Agent Native

simready-foundation-conform-fet-000-standard

This skill repairs USD assets to meet FET_000_STANDARD Core conformance requirements, fixing file naming, directory layout, asset paths, and undefined…

by NVIDIAOfficial publisherNot reviewed

Identity proven by GitHub's verified organisation badge (NVIDIA, NVIDIA-NeMo)

Agents
Claude Code, Codex, Cursor, Gemini CLI, GitHub Copilot, OpenCode, claude.ai and API
License
Apache-2.0 (permissive)
Pin
60b8bddpinned Oct 9, 2026
Context cost
about 2,800 tokenswhen the skill loads
GitHub stars
95on nvidia/simready-foundation
Scripts
None found

What it does

“Use for repairing FET_000_STANDARD Core failures (default `0.2.0`; use `0.1.0` when a profile pins it): asset file naming, directory layout, relative and resolvable paths, SimReady metadata, and undefined prims.”
The author's description, from SKILL.md

Generated summary from the skill's own text

This skill repairs USD assets to meet FET_000_STANDARD Core conformance requirements, fixing file naming, directory layout, asset paths, and undefined primitives. It stages repaired copies under an output directory and validates against the selected standard version (0.2.0 by default or 0.1.0 when pinned). The skill applies only safe, deterministic fixes and stops when validation gates fail or manual input is needed.

When to use it

  • USD assets fail FET_000_STANDARD Core feature validation checks
  • Converting CAD or URDF files to SimReady-conformant USD assets
  • Repairing portable naming, path resolution, and metadata issues
  • Preparing assets for robot or prop SimReady profiles

When not to

  • Asset failures are in higher-level features beyond Core conformance
  • Physics runtime variants (use FET_000_PHYSX, FET_000_NEWTON, or FET_000_MUJOCO)
  • In-place mutation of source assets is required without staging

Install

These commands install from the publisher's repository and need no account.

skills CLI

npx skills add nvidia/simready-foundation --skill simready-foundation-conform-fet-000-standard

Installs from the repository's default branch, which may have changed since the commit we checked.

GitHub CLI 2.90 or later

gh skill install nvidia/simready-foundation simready-foundation-conform-fet-000-standard@60b8bddb086f43c8cc394f50635b4e65b0ec36fd

Installs the commit we checked (60b8bdd).

Copy by hand

Download the folder at 60b8bdd and put it in .claude/skills/simready-foundation-conform-fet-000-standard for Claude Code and in .agents/skills/simready-foundation-conform-fet-000-standard for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.

Skill folder on GitHub at 60b8bdd

Claude Code plugin

/plugin install nvidia-skills@claude-plugins-official

The publisher's plugin in Claude's official marketplace. It may hold more than this skill, and we have not pinned it.

Copy for your agent

A prompt for any coding agent. It installs this skill from GitHub at the pinned commit, copies the files as they are, and runs nothing unless you ask.

Prompt

Install the agent skill "simready-foundation-conform-fet-000-standard" by NVIDIA.

Source, pinned to commit 60b8bddb086f43c8cc394f50635b4e65b0ec36fd:
https://github.com/nvidia/simready-foundation/tree/60b8bddb086f43c8cc394f50635b4e65b0ec36fd/skills/simready-foundation-conform-fet-000-standard

1. Download that folder at exactly this commit. Do not use the default branch.
2. Copy every file unchanged, keeping the folder structure, into .claude/skills/simready-foundation-conform-fet-000-standard/ for Claude Code and .agents/skills/simready-foundation-conform-fet-000-standard/ for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode. Create the folders if they do not exist.
3. Do not edit the files, and do not run any script in the folder unless I ask you to.
4. When you are done, list the files you copied and where you put them.

Listing and checks: https://www.agentnative.dev/skills/nvidia/simready-foundation-conform-fet-000-standard

SKILL.md at the pin

---
name: simready-foundation-conform-fet-000-standard
description: "Use for repairing FET_000_STANDARD Core failures (default `0.2.0`; use `0.1.0` when a profile pins it): asset file naming, directory layout, relative and resolvable paths, SimReady metadata, and undefined prims."
license: Apache-2.0
metadata:
  author: "Shaad Boochoon <sboochoon@nvidia.com>"
  tags:
    - simready
    - conformance
    - core
---


# SimReady Conform FET_000_STANDARD

## Purpose
Use this workflow skill to bring an existing USD asset into conformance with the selected `FET_000_STANDARD` Core feature contract, then hand the repaired copy back to profile validation.

