wanshuiyin
- 195 skills
- 0 followers
- 19k repo stars
- 2 days ago last updated
- ▌ Invention Structuring · wanshuiyinStructure a raw invention idea into a formal invention disclosure. Use when user says "构建发明", "structure invention", "发明构建", "invention disclosure", or wants to formalize a rough idea into a patent-ready structure.
- ▌ Specification Writing · wanshuiyinWrite the full patent specification from claims and invention disclosure. Use when user says "撰写说明书", "write specification", "写说明书", "patent description", or wants to draft the complete patent specification.
- ▌ Auto Paper Improvement Loop · wanshuiyinAutonomously 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", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.
- ▌ Mermaid Diagram · wanshuiyinGenerate Mermaid diagrams from user requirements. Supports flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, and 18 more diagram types.
- ▌ Alphaxiv · wanshuiyinQuick single-paper lookup via AlphaXiv LLM-optimized summaries with tiered source fallback. Use when user says "explain this paper", "summarize paper", pastes an arXiv/AlphaXiv URL, or provides a bare arXiv ID for quick understanding - not for broad literature search.
- ▌ Openalex · wanshuiyinSearch 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.
- ▌ Paper Writing 2 · wanshuiyinWorkflow 3: Full paper writing pipeline that goes from a narrative report to a polished, submission-ready PDF. Use when user says "写论文全流程", "write paper pipeline", "从报告到PDF", "paper writing", or wants the complete paper generation workflow.
- ▌ Grant Proposal 2 · wanshuiyinDraft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including 面上/青年/优青/杰青/海外优青/重点), ERC (EU), DFG (Germany), SNSF (Switzerland), ARC (Australia), NWO (Netherlands), and generic formats. Use when user says "write grant", "grant proposal", "申請書", "write KAKENHI", "科研費", "基金申请", "写基金", "NSF proposal", or wants to turn research ideas into a funding application.
- ▌ Paper Illustration Image2 · wanshuiyin bundleGenerate 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.
- ▌ Gemini Search · wanshuiyinSearch research papers via Gemini for broad literature discovery. Use when user says "gemini search", "gemini papers", "search with gemini", or wants AI-powered literature discovery beyond arXiv/Semantic Scholar indexes.
- ▌ Kill Argument · wanshuiyinTwo-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 simulation", or before submitting a theory paper that has already passed standard review rounds.
- ▌ Meta Optimize · wanshuiyinAnalyze ARIS usage logs and propose optimizations to SKILL.md files, reviewer prompts, and workflow defaults. Outer-loop harness optimization inspired by Meta-Harness (Lee et al., 2026). Use when user says "优化技能", "meta optimize", "improve skills", "分析使用记录", or wants to optimize ARIS's own harness components based on accumulated experience.
- ▌ Novelty Check · wanshuiyinVerify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.
- ▌ Patent Review · wanshuiyinGet an external patent examiner review of a patent application. Use when user says "专利审查", "patent review", "审查意见", "examiner review", or wants critical feedback on patent claims and specification.
- ▌ Proof Checker · wanshuiyinRigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via fresh-agent Codex GPT-6-Astra ultra review, fixes each gap with full derivations, re-reviews, and generates an audit report. Base review is same-family provisional. Use when user says "检查证明", "verify proof", "proof check", "审证明", "check this proof", or wants rigorous mathematical verification of a theory paper.
- ▌ Research Wiki · wanshuiyinPersistent research knowledge base that accumulates papers, ideas, experiments, claims, and their relationships across the entire research lifecycle. Inspired by Karpathy's LLM Wiki pattern. Use when user says "知识库", "research wiki", "add paper", "wiki query", "查知识库", or wants to build/query a persistent field map.
- ▌ Slides Polish · wanshuiyinPer-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 style leaks, fixes text-frame overflow, and catches per-slide layout drift. Trigger phrases: "polish slides", "slides 排版不对", "PPTX 字体太小", "和 Beamer 比一下", "per-page review", "和 codex 一页一页过".
