AI 概览 · 由大模型根据 SKILL.md 与仓库数据生成 · 2026年11月3日
面向机器学习研究与论文工作的 AI Agent Skill 集合
该集合包含多个用于研究与论文工作的 AI Agent Skill,资料显示其覆盖 arXiv 论文搜索与下载、单篇论文理解、文献综述、实验结果分析、消融规划、论文改进及引用核查等任务。Skill 以 Markdown 文件组织;仓库简介提到跨模型审阅、研究想法发现和实验自动化,但现有具体 Skill 资料不足以确认这些能力在所有工作流中的实现方式。
包含 Skill
87
可以单独安装
GitHub Star
19.4k
仓库累计 Star
近 7 天
+398
新增 Star
代码更新
2026年11月17日
最近一次推送
核心亮点
1覆盖研究流程
从论文检索、阅读整理到实验分析和论文核查均有对应 Skill。
2任务分工明确
不同 Skill 面向单篇论文查询、文献综述、引用检查等具体用途。
3部分任务给出产物
例如论文改进流程列出分轮 PDF 与审阅日志作为输出。
能做什么
- 搜索、下载并总结 arXiv 学术论文。
- 通过 AlphaXiv 相关摘要辅助理解单篇论文,不面向广泛文献搜索。
- 生成包含论文信息、方法、结果和局限等字段的文献表,并整理综述要点。
- 分析实验结果与指标,并规划消融研究。
- 检查论文引用信息,或逐字段交叉核对参考文献。
- 按两轮审阅、修改和重新编译流程改进已生成的论文。
适用场景
给出 arXiv 编号,查找并获取论文资料以便阅读。
围绕一个研究主题整理文献表,并归纳领域问题、研究方向和证据强弱。
对实验主结果进行分析,并在需要时规划消融研究。
提交论文前检查参考文献的作者、年份、出处或标识信息。
用之前和用之后
- 论文资料和参考文献信息需要逐项查找整理可由相应 Skill 辅助形成论文摘要、文献表或核查结果。
- 论文修改与重新编译需要手动安排步骤论文改进流程可按两轮审阅、修改和编译组织产物。
- 实验指标与结果需要自行归纳可用结果分析类 Skill 辅助整理指标和结论。
它是怎么工作的
第 1 步
选择对应研究任务
第 2 步
准备任务所需资料
第 3 步
查看输出并核验
快速上手
安装与复制命令见“安装方式”。
- 1
根据目标任务选择对应 Skill,例如论文检索、文献综述或引用核查。
- 2
打开对应的 SKILL.md,确认该任务的具体要求与输入。
- 3
按 Skill 说明准备论文、实验结果或参考文献等资料。
- 4
运行任务后检查生成内容;对于论文修改和引用信息,进一步核对结果。
适合谁
- 进行机器学习或相关学术研究的用户
- 需要检索、阅读或整理论文的用户
- 需要分析实验结果或规划消融研究的用户
- 准备检查论文引用或改进论文稿件的用户
局限
- 不同 Skill 的输入、输出和操作步骤并不一致,部分采集条目未提供详细步骤或输入输出信息。
- AlphaXiv Skill 面向单篇论文的快速查询与理解,不适用于广泛文献搜索。
- 仓库简介提及的部分总体能力,无法仅凭当前具体 Skill 资料确认其覆盖范围。
- 论文分析、修改和引用核查的结果仍需用户检查。
使用前注意
- · 采集资料中多个 Skill 的风险等级标记为 high,使用前应查看对应 SKILL.md,确认任务流程及输入要求。
- · 涉及论文改写、实验结论或引用核查时,应核验输出与原始资料是否一致。
- · 采集资料未说明各 Skill 对外部服务、网络访问或本地文件的具体依赖,执行前应查看源文件确认。
包含的 Skills · 87
- Ablation Planner工作流Ablation Planner 是一个可复用的 AI Agent Skill,适合用于main results pass result-to-claim (claimsupported=yes or partial) and ablation studies are needed for paper submission。skills/ablation-planner/SKILL.md
- Alphaxiv工作流Alphaxiv 是一个可复用的 AI Agent Skill,适合用于Quick 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 arskills/alphaxiv/SKILL.md
- Analyze Results工作流Analyze Results 是一个可复用的 AI Agent Skill,适合用于数据分析、指标解释和结论整理。skills/analyze-results/SKILL.md
- Arxiv工作流Arxiv 是一个可复用的 AI Agent Skill,适合用于Search, download, and summarize academic papers from arXiv. Use when user says "search arxiv", "download paper", "fetch arxiv", "arxiv search", "get paper pdf", or wants to find and save papers from arXiv tskills/arxiv/SKILL.md
- Auto Paper Improvement Loop工作流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", "论文润色循环", "auto improve", or wants to iteratively polish a generated paper.skills/auto-paper-improvement-loop/SKILL.md
- Auto Review Loop Llm工作流Auto Review Loop Llm 是一个可复用的 AI Agent Skill,适合用于资料研究、事实整理和结构化报告写作。skills/auto-review-loop-llm/SKILL.md
- Auto Review Loop Minimax工作流Auto Review Loop Minimax 是一个可复用的 AI Agent Skill,适合用于资料研究、事实整理和结构化报告写作。skills/auto-review-loop-minimax/SKILL.md
- Auto Review Loop工作流Auto Review Loop 是一个可复用的 AI Agent Skill,适合用于资料研究、事实整理和结构化报告写作。skills/auto-review-loop/SKILL.md
- Citation Audit工作流Zero-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 mismatcheskills/citation-audit/SKILL.md
- Citation Crosscheck工作流Double-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 mechaniskills/citation-crosscheck/SKILL.md
- Claims Drafting工作流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 of the patent pipeline.skills/claims-drafting/SKILL.md
