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.
ARIS is a collection of Markdown-based skills that define a workflow for autonomous machine-learning research, including idea discovery, experiment automation, and review loops. Researchers and AI coding agents use it across tools such as Claude Code, Codex, Cursor, and OpenClaw without depending on a single framework. The catalogue entries are ARIS workflow skills and agents.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code needs its repo
A workflow for writing a research paper section by section in LaTeX, a text format used to prepare structured technical documents. It starts from a paper outline and supports several academic venues and citation sources.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code needs its repo
A complete workflow for turning an invention description into patent filing documents. A patent is a legal document that claims exclusive rights to an invention, and the workflow supports Chinese, United States, and European filing formats.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code
A patentability assessment that checks whether an invention is new and not an obvious variation of earlier publicly known work. It uses patent standards rather than the looser standards used to judge research contributions.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code
A full workflow for preparing a patent application from an invention description. It covers the stages from finding earlier work through drafting, review, and formatting for Chinese, United States, or European filing.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code
A workflow that reviews a patent application as a patent examiner would. A patent examiner is the official who checks whether an application meets the legal requirements for patent protection.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code
A generator for creating pixel-art illustrations as SVG files, a resolution-independent image format made from shapes and code. It targets simple visuals for technical documents and presentations.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code
A search workflow for finding earlier patents and academic papers related to an invention. In patent work, prior art means publicly available earlier work that can affect whether an invention qualifies for protection.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code needs its repo
A mathematical proof review and repair workflow for LaTeX documents. It checks whether a proof has valid reasoning, addresses identified gaps, reviews the fixes, and produces an audit report.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code
Manage a stateful, run-directory-based proof project: continuation across runs, run-local source bookkeeping, manual GPT Pro handoff packages when a local attempt stalls, and an optional DeepSeek second opinion as additional evidence only. Use when the user asks for proof-run orchestration, a GPT Pro handoff, or…
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code
A tool for writing or checking rigorous mathematical proofs for claims such as theorems, lemmas, propositions, and corollaries.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code
A command-line tool for managing GPU compute jobs on the Qizhi platform, a service for running machine-learning workloads on shared GPUs.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code
Workflow 4: Submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal under venue limits, and manages follow-up rounds. Use when user says "rebuttal", "reply to reviewers", "ICML rebuttal", "OpenReview response", or wants to answer external reviews safely.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code needs its repo
A command-line tool for managing GPU jobs on the Qizhi computing platform, a service for running machine-learning workloads on shared graphics processors.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code needs its repo
Search and analyze research papers, find related work, summarize key ideas. Use when user says "find papers", "related work", "literature review", "what does this paper say", or needs to understand academic papers.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude CodeCodex needs its repo
A workflow for taking a broad research direction through experiments, external review, and preparation of a final paper PDF.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code needs its repo
An end-to-end workflow that first sharpens a vague research direction and then turns it into a detailed experiment plan.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code needs its repo
A research-planning guide that turns a broad research idea into a specific method and a small validation plan.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code needs its repo
Get a deep critical review of research from an external reviewer backend (Codex or manual). Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code
A persistent research knowledge base for storing papers, ideas, experiments, claims, and the links between them.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code
A workflow for adapting an already polished research paper for submission to a different publication venue. It makes text-only edits under restrictions such as no new experiments, bibliography changes, or framework changes.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code needs its repo
Use when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. Codex MCP evaluates results against intended claims and routes to next action (pivot, supplement, or confirm). Use after experiments finish — before writing the paper or running ablations.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code needs its repo
Search published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /arxiv (preprints) with citation counts, venue metadata, and TLDR. Use when user says "search semantic scholar", "find IEEE papers", "find journal papers", "venue papers", "citation search", or wants published literature…
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code needs its repo
Run GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero. Use when user says "modal run", "modal training", "modal inference", "deploy to modal", "need a GPU", "run on modal", "serverless GPU", or needs remote GPU compute.
wanshuiyin/Auto-claude-code-research-in-sleep
Skill Claude Code
Per-page Codex review + targeted python-pptx / Beamer fixes for academic talk slides. Use AFTER /paper-slides (or any externally generated PPTX/Beamer) when the deck looks 'mostly OK' but the user wants a final pass that aligns visual weight with a reference, bumps PPTX fonts to projector-readable size, kills italic…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: