omniverse-usd-performance-tuning

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Omniverse USD Performance Tuning

Omniverse USD 性能调优

When to Use

适用场景

Use this workflow for broad performance asks such as slow loading, high memory, low FPS, GPU crashes, conversion-quality triage, or generic requests to optimize a USD scene.

此工作流适用于各类性能相关需求，例如加载缓慢、内存占用过高、FPS偏低、GPU崩溃、转换质量排查，或是通用的USD场景优化请求。

Instructions

操作说明

Start from the mandatory runtime context gate before producing tuning output, unless the prompt is only asking for a static classification test.
Classify broad optimization requests as
```
ready_to_plan
```
; reserve
```
approval_required
```
for prompts that explicitly name a destructive operation to execute before planning.
Plan the full canonical chain through
```
optimization-report
```
, preserving the structured milestone order and the
```
profile-stage:baseline
```
/
```
profile-stage:after
```
labels when listing milestones.
Invoke downstream skill bodies only when their phase is reached, and keep raw runtime artifacts on disk while reading compact summaries.

Frontmatter keeps

version

and

tools

at top level for agentskills.io runtime compatibility. NVCARPS discoverability fields live under

metadata

除非仅需进行静态分类测试，否则在生成调优输出前，必须先通过运行时上下文检查门。
将通用优化请求归类为
```
ready_to_plan
```
；仅当请求明确提及在规划前需执行破坏性操作时，才标记为
```
approval_required
```
。
规划完整的标准流程链，最终生成
```
optimization-report
```
；列出里程碑时需保留结构化的里程碑顺序，以及
```
profile-stage:baseline
```
/
```
profile-stage:after
```
标签。
仅当进入对应阶段时才调用下游Skill主体；读取精简摘要的同时，需将原始运行时工件保留在磁盘上。

为兼容agentskills.io运行时，前置信息需将

version

和

tools

放在顶层。NVCARPS可发现性字段位于

metadata

下。

Output Format

输出格式

Return a plan or status summary that names the selected entry skill, uses

ready_to_plan

for generic optimization requests, includes the full milestone chain through

optimization-report

, and labels profile phases as

profile-stage:baseline

and

profile-stage:after

. For structured outputs, the broad-optimization milestone subsequence is

omniverse-usd-performance-tuning

profile-stage:baseline

usd-structure-assessment

usd-validation-runner

restructure-decision

apply-restructure

so-run-validators

so-interpret-validators

so-run-operations

profile-stage:after

compare-profiles

optimization-report

. End-to-end execution should produce an optimized stage when mutation runs and a report conforming to the

optimization-report

reference's schema (

scripts/optimization-report.schema.json

within that reference).

Use this workflow for broad performance asks such as slow loading, low FPS, high memory, GPU crashes, conversion quality, or "optimize my scene."

返回计划或状态摘要，需指定所选的入口Skill；对于通用优化请求，使用

ready_to_plan

；包含直至

optimization-report

的完整里程碑链，并将分析阶段标记为

profile-stage:baseline

和

profile-stage:after

。对于结构化输出，通用优化的里程碑子序列为：

omniverse-usd-performance-tuning

profile-stage:baseline

usd-structure-assessment

usd-validation-runner

restructure-decision

apply-restructure

so-run-validators

so-interpret-validators

so-run-operations

profile-stage:after

compare-profiles

optimization-report

。端到端执行完成后，若执行了变更操作，应生成优化后的场景；同时需生成符合

optimization-report

参考架构（该参考中的

scripts/optimization-report.schema.json

）的报告。

此工作流适用于各类性能相关需求，例如加载缓慢、FPS偏低、内存占用过高、GPU崩溃、转换质量问题，或是“优化我的场景”这类请求。

Entry skill rule

入口Skill规则

This skill is the named entry point for broad performance work whenever the agent has any verified way to do that work. Runtime probing details live in

setup-usd-performance-tuning

; this rule only decides which skill owns the user-facing performance request.

If the setup probe shows any verified runtime path - Kit, standalone, or even a partial stack such as Asset Validator only - enter here. If the user's requested tool is missing, return the specific
```
blocked_code
```
(
```
blocked_missing_scene_optimizer
```
,
```
blocked_missing_so_operation
```
, etc.) instead of substituting another workflow.
Enter at
```
setup-usd-performance-tuning
```
only when no runtime path is verified and runtime choice/setup is the first unresolved problem.
For
```
omniverse://
```
assets, enter at
```
omniverse-authentication
```
first. Authentication precedes setup and triage for remote assets.