- ▌ Citation Audit · wanshuiyinZero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — catching hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations. Use when user says "审查引用", "check citations", "citation audit", "verify references", "引用核对", or before submission to ensure bibliography integrity.
- ▌ Idea Discovery · wanshuiyinWorkflow 1: Full idea discovery pipeline to go from a broad research direction to validated, pilot-tested ideas. Use when user says "找idea全流程", "idea discovery pipeline", "从零开始找方向", or wants the complete idea exploration workflow.
- ▌ Run Experiment · wanshuiyinDeploy and run ML experiments on local or remote GPU servers. Use when user says "run experiment", "deploy to server", "跑实验", or needs to launch training jobs.
- ▌ Training Check · wanshuiyinInteractively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.
- ▌ Claims Drafting · wanshuiyinDraft 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 of the patent pipeline.
- ▌ Patent Pipeline · wanshuiyinFull patent drafting pipeline from invention description to jurisdiction-formatted filing documents. Supports CN (CNIPA), US (USPTO), EP (EPO). Supports invention patents and utility models. Use when user says "写专利", "patent pipeline", "专利申请", "draft patent", "写权利要求书", or wants to draft a complete patent application.
- ▌ Research Refine · wanshuiyinTurn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-6-Astra review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.
- ▌ Research Review · wanshuiyinGet a deep critical review of research from a fresh Codex agent or a selected Gemini, Grok, or Claude Code reviewer. Use when user says "review my research", "help me review", "get external review", or wants critical feedback on research ideas, papers, or experimental results.
- ▌ Result To Claim · wanshuiyinUse when experiments complete to judge what claims the results support, what they don't, and what evidence is still missing. A secondary Codex agent 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.
- ▌ Auto Review Loop · wanshuiyinAutonomous multi-round research review loop. Uses a fresh Codex agent or selected Gemini, Grok, or Claude Code reviewer, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.
- ▌ Experiment Audit · wanshuiyinAudit experiment integrity before claiming results. Uses fresh-agent GPT-6-Astra review (same-family provisional in the base Codex mirror) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.
- ▌ Experiment Bridge · wanshuiyinWorkflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says "实现实验", "implement experiments", "bridge", "从计划到跑实验", "deploy the plan", or has an experiment plan ready to execute.
- ▌ Paper Claim Audit · wanshuiyinZero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Uses a fresh Codex reviewer with no prior context; base output is same-family provisional. Use when user says "审查论文数据", "check paper claims", "verify numbers", "论文数字核对", or before submission to ensure paper-to-evidence fidelity.
- ▌ Paper Poster HTML · wanshuiyinDEFAULT poster pipeline — build an academic conference poster (ICML/NeurIPS/ICLR/CVPR/...) as a single HTML/CSS file with measurement-driven hard gates, real paper figures, a two-hue design-token system, and print-ready PDF via headless Chromium. Use when the user says "做海报", "poster", "conference poster", "paper poster", or asks to design/redo a research poster.
- ▌ Research Pipeline · wanshuiyinFull end-to-end research pipeline: from a broad research direction through idea discovery, experiments, and review all the way to a polished paper PDF. Use when user says "全流程", "full pipeline", "从找idea到投稿", "end-to-end research", or wants the complete autonomous research lifecycle.
- ▌ Resubmit Pipeline · wanshuiyinWorkflow 5: orchestrate a text-only resubmit of a polished paper to a different venue under hard constraints (no new experiments, no bib edits, no framework changes, never overwrite prior submissions). Use when user says "resubmit pipeline", "重投流程", "port paper to <new venue>", "resubmit to <venue>", "tighten paper for resubmission", or has a rejected/withdrawn paper to move to a different top venue under tight time budget.
- ▌ Auto Review Loop LLM · wanshuiyinAutonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".