Default to `FET_000_STANDARD@0.2.0` when the user asks for this feature without a version. Use `0.1.0` when the profile, validation report, or user explicitly pins it.

`FET_000_STANDARD` is the baseline Standard/OpenUSD Core feature. It verifies that an asset has portable file naming, directory layout, path handling, resolvable asset paths, and no unsafe undefined prims before higher-level visual, material, physics, robot, or runtime-specific features are applied. Version `0.1.0` includes `NP.006` and the original root-layer-only `SR.001`. Version `0.2.0` omits both. Nested provenance is `SR.003` on `FET_033_STANDARD@0.3.0`. USD/sidecar provenance union is `SR.004` on `FET_033_STANDARD@0.4.0`.

This skill is not the final validator and should not silently mutate source assets. It stages a repaired USD-family asset under the requested output directory, applies deterministic fixes only where safe, and stops when a validation gate still fails or a manual decision is required.

## Prerequisites

Read the source-of-truth files named below before editing. Work on staged outputs where the skill requires them, and keep validation evidence with the result.

## Source of Truth

Before changing an asset, load the exact `FET_000_STANDARD` manifest selected by the profile. In this repo, start with the canonical version:

- `nv_core/tiers/simready_foundation_tier_core/simready/foundation/tier_core/features/FET_000_STANDARD-0.2.0.json` (latest)
- `nv_core/tiers/simready_foundation_tier_core/simready/foundation/tier_core/features/FET_000_STANDARD-0.1.0.json` (preserved)
- `nv_core/tiers/simready_foundation_tier_core/simready/foundation/tier_core/features/FET_000_STANDARD.md`

This feature has no dependencies. Authoritative requirement lists:

| Version | Requirements |
|---|---|
| `0.1.0` | `NP.002`, `NP.003`, `NP.004`, `NP.005`, `NP.006`, `NP.007`, `NP.008`, `SR.001`, `HI.010` |
| `0.2.0` | `NP.002`, `NP.003`, `NP.004`, `NP.005`, `NP.007`, `NP.008`, `HI.010` |

If the selected profile names a newer `FET_000_STANDARD` version, use that manifest instead. Treat the JSON requirement list as authoritative when markdown and JSON disagree.

`FET_000_STANDARD` is the neutral Core feature and does not require physics
runtime variants. Runtime physics variant scaffolding (the `RV.*` Runtime
Variants requirements) lives in the separate runtime Core features
`FET_000_PHYSX`, `FET_000_NEWTON`, and `FET_000_MUJOCO`; repair those with their
own runtime-specific handling, not this Standard skill.

Because those runtime features layer runtime payloads on top of this neutral
base, keep the base **runtime-agnostic**: it carries only neutral
`UsdPhysics`/`physics:*` data and geometry (no `Physx*`/`Newton*`/`Mjc*`
schemas or `physx*:`/`newton:*`/`mjc:*` attributes), and it must not pin
`physics:approximation` to a runtime-specific value — never `sdf` on the base.
Leave `physics:approximation` unauthored on the neutral base so each runtime
payload can set its own value (a local base opinion outranks the payload arc in
LIVRPS and would leak into every runtime selection). See
`nv_core/tiers/simready_foundation_tier_core/simready/foundation/tier_core/capabilities/core/runtime_variants/runtime-physics-isolation-matrix.md`.

For per-requirement repair details, read `references/fet-000-standard-requirements.md` when a `FET_000_STANDARD` validation report or inspection identifies matching failures.

## Inputs

Collect these before editing:

| Input | Requirement |
|---|---|
| `usd_asset` | Required `.usd`, `.usda`, `.usdc`, or unpacked USD-family asset to repair. |
| `output_root` | Required or inferred folder for staged assets and reports. |
| `simready_profile` | Profile being validated, such as `Robotics-Prop`, `Robot-Body`, or `Robot-Gripper`. |
| `profile_version` | Profile version, if supplied by the user or validation command. |
| `validation_report` | Preferred JSON or markdown report from the failing profile/feature validation gate. |
| `source_asset` | Original CAD, DCC, URDF, MJCF, or conversion input path, used for provenance metadata. |
| `asset_name` and `asset_type` | Use explicit user values when provided; otherwise infer conservative defaults from the asset path and profile. |

## Instructions

Use this checklist when changing the repository:

