Research
920 skills.
Browse
novelty-checkwanshuiyinVerify 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.paper-claim-auditwanshuiyinZero-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-figurewanshuiyinGenerate 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-planwanshuiyinGenerate 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.prior-art-searchwanshuiyinSearch 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.proof-checkerwanshuiyinRigorous 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 audit report. 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.proof-writerwanshuiyinWrites 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 actually be completed under the stated assumptions.research-litwanshuiyinSearch 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.research-pipelinewanshuiyinFull 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.research-refinewanshuiyinTurn 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-refine-pipelinewanshuiyinRun 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-reviewwanshuiyinGet a deep critical review of research from an external reviewer backend (Codex 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.research-wikiwanshuiyinPersistent 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.result-to-claimwanshuiyinUse 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.run-experimentwanshuiyinDeploy 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.semantic-scholarwanshuiyinSearch published venue papers (IEEE, ACM, Springer, etc.) via Semantic Scholar API. Complements /arxiv (preprints) with citation counts, venue metadata, and TLDR. Use when user says "search semantic scholar", "find IEEE papers", "find journal papers", "venue papers", "citation search", or wants published literature beyond arXiv preprints.training-checkwanshuiyinInteractively monitor training metrics from the current Codex session, periodically checking WandB or fallback logs for NaN, divergence, plateaus, and broken runs.researchweizhenaConduct preliminary research on a topic and generate research outline. For academic research, benchmark research, technology selection, etc.research-add-fieldsweizhenaAdd field definitions to existing research outline.research-add-itemsweizhenaAdd items (research objects) to existing research outline.research-deepweizhenaRead research outline, launch independent agent for each item for deep research. Disable task output.research-reportweizhenaSummarize deep research results into markdown report, cover all fields, skip uncertain values.a-share-primary-theme-identificationwind-alice用于A股市场主线识别，聚焦市场结构 / 题材周期 / 资金行为。本skill主要用户问题回答、撰写报告、撰写金融类文章等场景。本报告输出内容较多，不适合简单对话场景。各类信息与数据的获取，可以使用wind.financial.data工具，以合理的关键字或关键字组合进行获取。每天开盘后、午盘、收盘后，用户都需要快速知道： 今天市场到底在交易什么，真正的主线是什么，情绪在什么位置，明天应该盯哪里。earnings-analysiswind-aliceCreate professional equity research earnings update reports (8-12 pages, 3,000-5,000 words) analyzing quarterly results for companies already under coverage. Fast-turnaround format focusing on beat/miss analysis, key metrics, updated estimates, and revised thesis. Includes 1-3 summary tables and 8-12 charts. Use when user requests "earnings update", "quarterly update", "earnings analysis", "Q1/Q2/Q3/Q4 results", or post-earnings report.post-market-debriefwind-alice用于盘后复盘，聚焦日常复盘 / 市场研究 / 交易总结。本skill主要用户问题回答、撰写报告、撰写金融类文章等场景。本报告输出内容较多，不适合简单对话场景。各类信息与数据的获取，可以使用wind.financial.data工具，以合理的关键字或关键字组合进行获取。收盘后需要快速复盘全天市场，搞清楚发生了什么、哪些信号值得重视、明天该怎么接。paper-spinewubing2023Research, write, review and deliver evidence-bound papers in one task, with user choices, real files, editable outputs and same-task revision.math-modelingxiaomacoltai当用户要求数学建模、建模竞赛、建模分析、代码求解、结果可视化或生成数学建模论文时使用。支持完整三阶段流程、单独执行任一角色，以及在关键节点使用独立 Subagent 进行阶段内质检；默认只启用质检 Subagent，用户可明确选择额外协作。arxiv-searchyorkeccakSearch arXiv physics, math, and computer science preprints using natural language queries. Powered by Valyu semantic search.biomedical-searchyorkeccakComplete biomedical information search combining PubMed, preprints, clinical trials, and FDA drug labels. Powered by Valyu semantic search.literature-searchyorkeccakComprehensive scientific literature search across PubMed, arXiv, bioRxiv, medRxiv. Natural language queries powered by Valyu semantic search.patents-searchyorkeccakSearch global patents with natural language queries. Prior art, patent landscapes, and innovation tracking via Valyu.pubmed-searchyorkeccakSearch PubMed biomedical literature with natural language queries powered by Valyu semantic search. Full-text access, integrate into your AI projects.searxng-searchyparesEnhanced web and package repository search using local SearXNG instanceshort-drama-novel-analyzezenstory-ai把长篇小说、连载网文或多集散稿拆成可追溯的原著分析：章节索引、改编价值快评、逐章功能提取、剧情单元与节奏聚合、人物与设定归并，最后给出改编价值判定与分集候选，交给 $short-drama-develop 立契约。