- ▌ Idea Discovery Robot · wanshuiyinWorkflow 1 adaptation for robotics and embodied AI. Orchestrates robotics-aware literature survey, idea generation, novelty check, and critical review to go from a broad robotics direction to benchmark-grounded, simulation-first ideas. Use when user says \"robotics idea discovery\", \"机器人找idea\", \"embodied AI idea\", \"机器人方向探索\", \"sim2real 选题\", or wants ideas for manipulation, locomotion, navigation, drones, humanoids, or general robot learning.
- ▌ Interview Cheatsheet · wanshuiyinGenerate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab). Use when the user says '写面试 cheat sheet', '写一份 X 教程', '帮我准备 Y 面试题', '出一份 X 速查', or wants a 600-1000 line Chinese tutorial on a specific ML topic.
- ▌ Patent Novelty Check · wanshuiyinAssess patent novelty and non-obviousness against prior art. Use when user says "专利查新", "patent novelty", "可专利性评估", "patentability check", or wants to evaluate if an invention is patentable.
- ▌ Paper Writing · wanshuiyinWorkflow 3: Full paper writing pipeline that goes from a narrative report to a polished, submission-ready PDF. Use when user says "写论文全流程", "write paper pipeline", "从报告到PDF", "paper writing", or wants the complete paper generation workflow.
- ▌ Grant Proposal · wanshuiyinDraft a structured grant proposal from research ideas and literature. Supports KAKENHI (Japan), NSF (US), NSFC (China, including 面上/青年/优青/杰青/海外优青/重点), ERC (EU), DFG (Germany), SNSF (Switzerland), ARC (Australia), NWO (Netherlands), and generic formats. Use when user says "write grant", "grant proposal", "申請書", "write KAKENHI", "科研費", "基金申请", "写基金", "NSF proposal", or wants to turn research ideas into a funding application.
- ▌ Rebuttal · wanshuiyinWorkflow 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.
- ▌ Meta Apply · wanshuiyinPrivileged applier that LANDS meta-optimize / corpus-audit patches the user approved, with a fresh landing review and human approval. Base Codex review is same-family provisional. Use when the user says "meta apply", "/meta-apply", "land the staged patches", "应用优化", after a /meta-optimize run.
- ▌ Paper Plan · wanshuiyinGenerate a structured paper outline from review conclusions and experiment results. Use when user says \"写大纲\", \"paper outline\", \"plan the paper\", \"论文规划\", or wants to create a paper plan before writing.
- ▌ Paper Talk · wanshuiyinEnd-to-end conference talk pipeline: paper → slide outline → Beamer + PPTX → per-page polish → assurance checks (claim / citation / anonymity) → final export and report. Default-good for academic conference talks (NeurIPS / ICML / ICLR / VALSE / 投稿 talks). Trigger phrases: "做 talk", "做 PPT 全流程", "talk pipeline", "end-to-end slides", "做演讲", "conference talk full workflow". Use when the user wants the complete talk artifact, not just a slide deck.
- ▌ Research Refine Pipeline · wanshuiyinRun an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal plus detailed experiment roadmap, or asks to "串起来", build a pipeline, do it end-to-end, or generate both the method and experiment plan together.
- ▌ Figure Spec · wanshuiyinGenerate deterministic publication-quality architecture, workflow, and pipeline diagrams from structured JSON (FigureSpec) into editable SVG. Use when user says "架构图", "workflow 图", "pipeline 图", "确定性矢量图", "figure spec", "draw architecture", or needs precise, editable, publication-ready vector diagrams. Preferred over AI illustration for formal architecture/workflow figures.
- ▌ Paper Write · wanshuiyin bundleDraft LaTeX paper section by section from an outline. Use when user says \"写论文\", \"write paper\", \"draft LaTeX\", \"开始写\", or wants to generate LaTeX content from a paper plan.
- ▌ Render HTML · wanshuiyin bundleRender an ARIS Markdown / JSON artifact (IDEA_REPORT, AUTO_REVIEW, KILL_ARGUMENT, PAPER_PLAN, research-wiki state, etc.) into a single-file HTML view designed for human reading. Use when the user says "渲染 HTML", "出一份 HTML 报告", "render html", "make this readable", "export to html", or wants a polished web-rendered view of a Markdown artifact.
