ARIS Auto-Review Loop
16,849 starsThe core skill of ARIS (Auto-Research-In-Sleep): an autonomous multi-round review loop that calls an external reviewer model (Codex by default) to critique and fix repeatedly until a policy-approved positive assessment or a cap is reached.
- First published：2026-03-10
- data as of：
- 2026-09-30
- Licence：
- MIT
When to use it
For autonomous ML research where paper-grade output benefits from cross-model review loops running unattended.
Caution
Multi-round cross-model review multiplies token cost; needs extra model CLIs (e.g. Codex) and keys. The suite is a large repo of 189 SKILL.md files — markdown-only and lightweight, but sprawling.
Install prompt
請幫我安裝「ARIS Auto-Review Loop」技能：從 https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep/tree/main/skills/auto-review-loop（技能路徑：skills/auto-review-loop/） 取得完整的技能目錄，放進我的 Agent 的技能目錄（例如專案內的 skills/ 資料夾，或該 Agent 文件指明的全域技能位置），確認裡面的 SKILL.md 存在、frontmatter 的 name 與 description 完整，然後列出這個技能宣告的腳本、外部工具與 API 需求，先不要執行任何腳本。Paste this to your agent. It deliberately contains no tool subcommands — check the tool's official docs for commands.
Compatible with
Related patterns