wanshuiyin/Auto-claude-code-research-in-sleep

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.

About the project

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.

16kStars on the repository
82Mods indexed here, across every type
yesterdayLast push, which is what freshness is scored on
MITLicence, which decides whether bodies are shown

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code needs its repo

A robotics-focused workflow for turning a broad robotics or embodied-AI direction into ideas grounded in papers, benchmarks, and experiments. Embodied AI means artificial intelligence that acts through a physical or simulated robot.

not rated 16k +270 changed 5d ago A Socket: passSnyk: warnSkillSpector: pass 104 tokens original MIT

idea-discovery

26

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code needs its repo

A full research-idea workflow that moves from a broad topic to candidate ideas, novelty checks, critical review, refinement, and an experiment plan.

not rated 16k +270 changed 5d ago A Socket: warnSnyk: failSkillSpector: warn 56 tokens original MIT

integrity-forensics

27

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code needs its repo

Run the Anti-Autoresearch integrity-forensics sweep (span-anchored evidence ledger → GPT auditors propose findings → a rules-only reporter that lists every proposal with what the auditor said about it) against a paper via a SHA-pinned thin launcher — then convert the verdict into a typed policy gate…

not rated 16k +270 changed 5d ago A SkillSpector: warn 162 tokens original MIT

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code needs its repo

A long Chinese study guide for preparing machine-learning and large-language-model job interviews, with explanations, formulas, code, comparisons, and practice questions.

not rated 16k +270 changed 5d ago A SkillSpector: pass 121 tokens original MIT

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code

A workflow for turning a rough invention idea into a structured invention disclosure, which is a document describing a possible patentable technical solution.

not rated 16k +270 changed 5d ago A Socket: passSnyk: passSkillSpector: pass 56 tokens original MIT

jurisdiction-format

30

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code

A document-formatting workflow for preparing a patent application for the filing rules of China, the United States, or Europe.

not rated 16k +270 yesterday A Socket: passSnyk: passSkillSpector: pass 47 tokens original MIT

kill-argument

31

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code needs its repo

Two-thread adversarial review: a fresh reviewer constructs the strongest 200-word rejection memo, then a second fresh reviewer defends the paper point-by-point and surfaces still-unresolved critical issues. Use when user says "kill argument", "adversarial review", "hostile review", "rebuttal preparation", "reviewer-2…

not rated 16k +270 changed 5d ago A Snyk: passSkillSpector: pass 88 tokens original MIT

mermaid-diagram

32

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code

Generate Mermaid diagrams from user requirements. Supports flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, and 18 more diagram types.

not rated 16k +270 yesterday A Socket: passSnyk: warnSkillSpector: warn 36 tokens original MIT

meta-apply

33

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code

A controlled workflow for applying previously reviewed changes to the coding-agent skill library.

not rated 16k +270 changed 5d ago A SkillSpector: pass 81 tokens original MIT

meta-optimize

34

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code needs its repo

A read-only review workflow that studies usage records and proposes changes to coding-agent skills, prompts, or default settings.

not rated 16k +270 changed 5d ago A Socket: passSnyk: passSkillSpector: warn 81 tokens original MIT

monitor-experiment

35

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code needs its repo

Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output.

not rated 16k +270 yesterday A Socket: passSnyk: warnSkillSpector: pass 35 tokens original MIT

novelty-check

36

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code

A literature search for checking whether a research idea has already been published. It compares the idea with recent papers and preprints, including work from major machine-learning conferences.

not rated 16k +270 changed 5d ago A Socket: passSnyk: warnSkillSpector: pass 49 tokens original MIT

openalex

37

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code needs its repo

Search academic papers via OpenAlex API for open citation data, institutional affiliations, and funding information. Use when user says "openalex search", "search openalex", "open citation graph", or wants comprehensive academic metadata beyond arXiv/Semantic Scholar.

not rated 16k +270 yesterday A SkillSpector: warn 55 tokens original MIT

overleaf-sync

38

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code

A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.

not rated 16k +270 yesterday B SkillSpector: warn 97 tokens original MIT

paper-claim-audit

39

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code needs its repo

A zero-context check that compares the numbers, comparisons, and scope statements in a paper with the raw experiment result files. It uses a fresh reviewer that has not seen the earlier research process.

not rated 16k +270 changed 5d ago A Socket: passSnyk: passSkillSpector: pass 77 tokens original MIT

paper-compile

40

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code

A build workflow that turns LaTeX source files into a PDF and checks whether the paper compiles correctly. LaTeX is a text-based system commonly used for academic papers.

not rated 16k +270 yesterday B Socket: passSnyk: passSkillSpector: warn 53 tokens original MIT

paper-figure

41

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code

A tool for turning experiment results into plots and comparison tables for research papers. It can also combine plots into multi-panel figures, such as a grid comparing datasets and methods.

not rated 16k +270 changed 5d ago A Socket: passSnyk: passSkillSpector: pass 41 tokens original MIT

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code needs its repo

Generate publication-quality academic illustrations through a local Codex app-server bridge that uses Codex native image generation. This is a separate experimental alternative to paper-illustration, intended for Claude Code users who want a GPT-image-style renderer without modifying the original skill.

not rated 16k +270 yesterday A Snyk: passSkillSpector: pass 59 tokens original MIT

paper-illustration

43

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code needs its repo

A workflow for generating academic illustrations, such as architecture diagrams and method visuals, with image generation and repeated review. Claude plans and checks the figure during the process.

not rated 16k +270 yesterday A Socket: passSnyk: warnSkillSpector: warn 67 tokens original MIT

paper-plan

44

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code needs its repo

A structured plan for writing a research paper, based on review conclusions and experiment results. It organizes the paper section by section and can target venues such as ICLR, NeurIPS, ICML, CVPR, or IEEE publications.

not rated 16k +270 changed 5d ago A Socket: passSnyk: warnSkillSpector: warn 47 tokens original MIT

paper-poster-html

45

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code

A workflow for building an academic conference poster as one HTML/CSS file and printing it to a PDF at an exact page size. It uses the paper’s real figures and checks layout details before review.

not rated 16k +270 changed 5d ago A Snyk: warnSkillSpector: warn 107 tokens original MIT

paper-poster

46

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code

DEPRECATED — superseded by /paper-poster-html. Kept only as a redirect for muscle memory; do not use for new posters.

not rated 16k +270 yesterday A Socket: passSnyk: warnSkillSpector: warn 33 tokens original MIT

paper-slides

47

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code needs its repo

A workflow for turning a completed research paper into conference presentation slides, an editable PowerPoint file, speaker notes, and a full talk script. A conference talk presents the paper's problem, method, results, and conclusions to an audience.

not rated 16k +270 changed 5d ago A Socket: passSnyk: failSkillSpector: warn 81 tokens original MIT

paper-talk

48

wanshuiyin/Auto-claude-code-research-in-sleep

Skill Claude Code needs its repo

An end-to-end workflow for turning a completed research paper into a conference talk. It can produce a slide outline, Beamer source, an editable PowerPoint deck, speaker notes, a talk script, and assurance reports.

not rated 16k +270 yesterday A SkillSpector: pass 113 tokens original MIT

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: