2 226 document skills from 443 authors. They read and assemble documents, spreadsheets and slide decks. Half of them fit into 1 834 tokens or less — that is what one costs your context window when the agent loads it. 567 ship runnable scripts rather than instructions alone. 24 of them cannot work without an MCP server, most often rube. We also found 384 copies of these same skills sitting in other people's repositories — counted once here, not 384 times.
2 226 unique 443 authors 1 278 updated this month 156 from vendors
Google Gemini File Search for managed RAG with 100+ file formats. Use for document Q&A, knowledge bases, or encountering immutability errors, quota issues, polling failures. Supports Gemini 3 Pro/Flash (Gemini 2.5 legacy).
Integrate MDMA into an application and build features with it — wire up parsing, the runtime store, React rendering, LLM streaming, custom components, prompts, and CI validation. Use this skill when the user asks to add MDMA to an app, build a chat that streams MDMA, author or maintain a custom prompt, validate MDMA documents, register a custom component, or expose MDMA to an agent via MCP. Generates focused, correct wiring that uses the right packages for the job instead of reinventing them.
Distil a chat thread, research session, or working document into a structured wiki page capturing the current state of knowledge. Always use this skill when the user says /wiki-crystallize, 'save this to my wiki', 'capture what we've worked out', 'write this up as a wiki page', 'update my wiki from this conversation', 'we've covered a lot', 'before I close this chat', or 'let's wrap up this thread'. Also use proactively when the conversation has covered significant ground and capturing the findings would orient future sessions, the context is getting heavy and insights risk being lost, or the user signals they are ending a working session - even if they don't say 'wiki'. The chat is the scaffolding; the wiki page is the artefact. When in doubt whether a session wrap is being requested, use this skill. Requires filesystem read/write access.
Process source files into synthesised wiki pages. Always use this skill when the user says /wiki-ingest, 'import these files', 'process my clippings', 'ingest this article', 'I have new articles to add', 'turn this PDF into a wiki page', 'what's in my raw/ folder', or 'what have I ingested'. Also use when the user mentions dropping a file somewhere to process, wants to turn any document, article, or PDF into a wiki page, or asks about files in raw/ or ingested/ - even if they don't say 'ingest'. Treats raw/ as a flat queue; scans all files, synthesises knowledge into wiki pages, and moves each source to ingested/ as an atomic commit. When in doubt whether source material processing is being requested, use this skill. Requires filesystem read/write/move access.
> Generate a full security-focused PRD (Product Requirements Document) from a plain-language feature description. Use this skill whenever someone wants to create a PRD, product spec, feature spec, requirements document, or says things like "write a PRD for", "create a spec for", "plan this feature", "document this feature", or "I need a requirements doc". (2) a Confluence page pushed to your configured space via Atlassian MCP (called directly), (3) a cursor-compatible .md plan file for .cursor/plans/, (4) a downloadable formatted markdown, Notion page mirror. Always use this skill for PRD and feature planning tasks.
WonderTrader/wtpy 量化交易开发综合指南，整合官方文档、社区笔记与实践案例。涵盖 wtpy Python 框架与 WonderTrader C++ 核心的策略开发、回测、仿真、实盘、数据管理、监控运维全流程。
>- Build and query a local Markdown knowledge base ("vault"). TWO functions — (1) CONVERT raw files (PDF, Word/docx, PowerPoint/pptx, Excel/xlsx, csv/tsv, images, html, md/txt, json/yaml/code, audio/video) into clean Markdown with retrieval-friendly frontmatter; local-first (pandoc / python-pptx / openpyxl / pymupdf4llm / whisper), with cloud OCR (MinerU) only as a fallback. (2) ANSWER questions over the resulting vault with retrieval discipline — self-monitor coverage, "build/sync my local knowledge base", "convert these files to markdown for AI", "整理我的资料库", "把文件转成 md 给 AI 读", "本地知识库", "读我的本地 vault are already in a single doc you can read directly.
