omniverse-usd-performance-tuning

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

Quality

88%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Quality

Content

77%Weight 40%Scale 1-3

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

The body is a strong, well-structured orchestrator with actionable routing, clear sequencing, and real validation checkpoints. Its weaknesses are moderate verbosity from duplicated trigger/chain statements and some deeply nested reference paths that go beyond one level.

Suggestions

Deduplicate the near-verbatim "Use this workflow for broad performance asks..." sentence (lines 30 and 46-47) and consolidate the milestone subsequence, which is restated in both the Output Format and plan-time sections.

Flatten or de-emphasize the deeply nested reference paths (e.g. the three-level instancing-readiness and so-run-validators/infrastructure paths) so SKILL.md points one level deep to the nearest README, which then routes further.

Consider moving the long op-curation rule list (Rules section) into references/operations/_curation.md or a dedicated routing reference so the top-level body stays a lean overview.

Dimension	Reasoning	Score
Conciseness	It avoids explaining concepts Claude already knows, but repeats trigger phrasing ("Use this workflow for broad performance asks..." appears twice) and restates the milestone subsequence in several places, so it could be tightened rather than every token earning its place.	2 / 3
Actionability	As an instruction-only orchestrator it provides concrete, executable guidance: exact milestone labels (profile-stage:baseline), named blocked_codes, real file paths, and specific op recommendations (meshCleanup with flags over mergeVertices).	3 / 3
Workflow Clarity	The multi-step process is clearly sequenced with a mandatory session-start gate, a numbered triage order, and explicit validation checkpoints ("Always validate before and after processor execution", "Always run composition audit before mutation") plus destructive-operation approval gating.	3 / 3
Progressive Disclosure	The body is a well-signaled overview pointing to real bundle files (verified: references/workflow.md, references/operations/_curation.json, references/report-templates/optimization-report.html.template), but some referenced paths are 2-3 levels deep (e.g. usd-structure-assessment/references/instancing-readiness/references/instancing-tradeoffs.md), pulling it below a clean one-level structure.	2 / 3
	Total	10 / 12 Passed

Description

100%Weight 40%Scale 1-3

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 is specific, uses natural trigger terms, and explicitly covers both what the skill does and when to use it, with a distinct USD-performance niche. It is concise without vague fluff.

Dimension	Reasoning	Score
Specificity	Names concrete actions ("USD performance diagnosis and optimization") plus several concrete symptom categories ("slow loading, high memory, low FPS"), matching the anchor that lists multiple specific concrete actions rather than vague language.	3 / 3
Completeness	Clearly answers what ("USD performance diagnosis and optimization") and when via an explicit "Use for slow loading, high memory, low FPS, or 'optimize my scene' requests" clause, satisfying both halves.	3 / 3
Trigger Term Quality	Includes natural user phrasings such as "slow loading", "high memory", "low FPS", and the quoted "optimize my scene", giving good coverage of terms a user would actually say.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (USD performance) and explicitly "delegates auth/runtime setup to Phase 0 owners", reducing overlap with adjacent setup skills.	3 / 3
	Total	12 / 12 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: 2 missing, 5 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: openai/plugins
Path: plugins/nvidia/skills/omniverse-usd-performance-tuning/SKILL.md
Commit: 11c74d6

Reviewed: 17 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.