simready-foundation-conform-fet-007-standard
This skill repairs non-visual sensor material attributes on USD assets to meet the FET_007_STANDARD specification version 0.2.0.
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 3,000 tokenswhen the skill loads
- GitHub stars
- 95on nvidia/simready-foundation
- Scripts
- None found
What it does
“Use for repairing SimReady nonvisual sensor material attributes on bound USD materials.”
Generated summary from the skill's own text
This skill repairs non-visual sensor material attributes on USD assets to meet the FET_007_STANDARD specification version 0.2.0. It classifies materials for radar, lidar, thermal, and other RTX sensor simulations by authoring base material, coating, and attribute tokens on bound UsdShade.Material prims. The skill inspects source material evidence, applies semantic classifications from an approved value list, validates repairs against the specification, and reports blocked cases requiring user judgement or missing material data.
When to use it
- Asset validation reports show FET_007_STANDARD failures on non-visual materials.
- Profile or user request explicitly targets FET_007_STANDARD conformance.
- Sensor material semantics need authoring or repair on USD props.
- Robot simulation requires accurate radar, lidar, or thermal material response.
When not to
- Asset has no bound visual materials to base classification on.
- Material class is outside the current FET_007_STANDARD allowed value list.
- Real material is ambiguous or multiple valid sensor classes apply equally.
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-007-standardInstalls 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-007-standard@60b8bddb086f43c8cc394f50635b4e65b0ec36fdInstalls the commit we checked (60b8bdd).
Copy by hand
Download the folder at 60b8bdd and put it in .claude/skills/simready-foundation-conform-fet-007-standard for Claude Code and in .agents/skills/simready-foundation-conform-fet-007-standard for Codex, Cursor, Gemini CLI, GitHub Copilot and OpenCode.
Claude Code plugin
/plugin install nvidia-skills@claude-plugins-officialThe 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-007-standard" by NVIDIA. Source, pinned to commit 60b8bddb086f43c8cc394f50635b4e65b0ec36fd: https://github.com/nvidia/simready-foundation/tree/60b8bddb086f43c8cc394f50635b4e65b0ec36fd/skills/simready-foundation-conform-fet-007-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-007-standard/ for Claude Code and .agents/skills/simready-foundation-conform-fet-007-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-007-standard
SKILL.md at the pin
---
name: simready-foundation-conform-fet-007-standard
description: "Use for repairing SimReady nonvisual sensor material attributes on bound USD materials."
license: Apache-2.0
metadata:
author: "Shaad Boochoon <sboochoon@nvidia.com>"
tags:
- simready
- conformance
- materials
---
# SimReady Conform FET_007_STANDARD Nonvisual Materials
## Purpose
Use this workflow skill when the selected profile, validation report, or user request targets `FET_007_STANDARD@0.2.0` non-visual sensor material attributes. FET_007_STANDARD authors and repairs sensor-facing material classification on bound `UsdShade.Material` prims so radar, lidar, thermal, and related RTX sensor simulations can reason about surfaces beyond visible shader appearance.
This is a material-semantics repair skill, not a shader-generation skill. Work on a staged copy under the requested output directory, preserve existing visual material bindings, and stop at the first FET_007_STANDARD issue that needs material identity or user judgement.
FET_007_STANDARD is optional in the consolidated Robotics-Prop profile and is not part of the default prop robotics profile sequence. When a profile does not include FET_007_STANDARD, run this skill only when the user explicitly asks for non-visual sensor material conformance or supplies a profile/workflow that includes `FET_007_STANDARD`.
