benchmark-evaluator

Community

End-to-end kernel benchmark orchestration.

AuthorJust-it
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Kernel benchmarks require consistent orchestration across multiple tasks; this skill automates scanning, dispatching, and aggregating results via a SubAgent workflow.

Core Features & Use Cases

  • Schedule and orchestrate KernelBench tasks
  • Dispatch kernelgen-workflow SubAgent to generate, verify, and benchmark per task
  • Persist per-task results and generate a final summary for the scheduling Agent

Quick Start

Provide the required inputs and run the evaluator to scan tasks, dispatch SubAgent for each task, and save per-task results to the output path.

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: benchmark-evaluator
Download link: https://github.com/Just-it/AscendOpGenAgent/archive/main.zip#benchmark-evaluator

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.