- ▌ Wiki Enrich · wanshuiyinFill in the per-paper TODO sections of research-wiki/papers/<slug>.md pages that literature-ingest skills leave as bare scaffolds. Use when user says 'enrich wiki', 'fill paper TODOs', 'wiki body 補完', '把 paper 摘要寫進 wiki', 'research-wiki 自動填', or after a batch ingest that left papers/ as TODO scaffolds.
- ▌ Idea Creator · wanshuiyinGenerate and rank research ideas given a broad direction. Use when user says "找idea", "brainstorm ideas", "generate research ideas", "what can we work on", or wants to explore a research area for publishable directions.
- ▌ Paper Figure · wanshuiyinGenerate publication-quality figures and tables from experiment results. Use when user says \"画图\", \"作图\", \"generate figures\", \"paper figures\", or needs plots for a paper.
- ▌ Paper Slides · wanshuiyinGenerate conference presentation slides (beamer LaTeX → PDF + editable PPTX) from a compiled paper, with speaker notes and full talk script. Use when user says "做PPT", "做幻灯片", "make slides", "conference talk", "presentation slides", "生成slides", "写演讲稿", or wants beamer slides for a conference talk.
- ▌ Research Lit · wanshuiyinSearch 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.
- ▌ Goal Pulse · wanshuiyin bundleEnable Goal Pulse by default on Codex Goal start, resume, or takeover, and on Claude Code /goal or explicitly authorized long autonomous work. Use a Codex timer or Claude Code native cron for bilingual execution reminders every 30 minutes. Supports start, status, stop, and a single pulse.
- ▌ Session Handoff · wanshuiyin bundlePrepare a grounded project handoff before switching to a fresh session, or continue authorized work from an existing handoff after checking current artifacts and running tasks.
- ▌ Auto Paper Improvement Loop 4 · wanshuiyinAutonomously 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", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.
- ▌ Lean Formalize 2 · wanshuiyin bundleDevelop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific proof obligation benefits from formal verification; use proof-writer for ordinary mathematical drafting.
- ▌ Keenable Search 2 · wanshuiyinKeyless web search and page fetch via Keenable. Use when user says "keenable search", "web search without an API key", "fetch this page as markdown", or needs broad web results beyond academic databases (arXiv, Semantic Scholar) with no search API key set up.
- ▌ Mermaid Diagram 2 · wanshuiyinGenerate Mermaid diagrams from user requirements. Save .mmd and .md files to figures/ with syntax verification. Supports flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, and many more diagram types.
- ▌ Firecrawl Search 2 · wanshuiyinWeb search and page scraping via Firecrawl, returning full-page markdown. Use when user says "firecrawl search", "firecrawl scrape" or "/firecrawl-search".
- ▌ Proof Orchestrator 2 · wanshuiyin bundleManage a stateful, run-directory-based proof project with Codex: 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 cross-run proof continuation — use /proof-writer for ordinary proof drafting and /proof-checker for rigorous verification or submission acceptance.
- ▌ Citation Crosscheck 2 · wanshuiyin bundleConditionally double-blind bibliographic cross-check (double-blind only when the host can isolate the web agent; a flag-only heuristic when isolation can't be attested): one agent extracts each cited entry verbatim from the local .bib, a second independently re-fetches the same paper's record from the web while blind to the .bib, and a third extractor emits a mechanical field-by-field delta to catch dropped/re-ordered authors, wrong years, wrong venues, and bad DOIs/arXiv ids. The main agent (never a shard) assigns the MATCH/MINOR/MISMATCH verdict per reference, and exports a side-by-side spreadsheet. Use when user says "citation crosscheck", "double-blind citation check", "verify bib against scholar", "bib field audit", "引用交叉核对", or before submission when bibliography FIELD accuracy (not just existence) must be certified.
