研究与知识

tao-finetune-clip

CLIP vision-language model for image-text retrieval, zero-shot classification, embedding extraction, ONNX

Fine-tune any HuggingFace CV / VLM / LLM model on local NVIDIA GPUs inside an NGC PyTorch container. Use when the user wants to fine-tune a HuggingFace model (full or LoRA), train a vision / VLM / LLM model end-to-end, generate a reproducible HF training pipeline, smoke-test a HuggingFace model locally before scale-up, push a fine-tuned model to the HF Hub with a model card, or emit a self-contained rerun skill for an existing HuggingFace finetune. Supports image classification, object detection, semantic / instance / panoptic segmentation, depth estimation, image-text-to-text VLM (SFT / LoRA), and LLM SFT / DPO / GRPO. Six-step workflow: inspect and qualify, hardware and NGC image, research, generate and smoke, train + eval + infer, push and emit rerun skill.

tao-finetune-cosmos-embed

Cosmos-Embed1 video-text embedding for text-to-video retrieval, video-to-video search, semantic deduplication, and fine-tuning. Use when the user asks to "fine-tune Cosmos-Embed1", "run cosmos-embed inference", "export Cosmos-Embed1", "embed videos", or "search videos with text".

tao-launch-workflow

Shared launch intake for any TAO workflow or action. Use when the user wants to run TAO AutoML, train, evaluate, infer, export, generate TensorRT engines, or launch DEFT/workflow jobs on an execution platform.

hsb-setup

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.

alphaear-search

Perform finance web searches and local context searches. Use when the user needs general finance info from the web (Jina/DDG/Baidu) or needs to retrieve finance information from a local document store (RAG).

rkiding

holoscan-setup

Guides Holoscan SDK installation: inspects the host, assesses platform compatibility, recommends an install method, and delegates to the matching install skill.

nemo-rl-brev-etiquette

Brev instance operating guidance for NeMo-RL agents working in /home/ubuntu/RL with limited workspace disk, a larger /ephemeral volume, and optional /home/ubuntu/RL/.env secrets. Use when running nemo-rl-auto-research campaigns, experiments, training jobs, model or dataset downloads, shared cache-heavy commands, log-producing runs, checkpoint generation, W&B or Hugging Face authenticated workflows, or any workflow that may create large files on Brev.

nv-generate-ct-rflow

Used for generating synthetic CT volumes and masks with NV-Generate-CTMR rflow-ct. Not for production training data without review.

earth2studio-discover

Find Earth2Studio models, data sources, and examples for a weather/climate use case. Do NOT use for writing inference code, downloading data, or installation.

vss-generate-video-report

Use this skill when producing a VSS analysis report — Mode A per-clip VLM, Mode B incident-range via video-analytics. Not for standalone video summarization, real-time alerts or ad-hoc Q&A.

nemo-mbridge-perf-moe-long-context

Long-context MoE training guidance for Megatron Bridge. Covers CP sizing, selective recompute, dispatcher choices, and practical patterns from DSV3, Qwen3, and Qwen3-Next long-context experiments.

nemo-mbridge-perf-moe-hardware-configs

Representative, point-in-time MoE training playbooks by hardware and model family. Use them as candidate seeds, then revalidate the exact runtime, semantics, topology, and steady-state throughput.

nemo-rl-docs

Documentation conventions for NeMo-RL. Covers docs/index.md updates and docstring format. Do NOT use for: bug fixes, test fixes, dependency bumps, refactoring, CI/CD changes, performance tuning, or any task that does not involve writing or updating documentation.

physicsnemo-discover

Official NVIDIA-authored guidance for navigating PhysicsNeMo — pick the model, datapipe, or example for a SciML/AI4Science task (surrogates, forecasting, downscaling, physics-informed, inverse, generative). Points at existing files via live repo search; never writes code. Do NOT use for installation or environment setup, training-loop or other code authoring/scaffolding, contributor/CI/packaging questions, repo-specific questions in physicsnemo-sym/-cfd/-curator, or general (non-physics) ML/PyTorch.

nemo-rl-auto-research

Autonomous NeMo-RL research agent workflow for directed hypothesis testing and open-ended discovery. Guides agents through the full experiment lifecycle: understanding recipes and environments, wiring RL or NeMo-gym runs, launching reproducible baselines and iterations, analyzing results, preserving human oversight, and using git plus TSV logs as the research ledger. Do NOT use for: bug fixes, code review, documentation, refactoring, dependency updates, or single-file changes.

basin

Build and troubleshoot Cloudflare Basin analytics workflows with Basin Pipelines, Basin Catalog, and Basin SQL. Use for streaming data into R2 Iceberg tables, managing catalogs, or querying those tables; also use for requests using the former Data Platform, Pipelines, R2 Data Catalog, or R2 SQL names.

cloudflare

nemotron-retrieval-recipes

Use when planning, debugging, tuning, evaluating, exporting, or deploying public Nemotron `embed`/`rerank` retrieval recipes.

cuopt-numerical-optimization-formulation

LP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.

cupynumeric-install

Install and verify cuPyNumeric for Python — requirements, commands, verification. Source builds are out of scope.

wecomcli-doc-manage

2.9Kresearch-knowledge

企业微信文档公共管理：搜索文档（最近浏览/创建）、文档改名、添加文档成员权限、设置文档加入规则。适用于所有文档类型（doc文档 / 在线表格 / 智能表格 / 智能文档）。新建或导入doc文档请使用 wecomcli-doc；新建或导入在线表格请使用 wecomcli-sheet；智能表格内容 CRUD 请使用 wecomcli-smartsheet；生成智能文档请使用 wecomcli-smartpage。"看过哪些文档/浏览历史"类需求走本技能，不要走 wecom_get_user_memory。

wecomteam