## 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 selected FET_007_STANDARD manifest and requirement docs:
- `nv_core/tiers/simready_foundation_tier_core/simready/foundation/tier_core/features/FET_007_STANDARD-0.2.0.json`
- `nv_core/tiers/simready_foundation_tier_core/simready/foundation/tier_core/features/FET_007_STANDARD.md`
- `nv_core/tiers/simready_foundation_tier_core/simready/foundation/tier_core/capabilities/nonvisual_sensors/nonvisual_materials/capability-nonvisual_materials.md`
- `nv_core/tiers/simready_foundation_tier_core/simready/foundation/tier_core/capabilities/nonvisual_sensors/nonvisual_materials/requirements.md`
- `nv_core/tiers/simready_foundation_tier_core/simready/foundation/tier_core/capabilities/nonvisual_sensors/nonvisual_materials/validation.py`
Treat the selected JSON manifest as authoritative for the required IDs. If the markdown, manifest, validator, or report disagree on allowed values or requirement behavior, follow the current validation report and call out the mismatch in the stage summary.
For per-requirement repair details, read `references/fet007-requirements.md` when a FET_007_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, if one includes FET_007_STANDARD. |
| `profile_version` | Profile version, if supplied by the user or validation command. |
| `validation_report` | Preferred JSON or markdown report from the failing profile or feature validation gate. |
| `fet007_feature` | Selected feature ID and version, currently `FET_007_STANDARD@0.2.0`. |
| `material_evidence` | Source DCC material metadata, visual material names, shader parameters, property reports, render review, or user-supplied material classifications. |
| `classification_policy` | User-approved defaults or mappings for unknown materials, coatings, and special attributes. |
## Instructions
Use this checklist when changing the repository:
1. Confirm the input asset exists and determine whether FET_007_STANDARD is actually selected by the profile or explicitly requested by the user.
2. Parse the validation report and filter to FET_007_STANDARD/NVM failures. Do not repair visual shader, texture, rigid-body, physics-material, or grasp issues in this skill.
3. Load the selected FET_007_STANDARD manifest version and the requirement repair map.
4. Create a staged output folder under `output_root`; do not mutate the source unless the user explicitly asks for in-place repair.
5. Inspect the stage before editing:
- default prim and composed payload/reference boundaries
- renderable `UsdGeom.Gprim` and `UsdGeom.Subset` prims with computed purpose `default` or `render`
- computed full-purpose material bindings for those prims
- bound and unbound `UsdShade.Material` prims
- existing `omni:simready:nonvisual:base`, `omni:simready:nonvisual:coating`, and `omni:simready:nonvisual:attributes`
- time samples on those attributes
- visual material evidence such as shader metallic, opacity, diffuse color, material names, texture names, and source DCC metadata
6. Decide the non-visual material classification before authoring:
- Use explicit source or user-supplied material labels first.
- Use strong visual-material evidence only when the mapping is obvious and allowed by the current validator.
- Use user-approved defaults for generic classes such as `plastic`, `steel`, `rubber`, `wood`, `fabric`, or `clear_glass`.
- Block when the real material is not representable by the allowed values, or when multiple classes are plausible.
7. Apply repairs in this order:
- Remove, move, or bind orphaned non-visual material attributes only when the material-binding intent is clear.
- Add or fix `omni:simready:nonvisual:base` from explicit material evidence.
- Add or fix `omni:simready:nonvisual:coating`, defaulting to `none` only when no coating evidence exists and that policy is approved.
- Add or fix `omni:simready:nonvisual:attributes`, using `["none"]` or an empty token array only when no special sensor attributes are intended by policy.
- Remove time samples from non-visual attributes only after preserving one intended default value.
- Re-check consistency with the visual material semantics.
8. Rerun the same validation gate when a profile includes FET_007_STANDARD, or the narrowest available Foundation/OAV capability check for non-visual materials. If no executable FET_007_STANDARD gate is available, report the USD inspection results and the validation gap.
9. Summarize the stage as passed, failed, skipped, or blocked. Stop when FET_007_STANDARD passes or the next FET_007_STANDARD failure requires material identity, sensor-response policy, visual review, or source-material data.
## Examples
Example request:
```text
Repair FET_007_STANDARD nonvisual sensor material attributes on a USD asset.
```
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 locally verifiable:
- Fix attribute type names to `token` or `token[]` when the value is already valid.
