hostbench

Community

Run and evaluate host GPU benchmark tests.

Authoraviralmansingka
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Host benchmark workflows require repeatedly collecting the right run parameters (subcommands, cloud/region, instance types, IPs/worker IDs, date ranges, and local-vs-S3 intent) and then safely executing the correct operational command without manual, error-prone retyping.

Core Features & Use Cases

  • Guided benchmark operations: Prompts for the right subcommand and arguments for running, comparing, evaluating, or inspecting benchmark results.
  • Conversation-aware prefill: Scans the chat for hints (instance types, cloud/region, IPs/worker IDs, usernames, date ranges, and file paths) to pre-fill AskUserQuestion options so confirmations are fast.
  • Safe, structured execution: Assembles the final invocation and runs it from the modal_host_bench directory using uv run main.py, including guidance for AWS credential wrapping when required.

Quick Start

Ask your AI to run hostbench to evaluate benchmark pass rates by saying: "Run /hostbench evaluate with the relevant since/until dates from this chat."

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: hostbench
Download link: https://github.com/aviralmansingka/dotfiles/archive/main.zip#hostbench

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.