offload-benchmark

Name: offload-benchmark
Availability: InStock
Author: Imbue

Automate local and Offload benchmarks for mng and sculptor, computing timing metrics and updating the README.

132|5|Updated Jan 21, 2026

Search Tags:#pytest #readme #timing #benchmark #offload #mng #sculptor

Ready to run

npx skills add https://github.com/imbue-ai/offload --skill offload-benchmark

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: offload-benchmark
Source: https://github.com/imbue-ai/offload/tree/main/skills/offload-benchmark
Command: npx skills add https://github.com/imbue-ai/offload --skill offload-benchmark

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Benchmark setup and README maintenance for Offload projects, enabling objective measurement of local vs Offload performance and automatic README updates for benchmarking data.

Core Features & Use Cases

Automates collection of timing data for mng and sculptor benchmark runs.
Computes time, time percentage, and speedups, then updates Offload README Benchmarks section.
Validates results and reports INVALID runs if tests fail.

Quick Start

Run this skill to execute local and Offload benchmarks for mng and sculptor, compute metrics, and update the Offload README.

Frequently Asked Questions about offload-benchmark

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I automate benchmark timing and update my README automatically?▼

You can automate benchmark timing and README updates by running a skill that compares local and Offload performance, collects wall-clock time and speedup metrics, and replaces the README Benchmarks section with the generated data.

How do I compare local and Offload pytest performance for mng and sculptor?▼

To compare local and Offload pytest performance for mng and sculptor, run a benchmarking skill that collects precise timing data, computes speedups, and identifies test counts from the pytest outputs.

Can I automatically generate and insert benchmark metrics into my project README?▼

Yes, you can generate and insert benchmark metrics into your project README by computing time, percentage, and speedup data, then feeding those metrics into a template that replaces the Offload README Benchmarks section.

How are invalid benchmark runs handled during automated pytest timing?▼

Invalid benchmark runs are flagged during automated pytest timing when tests fail, ensuring the generated README notes the INVALID results while preserving the rest of the document.

Do I need any external dependencies to run mng and sculptor benchmarks?▼

No external dependencies are required to run mng and sculptor benchmarks, as the skill operates without any listed dependencies to compare local and Offload performance and update the README.