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

80%

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

77%

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

A well-structured orchestrator body with strong actionability and workflow sequencing plus real, verified references; the main weaknesses are verbosity in the decision-rules prose and some two-level-deep reference nesting.

Suggestions

Break the dense entry-skill/decision-rules paragraph into shorter labeled rules or a compact table to improve conciseness and scanability.

Promote the two-level-deep references (runtime-context-header, optimization-tradeoffs, factory-level-structuring) to a single references/ level or summarize their key invariants inline so navigation stays one level deep.

Consider a short "Quick path" summary at the top so the common generic-optimization flow is visible before the full contract detail.

Dimension	Reasoning	Score
Conciseness	The body is information-dense and does not explain basic concepts, but several paragraphs (notably the entry-skill/decision-rules block) are long, clause-heavy, and could be tightened, so it is not fully lean.	2 / 3
Actionability	Provides concrete, copy-ready guidance: exact milestone subsequence, exact profile labels (profile-stage:baseline/after), specific blocker codes, and a concrete routing map — actionable despite being instruction-only.	3 / 3
Workflow Clarity	Sequences the canonical chain explicitly with validation checkpoints (preflight session-start gate, validate before/after processor execution, blocked codes) and feedback for error recovery.	3 / 3
Progressive Disclosure	The body is a well-organized overview with a clear Primary references list and real referenced files, but some references are two levels deep (e.g. setup-usd-performance-tuning/references/runtime-context-header.md), which keeps it below the one-level-deep ideal.	2 / 3
	Total	10 / 12 Passed

Description

82%

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 specific, well-targeted description with strong natural trigger terms and a clear niche; its main gap is the absence of an explicit "Use when…" clause, which limits completeness to 2.

Suggestions

Add an explicit "Use when…" clause naming the user-facing triggers (e.g. "Use when a USD stage loads slowly, drops FPS, uses too much memory, or needs scene optimization.") to lift completeness to 3.

Consider surfacing the diagnosis-only vs mutation distinction in the description so users can self-select the right entry path.

Dimension	Reasoning	Score
Specificity	Names concrete actions ("diagnosis and optimization") and multiple specific scenarios ("slow loading, high memory, low FPS, and broad scene-optimization requests"), matching the multi-action anchor rather than the domain-only level 2.	3 / 3
Completeness	Clearly states what the skill does, but the "when" is only implied via the handled-scenarios list and there is no explicit "Use when…" trigger clause, which the guidelines cap at 2.	2 / 3
Trigger Term Quality	Uses natural user phrasing ("slow loading", "high memory", "low FPS", "optimize") that a user would actually say, giving good coverage rather than just jargon.	3 / 3
Distinctiveness Conflict Risk	The USD performance tuning niche is specific and unlikely to conflict with other skills; the handled scenarios are domain-distinct.	3 / 3
	Total	11 / 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: 1 missing, 4 deeper-than-1-level	Warning

	Total	12 / 16 Passed

Repository: NVIDIA/skills
Path: skills/omniverse-usd-performance-tuning/SKILL.md
Commit: e3796e4

Reviewed: about 3 hours 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.