1. Confirm the input asset exists and record the original path.
2. Parse the validation report when available. If no report exists, run the same profile or feature validation gate first when the local tooling is available.
3. Filter to the selected `FET_000_STANDARD` version failures and the requirement IDs listed in that manifest. Do not repair unrelated feature failures in this skill.
4. Create a staged output folder under `output_root`, using safe lowercase path components.
5. Copy or export the input asset into the staged folder. Do not overwrite the source asset unless the user explicitly asks for in-place repair.
6. Apply fixes in this order:
   - Path and layout fixes for `NP.002`, `NP.003`, `NP.004`, and `NP.005`.
   - Metadata fixes for `SR.001` and `NP.006` only when the selected version is `0.1.0`. If the only Core failure is metadata and the Physical AI Skill Hub commands are available, prefer `apply-simready-foundation-metadata` over hand-editing.
   - Composition and asset path fixes for `NP.007` and `NP.008`.
   - Undefined prim cleanup for `HI.010` only when the affected over can be safely resolved or removed.
7. Rerun the same validation gate that failed, or the narrowest available `FET_000_STANDARD` validation gate for the selected version.
8. Summarize the stage as passed, failed, skipped, or blocked. Stop at the first remaining failing validation gate unless the user asks for best-effort continuation.

## Examples

Example request:

```text
Repair FET_000_STANDARD failures on a USD asset, including Core metadata and naming/path issues.
```

Expected result summary:

```text
staged_asset: repaired copy or output directory
validation: selected feature/profile gate and report path
remaining_failures: next failing requirement IDs, if any
```

## Repair Policy

Make automatic repairs only when the intended result is mechanical and portable:

- Rename copied files and folders to satisfy the Core naming and path rules.
- Place the main USD file at `asset_root/<intermediate>/<asset_file>.usd*` when repairing `NP.005`.
- For `SR.001` (`0.1.0` only), author `SimReady_Metadata`, `asset_name`, `asset_type`, `source_file`, and `usd_date_generated` directly in root-layer `customLayerData`.
- Rewrite absolute asset paths to relative paths only when the referenced file exists and is inside the staged asset root, or when it is safe to copy/package the dependency into the staged asset root.

Block and report instead of guessing when:

- A required dependency cannot be found.
- A path points outside the asset package and copying it would change ownership or licensing assumptions.
- An undefined prim might be a legitimate composition override after a missing reference is restored.
- Metadata values would require domain knowledge the user did not provide.
- Repairing one requirement would invalidate a higher-priority profile requirement.

## Metadata Defaults

When explicit values are unavailable, use conservative defaults:

| Field | Default |
|---|---|
| `asset_name` | Safe stem of the staged USD asset or asset root folder. |
| `asset_type` | `robot` for robot profiles, `prop` for prop profiles, otherwise `asset`. |
| `source_file` | `source_asset` when supplied; otherwise the original input asset path. |
| `usd_date_generated` | Current date in `YYYY-MM-DD` format at repair time. |

Author these fields at the top level of `customLayerData` and also include
the `SimReady_Metadata` key.

## Tested Metadata Repair

For a converted CAD asset that fails `FET_000_STANDARD@0.1.0` only on metadata (`SR.001` / `NP.006`), this command shape has been forward-tested:

```bash
uv run --python 3.12 apply-simready-foundation-metadata <usd-asset> \
  --output-dir <output-root>/<asset-name>/simready_usd \
  --profile <profile> \
  --profile-version <version> \
  --source-asset <source-asset> \
  --pipeline-step convert-cad-to-usd \
  --report <output-root>/apply-simready-foundation-metadata.json \
  --markdown-report <output-root>/apply-simready-foundation-metadata.md
```

Expected repair outputs:

- A staged copy of the USD asset under `<asset-name>/simready_usd/`.
- Root layer `customLayerData['SimReady_Metadata']`.
- A same-directory sidecar JSON file.

After rerunning profile validation, count this skill as successful when the selected `FET_000_STANDARD` version passes, even if the full profile still fails on non-Core features such as units, rigid bodies, multibody physics, or grasp vectors. Report those remaining feature failures as handoff work for their own skills.

## Validation Handoff

Preserve reports under the staged output directory. If the Physical AI Skill Hub validation commands are available, the normal handoff is:

```bash
uv run --python 3.12 validate-simready-profile <staged-usd> \
  --profile <profile> \
  --profile-version <version> \
  --report <output-root>/validation/fet-000-standard-after-repair.json
```

If those commands are not available, use the SimReady Foundations validator entrypoint configured in this checkout or inspect the relevant requirement validators directly. Always say which validation path was used.

## Limitations

- Do not silently mutate the source asset; work on the requested staged output.
- Do not hide later profile failures after the selected feature gate passes or fails.
- Do not invent geometry, metadata, or runtime behavior that conflicts with the asset intent.