- ▌ Research Refine Pipeline 2 · wanshuiyinRun an end-to-end workflow that chains `research-refine` and `experiment-plan`. Use when the user wants a one-shot pipeline from vague research direction to focused final proposal plus detailed experiment roadmap, or asks to "串起来", build a pipeline, do it end-to-end, or generate both the method and experiment plan together.
- ▌ Research Implement Feature 2 · wanshuiyinBuild a working artifact from a plain "implement X for me" request: a running end-to-end spine first, then one feature per rung, with every under-determined decision written to an assumption ledger BEFORE the code that depends on it and a sweep for the ones that slipped through undeclared (same-family provisional in the base Codex mirror). Use when user says "给我实现", "implement X", "帮我做一个能跑的", "先搭个原型再加功能", "build this feature", "prototype then extend", or hands over a capability description rather than an experiment plan.
- ▌ Proof Orchestrator · wanshuiyin bundleManage 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 cross-run proof continuation — use /proof-writer for ordinary proof drafting and /proof-checker for rigorous verification or submission acceptance.
- ▌ Citation Crosscheck · wanshuiyin bundleDouble-blind bibliographic cross-check: one agent extracts each cited entry verbatim from the local .bib, a second independently re-fetches the same paper's record from the web while blind to the .bib, and a third extractor emits a mechanical field-by-field delta to catch dropped/re-ordered authors, wrong years, wrong venues, and bad DOIs/arXiv ids. The main agent (never a shard) assigns the MATCH/MINOR/MISMATCH verdict per reference, and exports a side-by-side spreadsheet. Use when user says "citation crosscheck", "double-blind citation check", "verify bib against scholar", "bib field audit", "引用交叉核对", or before submission when bibliography FIELD accuracy (not just existence) must be certified.
- ▌ Auto Review Loop LLM 2 · wanshuiyinAutonomous research review loop using any OpenAI-compatible LLM API. Configure via llm-chat MCP server or environment variables. Trigger with "auto review loop llm" or "llm review".
- ▌ Idea Discovery Robot 3 · wanshuiyinWorkflow 1 adaptation for robotics and embodied AI. Orchestrates robotics-aware literature survey, idea generation, novelty check, and critical review to go from a broad robotics direction to benchmark-grounded, simulation-first ideas. Use when user says "robotics idea discovery", "机器人找idea", "embodied AI idea", "机器人方向探索", "sim2real 选题", or wants ideas for manipulation, locomotion, navigation, drones, humanoids, or general robot learning.
- ▌ Interview Cheatsheet 3 · wanshuiyinGenerate a long-form Chinese interview-prep cheat sheet on a specific ML/LLM topic — formulas with derivations, from-scratch PyTorch code, comparison tables, and 25 高频面试题 (L1 必会 / L2 进阶 / L3 顶级 lab). Use when the user says '写面试 cheat sheet', '写一份 X 教程', '帮我准备 Y 面试题', '出一份 X 速查', or wants a 600-1000 line Chinese tutorial on a specific ML topic.
- ▌ Patent Novelty Check 2 · wanshuiyinAssess patent novelty and non-obviousness against prior art. Use when user says "专利查新", "patent novelty", "可专利性评估", "patentability check", or wants to evaluate if an invention is patentable.
- ▌ Deepxiv 2 · wanshuiyinSearch and progressively read open-access academic papers through DeepXiv. Use when the user wants layered paper access, section-level reading, trending papers, or DeepXiv-backed literature retrieval.
- ▌ Invention Structuring 2 · wanshuiyinStructure a raw invention idea into a formal invention disclosure. Use when user says "构建发明", "structure invention", "发明构建", "invention disclosure", or wants to formalize a rough idea into a patent-ready structure.
- ▌ Specification Writing 2 · wanshuiyinWrite the full patent specification from claims and invention disclosure. Use when user says "撰写说明书", "write specification", "写说明书", "patent description", or wants to draft the complete patent specification.