- Comm Lit Review工作流Comm Lit Review 是一个可复用的 AI Agent Skill,适合用于资料研究、事实整理和结构化报告写作。skills/comm-lit-review/SKILL.md
- Deepxiv工作流Deepxiv 是一个可复用的 AI Agent Skill,适合用于Search 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。skills/deepxiv/SKILL.md
- Dse Loop工作流Dse Loop 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。skills/dse-loop/SKILL.md
- Embodiment Description工作流Write detailed embodiment descriptions for patent specifications. Use when user says "撰写实施例", "write embodiment", "实施例描述", "detailed description", or wants to describe how to practice an invention.skills/embodiment-description/SKILL.md
- Exa Search工作流Exa Search 是一个可复用的 AI Agent Skill,适合用于数据分析、指标解释和结论整理。skills/exa-search/SKILL.md
- Experiment Audit工作流Audit 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 eskills/experiment-audit/SKILL.md
- Experiment Bridge工作流Workflow 1.5: Bridge between idea discovery and auto review. Reads EXPERIMENTPLAN.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 tskills/experiment-bridge/SKILL.md
- Experiment Plan工作流Experiment Plan 是一个可复用的 AI Agent Skill,适合用于资料研究、事实整理和结构化报告写作。skills/experiment-plan/SKILL.md
- Experiment Queue工作流SSH job queue for multi-seed/multi-config ML experiments with OOM-aware retry, stale-screen cleanup, and wave-transition race prevention. Use when user says "batch experiments", "队列实验", "run grid", "multi-seed sweep", "auto-chain experimenskills/experiment-queue/SKILL.md
- Feishu Notify工作流Send notifications to Feishu/Lark. Internal utility used by other skills, or manually via /feishu-notify. Use when user says "发飞书", "notify feishu", or other skills need to send status updates.skills/feishu-notify/SKILL.md
- Figure Description工作流Process user-provided patent figures and generate formal drawing descriptions. Use when user says "附图处理", "figure description", "附图说明", "drawings description", or wants to describe patent figures with reference numerals.skills/figure-description/SKILL.md
- Figure Spec工作流Generate 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 architectureskills/figure-spec/SKILL.md
- Firecrawl Search工作流Firecrawl Search 是一个可复用的 AI Agent Skill,适合用于Web search and page scraping via Firecrawl, returning full-page markdown. Use when user says "firecrawl search", "firecrawl scrape" or "/firecrawl-search"。skills/firecrawl-search/SKILL.md
- Formula Derivation工作流Structures 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 theskills/formula-derivation/SKILL.md
- Gemini Search工作流Gemini Search 是一个可复用的 AI Agent Skill,适合用于资料研究、事实整理和结构化报告写作。skills/gemini-search/SKILL.md
- Grant Proposal工作流Draft 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 genskills/grant-proposal/SKILL.md
- Idea Creator工作流Generate 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.skills/idea-creator/SKILL.md
- Idea Discovery Robot工作流Workflow 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. Useskills/idea-discovery-robot/SKILL.md
- Idea Discovery工作流Workflow 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.skills/idea-discovery/SKILL.md
- Integrity Forensics工作流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 thinskills/integrity-forensics/SKILL.md
- Interview Cheatsheet工作流Generate 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 sheetskills/interview-cheatsheet/SKILL.md
