一键导入
benchmark-developer
Skill for Analyst / PR roles to compare cross-stack performance and publish reproducible, community-facing benchmarks.
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。
菜单
Skill for Analyst / PR roles to compare cross-stack performance and publish reproducible, community-facing benchmarks.
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
Enforce the Product -> UI/UX -> Engineering development loop for new features. Run when starting a feature, reviewing progress, or before merging to main.
Skill for helping Solutions Architects and Customer Engineers sweep configurations and find optimal end-to-end stack setups.
Skill for helping llm-d Feature Developers run, compare, and validate benchmarks for new optimization features.
Skill for helping Stack Operators monitor production stacks, perform regular stress tests, and detect regressions.
| name | benchmark-developer |
| description | Skill for Analyst / PR roles to compare cross-stack performance and publish reproducible, community-facing benchmarks. |
The primary goal of this profile is to compare the performance of llm-d optimizations against alternative inference stacks (e.g., Dynamo) and share easy-to-understand benchmarks with the broader community.
When designing and developing features for this user profile, you must:
Prioritize Presentation:
Lower the Technical Ceiling:
Enable Cross-Stack Comparisons: