skills.rest
burtenshawburtenshawCommunity·4 Agent Skills Included

multiautoresearch

Automated machine learning experiment planning, benchmarking, and optimization

Runs disciplined machine learning experiments across pre-training, post-training, and local inference projects. Eliminates manual benchmark tracking, duplicate runs, and messy experiment notes with structured workflows and managed cloud jobs. Helps researchers test single-change hypotheses, record results, and optimize model speed faster.
303|41
↗
npx skills add burtenshaw/multiautoresearch --all -g -y
Available:

Instructs your AI agent on how to route work to the correct pre-training, post-training, or inference sub-project and follow each project's own rules.

All Skills in This Repository (4)

Pure Emerald Level Indicators
📦 In Repo
burtenshawburtenshaw

autolab-managed-experiment

Coordinate a single Autolab benchmark experiment from local master to Hugging Face Jobs.

Community
Intermediate
📦 In Repo
burtenshawburtenshaw

hf-cli

Manage Hugging Face Hub repositories, models, and datasets via the hf CLI.

Community
Intermediate
📦 In Repo
burtenshawburtenshaw

autolab-hermes-delegation

Orchestrate multi-agent Autolab Hermes delegation with role contracts and parent rules.

Community
Advanced
📦 In Repo
burtenshawburtenshaw

autolab-reporter

Automate fleet monitoring and reporting for Autolab HF Jobs.

Community
Intermediate

Frequently Asked Questions

FAQPage Schema
How to install multiautoresearch?▼

Run `npx skills add burtenshaw/multiautoresearch --all -g -y` in your terminal to install all skills in this suite globally.

How to automate ML experiments with AI?▼

This suite lets your AI agent plan single-change hypotheses, launch managed Hugging Face Jobs benchmarks, and record results automatically.

How to speed up local llama.cpp inference?▼

The inference project guides your agent through GGUF model selection, quant choice, and repeatable llama-server benchmarks to find the fastest setup.

Does multiautoresearch work with Claude Code and OpenCode?▼

Yes. It includes native configurations for OpenCode, Claude Code, Codex, Pi, and Hermes, all following the same experiment workflow.

Can I run post-training benchmarks without manual setup?▼

Yes. The post-training project prepares data, trains, and evaluates your model with fixed commands, locally or on Hugging Face Jobs.

Related Repositories in Education & Research

View All in Education & Research→
shareAI-labshareAI-lab
75.8k

learn-claude-code

Learn to build AI agent harnesses from scratch

Official📦 4 Skills
microsoftmicrosoft
73.6k

ai-agents-for-beginners

Learn to build, deploy, and secure AI agents step by step

Official📦 8 Skills
leonardomsoleonardomso
66.5k

33-js-concepts

Master 33 essential JavaScript concepts with tested, verified guides

Community📦 6 Skills