- Replace invalid token values with a clear approved mapping from source material evidence.
- Remove time samples and author a default value when one sampled value is clearly the intended static material label.
- Move non-visual attributes from an unbound duplicate material to the bound material only when the duplicate relationship is obvious.
- Remove non-visual attributes from a clearly orphaned scratch material only when that material is not referenced or bound.
Block and report instead of guessing when:
- A material has no reliable source classification.
- A visual material name or shader color is too generic to identify a sensor material class.
- The asset material is outside the current allowed FET_007_STANDARD value list.
- The validator and docs disagree and the repair would risk making sensor semantics less truthful.
- A material appears visually inconsistent with the proposed non-visual class.
- The staged asset has no bound visual materials and the user did not ask to create visual materials first.
## Classification Guidance
FET_007_STANDARD values are semantic labels, not visual decoration. Do not choose them just to satisfy the validator.
Use the current validator value list for pass/fail decisions. Notable current values include:
- Base examples: `aluminum`, `steel`, `oxidized_steel`, `iron`, `plastic`, `rubber`, `wood`, `fabric`, `leather`, `clear_glass`, `frosted_glass`, `concrete`, `brick`, `stone`, `water`, `snow`, `ice`, `calibration_lambertian`
- Coating values: `none`, `paint`, `clearcoat`, `paint_clearcoat`
- Attribute values: `none`, `emissive`, `retroreflective`, `single_sided`, `visually_transparent`
Common consistency checks:
- Metallic visual materials should map to a metal base such as `steel`, `aluminum`, `iron`, `brass`, or `bronze`.
- Transparent visual materials should usually use a glass-like base and include `visually_transparent`.
- Painted materials should use a base material plus `paint` or `paint_clearcoat`.
- Rubber-like dark flexible surfaces should use `rubber`, not generic `plastic`, when evidence supports it.
- Emissive visual materials should include `emissive`; road reflectors and similar objects may include `retroreflective`.
## Validation Handoff
Preserve reports under the staged output directory. If a selected profile includes FET_007_STANDARD and the Physical AI Skill Hub validation commands are available, use the same profile gate that exposed the failure:
```bash
uv run --python 3.12 validate-simready-profile <staged-usd> \
--profile <profile> \
--profile-version <version> \
--foundation-root <simready-foundation-root> \
--foundation-spec-root <simready-foundation-root>/nv_core/sr_specs/docs \
--report <output-root>/simready-profile-after-fet007.json
```
If no selected profile includes FET_007_STANDARD, do not mutate a profile TOML file just to test the skill. Run the available non-visual materials capability validator directly if the local environment exposes it; otherwise report the deterministic USD inspection and note that profile validation cannot exercise FET_007_STANDARD until a profile selects it.
## 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, if any. |
| `fet007_feature` | Selected FET_007_STANDARD feature ID and version. |
| `material_evidence` | Source used for non-visual classification. |
| `classified_materials` | Bound material prims and authored base/coating/attribute values. |
| `unbound_material_repairs` | Orphaned attribute fixes or bindings changed for NVM.004. |
| `time_sample_repairs` | Attributes changed for NVM.006. |
| `requirements_repaired` | Requirement IDs changed by this skill. |
| `requirements_blocked` | Requirement IDs that need material identity, source data, or user judgement. |
| `validation_report` | Path to the rerun validation or inspection report. |
| `next_step` | Usually run FET_007_STANDARD-capable validation or collect missing material evidence. |
Keep the user-facing summary short: which materials were classified, what evidence justified the values, what validation could run, and what remains blocked.
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-007-standard/SKILL.md.
View SKILL.md on GitHub at 60b8bddFiles
- SKILL.md12 KB · 742de26075d7
- assets/
- openai.yaml457 B · 22989a839151
- evals/
- evals.json1.6 KB · fa6222e7924f
- references/
- fet007-requirements.md6.1 KB · fe3a1d268dc6
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 60b8bddMore 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
Related in Coding workflow
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