将法条/规范文件（.txt/.docx/.pdf）转为 Markdown。适用于用户要求“法条转 markdown”“pdf/docx 转 markdown”。处理 .pdf/.docx 时先检查是否已安装 mineru-ocr skill；未安装先引导安装，安装后优先用 mineru-ocr；仅在用户明确同意时再用本地回退方案。
Chinese legal workflow skills for lawyers, legal counsel, litigation, criminal defense, labor disputes, bankruptcy, contract review, compliance, legal research, and legal document drafting.
| 刑事辩护专业流程编排 Skill，负责根据刑事诉讼阶段和特殊标签进行专业路由、 阶段转换提示、关键期限提示和下一步工作建议。当用户提及"刑事案件"、 "刑事辩护"、"刑辩"等关键词，或需要跨阶段协调刑事辩护工作时触发。 事项建档、路径、文件读取、来源披露、OCR 校正和缺口归档由「法律工作总控」统一处理。
基于"六来源体系"、请求权基础6步法与要件审判九步法融合框架，进行系统性法律分析，按总控当前事项记录和复盘台账衔接，生成法律服务建议书Word文档。当用户发送客户编号并提及"初步法律分析"、"法律分析"、"请求权分析"等指令时触发使用。
劳动争议诉讼专业流程编排 Skill。整合17个子Skill：复用14个现有通用Skill + 3个劳动争议专属Skill（劳动争议仲裁程序管理、劳动关系认定与经济补偿计算、劳动争议证据体系）。用于判断劳动争议阶段（协商→调解→仲裁→一审→二审，L0-L15/LM系列）、识别W/E代理角色、区分劳动者代理、用人单位争议代理和用人单位日常劳动合规任务、推荐下一步子Skill、提示关键节点确认和期限；事项建档、路径、文件读取、来源披露、OCR 校正和缺口归档由「法律工作总控」统一处理。
庭前准备。基于起诉状、法律分析、诉讼可视化、案例汇编、质证意见等前置文档，自动归纳争议焦点，生成争点导向型庭审提纲、质证攻防矩阵、举证策略规划表、开庭陈述提纲、法庭辩论提纲、代理词和诉讼法律服务方案。当用户发送客户编号并提及"庭前准备"、"庭审提纲"、"代理词"、"诉讼方案"等指令时触发使用。
将法律文本（法律条文或法律案例）转换为规范的 Markdown 格式，删除推广冗余信息。本技能应在用户需要处理法律条文（如民法典、刑法等）、整理法律案例（如最高法典型案例、裁判文书等）、或从粘贴文本中格式化法律文档时使用。注意：本技能只负责格式化和内容清理，不包含内容抓取能力。内容获取应由其他 skill（如 wechat-article-fetch）完成，AI 会自动判断技能协作顺序。
根据案件材料或沟通记录生成各类法律服务文档（诉讼方案、咨询报告、非诉方案、建议书、沟通报告等）。本技能应在用户需要将案件材料、咨询记录或沟通内容整理为专业法律文档时使用。
制作民商事诉讼案件沟通记录文档，依据《诉讼精细化》手册要求，采用对话式笔录格式记录与客户首次深度沟通的内容，最终生成Word格式的案件沟通记录。当用户发送客户编号并提及"案件沟通记录"、"制作沟通记录"或类似指令时触发使用。
民事一审诉讼与破产案件专业流程编排 Skill。整合25个子Skill：民事诉讼14个（法律咨询助手、案件沟通记录、初步法律分析、委托合同管理、法规案例检索、调查取证与证据管理、立案管理、诉讼可视化、案件讨论与提纲、诉讼文书起草、庭前准备、庭审与庭后工作、调解与和解、诉讼分析工具、结案归档）+ 破产案件10个（破产法律分析、破产申请与受理、管理人工作、财产调查与管理、债权申报与审查、债权人会议、重整程序、破产和解程序、破产清算、破产文书生成）。用于判断民事/破产案件阶段（S0-S16/SM/BP系列）、推荐下一步子Skill、提示关键节点确认和期限；事项建档、路径、文件读取、来源披露、OCR 校正和缺口归档由「法律工作总控」统一处理。