The decision is about ownership, not order. Setup, authentication, and triage all run in their normal phase order; this rule only fixes which skill the agent names as the entry skill in its response.

当Agent拥有任何已验证的执行路径时，此Skill是处理通用性能需求的指定入口点。运行时探测细节在

setup-usd-performance-tuning

中定义；本规则仅决定哪个Skill负责响应用户的性能请求。

如果设置探测显示存在任何已验证的运行时路径（Kit、独立运行时，甚至仅Asset Validator这类部分栈），则从此处进入。若用户请求的工具缺失，返回特定的
```
blocked_code
```
（如
```
blocked_missing_scene_optimizer
```
、
```
blocked_missing_so_operation
```
等），而非替换为其他工作流。
仅当无已验证的运行时路径，且运行时选择/设置是首个未解决的问题时，才从
```
setup-usd-performance-tuning
```
进入。
对于
```
omniverse://
```
资产，需先进入
```
omniverse-authentication
```
。远程资产的认证优先于设置和排查。

本规则关注的是职责归属，而非执行顺序。设置、认证和排查均按正常阶段顺序执行；此规则仅确定Agent在响应中指定哪个Skill作为入口Skill。

Runtime context — session-start gate (mandatory)

运行时上下文 — 会话启动检查门（必填）

Before any other tuning output, follow the mandatory session-start gate in

skills/omniverse-usd-performance-tuning/references/setup-usd-performance-tuning/references/runtime-context-header.md

. That reference owns

output_path

, the canonical

setup-preflight.json

location, Format A/Format B, and the "do not improvise a silent probe" anti-pattern.

Required outcomes:

Missing or unreadable preflight: invoke
```
setup-usd-performance-tuning
```
.
Present preflight: print Format A and wait for the user to choose Continue, Change Kit, Switch to standalone, or Re-run probe.
Confirmed runtime in the same session: use compact Format B for follow-up status.

[Kit: {runtime_context.kit.application} {runtime_context.kit.version}  |  SO: {runtime_context.sceneOptimizer.version}  |  AV: {runtime_context.assetValidator.version}]

在生成任何调优输出之前，需遵循

skills/omniverse-usd-performance-tuning/references/setup-usd-performance-tuning/references/runtime-context-header.md

中的必填会话启动检查门。该参考定义了

output_path

、标准

setup-preflight.json

位置、格式A/格式B，以及“不得擅自执行静默探测”的反模式。

预期结果：

预检文件缺失或无法读取：调用
```
setup-usd-performance-tuning
```
。
预检文件存在：打印格式A，等待用户选择“继续”“更换Kit”“切换到独立运行时”或“重新运行探测”。
同一会话中已确认运行时：后续状态使用精简的格式B。

[Kit: {runtime_context.kit.application} {runtime_context.kit.version}  |  SO: {runtime_context.sceneOptimizer.version}  |  AV: {runtime_context.assetValidator.version}]

Runtime artifact token budget

运行时工件令牌预算

Before reading Kit logs, Asset Validator CSVs, Scene Optimizer logs, Tracy CSVs, or other runtime output, follow

references/runtime-artifact-token-budget.md

. Keep raw artifacts on disk, read summary JSON first, and use bounded log snapshots instead of full dumps or live streams.

在读取Kit日志、Asset Validator CSV、Scene Optimizer日志、Tracy CSV或其他运行时输出之前，需遵循

references/runtime-artifact-token-budget.md

。将原始工件保留在磁盘上，优先读取摘要JSON，使用有限的日志快照而非完整转储或实时流。

Plan-time vs execution-time approval

规划时与执行时的审批

approval_required

at planning time is reserved for requests that explicitly name a destructive operation. Use the following rule when deciding between

ready_to_plan

and

approval_required

approval_required
at planning time — the user's request itself names a destructive operation: "flatten this stage", "decimate the meshes", "merge prototypes", "delete unused prims", or any specific named mutation that cannot be undone within the same workflow. In this case the agent's first response must be an approval prompt that names the operation, before the agent commits to a plan that executes it.
ready_to_plan
at planning time — the user's request is general: "optimize this scene", "make it load faster", "reduce GPU memory", "improve interactivity". The agent lays out the full plan, including any destructive operations the plan would invoke (for example
```
so-run-operations
```
with
```
mergeMaterials
```
), without withholding the plan itself. Approval for each destructive operation is requested alongside plan approval.

