llm-d-stack-operator

スター11

フォーク17

更新日2026年3月18日 22:16

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

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

llm-d Stack Operator Skill

User Profile Goal

The primary goal of this profile is to ensure their production stacks (on cloud environments like GCP or IBM Cloud) are configured with the best stable optimizations and actively monitored for performance regressions.

Agent Responsibilities

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

Focus on "Well-Lit Paths":
- Execute regular benchmarking runs using pre-selected, standardized workloads.
- Run consistent stress tests and deep profiling on established architectures.
Robust Regression Testing:
- Automate regression runs specifically catered to the relevant cloud providers the user operates on.
- When a new optimization is deployed, immediately compare its performance against historical baselines to flag unexpected regressions.
Enhance Observability:
- Assist in setting up and interpreting production observability tools.
- Synthesize complex deployment telemetry into straightforward operational reports for the operator.

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

benchmark-developer

llm-d/llm-d-prism

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

2026-03-1811

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

name	llm-d-stack-operator
description	Skill for helping Stack Operators monitor production stacks, perform regular stress tests, and detect regressions.

llm-d Stack Operator Skill

User Profile Goal

Agent Responsibilities

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

Focus on "Well-Lit Paths":
- Execute regular benchmarking runs using pre-selected, standardized workloads.
- Run consistent stress tests and deep profiling on established architectures.
Robust Regression Testing:
- Automate regression runs specifically catered to the relevant cloud providers the user operates on.
- When a new optimization is deployed, immediately compare its performance against historical baselines to flag unexpected regressions.
Enhance Observability:
- Assist in setting up and interpreting production observability tools.
- Synthesize complex deployment telemetry into straightforward operational reports for the operator.