AutoGineer
Generated banner for Tao List Capabilities
Generated logo for Tao List Capabilities

Tao List Capabilities

NVIDIAOfficialCreated by NVIDIA Corporation

  • Skill
  • Tool integration
  • Data and AI
  • Apache-2.0
  • Medium risk
Download ZIP

From the author

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".
— the description by NVIDIA Corporation

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

The tao-list-capabilities skill provides a standardized method for querying the contents and features of the TAO Skill Bank. By leveraging packaged manifests and helper scripts, it allows users to programmatically discover supported models, available data and application workflows, execution platforms, and AutoML support. It ensures that information provided to the user is accurate and derived directly from the current environment's configuration rather than static documentation.

What it does

  • Lists all available application and data workflows within the TAO Skill Bank.
  • Identifies supported models and their specific action capabilities like training, evaluation, and inference.
  • Reports on AutoML support for specific models and compression actions.
  • Discovers and lists compatible execution platforms.
  • Uses internal manifests to ensure accurate reporting of model and action schemas.

When to use it

  • When a user asks for a general overview of what the TAO Skill Bank can do.
  • When a user needs to know which specific AI models are available for use.
  • When a user wants to verify if a specific model supports AutoML or compression actions.
  • When a user asks about available workflows for data processing or application development.

Advantages

  • Provides a single source of truth by reading directly from packaged manifests.
  • Reduces manual effort in scanning directories or documentation for capability discovery.
  • Ensures compatibility with the current environment's installed skills.
  • Supports granular queries for specific actions like pruning, distillation, or quantization.

Usage examples

“What can the TAO Skill Bank do?”
The agent executes the capability script to return a comprehensive list of available application workflows, data processing tasks, and supported execution platforms.
“Which TAO models support AutoML?”
The agent runs the AutoML support script to filter and display only those models that have valid AutoML schema definitions.

Install

  1. Download the skill as a ZIP:

    https://mp-staging.autogineer.com/agent-skills/nvidia/tao-list-capabilities/download

  2. Unzip it into the cross-client skills folder of your project:

    mkdir -p .agents/skills && unzip tao-list-capabilities.zip -d .agents/skills

Documentation by NVIDIA Corporation

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.

Files

skill-card.md

Description: <br>

Answer what the TAO Skill Bank plugin can do by generating the response from packaged application, data, model, AutoML, and platform manifests. <br>

This skill is ready for commercial/non-commercial use. <br>

Owner

NVIDIA <br>

License/Terms of Use: <br>

Apache 2.0 <br>

Use Case: <br>

Developers and engineers use this skill to discover available TAO Skill Bank capabilities, supported models, workflow coverage, and AutoML support. <br>

Deployment Geography for Use: <br>

Global <br>

Requirements / Dependencies: <br>

Requires API Key or External Credential: [Not Specified] <br> Credential Type(s): [None identified] <br>

Do not include secrets in prompts/logs/output; use least-privilege credentials; rotate keys as appropriate. <br>

Known Risks and Mitigations: <br>

Risk: Review before execution as proposals could introduce incorrect or misleading guidance into skills. <br> Mitigation: Review and scan skill before deployment. <br>

Reference(s): <br>

Skill Output: <br>

Output Type(s): [Analysis, Shell commands] <br> Output Format: [Plain text capability listings] <br> Output Parameters: [1D] <br> Other Properties Related to Output: [None] <br>

Evaluation Agents Used: <br>

  • Claude Code (aws/anthropic/bedrock-claude-opus-4-8) <br>

  • Codex (openai/openai/gpt-5.5) <br>

Evaluation Tasks: <br>

1 evaluation task (1 positive), 3 attempts per task, each in an isolated sandbox pod. <br>

Evaluation Metrics Used: <br>

Reported benchmark dimensions: <br>

  • Security: Whether the skill is safe to use — checks for unsafe operations, secret leakage, and unauthorized access. <br>

  • Correctness: Whether the answer is correct against the reference answer. <br>

  • Discoverability: Whether the right skill was loaded when needed — skill selection, decoy avoidance, and workflow execution. <br>

  • Effectiveness: Whether the skill helped complete the task — goal completion (50%) and expected workflow adherence (50%). <br>

  • Efficiency: Whether the skill avoided wasted tool calls and token usage — tool-call productivity (50%) and token efficiency (50%). <br>

Underlying evaluation signals used in this run: <br>

  • security: Checks for unsafe operations, secret leakage, and unauthorized access. <br>

  • skill_execution: Whether the expected skill was selected, decoys were avoided, and the workflow executed. <br>

  • accuracy: Final-answer correctness against the reference answer. <br>

  • goal_accuracy: Whether the user's goal was achieved. <br>

  • behavior_check: Whether the expected workflow behavior was followed. <br>

  • skill_efficiency: Tool-call productivity. <br>

  • token_efficiency: Actual uncached prompt plus completion token usage. <br>

Evaluation Results: <br>

MeasureClaude Code (Baseline → Skill Uplift)Codex (Baseline → Skill Uplift)
Overall99.7%76.5%
Security100.0% → 100.0% (±0.0 pts)100.0% → 100.0% (±0.0 pts)
Correctness0.0% → 100.0% (+100.0 pts)40.0% → 70.0% (+30.0 pts)
Discoverability100.0%47.5%
Effectiveness16.7% → 100.0% (+83.3 pts)48.3% → 65.8% (+17.5 pts)
Efficiency98.6%99.1%

Skill Version(s): <br>

0.1.0 (source: frontmatter) <br>

Ethical Considerations: <br>

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal team to ensure this skill meets requirements for the relevant industry and use case and addresses unforeseen product misuse. <br>

(For Release on NVIDIA Platforms Only) <br> Please report quality, risk, security vulnerabilities or NVIDIA AI Concerns here. <br>

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Declares allowed tools

The author says: Requires the packaged TAO skill bank helper scripts.

Security

What our scanner noticed· Medium risk

  • Large base64-encoded blobs

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by
NVIDIA Corporation
Publisher
NVIDIA (Official)
Source
NVIDIA/skills · skills/tao-list-capabilities · commit fce3cca
Licence
Apache License 2.0 (redistribution allowed)
  • LICENSE (added by AutoGineer from LICENSE-APACHE)
  • ATTRIBUTION.md (written by AutoGineer)
Synced

AutoGineer is not affiliated with or endorsed by NVIDIA Corporation or NVIDIA.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download tao-list-capabilities.zip