The distinction is between authorising a plan and authorising a destructive action. A general optimisation request authorises planning; it does not authorise execution of specific destructive operations.

For structured runtime-test responses and similar planning summaries:

A future
```
restructure-decision
```
prompt is a planned user-decision gate, not a reason to set the top-level response
```
decision
```
to
```
approval_required
```
for a generic optimization request.
For a generic optimization request, set
```
decision: "ready_to_plan"
```
and include the full intended chain in both
```
committed_milestones
```
and
```
planned_phases
```
, through
```
optimization-report
```
.

It is valid for

gates_observed

to include

asks_user_for_restructure_decision

while the top-level

decision

remains

ready_to_plan

Whenever a chain names profile phases, use the exact labels
```
profile-stage:baseline
```
and
```
profile-stage:after
```
; do not emit the ambiguous bare
```
profile-stage
```
token.
Start structured milestone lists with
```
omniverse-usd-performance-tuning
```
as the owning entry skill. Include
```
setup-usd-performance-tuning
```
only as additional Phase 0 context, not as a replacement for the entry skill milestone.
For broad optimization requests, preserve the milestone subsequence from Output Format above exactly, with optional extra analysis steps inserted only where they do not reorder it.
Do not list
```
so-run-validators
```
or
```
so-interpret-validators
```
before
```
restructure-decision
```
in broad optimization milestone summaries. Phase-aware validator routing still happens through
```
usd-validation-runner
```
; the SO validator executor/interpreter milestones appear after the restructure decision path in the structured plan contract.

规划阶段的

approval_required

仅适用于明确提及破坏性操作的请求。判断

ready_to_plan

和

approval_required

时遵循以下规则：

规划阶段标记为
approval_required
— 用户请求本身明确提及破坏性操作：“展平此场景”“精简网格”“合并原型”“删除未使用的prims”，或任何无法在同一工作流内撤销的特定变更操作。在此情况下，Agent的首次响应必须是针对该操作的审批提示，之后才能提交执行该操作的计划。
规划阶段标记为
ready_to_plan
— 用户请求为通用型：“优化此场景”“加快加载速度”“降低GPU内存占用”“提升交互性”。Agent需列出完整计划，包括计划中会调用的任何破坏性操作（例如带有
```
mergeMaterials
```
的
```
so-run-operations
```
），无需隐藏计划本身。针对每个破坏性操作的审批需与计划审批一同请求。

二者的区别在于授权计划和授权破坏性操作。通用优化请求授权规划，但不授权执行特定的破坏性操作。

对于结构化运行时测试响应及类似的规划摘要：

未来的
```
restructure-decision
```
提示是计划中的用户决策检查门，并非将顶层响应
```
decision
```
设置为
```
approval_required
```
的理由（针对通用优化请求）。
对于通用优化请求，设置
```
decision: "ready_to_plan"
```
，并在
```
committed_milestones
```
和
```
planned_phases
```
中包含直至
```
optimization-report
```
的完整预期流程链。

gates_observed

中包含

asks_user_for_restructure_decision

，同时顶层

decision

仍为

ready_to_plan

是合理的。

当流程链提及分析阶段时，需使用精确的标签
```
profile-stage:baseline
```
和
```
profile-stage:after
```
；不得使用模糊的
```
profile-stage
```
令牌。
结构化里程碑列表需以
```
omniverse-usd-performance-tuning
```
作为负责的入口Skill开头。仅将
```
setup-usd-performance-tuning
```
作为第0阶段的附加上下文包含，不得替换入口Skill里程碑。
对于通用优化请求，需严格保留上述“输出格式”中的里程碑子序列，仅可在不改变顺序的前提下插入可选的额外分析步骤。
在通用优化里程碑摘要中，不得将
```
so-run-validators
```
或
```
so-interpret-validators
```
列在
```
restructure-decision
```
之前。阶段感知的验证器路由仍通过
```
usd-validation-runner
```
实现；SO验证器执行器/解释器里程碑需在结构化计划合约中的重构决策路径之后出现。

Output expectation

输出预期

End-to-end optimization work should produce both an optimized USD stage, when mutation is executed, and a structured optimization report conforming to the

optimization-report

reference's

scripts/optimization-report.schema.json

. The HTML report must be rendered from

references/report-templates/optimization-report.html.template

via

render_preview.py

— never hand-write HTML. Diagnosis-only work should still end with a report or summary that states no optimized stage was written.

