omniverse-usd-performance-tuning

Top-level workflow skill for USD performance diagnosis and optimization. Handles slow loading, high memory, low FPS, and broad scene-optimization requests; delegates auth/runtime setup to Phase 0 owners.

Quality

67%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./skills/omniverse-usd-performance-tuning/SKILL.md

Quality

Content

81%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.

The content is a well-structured orchestrator skill body: lean, directive, and rich with concrete invariants, validation checkpoints, and a clearly sequenced plan contract. Its only notable weakness is reference nesting that goes beyond the recommended one level deep.

Dimension	Reasoning	Score
Conciseness	The body is dense, directive, and free of concept-explanation fluff — it assumes Claude knows USD and Omriverse concepts and spends tokens on policy and invariants rather than background, with only minor passages that could be tightened.	4 / 5
Actionability	It gives concrete, executable guidance: exact profile labels ('profile-stage:baseline/after'), specific operation names, real referenced file paths, and an explicit ordered subsequence, though as an orchestrator skill it is policy/instruction-heavy rather than copy-paste code.	4 / 5
Workflow Clarity	It provides a clearly sequenced plan contract with conditionally-required milestones, validate-before-and-after-mutation rules, evidence-based gating, blocker codes, and explicit final-response/report requirements — strong validation checkpoints for destructive and batch operations.	5 / 5
Progressive Disclosure	The SKILL.md is an overview pointing to one-level references (workflow.md, operations.json, report templates) with all cited paths verified real, but the bundle contains files nested up to four levels deep and the body cites some two-level paths, exceeding the ideal one-level-deep structure.	4 / 5
	Total	17 / 20 Passed

Description

53%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.

The description clearly identifies the skill's USD performance niche and lists concrete symptom triggers, giving it strong distinctiveness. Its main weakness is the absence of an explicit 'Use when...' trigger clause and limited keyword variations, which cap completeness and trigger-term quality at 3.

Suggestions

Add an explicit 'Use when...' clause naming the trigger situations (e.g. 'Use when a USD scene loads slowly, runs at low FPS, uses excessive memory, or needs optimization').

Broaden trigger-term coverage with synonyms and extensions users actually say (e.g. 'frame rate', 'memory usage', '.usd/.usda/.usdc files', 'Omniverse Kit FPS').

Reframe symptom areas as concrete optimization actions (profiling, dedupe, decimation, primitive fitting, restructure) to lift specificity toward comprehensive coverage.

Dimension	Reasoning	Score
Specificity	Names the USD performance domain plus concrete symptom areas ('slow loading, high memory, low FPS, and broad scene-optimization requests'), but frames capabilities as problem categories rather than enumerating distinct optimization operations, so coverage is solid yet not comprehensive.	3 / 5
Completeness	The 'what' is clear (USD performance diagnosis and optimization) but 'when' is only weakly implied through the symptom list with no explicit trigger guidance, so per the missing-'Use when' guideline it caps at 3.	3 / 5
Trigger Term Quality	It surfaces a few natural user phrases ('slow loading', 'high memory', 'low FPS') but lacks synonyms, file extensions, and a 'Use when...' trigger clause, leaving common variations missing.	3 / 5
Distinctiveness Conflict Risk	It is scoped tightly to USD/Omniverse performance with a distinct symptom trigger set and minimal overlap with other skills; only minor overlap risk with general profiling skills keeps it just below 5.	4 / 5
	Total	13 / 20 Passed

Validation

75%

Warnings & errors only

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

Criteria	Description	Result
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, 4 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: NVIDIA/skills
Path: skills/omniverse-usd-performance-tuning/SKILL.md
Commit: 20bb6aa

Reviewed: 3 days ago

Table of Contents

Discovery Implementation Validation

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.