菜单
Investigate performance bottlenecks in a RenderDoc capture and explain which passes or draws are expensive and why. Use when asked to find the hottest work in a frame, rank expensive draws, explain GPU cost, or produce an optimization report for a RenderDoc capture.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Inspect buffer resources and their contents in a RenderDoc capture, including raw bytes and event context. Use when asked to inspect a GPU buffer, constant-buffer contents, structured data, or the meaning of selected buffer bytes in a RenderDoc capture.
Explain the currently selected RenderDoc draw, event, or resource in practical terms. Use when the user refers to "this", "current", or "selected" in a RenderDoc capture and wants to know what it is doing, why it matters, or what to inspect next.
Summarize the structure of a RenderDoc capture and identify its top-level passes, markers, and likely inspection targets. Use when asked for a frame overview, pass breakdown, render flow, first-look summary, or "what is happening in this frame?" for a RenderDoc capture.
Map RenderDoc passes, events, and shaders back to likely project-side source files and implementation points. Use when asked where a pass is implemented, which project files correspond to a capture event, or how a RenderDoc shader links back to workspace code.
Review shader behavior for a RenderDoc event, including stage roles, bindings, constant buffers, and likely issues. Use when asked to analyze a shader, explain shader-stage behavior, inspect bindings, review constant data, or suggest shader optimizations from a RenderDoc capture.
Trace how a texture is produced, consumed, and related to passes in a RenderDoc capture. Use when asked where a texture comes from, which draws sample it, where a render target is written, or how a texture flows through a frame.
| name | renderdoc-performance-investigation |
| description | Investigate performance bottlenecks in a RenderDoc capture and explain which passes or draws are expensive and why. Use when asked to find the hottest work in a frame, rank expensive draws, explain GPU cost, or produce an optimization report for a RenderDoc capture. |
Find the real hotspots first, then drill from timing evidence into geometry, shader, and texture pressure.
Resolve capture state.
Call renderdoc_openCapture first if capture state is unknown.
Build frame context.
Call renderdoc_getFrameSummary.
Call renderdoc_getCaptureInfo if API or replay context may matter.
Fetch timing evidence.
Call renderdoc_getActionTimings.
Do not make "hot" or "slow" claims without timing data unless you clearly mark them as hypotheses.
Identify the hottest passes and leaf draws. Prefer the most expensive top-level groups first, then the hottest leaf events inside them.
Drill into each hot event.
Call renderdoc_getEventDetails.
Call renderdoc_getMeshData when geometry pressure may matter.
Call renderdoc_getShaderInfo or renderdoc_getPipelineState for shader and binding pressure.
Call renderdoc_getResourceDetail or renderdoc_getTextureInfo when large or suspicious textures may contribute.
End with concrete recommendations. Tie every recommendation back to a measured event or resource.
Organize findings by:
For each hot event, report the EID, the full marker path if available, the timing evidence, and the most likely source of cost.