端到端优化工作完成后，若执行了变更操作，应生成优化后的USD场景；同时需生成符合

optimization-report

参考中

scripts/optimization-report.schema.json

的结构化优化报告。HTML报告必须通过

render_preview.py

从

references/report-templates/optimization-report.html.template

渲染生成 — 不得手动编写HTML。仅诊断类工作也需以报告或摘要结尾，说明未生成优化场景。

Purpose

目的

Route digital twin USD performance requests into the right diagnostic and optimization workflow while preserving evidence before mutation.

将数字孪生USD性能请求路由至正确的诊断和优化工作流，同时在变更前保留证据。

Prerequisites

前提条件

Stage path or enough context to identify the target asset.
User goal: diagnosis only, validation, profiling, or processor execution.
Runtime availability status from
```
setup-usd-performance-tuning
```
when not already known.
Permission status for in-place mutation vs writing a separate optimized output.

场景路径或足够识别目标资产的上下文信息。
用户目标：仅诊断、验证、分析或执行处理操作。
未知运行时可用性时，需从
```
setup-usd-performance-tuning
```
获取状态。
是否允许原地变更或需写入单独的优化输出的权限状态。

Examples

示例

"This USD loads slowly; triage what to check first."
"Route a low-FPS CAD scene through the performance workflow."

“这个USD加载缓慢，排查首先需要检查什么。”
“将低FPS的CAD场景通过性能工作流处理。”

Triage order

排查顺序

Runtime gate. Follow the mandatory session-start gate above before validation, profiling, or optimization. Do not scan, probe, install, or pick Kit/standalone runtimes directly in this skill;
```
setup-usd-performance-tuning
```
owns probe/chooser/install dispatch and writes the preflight consumed here.
Identify the target problem:
- Load time.
- FPS or interactivity.
- GPU or system memory.
- Crash or device lost.
- CAD conversion quality.
- Validation failure.
Gather minimum context:
- Stage path and size.
- Whether the stage is local, mounted, or
```
omniverse://
```
  remote. For remote assets, route through
```
omniverse-authentication
```
  before first open.
- Kit or USD runtime.
- Whether the workload is CAD, VFI, AIF, Isaac, or generic OpenUSD.
- Whether in-place mutation is allowed.
- Whether the user wants diagnosis only or processor execution.
Route:
- USD composition questions:
```
usd-structure-assessment
```
  (composition is now part of the SA umbrella; deeper detail in
```
skills/omniverse-usd-performance-tuning/references/usd-structure-assessment/references/composition-audit.md
```
  ).
- Validation and content issues:
```
usd-validation-runner
```
  (master router; routes to
```
validate-*
```
  family or
```
so-run-validators
```
  based on intent).
- Edit/output decisions:
```
usd-edit-target-planner
```
  (also owns variant/payload gates).
- Repeated copied hierarchy or high mesh count with no instancing:
```
usd-hierarchy-dedupe-candidates
```
  .
- Restructure decision (monolithic stage, asset boundary materialization):
```
restructure-decision
```
  .
- CAD converter settings: read
```
references/cad-conversion/README.md
```
  (niche pre-USD concern; see reference for details).
- Scene Optimizer:
```
so-run-validators
```
  ,
```
so-interpret-validators
```
  ,
```
so-run-operations
```
  .

运行时检查门。在进行验证、分析或优化之前，需遵循上述必填的会话启动检查门。不得在此Skill中直接扫描、探测、安装或选择Kit/独立运行时；
```
setup-usd-performance-tuning
```
负责探测/选择器/安装调度，并写入供此Skill使用的预检文件。
识别目标问题：
- 加载时间。
- FPS或交互性。
- GPU或系统内存。
- 崩溃或设备丢失。
- CAD转换质量。
- 验证失败。
收集最低限度的上下文信息：
- 场景路径和大小。
- 场景是本地、挂载还是
```
omniverse://
```
  远程资产。对于远程资产，首次打开前需通过
```
omniverse-authentication
```
  路由。
- Kit或USD运行时。
- 工作负载类型：CAD、VFI、AIF、Isaac或通用OpenUSD。
- 是否允许原地变更。
- 用户需要仅诊断还是执行处理操作。
路由：
- USD组合问题：
```
usd-structure-assessment
```
  （组合现在属于SA的范畴；详细内容见
```
skills/omniverse-usd-performance-tuning/references/usd-structure-assessment/references/composition-audit.md
```
  ）。
- 验证和内容问题：
```
usd-validation-runner
```
  （主路由器；根据意图路由至
```
validate-*
```
  系列或
```
so-run-validators
```
  ）。
- 编辑/输出决策：
```
usd-edit-target-planner
```
  （同时负责变体/负载检查门）。
- 重复的复制层级或无实例化的高网格数量：
```
usd-hierarchy-dedupe-candidates
```
  。
- 重构决策（单体场景、资产边界具体化）：
```
restructure-decision
```
  。
- CAD转换器设置：阅读
```
references/cad-conversion/README.md
```
  （USD生成前的 niche 关注点；详见参考文档）。
- Scene Optimizer：
```
so-run-validators
```
  、
```
so-interpret-validators
```
  、
```
so-run-operations
```
  。