用户说“导入这本小说”“拆这本书”“分析原著”“这本书能不能改短剧”“先看看值不值得拆”“把长篇拆成分集候选”，或直接给出小说文件路径时使用。只做只读的结构化分析，不写剧本、不建资产、不生成媒体，也不替创作者决定改编方案。deep-researchzernieUse when the user asks to research a topic in depth, map a competitive/market landscape, run a multi-source investigation, or "fan out" parallel research agents — anything where many findings must be gathered and then NOT lost. Enforces durable, detail-preserving research (write full findings to disk; keep a full appendix beside the synthesis).news-summaryzjfls新闻搜索、新闻摘要、新闻汇总、热点新闻、最新新闻、新闻整理、新闻收集。帮你搜索最近几天的相关新闻（12-25条），生成精美的HTML摘要页面，每条新闻都有摘要和AI深度解读功能，自动打开浏览器展示scientific-toolkit-skillzlanqingResearch computing toolkit for optoelectronic information science and engineering, MATLAB/Octave, Python scientific analysis, signal processing, image processing, statistics, simulation, optimization, publication figures, sensor/time-series data, citation lookup, and common scientific libraries. Use when the user asks for MATLAB code, scientific Python, data analysis, plots, simulations, formulas, statistics, machine learning, optical/physical/materials computation, or reproducible research worka-stock-daily-reportzsxinkA股每日简报自动生成系统。抓取东方财富实时数据，生成包含大盘指数、热门板块、资金动向等完整信息的日报报告。stock-sector-monitoringzuoaMonitors China A-share concept sectors and Dragon Tiger List (龙虎榜) via Tushare, then generates structured markdown reports. Use when users ask to track sector momentum, fetch top_list (doc_id=106), remove ST stocks, rank movers, or save monitoring output as .md files.ponytail-gaindietrichgebert24KShow ponytail measured impact as a scoreboard: less code, less cost, more speed, from the benchmark medians. One-shot display.meme-rushbinance6.5KLive launchpad feed + AI hot topics for meme tokens. (1) meme-rush: real-time lifecycle feed on launchpads (Pump.fun, Four.meme) — brand-new launches, currently-finalizing / bonding-curve tokens, and just-migrated-to-DEX tokens; filter by dev behavior, age, market cap. (2) topic-rush: AI-detected hot market narratives with the associated tokens ranked by inflow. Use for: "new pump.fun launches", "what just migrated", "currently bonding", "hot narratives", "what topic is pumping right now", "livereal-estate-searchnomadamas5.7KKorean apartment/officetel/villa/single-house real transaction price and rent lookups via k-skill-proxy. Based on tae0y's real-estate-mcp and MOLIT public data APIs.public-restroom-nearbynomadamas4.5KUse when the user asks for nearby public/open restrooms or 근처 화장실. Always ask the user's current location first, then use the official nationwide public-restroom standard dataset plus Kakao anchor resolution.donation-place-searchnomadamas3.7KUse when the user asks where to donate, 기부처 조회, or donation place recommendations by Korean location and category. Recommend recipients with best-effort 1365 verification-assist links and never execute donations. 돌쇠에서는 공식 표면을 통한 후속 액션까지 진행한다.critical-thinking-logical-reasoningsammcj2.3KCritically analyse the reasoning in written content (articles, blogs, transcripts, reports), not code. Use only when explicitly asked to critically analyse or critique an argument.cuopt-numerical-optimization-formulationnvidia2.1KLP, MILP, QP — concepts, problem-text parsing, and formulation patterns (parameters, constraints, decisions, objective). Concepts only; no API.streamlit-to-marimomarimo-team2.1KConvert a Streamlit app to a marimo notebookdali-dynamic-modenvidia2.1KDALI imperative dynamic mode (`nvidia.dali.experimental.dynamic`, ndd): use when working on ndd code or migrating pipelines; skip pipeline-only tasks.trump-perspectivealchaincyf1.7K唐纳德·特朗普（Donald Trump）的思维框架与行为逻辑。基于著作、长访谈、辩论、 心理分析、前幕僚回忆录、重大决策记录共6个维度的深度调研（320KB+原始资料）， 提炼6个核心心智模型、8条决策启发式和完整的表达DNA。 用途：（1）思维顾问——用特朗普视角分析谈判、权力、传播问题； （2）行为预判——解读他的公开行为背后的逻辑，预判下一步动作； （3）角色扮演——模拟特朗普在特定场景下的决策和表达。 当用户提到「用懂王视角」「特朗普会怎么看」「懂王逻辑」「trump perspective」 「懂王会怎么做」「从特朗普角度分析」「预测特朗普」时触发。pufferlibk-dense-ai1.6KVersion-aware guidance for PufferLib reinforcement-learning environments, vectorization, policies, PuffeRL training, evaluation, and safe checkpoint review. Use when adapting Gymnasium/PettingZoo environments to published PufferLib 3.0.0 or working with the redesigned native 4.0 source line.