在法律业务 Skill 生成正文或要素式字段后、法律文书模板与导出生成本地 Word 前触发。用于审查 draft.html/preflight-meta.json 或 complaint-data.json/fill-plan.json、读取复查摘要、法规校验摘要、来源边界和用户确认记录，决定是否可以进入正式 DOCX 导出；发现问题后必须闭环推进到业务 Skill 整改、用户确认或材料读取流程。
legal 文件夹通用入口 Skill。用于法律咨询、案件办理、合同、产品法务、监管合规、诉讼、刑辩、劳动争议、破产、合规、文书、检索等任务的语义路由、案件隔离、来源披露、文件读取复查、法规/Wiki 校验、OCR 校正、缺口提示和合同偏好学习。用户提出任何法律工作请求、客户编号、案件材料处理、法律文书生成或需要自动匹配 legal 子 Skill 时触发。
基于三层检索法进行系统性法律法规与案例检索，与前序"初步法律分析"请求权路径联动，输出法官版《法律法规及案例汇编》和律师版《法规案例检索报告》双文档，按总控当前事项记录和复盘台账衔接。当用户发送客户编号并提及"检索法规案例"、"法规汇编"、"案例检索"等指令时触发使用。
统一处理法律工作中最终需要输出本地 Word（.docx）的文书、报告、清单、笔录、意见书、函件、合同和正式交付文件。由法律工作总控强制路由调用；业务 Skill 负责正文和法律判断，本 Skill 负责选择格式 profile、接收语义 HTML 或要素式填充数据、导出 DOCX、结构体检和兜底模板。
基于《企业破产法》及司法解释，进行破产案件的系统性法律分析，支持管理人、债权人代理、债务人代理三种角色视角，生成标准化破产法律分析报告Word文档。当用户发送客户编号并提及"破产法律分析"、"破产分析"指令时触发使用，或在破产案件流程中自动衔接（BP1→BP2）。
基于Mermaid语法生成诉讼可视化图表（法律关系图、时间轴图、争点树、要件分析图、攻防对抗图、证据链图谱），按总控当前事项记录和复盘台账衔接，生成诉讼可视化报告Word文档（法官版+律师版）。当用户发送客户编号并提及"可视化"、"诉讼可视化"、"制作图表"等指令时触发使用。
民事、刑事及劳动争议诉讼共用的案件运营管理 Skill。用于案件更新、传票/开庭通知/举证通知/应诉通知/裁判文书处理、期限台账、飞书日历提醒、事实时间线和程序时间线维护、飞书思维导图同步、案件简报、诉讼案件总览、案件组合状态、案件关闭与结案归档检查。案件隔离、建档、材料读取复查、来源披露、OCR 校正、缺口归档和法规核验由法律工作总控统一处理。
预包装食品标签合规审核技能，用于审核食品标签是否符合 GB 7718（预包装食品标签通则）和 GB 28050（预包装食品营养标签通则）。适用场景：(1) 用户提交食品标签图片、文字或文档要求合规审核时；(2) 用户提到"食品标签审核""标签合规""营养标签审查""GB 7718""GB 28050"等关键词时；(3) 用户要求检查食品标签是否存在缺项、错误或违规风险时。支持 2011 版和 2025 版标准。
Manipulate, annotate, and render phylogenetic trees programmatically with the ETE Toolkit (ete3) — parse and edit Newick/NHX, detect duplication/speciation events, infer orthology and paralogy, query NCBI taxonomy, and export PDF/SVG figures. Use when traversing or reformatting tree files, doing phylogenomic comparative analysis, or producing publication tree graphics in Python. Part of the AlterLab Academic Skills suite.