Optimization ordering

优化顺序

Follow the canonical ordering in workflow.md § Operation ordering invariants. The high-level rule: prototypes first → per-asset validation → stage-level operations last. The workflow reference owns the full invariant list (meshCleanup before decimateMeshes, deduplication before decimation, never merge if instanced, etc.) and the analysis-only ops catalogue.

遵循workflow.md § 操作顺序不变量中的标准顺序。高层规则：先处理原型 → 再进行逐资产验证 → 最后执行场景级操作。工作流参考定义了完整的不变量列表（meshCleanup在decimateMeshes之前， deduplication在decimation之前，实例化场景绝不合并等）以及仅分析类操作目录。

Rules

规则

Always run composition audit before mutation.
Always validate before and after processor execution.
Optimize prototypes before per-asset validation.
Do not run whole-stage mesh deduplication on very large CAD scenes before checking for hierarchy-level reuse.
Do not recommend a fixed optimization stack without bottleneck evidence.
Do not invent numeric thresholds or expected percentage wins.
Prefer canonical SO ops over specialty / documentary ones. The op curation in
```
references/operations/_curation.json
```
classifies every op as
```
canonical
```
,
```
specialty
```
,
```
analysis
```
,
```
documentary
```
, or
```
deprecated
```
. When more than one op could resolve the same finding, recommend the canonical one first and only reach for a specialty op when the user explicitly asks or the rationale warrants it. Specifically:
- For vertex welding, prefer canonical
```
meshCleanup
```
  with explicit flags over the standalone
```
mergeVertices
```
  op. The standalone op is a legacy/specialty surface; use upstream
```
usd-optimize
```
  for the operation mechanics and local approval policy before mutating.
- For hierarchy dedupe, recommend
```
usd-hierarchy-dedupe-candidates
```
  +
```
apply-restructure
```
  (the USD-authored rewrite path).
- For per-mesh dedupe, recommend
```
deduplicateGeometry
```
  (canonical) over
```
findCoincidingGeometry
```
  (analysis — produces a report, not a change).
- Do not recommend
```
documentary
```
  -status ops (e.g.,
```
boxClip
```
  ,
```
deletePrims
```
  ,
```
removeAttributes
```
  ,
```
removeUntypedPrims
```
  ,
```
merge
```
  outside its narrow non-instanced case) without an explicit user request. Documentary ops survive in the per-op
```
references/operations/<key>.md
```
  routing stubs for completeness but are excluded from agent-initiated recommendations.
- Specialty ≠ documentary. Ops classified as
```
specialty
```
  in
```
_curation.json
```
  either (a) have validator-finding evidence that wires them into the
```
so-interpret-validators
```
  chain (e.g.
```
sparseMeshes
```
  ,
```
optimizePrimvars
```
  ), or (b) are load-bearing escape hatches needed for specific downstream contexts (e.g.
```
primitivesToMeshes
```
  when output must be
```
UsdGeomMesh
```
  ,
```
utilityFunction
```
  for instancing toggles and material rebinding,
```
pythonScript
```
  for
```
so-create-proxy
```
  recipes). Recommend specialty ops when their validator fires OR when their downstream context applies — the suppression above only targets
```
documentary
```
  ops.

