TAO Skill Bank Capabilities

tao-list-capabilities

Answer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, AutoML, and platform manifests. Use when the user asks "what can TAO Skill Bank do", "list TAO models", "which TAO workflows are available", or "what supports AutoML".

nvidia/skills·1.6Kinstalls3.5Kstars

SKILL.md

Full skill instructions

TAO Skill Bank Capabilities

Standalone install? If this session was not initialized by the TAO skill bank plugin, run the tao-setup skill first (host preflight, credentials, cross-skill discovery).

Use this skill when the user asks what tao-skill-bank can do, asks for plugin capabilities, asks which application or data workflows are available, asks which models are supported, or asks what models are capable with AutoML.

Quick Start

Run scripts/list_tao_capabilities.py for general capability questions, or scripts/list_tao_models.py for model/action and AutoML support questions.

Capability Answers

For a general capabilities answer, run the packaged helper:

${TAO_SKILL_BANK_PATH:-~/tao-skill-bank}/scripts/list_tao_capabilities.py \
  --skill-bank ${TAO_SKILL_BANK_PATH:-~/tao-skill-bank} --format text

Use the helper output as the source of truth for the answer instead of manually enumerating capabilities from this skill or plugin metadata. Include:

Every top-level application workflow under applications/ and what it can do.
Every top-level data workflow under data/ and what it can do.
Supported execution platforms, discovered from the installed platform skills (tao-run-on-docker / -slurm / -kubernetes / -brev, plus any external one); on a runtime that surfaces only the core router skills, read skills/platform/tao-run-on-*/SKILL.md frontmatter.
The fine-tuning/deployment workflow coverage for models under models/: train, evaluate, inference, export, and TensorRT engine generation when those actions are present in the packaged schema manifest.
AutoML support and the AutoML per-action schema gate.

Model Lists

When the user asks which TAO models are available or which actions a model can run, use the packaged model-list script instead of manually scanning model folders:

${TAO_SKILL_BANK_PATH:-~/tao-skill-bank}/scripts/list_tao_models.py \
  --skill-bank ${TAO_SKILL_BANK_PATH:-~/tao-skill-bank} --scope all --format text

The model list comes from skills/models/schemas.manifest.json.

AutoML Lists

When the user asks what models are capable with AutoML, use the same model-list script in AutoML mode, or the compatibility wrapper:

${TAO_SKILL_BANK_PATH:-~/tao-skill-bank}/scripts/list_tao_models.py \
  --skill-bank ${TAO_SKILL_BANK_PATH:-~/tao-skill-bank} --scope automl --format text

${TAO_SKILL_BANK_PATH:-~/tao-skill-bank}/scripts/list_automl_support.py \
  --skill-bank ${TAO_SKILL_BANK_PATH:-~/tao-skill-bank} --format text

Use --action distill, --action prune, or --action quantize when the user asks about a specific compression action.

AutoML support for an action requires skills/models/<model_skill>/schemas/<action>.schema.json to be packaged with the plugin and parse successfully as JSON. If that dataclass schema is missing or invalid, do not describe the model/action as AutoML-supported.

Install skill

Copy and run in your terminal

npx -y skills add https://github.com/nvidia/skills --skill tao-list-capabilities

View on GitHub

tao-list-capabilities

rag-blueprint
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).
3.1K installs
accelerated-computing-cudf
Official NVIDIA-authored guidance for NVIDIA cuDF GPU DataFrames, pandas acceleration, dask-cuDF, ETL, joins, groupby, CSV/Parquet I/O, nullable semantics, and multi-GPU DataFrame workloads.
3K installs
cuopt-developer
Modify, build, test, debug, and contribute to NVIDIA cuOpt (C++/CUDA, Python, server, CI). Use for solver internals, PRs, DCO, and code conventions.
2.7K installs
cuopt-install
Install cuOpt for Python, C, or server via pip, conda, or Docker; verify the install. For building cuOpt from source, see cuopt-developer.
2.5K installs

More skills from nvidia

nvidia/skills

cudaq-guide

CUDA-Q onboarding guide for installation, test programs, GPU simulation, QPU hardware, and quantum applications.

3.5K 2.5K

View

nvidia/skills

data-designer

Use when the user wants to create a dataset, generate synthetic data, or build a data generation pipeline.

3.5K 2.4K

View

nvidia/skills

deepstream-dev

NVIDIA DeepStream SDK development with Python pyservicemaker API. Use when building video analytics pipelines, GStreamer-based video processing, TensorRT inference integration, object detection/tracking, or Kafka/message broker integration.

3.5K 2.4K

View

nvidia/skills

rag-eval

Filesystem RAG benchmarks: corpus/, train.json, evaluate_rag.py (RAGAS quality). Not for prod monitoring, latency/throughput benchmarking (use rag-perf), or evals outside this repo layout.

3.5K 2.3K

View

nvidia/skills

nemo-retriever

Use when the user wants to search, query, extract, transcribe, describe, quote, filter, or aggregate across documents — PDFs, scanned forms / images (`.jpg` `.png` `.tiff`), Office (`.docx` `.pptx`), text (`.html` `.txt`), audio (`.mp3` `.wav` `.m4a`), or video (`.mp4` `.mov`). Prefer this over native Read / Grep for multi-file or non-PDF corpora. Not for: editing files, web browsing, single-file plain-text lookups, fine-tuning.

3.5K 2.3K

View

nvidia/skills

omniverse-cad-to-simready

Coordinate the end-to-end CAD/source-asset to SimReady workflow. Use for broad requests such as CAD to SimReady, source asset to simulation-ready USD, or prop packaging that require conversion, material/physics assignment, SimReady conformance, validation, and optional package creation; deploy or verify Content Agents services first when property assignment is enabled; route single-stage work through nested references.

3.5K 2.3K

View

nvidia/skills

deepstream-import-vision-model

Use this skill to bring any vision model from HuggingFace or NVIDIA NGC into an NVIDIA DeepStream pipeline with end-to-end automation: ONNX download, SafeTensors export, TRT engine build, custom nvinfer bbox parser, multi-stream benchmark, and PDF report. Object detection models only.

3.5K 2.3K

View

nvidia/skills

omniverse-usd-performance-tuning

Top-level workflow skill for USD performance diagnosis and optimization. Handles slow loading, high memory, low FPS, and broad scene-optimization requests; delegates auth/runtime setup to Phase 0 owners.

3.5K 2.3K

View

nvidia/skills

cuopt-routing-api-python

Vehicle routing (VRP, TSP, PDP) with cuOpt — Python API only. Use when the user is building or solving routing in Python.

3.5K 2.2K

View

nvidia/skills

skill-card-generator

Use only to generate or update a governance skill card for a specified existing agent skill directory. Do not use for explaining, listing, comparing, or discussing skill capabilities.

3.5K 2.2K

View

nvidia/skills

omniverse-realtime-viewer

Use as the top-level router for Omniverse Realtime Viewer USD app requests and focused viewer reference documents.

3.5K 2.2K

View

nvidia/skills

rag-perf

Performance benchmarking for a deployed NVIDIA RAG Blueprint server: profiling pass + aiperf load test driven by a single YAML config. Not for accuracy / RAGAS scoring (use rag-eval) or for deploying / repairing services (use rag-blueprint).

3.5K 2.1K

View