Use when main results pass result-to-claim (`claim_supported = yes` or `partial`) and ablation studies are needed for paper submission. A secondary Codex agent
所属插件包:aris
正在加载项目…
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.
One-time setup after installing ARIS as a Claude Code plugin — registers the Codex reviewer MCP server from the plugin directory and points ARIS helpers at it.
所属插件包:aris
Use when main results pass result-to-claim (`claim_supported = yes` or `partial`) and ablation studies are needed for paper submission. A secondary Codex agent
所属插件包:aris
Use when main results pass result-to-claim (claim_supported=yes or partial) and ablation studies are needed for paper submission.
其他仓库内容 · 未声明插件包归属
Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes a
其他仓库内容 · 未声明插件包归属
Quick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes a
所属插件包:aris
Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpr
其他仓库内容 · 未声明插件包归属
Analyze ML experiment results, compute statistics, generate comparison tables and insights. Use when user says "analyze results", "compare", or needs to interpr
所属插件包:aris
Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf",
所属插件包:aris
Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf",
其他仓库内容 · 未声明插件包归属
Autonomously improve a generated paper via Claude review through claude-review MCP → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "impro
其他仓库内容 · 未声明插件包归属
Autonomously improve a generated paper via GPT-6-Astra xhigh review → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润
其他仓库内容 · 未声明插件包归属
Autonomously improve a generated paper via GPT-6-Astra xhigh review → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "improve paper", "论文润
所属插件包:aris
Autonomously improve a generated paper via Gemini review through gemini-review MCP → implement fixes → recompile, for 2 rounds. Use when user says "改论文", "impro
其他仓库内容 · 未声明插件包归属
Autonomous multi-round research review loop. Repeatedly reviews using Gemini via gemini-review MCP, implements fixes, and re-reviews until positive assessment o
其他仓库内容 · 未声明插件包归属
Autonomous multi-round research review loop. Repeatedly reviews using Claude Code via claude-review MCP, implements fixes, and re-reviews until positive assessm
其他仓库内容 · 未声明插件包归属
Autonomous multi-round research review loop. In Copilot CLI it defaults to the native complementary rubber-duck subagent with host-event model evidence; elsewhe
其他仓库内容 · 未声明插件包归属
Autonomous multi-round research review loop. Repeatedly reviews using a secondary Codex agent, implements fixes, and re-reviews until positive assessment or max
所属插件包:aris
Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop
所属插件包:aris
Autonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop
其他仓库内容 · 未声明插件包归属
Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto rev
所属插件包:aris
Autonomous multi-round research review loop using MiniMax API. Use when you want to use MiniMax instead of Codex MCP for external review. Trigger with "auto rev
其他仓库内容 · 未声明插件包归属
Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — c
所属插件包:aris
Zero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — c
其他仓库内容 · 未声明插件包归属
Draft patent claims for an invention. Use when user says "撰写权利要求", "draft claims", "写权利要求书", "claim drafting", or wants to create patent claims. The core skill
其他仓库内容 · 未声明插件包归属