变更前必须先执行组合审计。
处理操作执行前后必须进行验证。
先优化原型，再进行逐资产验证。
在检查层级复用情况之前，不得对大型CAD场景执行全场景网格去重。
不得在无瓶颈证据的情况下推荐固定的优化栈。
不得自行设定数值阈值或预期性能提升百分比。
优先推荐标准SO操作，而非特殊/文档类操作。
```
references/operations/_curation.json
```
中的操作分类将每个操作标记为
```
canonical
```
（标准）、
```
specialty
```
（特殊）、
```
analysis
```
（分析）、
```
documentary
```
（文档）或
```
deprecated
```
（已弃用）。当多个操作可解决同一问题时，优先推荐标准操作；仅当用户明确要求或有合理依据时，才使用特殊操作。具体规则：
- 对于顶点焊接，优先使用带显式标志的标准
```
meshCleanup
```
  ，而非独立的
```
mergeVertices
```
  操作。独立操作属于遗留/特殊场景；变更前需使用上游
```
usd-optimize
```
  处理操作机制，并遵循本地审批策略。
- 对于层级去重，推荐
```
usd-hierarchy-dedupe-candidates
```
  +
```
apply-restructure
```
  （基于USD编写的重写路径）。
- 对于逐网格去重，推荐
```
deduplicateGeometry
```
  （标准）而非
```
findCoincidingGeometry
```
  （分析类 — 仅生成报告，不执行变更）。
- 若无用户明确请求，不得推荐
```
documentary
```
  状态的操作（例如
```
boxClip
```
  、
```
deletePrims
```
  、
```
removeAttributes
```
  、
```
removeUntypedPrims
```
  、非实例化场景外的
```
merge
```
  ）。文档类操作仅在每个操作的
```
references/operations/<key>.md
```
  路由存根中保留以保证完整性，但Agent不得主动推荐。
- 特殊操作≠文档类操作。
```
_curation.json
```
  中标记为
```
specialty
```
  的操作要么（a）有验证器发现的证据可接入
```
so-interpret-validators
```
  流程（例如
```
sparseMeshes
```
  、
```
optimizePrimvars
```
  ），要么（b）是特定下游场景所需的关键应急方案（例如当输出必须为
```
UsdGeomMesh
```
  时的
```
primitivesToMeshes
```
  ，用于实例化切换和材质重新绑定的
```
utilityFunction
```
  ，用于
```
so-create-proxy
```
  方案的
```
pythonScript
```
  ）。当对应的验证器触发或下游场景适用时，可推荐特殊操作 — 上述限制仅针对
```
documentary
```
  操作。

Limitations

局限性

Does not replace downstream reference instructions; load each required reference before executing it.
Does not install runtimes directly; follow setup or install references when requirements are missing.
Does not authorize mutation when the user has not allowed writes.

无法替代下游参考文档的说明；执行每个步骤前需加载对应阶段的嵌套
```
README.md
```
参考并遵循其指示。
无法直接安装运行时；当依赖缺失时需遵循设置或安装参考文档。
用户未允许写入时，不得授权变更操作。

Troubleshooting

故障排除

If runtime status is unclear, run
```
setup-usd-performance-tuning
```
before profiling or validation.
If the reported problem is vague, gather stage path, workload type, and whether diagnosis or execution is requested.
If the workflow suggests mutation before evidence, return to baseline profiling and composition audit first.

若运行时状态不明确，在分析或验证前先运行
```
setup-usd-performance-tuning
```
。
若报告的问题模糊，收集场景路径、工作负载类型以及用户需要诊断还是执行操作。
若工作流建议在无证据的情况下执行变更，需先回到基线分析和组合审计。

References

参考文档

Before routing, read:

```
skills/omniverse-usd-performance-tuning/references/usd-structure-assessment/references/optimization-tradeoffs.md
```
— identify which pipeline phase the scene is in (extraction, structuring, or optimization). The right action depends on the phase.

skills/omniverse-usd-performance-tuning/references/usd-structure-assessment/references/factory-level-structuring.md

— understand the three pillars (assets, aggregation, animation) and the seven-step structuring pattern.

If you have network access, prefer the live URLs (noted in each reference file) for the most current version.

路由前需阅读：

```
skills/omniverse-usd-performance-tuning/references/usd-structure-assessment/references/optimization-tradeoffs.md
```
— 识别场景所处的流水线阶段（提取、结构化或优化）。正确的操作取决于所处阶段。

skills/omniverse-usd-performance-tuning/references/usd-structure-assessment/references/factory-level-structuring.md

— 理解三大支柱（资产、聚合、动画）和七步结构化模式。

若有网络访问权限，优先使用每个参考文件中注明的实时URL以获取最新版本。

Required execution flow

必填执行流程

Read

references/workflow.md

for the canonical Phase 0-7 flow, including Kit/standalone branches, validator-stack routing, operation ordering, termination conditions, duration hints, and the optional iteration pattern. The compact root map at

references/skill-map.md

only routes agents into this workflow.

