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
ARCHETYPE
Skill Collector
Ten-plus skills loaded on demand. A procedural-knowledge library.
Copy this rig
# review before running: this installs third-party code $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/commands ./rig-auto-claude-code-research-in-sleep/commands $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills ./rig-auto-claude-code-research-in-sleep/skills
MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.
$ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/ablation-planner .claude/skills/ablation-planner $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/alphaxiv .claude/skills/alphaxiv $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/analyze-results .claude/skills/analyze-results $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/arxiv .claude/skills/arxiv $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/auto-paper-improvement-loop .claude/skills/auto-paper-improvement-loop $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/auto-review-loop-llm .claude/skills/auto-review-loop-llm $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/auto-review-loop-minimax .claude/skills/auto-review-loop-minimax $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/auto-review-loop .claude/skills/auto-review-loop $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/citation-audit .claude/skills/citation-audit $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/claims-drafting .claude/skills/claims-drafting $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/comm-lit-review .claude/skills/comm-lit-review $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/deepxiv .claude/skills/deepxiv $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/dse-loop .claude/skills/dse-loop $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/embodiment-description .claude/skills/embodiment-description $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/exa-search .claude/skills/exa-search $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/experiment-audit .claude/skills/experiment-audit $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/experiment-bridge .claude/skills/experiment-bridge $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/experiment-plan .claude/skills/experiment-plan $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/experiment-queue .claude/skills/experiment-queue $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/feishu-notify .claude/skills/feishu-notify $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/figure-description .claude/skills/figure-description $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/figure-spec .claude/skills/figure-spec $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/formula-derivation .claude/skills/formula-derivation $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/gemini-search .claude/skills/gemini-search $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/grant-proposal .claude/skills/grant-proposal $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/idea-creator .claude/skills/idea-creator $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/idea-discovery-robot .claude/skills/idea-discovery-robot $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/idea-discovery .claude/skills/idea-discovery $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/integrity-forensics .claude/skills/integrity-forensics $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/interview-cheatsheet .claude/skills/interview-cheatsheet $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/invention-structuring .claude/skills/invention-structuring $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/jurisdiction-format .claude/skills/jurisdiction-format $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/kill-argument .claude/skills/kill-argument $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/lean-formalize .claude/skills/lean-formalize $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/mermaid-diagram .claude/skills/mermaid-diagram $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/meta-apply .claude/skills/meta-apply $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/meta-optimize .claude/skills/meta-optimize $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/monitor-experiment .claude/skills/monitor-experiment $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/novelty-check .claude/skills/novelty-check $ npx degit wanshuiyin/Auto-claude-code-research-in-sleep/skills/openalex .claude/skills/openalex
This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 7,204 rigs:
{
"permissions": {
"deny": [
"Read(./.env)",
"Read(**/.env)",
"Read(~/.ssh/**)",
"Bash(rm -rf *)",
"Read(**/*.pem)",
"Bash(rm -rf /)",
"Bash(git push --force:*)",
"Bash(sudo *)",
"Read(.env)",
"Bash(rm -rf /*)",
"Read(./.env.*)",
"Read(~/.aws/**)",
"Bash(git push --force*)",
"Bash(rm -rf:*)",
"Read(**/*.key)",
"Read(**/.env.*)",
"Bash(sudo:*)",
"Bash(git reset --hard*)",
"Bash(git reset --hard:*)",
"Read(.env.*)"
],
"ask": [
"Bash(git push:*)",
"Bash(git push *)",
"Bash(git commit:*)",
"Bash(rm *)",
"Bash(rm:*)",
"Bash(git rebase *)",
"Bash(wget *)",
"Bash(npm publish:*)",
"Bash(git commit *)",
"Bash(gh pr merge *)"
]
}
} Skills (84)
ablation-planneralphaxivanalyze-resultsarxivauto-paper-improvement-loopauto-review-loop-llmauto-review-loop-minimaxauto-review-loopcitation-auditclaims-draftingcomm-lit-reviewdeepxivdse-loopembodiment-descriptionexa-searchexperiment-auditexperiment-bridgeexperiment-planexperiment-queuefeishu-notifyfigure-descriptionfigure-specformula-derivationgemini-searchgrant-proposalidea-creatoridea-discovery-robotidea-discoveryintegrity-forensicsinterview-cheatsheetinvention-structuringjurisdiction-formatkill-argumentlean-formalizemermaid-diagrammeta-applymeta-optimizemonitor-experimentnovelty-checkopenalexoverleaf-syncpaper-claim-auditpaper-compilepaper-figurepaper-illustration-image2paper-illustrationpaper-planpaper-poster-htmlpaper-posterpaper-slidespaper-talkpaper-writepaper-writingpatent-novelty-checkpatent-pipelinepatent-reviewpixel-artprior-art-searchproof-checkerproof-orchestratorproof-writerqzclirebuttalrender-htmlresearch-implement-featureresearch-litresearch-pipelineresearch-refine-pipelineresearch-refineresearch-reviewresearch-wikiresubmit-pipelineresult-to-claimrun-experimentsemantic-scholarserverless-modalslides-polishspecification-writingsystem-profiletraining-checkvast-gpuweb-debug-searchwiki-enrichwriting-systems-papers
Slash commands (1)
/setup
Similar rigs
Yichen-ZJU/claude-for-research
Autonomous research for Claude Code: literature, ideas, unattended experiments, writing and review. 115 skills, two loops.
Skill Collector 7.0k tok ·
wanshuiyin/ARIS-in-AI-Offer
Bilingual (中文+EN) ML / LLM / diffusion / agent interview cheat sheets for AI 秋招 — generated by ARIS /interview-cheatsheet, rendered by /render-html into single-file HTML, reads anywhere — plus a CV→DBLP-fact-checked academic homepage genera
Minimalist 260 tok ·
nicehiro/dotfiles
—
Skill Collector 6.5k tok ·
diillson/chatcli
ChatCLI is a command-line application that utilizes LLMs—such as those from Anthropic, OpenAI, and others—to facilitate interactive conversations within the terminal. At its core, it features a specialized agent and tools that provide uniqu
Skill Collector 3.8k tok ·