Skill 与 AgentSKILLS & AGENTS· MCP-SERVER
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.
根据公开文档整理，未运行实测；费用以项目官网为准。Based on public documentation, without runtime testing. Check the project site for pricing.
能力CAPABILITIES
上手GET STARTED
git clone https://github.com/wanshuiyin/Auto-claude-code-research-in-sleep.git选择与你的环境对应的方式。命令来自项目文档，未运行实测。Choose the option for your environment. Commands come from project documentation and have not been run-tested.
使用限制LIMITATIONS
以下要求与风险来自文档静态检查，未执行项目代码；扫描没有命中，不代表使用安全。Risk here is evidence, not an alarm. These findings come from static scanning of the docs; we never execute a project’s code.
限制LIMITS
需检查Needs review
静态扫描STATIC SCAN
01执行 Shell 命令Runs shell commandsskills/ablation-planner/SKILL.md
allowed-tools: Bash(*)
02读写本地文件Reads and writes local filesskills/ablation-planner/SKILL.md
allowed-tools: Write
03读写本地文件Reads and writes local filesskills/ablation-planner/SKILL.md
allowed-tools: Edit
04执行 Shell 命令Runs shell commandsskills/alphaxiv/SKILL.md
allowed-tools: Bash(*)
05读取 API KeyReads an API keyskills/gemini-search/SKILL.md
Claude Code automatically loads `.claude/.env` as environment variables.
06读取 API KeyReads an API keyskills/openalex/SKILL.md
Claude Code automatically loads `.claude/.env` as environment variables.
07控制浏览器Controls a browserskills/paper-poster-html/SKILL.md
via Playwright print emulation. **Iterate by measuring, not eyeballing** — the screen
项目动态PROJECT ACTIVITY
首次发现FIRST SEEN
26 OCT 202626 OCT 2026
状态STATUS
持续活跃Active
{
"agents": [
{
"agent": "claude-code",
"evidence": "tree: .claude-plugin/"
},
{
"agent": "codex",
"evidence": "readme: …c.com/en/docs/claude-code) / [Codex CLI](skills/skills-codex/) / [Cur…"
},
{
"agent": "windsurf",
"evidence": "readme: …s/COPILOT_CLI_ADAPTATION.md), Windsurf, or your own agent and the wo…"
},
{
"agent": "cline",
"evidence": "readme: …ver for Claude Code / Codex / Cline. Alternative implementation p…"
},
{
"agent": "gemini-cli",
"evidence": "readme: …*Action required**: requires `gemini-cli` v0.40+ (run `gemini --versio…"
},
{
"agent": "copilot",
"evidence": "readme: …ANTIGRAVITY_ADAPTATION.md) / [GitHub Copilot CLI](docs/COPILOT_CLI_ADAPTAT…"
},
{
"agent": "claude-desktop",
"evidence": "skills/gemini-search/SKILL.md: …e.json` (or `%APPDATA%\\Claude\\claude_desktop_config.json` for Claude Desktop), add: `…"
},
{
"agent": "vscode",
"evidence": "skills/mermaid-diagram/SKILL.md: …n preview (renders on GitHub, VS Code, etc.) figures/<diagram-nam…"
}
],
"apiKey": "sage instead of a misleading `OPENAI_API_KEY`/`gpt-5.5` error. Built with the v0.4.1",
"docker": null,
"taxonomy": {
"scores": {
"design": 0,
"ai-tools": 12,
"dev-tools": 1,
"indie-web": 0,
"skill-agent": 10,
"productivity": 0
},
"primary": "skill-agent",
"secondary": "mcp-server"
},
"localRuntime": "ure sources), `/qzcli` (Qizhi GPU jobs). 46 existing SKILL.md refreshed —",
"skillMdTotal": 197,
"skillMdErrors": [],
"treeTruncated": false,
"categoryScores": {
"data": 14,
"agent": 5,
"media": 0,
"design": 0,
"browser": 0,
"devtool": 1,
"security": 0,
"marketing": 0,
"productivity": 1
},
"classification": [
{
"signal": "60 SKILL.md with name + description",
"weight": 0.95
},
{
"signal": "skills/ directory with 295 markdown files",
"weight": 0.75
},
{
"signal": "README describes a Claude / Agent Skill",
"weight": 0.7
},
{
"signal": "Claude Code plugin manifest",
"weight": 0.7
},
{
"signal": "MCP topic + README",
"weight": 0.6
},
{
"signal": "description mentions AI",
"weight": 0.2
}
],
"scannedSources": [
"readme",
"skills/ablation-planner/SKILL.md",
"skills/alphaxiv/SKILL.md",
"skills/analyze-results/SKILL.md",
"skills/arxiv/SKILL.md",
"skills/auto-paper-improvement-loop/SKILL.md",
"skills/auto-review-loop-llm/SKILL.md",
"skills/auto-review-loop-minimax/SKILL.md",
"skills/auto-review-loop/SKILL.md",
"skills/citation-audit/SKILL.md",
"skills/citation-crosscheck/SKILL.md",
"skills/claims-drafting/SKILL.md",
"skills/comm-lit-review/SKILL.md",
"skills/deepxiv/SKILL.md",
"skills/dse-loop/SKILL.md",
"skills/embodiment-description/SKILL.md",
"skills/exa-search/SKILL.md",
"skills/experiment-audit/SKILL.md",
"skills/experiment-bridge/SKILL.md",
"skills/experiment-plan/SKILL.md",
"skills/experiment-queue/SKILL.md",
"skills/feishu-notify/SKILL.md",
"skills/figure-description/SKILL.md",
"skills/figure-spec/SKILL.md",
"skills/firecrawl-search/SKILL.md",
"skills/formula-derivation/SKILL.md",
"skills/gemini-search/SKILL.md",
"skills/grant-proposal/SKILL.md",
"skills/idea-creator/SKILL.md",
"skills/idea-discovery-robot/SKILL.md",
"skills/idea-discovery/SKILL.md",
"skills/integrity-forensics/SKILL.md",
"skills/interview-cheatsheet/SKILL.md",
"skills/invention-structuring/SKILL.md",
"skills/jurisdiction-format/SKILL.md",
"skills/keenable-search/SKILL.md",
"skills/kill-argument/SKILL.md",
"skills/lean-formalize/SKILL.md",
"skills/mermaid-diagram/SKILL.md",
"skills/meta-apply/SKILL.md",
"skills/meta-optimize/SKILL.md",
"skills/monitor-experiment/SKILL.md",
"skills/novelty-check/SKILL.md",
"skills/openalex/SKILL.md",
"skills/overleaf-sync/SKILL.md",
"skills/paper-claim-audit/SKILL.md",
"skills/paper-compile/SKILL.md",
"skills/paper-figure/SKILL.md",
"skills/paper-illustration-image2/SKILL.md",
"skills/paper-illustration/SKILL.md",
"skills/paper-plan/SKILL.md",
"skills/paper-poster-html/SKILL.md",
"skills/paper-poster/SKILL.md",
"skills/paper-slides/SKILL.md",
"skills/paper-talk/SKILL.md",
"skills/paper-write/SKILL.md",
"skills/paper-writing/SKILL.md",
"skills/patent-novelty-check/SKILL.md",
"skills/patent-pipeline/SKILL.md",
"skills/patent-review/SKILL.md",
"skills/pixel-art/SKILL.md"
],
"skillMdFetched": 60
}