- Invention Structuring工作流Structure 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.skills/invention-structuring/SKILL.md
- Jurisdiction Format工作流Compile patent application into jurisdiction-specific filing format. Use when user says "格式转换", "jurisdiction format", "国家格式", "compile patent", or wants formatted patent documents for CN/US/EP filing. 批量生成和迭代广告创意文案,适合投放前素材准备。skills/jurisdiction-format/SKILL.md
- Keenable Search工作流Keenable Search 是一个可复用的 AI Agent Skill,适合用于数据分析、指标解释和结论整理。skills/keenable-search/SKILL.md
- Kill Argument工作流Kill Argument 是一个可复用的 AI Agent Skill,适合用于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 criticalskills/kill-argument/SKILL.md
- Lean Formalize工作流Lean Formalize 是一个可复用的 AI Agent Skill,适合用于Develop 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 tskills/lean-formalize/SKILL.md
- Mermaid Diagram工作流Mermaid Diagram 是一个可复用的 AI Agent Skill,适合用于生成Mermaid diagrams from user requirements. Supports flowcharts, sequence diagrams, class diagrams, ER diagrams, Gantt charts, and 18 more diagram types。skills/mermaid-diagram/SKILL.md
- Meta Apply工作流Privileged applier that LANDS meta-optimize / corpus-audit patches the user approved — the ONLY skill permitted to mutate the skill corpus from a self-modification proposal, with cross-model jury and human approval at landing. Use when the 批量生成和迭代广告创意文案,适合投放前素材准备。skills/meta-apply/SKILL.md
- Meta Optimize工作流Analyze 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 批量生成和迭代广告创意文案,适合投放前素材准备。skills/meta-optimize/SKILL.md
- Monitor Experiment工作流Monitor Experiment 是一个可复用的 AI Agent Skill,适合用于Monitor running experiments, check progress, collect results. Use when user says "check results", "is it done", "monitor", or wants experiment output。skills/monitor-experiment/SKILL.md
- Novelty Check工作流Verify 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.skills/novelty-check/SKILL.md
- Openalex工作流Openalex 是一个可复用的 AI Agent Skill,适合用于数据分析、指标解释和结论整理。skills/openalex/SKILL.md
- Overleaf Sync工作流Two-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", "skills/overleaf-sync/SKILL.md
- Paper Claim Audit工作流Zero-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 paperskills/paper-claim-audit/SKILL.md
- Paper Compile工作流Compile LaTeX paper to PDF, fix errors, and verify output. Use when user says "编译论文", "compile paper", "build PDF", "生成PDF", or wants to compile LaTeX into a submission-ready PDF.skills/paper-compile/SKILL.md
- Paper Figure工作流Generate 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.skills/paper-figure/SKILL.md
- Paper Illustration Image2工作流Paper Illustration Image2 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。skills/paper-illustration-image2/SKILL.md
- Paper Illustration工作流Generate publication-quality AI illustrations for academic papers using Gemini image generation. Creates architecture diagrams, method illustrations with Claude-supervised iterative refinement loop. Use when user says "生成图表", "画架构图", "AI绘图skills/paper-illustration/SKILL.md
- Paper Plan工作流Generate 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.skills/paper-plan/SKILL.md
- Paper Poster Html工作流DEFAULT 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 Chskills/paper-poster-html/SKILL.md
