and unstable training, and improve checkpointing, recovery, and performance across multiple GPUs and machines.
Turn a research proposal into an experiment plan tied to specific paper claims. Define comparisons, evaluation measures, tests that remove individual components, run order, and compute estimates, with a written plan and tracker for execution.
Evaluate language models on knowledge, math, coding, safety, and image understanding benchmarks. The skill guides reproducible runs in containers using local Docker, Slurm clusters, or cloud execution, with shared configurations for model comparison and result export.
Prepare and run PAIDF Cosmos Predict video generation for DEFT media samples.
The English summary is being prepared. Showing the original description.
NVIDIA RAG Blueprint — deploy, configure, troubleshoot, and manage. Handles any RAG action: deploy, install, start, enable, disable, toggle, change, configure, troubleshoot, debug, fix, shutdown, stop, or tear down any RAG feature or service (Agentic RAG, VLM, guardrails, query rewriting, models, search, ingestion, observability, summarization, reasoning, and more).
The English summary is being prepared. Showing the original description.
Validate and use packed sequences and long-context training in Megatron-Bridge, including offline LLM packing, collate-time VLM packing, Energon online packing, and CP constraints.
The English summary is being prepared. Showing the original description.