benchmark-developer

スター11

フォーク17

更新日2026年3月18日 22:16

Skill for Analyst / PR roles to compare cross-stack performance and publish reproducible, community-facing benchmarks.

インストール

Codex または Claude でインストールこの Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。

Manusで実行

ソース

llm-d

llm-d/llm-d-prism

GitHub リポジトリを開く Creator のリポジトリを見る

ダウンロード

Manusで実行

Benchmark Developer (Analyst / PR) Skill

User Profile Goal

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.

Agent Responsibilities

When designing and developing features for this user profile, you must:

Prioritize Presentation:
- Create high-quality, easy-to-understand visualizations and tables that are ready to be embedded into public reports, social media posts, or PR materials.
- Clearly highlight price/performance ratios of various components.
Lower the Technical Ceiling:
- Assume this user is a 3rd-party (3P) to the core llm-d community. Do not assume deep familiarity with internal codebase quirks or complex bespoke tooling setup.
- Create one-click reproducible scripts where possible.
Enable Cross-Stack Comparisons:
- Guide the generation of benchmarking tools that can smoothly test not just llm-d, but competitor stacks simultaneously for fairness and clear, objective reporting.

このリポジトリの他の Skills

同じリポジトリ

enforce-development-loop

llm-d/llm-d-prism

Enforce the Product -> UI/UX -> Engineering development loop for new features. Run when starting a feature, reviewing progress, or before merging to main.

2026-07-0911

config-tuner

llm-d/llm-d-prism

Skill for helping Solutions Architects and Customer Engineers sweep configurations and find optimal end-to-end stack setups.

2026-03-1811

llm-d-feature-developer

llm-d/llm-d-prism

Skill for helping llm-d Feature Developers run, compare, and validate benchmarks for new optimization features.

2026-03-1811

llm-d-stack-operator

llm-d/llm-d-prism

Skill for helping Stack Operators monitor production stacks, perform regular stress tests, and detect regressions.

2026-03-1811

name	benchmark-developer
description	Skill for Analyst / PR roles to compare cross-stack performance and publish reproducible, community-facing benchmarks.

Benchmark Developer (Analyst / PR) Skill

User Profile Goal

Agent Responsibilities

When designing and developing features for this user profile, you must:

Prioritize Presentation:
- Create high-quality, easy-to-understand visualizations and tables that are ready to be embedded into public reports, social media posts, or PR materials.
- Clearly highlight price/performance ratios of various components.
Lower the Technical Ceiling:
- Assume this user is a 3rd-party (3P) to the core llm-d community. Do not assume deep familiarity with internal codebase quirks or complex bespoke tooling setup.
- Create one-click reproducible scripts where possible.
Enable Cross-Stack Comparisons:
- Guide the generation of benchmarking tools that can smoothly test not just llm-d, but competitor stacks simultaneously for fairness and clear, objective reporting.