git:20260518.2d3c27b to git:20260710.2925510
16 added, 20 removed. Audit A to B.
---
- name: "Automate ML research loops with ARIS skills"
- slug: "automate-ml-research-loops-with-aris-skills"
+ title: "Automate ML research loops with ARIS skills"
description: "Use ARIS to run Markdown-based agent skills for literature review, idea discovery, cross-model critique, experiment planning, and paper-writing support."
- github_stars: 9609
- verification: "listed"
+ verification: "security_reviewed"
source: "https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep"
author: "wanshuiyin"
publisher_type: "individual"
- category: "Templates & Workflows"
- framework: "Multi-Framework"
+ category:
+ - "Templates & Workflows"
+ framework:
+ - "Multi-Framework"
tool_ecosystem:
github_repo: "wanshuiyin/Auto-claude-code-research-in-sleep"
github_stars: 9609
---
# Automate ML research loops with ARIS skills
Use ARIS to run Markdown-based agent skills for literature review, idea discovery, cross-model critique, experiment planning, and paper-writing support.
## Prerequisites
ARIS skills or ARIS-Code CLI, Claude Code/Codex/OpenClaw-compatible agent, configured model providers
## Installation
- Use the upstream install or setup path that matches your environment:
- - git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep.git
- - npm install -g @openai/codex
- - pip install deepxiv-sdk
- - pip install exa-py
+ Choose whichever fits your setup:
- Requirements and caveats from upstream:
- - 🪶 **Radically lightweight — zero dependencies, zero lock-in.** The entire system is plain Markdown files. No framework to learn, no database to maintain, no Docker to configure, no daemon to babysit. Every skill is a...
- - **2026-04-03** — ☁️ **[Modal serverless GPU](skills/serverless-modal/SKILL.md)** — no GPU? gpu: modal in CLAUDE.md, one command (modal run launcher.py), no SSH, no Docker, auto scale-to-zero. **$30/month free tier** —...
+ 1. Copy this skill folder into your local skills directory.
+ 2. Clone the repo and symlink or copy the skill into your agent workspace.
+ 3. Add the repo as a git submodule if you manage shared skills centrally.
+ 4. Install it through your internal provisioning or packaging workflow.
+ 5. Download the folder directly from GitHub and place it in your skills collection.
- Basic usage or getting-started notes:
- - **v0.4.10** (2026-05-17) — Stream + MCP reliability + multi-provider pricing. C6 whole-stream restart in Anthropic MessageStream + OpenAI SSE loop on chunk decode failure / premature EOF (ARIS_STREAM_RETRY, default 2,...
- - 🌙 **Let Claude Code do research while you sleep.** Wake up to find your paper scored, weaknesses identified, experiments run, and narrative rewritten — autonomously.
- - Custom [Claude Code](https://docs.anthropic.com/en/docs/claude-code) skills for autonomous ML research workflows. These skills orchestrate **cross-model collaboration** — Claude Code drives the research while an exter...
+ Install command or upstream instructions:
- - Source: https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep
- - Extracted from upstream docs: https://raw.githubusercontent.com/wanshuiyin/Auto-claude-code-research-in-sleep/HEAD/README.md
+ ```
+ Install the ARIS skill pack or download the latest ARIS-Code release, configure model providers, then invoke the relevant research skill from the supported agent runtime or CLI.
+ ```
## Documentation
- https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep
## Source
- [Agent Skill Exchange](https://agentskillexchange.com/skills/automate-ml-research-loops-with-aris-skills/)