Ecc
The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond.
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works with Claude Code, Codex, OpenClaw, or any LLM agent.
<p align="center"> <a href="https://huggingface.co/papers/2605.03042"> <img src="docs/hf_daily_paper_1.svg" alt="Hugging Face Daily Paper · #1 Paper of the Day" width="360"> </a> </p> [](#quick-start) · [](#how-to-run) · [](https://huggingface.co/papers/2605.03042) · [](https://wanshuiyin.github.io/Auto-claude-code-research-in-sleep/ARIS_INTRO.html) · [](docs/aris_intro_slides.pdf) · [](AGENT_GUIDE.md) ·
git clone --depth 1 https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep.git ~/.claude/skills/auto-claude-code-research-in-sleep
Restart Claude Code afterwards. See the README for skill-specific setup.
Using Codex CLI? Copy the same folder to ~/.codex/skills/auto-claude-code-research-in-sleep instead.
No specific triggers listed.
<p align="center"> <a href="https://huggingface.co/papers/2605.03042"> <img src="docs/hf_daily_paper_1.svg" alt="Hugging Face Daily Paper · #1 Paper of the Day" width="360"> </a> </p> [](#quick-start) · [](#how-to-run) · [](https://huggingface.co/papers/2605.03042) · [](https://wanshuiyin.github.io/Auto-claude-code-research-in-sleep/ARIS_INTRO.html) · [](docs/aris_intro_slides.pdf) · [](AGENT_GUIDE.md) ·
Clone it into your personal skills folder: git clone --depth 1 https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep.git ~/.claude/skills/auto-claude-code-research-in-sleep — then restart Claude Code.
Auto Claude Code Research In Sleep is open source on GitHub (19495 stars at last check) and published by wanshuiyin.
Browse other research skills in the Research category of this directory.