NVIDIAKnown publisherNVIDIA/simready-foundation/.agents/skills/simready-foundation-conform-fet-004-robot-mujoco/SKILL.md

simready-foundation-conform-fet-004-robot-mujoco

Skill156 starsChanged 53 days agoApache-2.0View on GitHub

Use for repairing exact FET_004_ROBOT_MUJOCO SimReady conformance for robot MuJoCo multibody physics, including MuJoCo collider requirements and robot joint topology. Use when a profile, validation report, or user request names FET_004_ROBOT_MUJOCO; default to version `0.1.0` unless pinned otherwise.

In this repository241 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 3 are distinctive, and 4 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Use this exact feature skill when the selected profile, validation report, or user request names FET_004_ROBOT_MUJOCO.
line 17
Very specific:
Default to FET_004_ROBOT_MUJOCO@0.1.0 when no version is specified.
line 19
Distinctive:
Before changing an asset or package, read:
line 23
Very specific:
When the input already conforms to the neutral base feature, prefer the deterministic feature adapter to author the runtime-specific data …
line 37
Distinctive:
Create or use a staged output location unless the user explicitly asks for in-place edits.
line 50
Distinctive:
Do not create geometry to pass this feature.
line 51
Very specific:
Use MjcCollisionAPI and MuJoCo mesh collision attributes only where required by the selected contract.
line 53

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

SimReady Conform FET_004_ROBOT_MUJOCO

Purpose

Use this exact feature skill when the selected profile, validation report, or user request names FET_004_ROBOT_MUJOCO. It repairs robot-specific MuJoCo multibody conformance without creating new geometry.

Default to FET_004_ROBOT_MUJOCO@0.1.0 when no version is specified.

Source of Truth

Before changing an asset or package, read:

nv_core/tiers/simready_foundation_tier_core/simready/foundation/tier_core/features/FET_004_ROBOT_MUJOCO-0.1.0.json
nv_core/tiers/simready_foundation_tier_core/simready/foundation/tier_core/features/FET_004_ROBOT_MUJOCO.md
MuJoCo rigid-body requirement docs linked from FET_003_MUJOCO.md when collider failures are reported

Feature Versions

Version	Dependencies	Requirements
`0.1.0`	None	Robot rigid-body, joint, articulation, nested-body, and MuJoCo collider requirements listed in `FET_004_ROBOT_MUJOCO-0.1.0.json`

Feature Adapter

When the input already conforms to the neutral base feature, prefer the deterministic feature adapter to author the runtime-specific data first (via the workspace upgrade command; see nv_core/sr_specs/docs/guides/feature_adapters/feature_adapters.md), then repair only the residual requirements below.

Adapter module	Adapter	Transition	Authors
`nv_core/cip_specs/asset_handler_modules/neutral_to_mujoco`	`rigid_body_neutral_to_robot_mujoco`	`FET_003_STANDARD@0.1.0` -> `FET_004_ROBOT_MUJOCO@0.1.0`	Mesh extents; `MjcCollisionAPI` (+`mjc:group`) / `MjcMeshCollisionAPI` with `physics:approximation = "convexHull"` on existing colliders.

The adapter runs on a staged output stage and never creates geometry, joints, or articulation topology; it only annotates existing colliders.
The robot rigid-body, JT.*, articulation, and nested-body requirements require existing robot link/joint topology and must be repaired manually per the Workflow below.

Workflow

Identify the exact selected feature/version from the profile TOML, validation report, or user request.
Load the selected manifest, feature markdown, and failing requirement docs before editing.
Create or use a staged output location unless the user explicitly asks for in-place edits.
Do not create geometry to pass this feature; use existing robot link geometry and hierarchy.
Preserve the robot link/joint topology and repair USD physics schemas, relationships, articulation APIs, masses, and MuJoCo collider schemas.
Use MjcCollisionAPI and MuJoCo mesh collision attributes only where required by the selected contract.
Rerun the narrowest available validation gate and report any missing MuJoCo runtime evidence.

Report Fields

Field	Meaning
`feature`	Exact feature ID and version, for example `FET_004_ROBOT_MUJOCO@0.1.0`.
`input`	Source asset, package root, or package definition inspected.
`output`	Staged output path, or `in-place` only when explicitly requested.
`requirements_repaired`	Requirement IDs repaired in this pass.
`validation`	Command or inspection used to verify this exact feature.
`status`	`passed`, `failed`, `skipped`, or `blocked`.
`next_step`	The next exact feature skill or runtime evidence needed.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free