Generates professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings — biomarker-stratified patient cohort analyses with outcomes and evidence-based treatment recommendation reports with decision algorithms, supporting GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance, output as publication-ready LaTeX/PDF. Use when building a CDS document, cohort analysis, or treatment recommendation report for drug development, clinical research, or evidence synthesis, or when GRADE grading, hazard ratios, survival/waterfall plots, or biomarker stratification are requested. Part of the AlterLab Academic Skills suite.
Trains single-agent reinforcement learning agents with Stable-Baselines3 — PPO, SAC, DQN, TD3, DDPG, and A2C behind a scikit-learn-like API. Use for standard single-agent RL experiments, quick prototyping, well-documented algorithm implementations on Gymnasium environments, or adding callbacks and evaluation. For high-throughput parallel training, multi-agent systems, or custom vectorized environments prefer alterlab-pufferlib. Part of the AlterLab Academic Skills suite.
Convert files and Office documents to clean, LLM-friendly Markdown with Microsoft MarkItDown (markitdown CLI/Python), supporting PDF, DOCX, PPTX, XLSX, images (EXIF + OCR), audio (transcription), HTML, CSV, JSON, XML, ZIP archives, EPUB e-books, and YouTube transcript URLs, with optional AI image descriptions. Use when converting a document, PDF, slide deck, spreadsheet, scanned image, audio file, web page, or e-book into Markdown text for ingestion or LLM processing, extracting text via OCR, transcribing audio, or batch-converting mixed file formats to token-efficient Markdown. Part of the AlterLab Academic Skills suite.
Run Open Notebook, a self-hosted open-source alternative to Google NotebookLM with a full REST API, for AI-powered research and document analysis. Use when organizing research materials into notebooks, ingesting diverse content sources (PDFs, videos, audio, web pages, Office documents), generating AI-powered notes and summaries, creating multi-speaker podcasts from research, chatting with documents using context-aware AI, searching across materials with full-text and vector search, or running custom content transformations. Supports 18+ AI providers including OpenAI, Anthropic, Google, Ollama, LM Studio, Groq, and Mistral with complete data privacy through self-hosting. For a one-shot file-to-Markdown conversion (no notebook, chat, or search), use alterlab-markitdown instead. Part of the AlterLab Academic Skills suite.
Explore a single PDF in depth — parse it once, then answer questions across its sections, figures, tables, and appendices — comparing methods across sections, extracting every instance of a pattern within the document, and reading values off its charts and tables. Use when interrogating one paper or report end-to-end, pulling every occurrence of something inside a document, or reading data from a figure/table in a PDF, serving the literature-review and paper-review pipeline. To build a comparison table across MANY papers prefer alterlab-pdf-extract; to simply convert a PDF to Markdown prefer alterlab-markitdown; for reference/citation management prefer alterlab-pyzotero. Part of the AlterLab Academic Skills suite.
Applies computational methods to humanities research — text mining and NLP (LDA/BERTopic topic modeling, sentiment, named entity recognition with spaCy/NLTK), corpus linguistics (concordance, collocation, keyness), digital archives (Dublin Core, TEI XML), GIS for history, network analysis, stylometry and authorship attribution, OCR (Tesseract, Kraken, Transkribus), and data visualization (Gephi, Palladio). Use when distant-reading a literary corpus, mapping historical events or trade networks, attributing disputed authorship, digitizing historical documents, or building digital scholarly editions. Part of the AlterLab Academic Skills suite.
Free Elicit-columns analog — ingest N PDFs (or any MarkItDown-supported document) and build a per-paper evidence table with user-defined columns, one row per paper and one column per attribute/question you want pulled from every source. Use when extracting structured data across many papers into a comparison table or data-extraction sheet (sample size, methods, main finding, effect, population/intervention/outcome, limitations), screening a corpus into a spreadsheet, or pulling the same fields from a stack of PDFs into CSV/Markdown. Routes conversion through MarkItDown; offline heuristic backend by default, optional LLM backend for precise answers. Part of the AlterLab Academic Skills suite.
