ARIS: Auto-claude-code-research-in-sleep
What it is. ARIS (Auto-Research-In-Sleep): about 80 Markdown-only skills for autonomous ML research with no framework lock-in: literature search (arXiv, OpenAlex, Semantic Scholar, alphaXiv), idea discovery, novelty checks, experiment planning and monitoring (Modal, Vast GPU), an auto-research loop, paper writing, figures, posters, slides, rebuttals, resubmission, patent pipelines, and cross-model review loops via Codex or Gemini MCP. The README documents workflows from idea to camera-ready and a "research wiki" that persists memory between runs.
| Upstream | wanshuiyin/Auto-claude-code-research-in-sleep |
| License | MIT |
| Author | wanshuiyin |
| Stars (at fetch) | 15,959 |
| Fetched | 2026-09-10 |
Install
- Clone the repo and run
bash tools/install_aris.sh(project-local symlinks;--list-groupsshows the 10 groups,--groups paper-core,lit-searchinstalls a subset), or copyskills/*into~/.claude/skills/. - Review skills need the Codex MCP configured; see the README section "Set up Codex MCP".
Skills
Skill folders (skills/<name>/SKILL.md): ablation-planner, alphaxiv, analyze-results, arxiv, auto-paper-improvement-loop, auto-review-loop, auto-review-loop-llm, auto-review-loop-minimax, citation-audit, claims-drafting, comm-lit-review, deepxiv, dse-loop, embodiment-description, exa-search, experiment-audit, experiment-bridge, experiment-plan, experiment-queue, feishu-notify, figure-description, figure-spec, formula-derivation, gemini-search, grant-proposal, idea-creator, idea-discovery, idea-discovery-robot, integrity-forensics, interview-cheatsheet, invention-structuring, jurisdiction-format, kill-argument, mermaid-diagram, meta-apply, meta-optimize, monitor-experiment, novelty-check, openalex, overleaf-sync, paper-claim-audit, paper-compile, paper-figure, paper-illustration, paper-illustration-image2, paper-plan, paper-poster, paper-poster-html, paper-slides, paper-talk, paper-write, paper-writing, patent-novelty-check, patent-pipeline, patent-review, pixel-art, prior-art-search, proof-checker, proof-orchestrator, proof-writer, qzcli, rebuttal, render-html, research-lit, research-pipeline, research-refine, research-refine-pipeline, research-review, research-wiki, resubmit-pipeline, result-to-claim, run-experiment, semantic-scholar, serverless-modal, skills-codex, skills-codex-claude-review, skills-codex-gemini-review, slides-polish, specification-writing, system-profile, training-check, vast-gpu, web-debug-search, wiki-enrich, writing-systems-papers.
Back to Agent skills.