- Paper Poster工作流Paper Poster 是一个可复用的 AI Agent Skill,适合用于DEPRECATED — superseded by /paper-poster-html. Kept only as a redirect for muscle memory; do not use for new posters。skills/paper-poster/SKILL.md
- Paper Slides工作流Generate 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sli 把文本、资料或参考风格整理成演示文稿生成流程。skills/paper-slides/SKILL.md
- Paper Talk工作流End-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 / V 把文本、资料或参考风格整理成演示文稿生成流程。skills/paper-talk/SKILL.md
- Paper Write工作流Draft 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.skills/paper-write/SKILL.md
- Paper Writing工作流Workflow 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.skills/paper-writing/SKILL.md
- Patent Novelty Check工作流Assess 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.skills/patent-novelty-check/SKILL.md
- Patent Pipeline工作流Full 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skills/patent-pipeline/SKILL.md
- Patent Review工作流Get 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.skills/patent-review/SKILL.md
- Pixel Art工作流Generate pixel art SVG illustrations for READMEs, docs, or slides. Use when user says "画像素图", "pixel art", "make an SVG illustration", "README hero image", or wants a cute visual. 把文本、资料或参考风格整理成演示文稿生成流程。skills/pixel-art/SKILL.md
- Prior Art Search工作流Search patent databases and academic literature for prior art relevant to an invention. Use when user says "现有技术检索", "prior art search", "专利检索", "check patents", or wants to find relevant prior art.skills/prior-art-search/SKILL.md
- Proof Checker工作流Rigorous mathematical proof verification and fixing workflow. Reads a LaTeX proof, identifies gaps via cross-model review (external reviewer backend, ultra reasoning), fixes each gap with full derivations, re-reviews, and generates an audiskills/proof-checker/SKILL.md
- Proof Orchestrator工作流Proof Orchestrator 是一个可复用的 AI Agent Skill,适合用于Manage 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 DeepSe 把开发任务从需求接收到验收交付串成端到端流程。skills/proof-orchestrator/SKILL.md
- Proof Writer工作流Writes rigorous mathematical proofs for ML/AI theory. Use when asked to prove a theorem, lemma, proposition, or corollary, fill in missing proof steps, formalize a proof sketch, 补全证明, 写证明, 证明某个命题, or determine whether a claimed proof can askills/proof-writer/SKILL.md
- Qzcli工作流Manage GPU compute jobs on the Qizhi (启智) platform using qzcli — a kubectl-style CLI tool. Use when user says "qzcli", "启智平台", "submit job", "stop job", "查计算组", "avail", "list jobs", "batch submit", or needs to manage distributed trainingskills/qzcli/SKILL.md
- Rebuttal工作流Rebuttal 是一个可复用的 AI Agent Skill,适合用于Workflow 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 "skills/rebuttal/SKILL.md
- Render Html工作流Render an ARIS Markdown / JSON artifact (IDEAREPORT, AUTOREVIEW, KILLARGUMENT, PAPERPLAN, 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 htmlskills/render-html/SKILL.md
- Research Implement Feature工作流Build 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 askills/research-implement-feature/SKILL.md
- Research Lit工作流Research Lit 是一个可复用的 AI Agent Skill,适合用于资料研究、事实整理和结构化报告写作。skills/research-lit/SKILL.md