- ▌ Paper Illustration Image2 2 · wanshuiyin bundleGenerate 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.
- ▌ Research Implement Feature · wanshuiyinBuild a working artifact from a plain "implement X for me" request: a running end-to-end spine first, then one feature per rung, with every under-determined decision written to an assumption ledger BEFORE the code that depends on it and a cross-model sweep for the ones that slipped through undeclared. Use when user says "给我实现", "implement X", "帮我做一个能跑的", "先搭个原型再加功能", "build this feature", "prototype then extend", or hands over a capability description rather than an experiment plan.
- ▌ Auto Review Loop 4 · wanshuiyinAutonomous multi-round research review loop. In Copilot CLI it defaults to the native complementary rubber-duck subagent with host-event model evidence; elsewhere it uses Codex, while explicit external reviewer overrides remain available. Implements fixes and re-reviews until a policy-approved positive assessment or max rounds is reached.
- ▌ Experiment Audit 2 · wanshuiyinAudit experiment integrity before claiming results. Uses cross-model review (external reviewer backend) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.
- ▌ Firecrawl Search · wanshuiyinWeb search and page scraping via Firecrawl, returning full-page markdown. Use when user says "firecrawl search", "firecrawl scrape" or "/firecrawl-search".
- ▌ Experiment Bridge 2 · wanshuiyinWorkflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENT_PLAN.md, implements experiment code, deploys to GPU, collects initial results. Use when user says "实现实验", "implement experiments", "bridge", "从计划到跑实验", "deploy the plan", or has an experiment plan ready to execute.
- ▌ Paper Claim Audit 2 · wanshuiyinZero-context verification that every number, comparison, and scope claim in the paper matches raw result files. Uses a fresh cross-model reviewer with NO prior context to prevent confirmation bias. Use when user says "审查论文数据", "check paper claims", "verify numbers", "论文数字核对", or before submission to ensure paper-to-evidence fidelity.
- ▌ Paper Poster HTML 3 · wanshuiyin bundleDEFAULT poster pipeline — build an academic conference poster (ICML/NeurIPS/ICLR/CVPR/...) as a single HTML/CSS file with measurement-driven hard gates, real paper figures, a two-hue design-token system, and print-ready PDF via headless Chromium. Use when the user says "做海报", "poster", "conference poster", "paper poster", or asks to design/redo a research poster. Supersedes the retired LaTeX /paper-poster.
- ▌ Research Pipeline 2 · wanshuiyinFull end-to-end research pipeline: from a broad research direction through idea discovery, experiments, and review all the way to a polished paper PDF. Use when user says "全流程", "full pipeline", "从找idea到投稿", "end-to-end research", or wants the complete autonomous research lifecycle.
- ▌ Resubmit Pipeline 2 · wanshuiyinWorkflow 5: orchestrate a text-only resubmit of a polished paper to a different venue under hard constraints (no new experiments, no bib edits, no framework changes, never overwrite prior submissions). Use when user says "resubmit pipeline", "重投流程", "port paper to <new venue>", "resubmit to <venue>", "tighten paper for resubmission", or has a rejected/withdrawn paper to move to a different top venue under tight time budget.
- ▌ Formula Derivation · wanshuiyinStructures and derives research formulas when the user wants to 推导公式, build a theory line, organize assumptions, turn scattered equations into a coherent derivation, or rewrite theory notes into a paper-ready formula document. Use when the derivation target is not yet fully fixed, the main object still needs to be chosen, or the user needs a coherent derivation package rather than a finished theorem proof.
- ▌ Lean Formalize · wanshuiyin bundleDevelop and verify a mathematical proof in Lean, continue an incomplete Lean project, or audit whether it proves the original statement. Connect actual inputs to intermediate lemmas, assemble the target theorem, check its transitive axioms, and provide a reproducible handoff. Use when Lean is requested or a specific proof obligation benefits from formal verification; use proof-writer for ordinary mathematical drafting.