Drives TÜBİTAK Açık Bilim Politikası (Open Science Policy) compliance and deposition into Aperta — TÜBİTAK ULAKBİM's national open archive at aperta.ulakbim.gov.tr — encoding the binding mandates (green-road deposit of the accepted manuscript on acceptance; open access within 6 months for fen/mühendislik (STEM) and 12 months for sosyal/beşeri (SSH); İlke-6 documentation when data must stay closed for KVKK/privacy reasons) and scaffolding a TÜBİTAK Veri Yönetim Planı / VYP (data management plan) at grant-application time. Use when depositing to Aperta, complying with the TÜBİTAK açık bilim policy, preparing a TÜBİTAK data management plan (VYP), reporting open-access compliance in a final report, or documenting a justified data embargo. For Zenodo/Dryad/OSF and international DMPs prefer alterlab-open-science; for the KVKK lawful-basis/anonymisation plan prefer alterlab-kvkk-dmp. Part of the AlterLab Academic Skills suite.
Builds plots with the matplotlib Python library (pyplot and the object-oriented Figure/Axes API) for full low-level customization, exporting to PNG/PDF/SVG. Use when fine-grained control over individual plot elements is needed — custom line/scatter/bar/histogram/heatmap/contour/box/violin/3D plots, rcParams and style-sheet tuning, or GridSpec subplot layouts inside a scientific Python workflow. Does NOT cover opinionated journal-ready multi-panel figure workflows (Nature/Science/Cell formatting, colorblind-safe palettes, significance annotations); for those prefer alterlab-scientific-viz instead. Part of the AlterLab Academic Skills suite.
Creates professional research posters in LaTeX using beamerposter, tikzposter, or baposter — handles layout design, color schemes, multi-column formats, figure integration, and poster-specific visual-communication best practices. Use when building a conference or academic poster in LaTeX. For PowerPoint/PPTX poster output prefer pptx-posters instead. Part of the AlterLab Academic Skills suite.
Creates research posters in HTML/CSS with responsive layouts and easy visual integration, exportable to PDF or PPTX. Use ONLY when the user explicitly requests a PowerPoint/PPTX/PPT poster, an HTML/web-based poster, or a poster they will edit in PowerPoint, or when LaTeX is unavailable. For a standard/conference research poster with no format named, use alterlab-latex-posters instead; for a slide deck/oral-talk presentation, use alterlab-scientific-slides. Part of the AlterLab Academic Skills suite.
Reads, parses, and generates documents in various formats like Markdown, PDF, docx, CSV, or HTML. Uses bash commands to invoke document conversion tools like pandoc or python scripts.
Converts files between formats (e.g., PDF to text, image OCR, docx to pdf) using system tools available in bash (like pandoc, tesseract, ImageMagick, or pdf2text).
Alignment conversation starting from a user's rough idea. Co-decides with the user whether the idea should be acted on directly in the current session, or fixed into a formal Task by producing four documents in `.task/` for independent dispatch. Handles lightweight 'do it now while we talk', heavyweight 'define precisely, run later', and 'just help me think about this' — all on the same skill. Use when the user describes a task or intent they want to align on. Trigger phrases include 'help me plan this', 'let's think this through', 'I want to explore X', 'I have an idea', '/task-alignment'. Also use proactively when a user jumps into a complex task without defining scope or success criteria — pause, align, and help them pick the right vessel (this session vs. a task).
| Download the actual PDF binary from bot-gated sites (taxpolicycenter.org, urban.org, SSRN-hosted mirrors, think-tank/publisher sites) via the Wayback Machine id_ URL form. "EOF marker not found" on a freshly downloaded file, (3) Firecrawl can parse the PDF to markdown but you need the original file on disk (e.g., filing a reference copy).