- Research Pipeline工作流Full 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 wantsskills/research-pipeline/SKILL.md
- Research Refine Pipeline工作流Run 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 askills/research-refine-pipeline/SKILL.md
- Research Refine工作流Turn 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ideskills/research-refine/SKILL.md
- Research Review工作流Research Review 是一个可复用的 AI Agent Skill,适合用于资料研究、事实整理和结构化报告写作。skills/research-review/SKILL.md
- Research Wiki工作流Persistent 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", "addskills/research-wiki/SKILL.md
- Resubmit Pipeline工作流Workflow 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 pipelineskills/resubmit-pipeline/SKILL.md
- Result To Claim工作流Result To Claim 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。skills/result-to-claim/SKILL.md
- Run Experiment工作流Deploy 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.skills/run-experiment/SKILL.md
- Semantic Scholar工作流Semantic Scholar 是一个可复用的 AI Agent Skill,适合用于数据分析、指标解释和结论整理。skills/semantic-scholar/SKILL.md
- Serverless Modal工作流Serverless Modal 是一个可复用的 AI Agent Skill,适合用于Run GPU workloads on Modal — training, fine-tuning, inference, batch processing. Zero-config serverless: no SSH, no Docker, auto scale-to-zero. Use when user says "modal run", "modal training", "skills/serverless-modal/SKILL.md
- Slides Polish工作流Per-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 weig 把文本、资料或参考风格整理成演示文稿生成流程。skills/skills-codex/slides-polish/SKILL.md
- Specification Writing工作流Write 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.skills/skills-codex/specification-writing/SKILL.md
- System Profile工作流System Profile 是一个可复用的 AI Agent Skill,适合用于数据分析、指标解释和结论整理。skills/skills-codex/system-profile/SKILL.md
- Training Check工作流Training Check 是一个可复用的 AI Agent Skill,适合用于代码开发、调试、评审或工程交付前的任务拆解。skills/skills-codex/training-check/SKILL.md
- Vast Gpu工作流Vast Gpu 是一个可复用的 AI Agent Skill,适合用于Rent, manage, and destroy GPU instances on vast.ai. Use when user says "rent gpu", "vast.ai", "rent a server", "cloud gpu", or needs on-demand GPU without owning hardware。skills/skills-codex/vast-gpu/SKILL.md
- Web Debug Search工作流Web Debug Search 是一个可复用的 AI Agent Skill,适合用于Search GitHub, Stack Exchange, Chinese technical communities, official documentation, and general developer web sources for software errors, compatibility problems, API usage questions, and real-skills/skills-codex/web-debug-search/SKILL.md
- Wiki Enrich工作流Fill 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skills/skills-codex/wiki-enrich/SKILL.md
- Writing Systems Papers工作流Paragraph-level structural blueprint for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Provides page allocation, paragraph templates, and writing patterns. Use when user says "写系统论文", "systems paper structure",skills/skills-codex/writing-systems-papers/SKILL.md
公开来源
相关 Skills
查看更多last30days-skill
1 Skills热点研究技能 · mvanhorn
用于围绕主题开展资料研究、整理事实并撰写结构化报告,适合需要汇总多类信息来源的研究任务。
scientific-agent-skills
177 Skills科学研究技能集 · K-Dense-AI
覆盖生物、化学、医学等科研场景,可用于数据分析、论文检索、资料整理及部分专业工具工作流。
nature-skills
24 Skills科研写作绘图技能集 · Yuan1z0825
覆盖文献检索与引文核对、论文精读、科研绘图、实验记录和论文资料处理等场景,帮助整理研究证据、生成结构化内容并完成特定科研工作流。
Supervisor-Skills
12 Skills科研导师技能集 · HKUSTDial
支持资料研究、论文段落与稿件起草、审稿意见回应等科研场景,可用于整理研究材料并辅助推进论文写作。