- ▌ Run Experiment 2 · wanshuiyinDeploy and run ML experiments on local, remote, Vast.ai, or Modal serverless GPU. Use when user says "run experiment", "deploy to server", "跑实验", or needs to launch training jobs.
- ▌ Training Check 2 · wanshuiyinPeriodically check WandB metrics during training to catch problems early (NaN, loss divergence, idle GPUs). Avoids wasting GPU hours on broken runs. Use when training is running and you want automated health checks.
- ▌ Claims Drafting 2 · wanshuiyinDraft 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 of the patent pipeline.
- ▌ Keenable Search · wanshuiyinKeyless web search and page fetch via Keenable. Use when user says "keenable search", "web search without an API key", "fetch this page as markdown", or needs broad web results beyond academic databases (arXiv, Semantic Scholar) with no search API key set up.
- ▌ Patent Pipeline 2 · wanshuiyinFull patent drafting pipeline from invention description to jurisdiction-formatted filing documents. Supports CN (CNIPA), US (USPTO), EP (EPO). Supports invention patents and utility models. Use when user says "写专利", "patent pipeline", "专利申请", "draft patent", "写权利要求书", or wants to draft a complete patent application.
- ▌ Research Refine 4 · wanshuiyinTurn a vague research direction into a problem-anchored, elegant, frontier-aware, implementation-oriented method plan via iterative GPT-6-Astra review. Use when the user says "refine my approach", "帮我细化方案", "decompose this problem", "打磨idea", "refine research plan", "细化研究方案", or wants a concrete research method that stays simple, focused, and top-venue ready instead of a vague or overbuilt idea.
- ▌ Research Review 4 · wanshuiyinGet a deep critical review of research from a selected reviewer (Codex by default, Gemini, Grok, Claude Code, 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.
- ▌ Result To Claim 2 · wanshuiyinUse 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.
- ▌ Citation Audit 2 · wanshuiyinZero-context verification that every bibliographic entry in the paper is real, correctly attributed, and used in a context the cited paper actually supports — catching hallucinated authors, wrong years, fabricated venues, version mismatches, and wrong-context citations. Use when user says "审查引用", "check citations", "citation audit", "verify references", "引用核对", or before submission to ensure bibliography integrity.
- ▌ Idea Discovery 3 · wanshuiyinWorkflow 1: Full idea discovery pipeline to go from a broad research direction to validated, pilot-tested ideas. Use when user says "找idea全流程", "idea discovery pipeline", "从零开始找方向", or wants the complete idea exploration workflow.
- ▌ Research Lit 2 · wanshuiyinSearch 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.
- ▌ Gemini Search 2 · wanshuiyinSearch research papers via Gemini for broad literature discovery. Use when user says "gemini search", "gemini papers", "search with gemini", or wants AI-powered literature discovery beyond arXiv/Semantic Scholar indexes.
- ▌ Kill Argument 2 · wanshuiyinTwo-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 simulation", or before submitting a theory paper that has already passed standard review rounds.
- ▌ Meta Optimize 2 · wanshuiyinAnalyze ARIS usage logs and propose optimizations to SKILL.md files, reviewer prompts, and workflow defaults. Outer-loop harness optimization inspired by Meta-Harness (Lee et al., 2026). Use when user says "优化技能", "meta optimize", "improve skills", "分析使用记录", or wants to optimize ARIS's own harness components based on accumulated experience.
- ▌ Novelty Check 4 · wanshuiyinVerify research idea novelty against recent literature. Use when user says "查新", "novelty check", "有没有人做过", "check novelty", or wants to verify a research idea is novel before implementing.
- ▌ Overleaf Sync · wanshuiyinTwo-way sync between a local paper directory and an Overleaf project, so ARIS audit/edit workflows stay on the local copy while collaborators edit in the Overleaf web UI. Use when user says "同步 overleaf", "overleaf sync", "推送到 overleaf", "connect overleaf", "Overleaf 桥接", "pull overleaf", "push overleaf", or wants to bridge their ARIS paper directory with an Overleaf project.