CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

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.

65

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Critical

Do not install without reviewing

The canonical home for this skill is omniverse-cad-to-simready in NVIDIA/skills

SKILL.md
Quality
Evals
Security

Quality

Content

73%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A strong orchestrator skill: the workflow is unambiguous, gated, and equipped with feedback loops and a genuinely useful troubleshooting table. Its main cost is redundancy — deployment-ordering and stop-at-first-failure rules are repeated across four sections — plus repo-meta content that dilutes the operational core.

Suggestions

State the 'deploy Content Agents first' and 'stop at the first failing gate' rules once in Hard Rules and reference them from First Action, Instructions, and Limitations instead of repeating them verbatim in each section.

Move the 'Publishing Layout Notes' section into a reference file (e.g. a publishing/README) — it concerns repo layout, not workflow execution, and adds ~15 lines of context cost to every invocation.

Show one representative stage command inline in Instructions step 3 or 5 (e.g. the preflight invocation from `references/commands.md`) so the first executable action is copy-paste ready before the reader must open commands.md.

DimensionReasoningScore

Conciseness

The body is operational rather than educational — no padding explaining USD or CAD concepts — but the deployment-first and stop-at-first-failure rules are restated in 'First Action', 'Instructions', 'Limitations', and twice in 'Hard Rules', and the 'Publishing Layout Notes' section is repo-meta content irrelevant to executing the workflow.

3 / 5

Actionability

The 14 numbered steps name concrete stage references, env vars, gate order, and exact repair commands (e.g. the `docker exec --user root ... chmod -R a+rX` fix), with invocations delegated to the well-signaled `references/commands.md`; the body itself shows few literal command lines, leaving minor gaps.

4 / 5

Workflow Clarity

Steps 1–14 are explicitly sequenced with validation gates in a fixed order (`validate-usd-minimum`, then the four profile validators), an explicit repair feedback loop (rerun `simready-conform-profile` on `simready-validate` findings), and clear blocked/failed/needs_rerun dispositions with stop conditions.

5 / 5

Progressive Disclosure

'Detailed References' clearly signals four one-level-deep references (all verified to exist in the bundle) with per-file descriptions and a 'read only what you need' rule, but the actual bundle nests 2–3 levels (e.g. `convert-to-usd/references/usd-convert-cad/README.md`) and some inline material (Publishing Layout Notes) would fit better in a reference file.

4 / 5

Total

16

/

20

Passed

Description

88%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A well-crafted description that concretely states capabilities, triggers, and the orchestrator's scope in third person, with explicit use-when phrasing. Only weakness is thin coverage of source-format synonyms and file extensions that users would naturally mention.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'conversion, material/physics assignment, SimReady conformance, validation, and optional package creation' plus 'deploy or verify Content Agents services first' — in third person ('Coordinate'), with no vague filler.

5 / 5

Completeness

Explicitly answers what ('Coordinate the end-to-end CAD/source-asset to SimReady workflow...') and when ('Use for broad requests such as CAD to SimReady, source asset to simulation-ready USD, or prop packaging') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural user phrasings are present ('CAD to SimReady', 'source asset to simulation-ready USD', 'prop packaging'), but common variations and file extensions users would say are missing (.step/.stp, URDF, OBJ, mesh).

4 / 5

Distinctiveness Conflict Risk

The CAD-to-SimReady orchestrator niche is clear and it explicitly distinguishes broad end-to-end requests from the single-stage skills it routes to ('route single-stage work through nested references'), but the generic words 'conversion' and 'validation' carry some overlap risk with those sibling stage skills.

4 / 5

Total

18

/

20

Passed

Validation

75%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 12 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

referenced_paths_exist

Referenced path issues: 1 missing, 2 deeper-than-1-level

Warning

Total

12

/

16

Passed

Repository

openai/plugins

Path

plugins/nvidia/skills/omniverse-cad-to-simready/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.