## Troubleshooting

- Error: validation tooling is unavailable. Solution: run the narrowest available USD or static check and report the gap.
- Error: a repair would change asset intent. Solution: stop and ask for direction or stage the smallest reversible edit.
- Error: later profile gates still fail. Solution: report the next failing feature and hand off to the matching conformance skill.

## Resources

- `assets/openai.yaml` preserves optional UI metadata for clients that read skill display hints. It is not required for the workflow.
- `references/` contains detailed requirement notes; load only the files needed for the active validation failure.

## Summary Format

Report:

| Field | Meaning |
|---|---|
| `input_usd_path` | Original USD path. |
| `output_usd_path` | Latest staged/repaired USD path. |
| `profile` and `profile_version` | Validation target. |
| `requirements_repaired` | Requirement IDs changed by this skill. |
| `requirements_blocked` | Requirement IDs that need user or upstream data. |
| `validation_report` | Path to the rerun validation report. |
| `next_step` | Usually rerun the full selected profile validation. |

Keep the user-facing summary short: what was fixed, what still fails, and the first validation gate that blocks progress.

From nvidia/simready-foundation at 60b8bdd, shown as plain text under its license: Apache-2.0 (permissive). The license text is in skills/simready-foundation-conform-fet-000-standard/SKILL.md.

View SKILL.md on GitHub at 60b8bdd

Files

4 files, 20 KB in total. Each file has a sha256 in the pin's manifest; the first 12 characters are shown.

Skill folder on GitHub at 60b8bdd
All 50 skills from NVIDIA

More from NVIDIA

  • error-explainer

    This skill helps the agent understand and explain compiler and runtime errors.

    Claude Code, Codex, Cursor +4 · about 66 tokens · pinned 6 days ago

  • order-lookup

    This skill retrieves and modifies individual orders in an e-commerce system.

    Claude Code, Codex, Cursor +4 · about 100 tokens · pinned 6 days ago

  • debug-openshell-cluster

    Diagnoses OpenShell gateway deployment problems across Docker, Podman, Kubernetes, and VM compute platforms.

    Claude Code, Codex, Cursor +4 · about 19.1K tokens · pinned 6 days ago

  • nemo-automodel-model-onboarding

    This skill guides adding or modifying model architecture support in NeMo AutoModel, covering discovery of model type from config, implementation of custom…

    Claude Code, Codex, Cursor +3 · about 5.6K tokens · pinned 6 days ago

  • nvflare-convert-lightning

    Converts existing PyTorch Lightning training code into an NVFLARE federated learning job by patching the trainer with the Lightning Client API, configuring…

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 3K tokens · pinned 6 days ago

  • nvflare-convert-pytorch

    Converts existing plain PyTorch training code into NVFLARE federated learning jobs using the Client API for model exchange, local validation, and job export.

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 2.5K tokens · pinned 6 days ago

All Coding workflow skills
  • planning

    This skill orchestrates multi-workflow projects with dependencies and shared data tables by creating a task graph in the orchestrator via the create-tasks tool.

    by n8nOfficial publisher

    Claude Code, Codex, Cursor +3 · about 2.4K tokens · pinned 6 days ago

  • progressive-building

    This skill implements incremental workflow development for agents building or extending workflows.

    by n8nOfficial publisher

    Claude Code, Codex, Cursor +3 · about 1.4K tokens · pinned 6 days ago

  • workflow-builder

    Builds and edits n8n workflows using the TypeScript SDK.

    by n8nOfficial publisher

    Claude Code, Codex, Cursor +3 · about 14.2K tokens · pinned 6 days ago

  • remotion-upgrade

    This skill upgrades Remotion and its related packages to the latest stable version.

    by RemotionOfficial publisher

    Claude Code, Codex, Cursor +3 · about 460 tokens · pinned 6 days ago

  • remotion-upgrade

    This skill upgrades Remotion and related packages across a project, automatically detecting the package manager and workspaces.

    by RemotionOfficial publisher

    Claude Code, Codex, Cursor +3 · about 460 tokens · pinned 6 days ago

  • final-release-review

    Audits Python SDK release candidates or plans against the previous release, comparing diffs for regressions, API changes, and version compatibility.

    by OpenAIOfficial publisher

    Contains scripts

    Claude Code, Codex, Cursor +3 · about 5.4K tokens · pinned 6 days ago

The skills listed here are third-party software, collected from public GitHub repositories as a catalog of recent skills and provided as is. Agent Native does not write or control them and is not responsible for any harm, loss or damage caused by installing or using them. Labels and checks describe what we saw at one commit and are not a guarantee. Read a skill's files before you run it. Terms of use