Do not treat downstream phase names as plain checklist labels. Before executing each step, load that phase's nested

README.md

reference and follow its instructions. Claude Code only exposes the public catalog skill; it does not recursively inject

profile-stage

usd-structure-assessment

, or other nested references.

The final deliverable must come from

optimization-report

: save both the structured JSON report and the generated Markdown summary. Do not substitute an ad hoc

SUMMARY.md

or chat-only recap for the optimization report.

For deeper subtopic guidance, consult the references:

skills/omniverse-usd-performance-tuning/references/usd-structure-assessment/references/composition-audit.md

skills/omniverse-usd-performance-tuning/references/usd-structure-assessment/references/layer-health.md

- subtopic detail for SA's Phase 1 checklist.

skills/omniverse-usd-performance-tuning/references/usd-structure-assessment/references/instancing-readiness/references/instancing-tradeoffs.md

- merge safety, decision tree for instancing choices.

skills/omniverse-usd-performance-tuning/references/usd-structure-assessment/references/usd-edit-target-planner/references/variants-payloads.md

- deeper variant/payload trade-offs (gates are inline in usd-edit-target-planner).

```
references/cad-conversion/README.md
```
- CAD converter settings.
```
references/upstreams/usd-optimize.md
```
- upstream SO mechanics and prebuilt package resolution.

skills/omniverse-usd-performance-tuning/references/usd-validation-runner/references/so-run-validators/references/infrastructure.md

- local handoff for SO validator infrastructure.

skills/omniverse-usd-performance-tuning/references/usd-validation-runner/references/validation-scoping.md

- tier 1/2/3 plan + scene-aware adjustment.

skills/omniverse-usd-performance-tuning/references/optimization-report/references/optimization-report-template.md

- the data contract every phase populates.

For full Kit runtime profiling (FPS, frame time, Hydra/RTX metrics), refer to the external profiling skills at NVIDIA/omniperf.

阅读

references/workflow.md

获取标准的第0-7阶段流程，包括Kit/独立运行时分支、验证器栈路由、操作顺序、终止条件、时长提示以及可选的迭代模式。

references/skill-map.md

中的精简根图仅用于将Agent路由至此工作流。

不得将下游阶段名称视为简单的 checklist 标签。执行每个步骤前，需加载该阶段的嵌套

README.md

参考并遵循其指示。Claude Code仅暴露公开目录Skill；不会递归注入

profile-stage

、

usd-structure-assessment

或其他嵌套参考。

最终交付物必须来自

optimization-report

：保存结构化JSON报告和生成的Markdown摘要。不得用临时的

SUMMARY.md

或仅聊天式的总结替代优化报告。

如需更深入的子主题指导，请参考以下文档：

skills/omniverse-usd-performance-tuning/references/usd-structure-assessment/references/composition-audit.md

、

skills/omniverse-usd-performance-tuning/references/usd-structure-assessment/references/layer-health.md

— SA第1阶段检查清单的子主题细节。

skills/omniverse-usd-performance-tuning/references/usd-structure-assessment/references/instancing-readiness/references/instancing-tradeoffs.md

— 合并安全性、实例化选择决策树。

skills/omniverse-usd-performance-tuning/references/usd-structure-assessment/references/usd-edit-target-planner/references/variants-payloads.md

— 更深入的变体/负载权衡（检查门内置于usd-edit-target-planner）。

```
references/cad-conversion/README.md
```
— CAD转换器设置。
```
references/upstreams/usd-optimize.md
```
— 上游SO机制和预构建包解析。

skills/omniverse-usd-performance-tuning/references/usd-validation-runner/references/so-run-validators/references/infrastructure.md

— SO验证器基础设施的本地交接。

skills/omniverse-usd-performance-tuning/references/usd-validation-runner/references/validation-scoping.md

— 第1/2/3级计划 + 场景感知调整。

skills/omniverse-usd-performance-tuning/references/optimization-report/references/optimization-report-template.md

— 每个阶段需填充的数据契约。

如需完整的Kit运行时分析（FPS、帧时间、Hydra/RTX指标），请参考NVIDIA/omniperf中的外部分析Skill。