Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Documents
Generate a Product Requirements Document (PRD) for a new feature. Use when planning a feature, starting a new project, or when asked to create a PRD. After PRD is confirmed, use /prd-to-spec (optional) for technical design, then /to-issues to create implementable tickets. Triggers on: create a prd, write prd for, plan this feature, requirements for, spec out, 写PRD, 需求文档, 需求分析, 规格说明.
Converts Markdown to styled HTML with WeChat-compatible themes. Supports code highlighting, math, PlantUML, footnotes, alerts, and infographics. Use when user asks for "markdown to html", "convert md to html", "md转html", or needs styled HTML output from markdown.
Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.
Command-line interface for Mermaid Live Editor - Create, edit, and render Mermaid diagrams via stateful project files and mermaid.ink renderer URLs. Designed for AI agents and power users who need to generate flowcharts, sequence diagrams, and other visualizations without a GUI.
Reconstructs reference images into high-fidelity, editable Draw.io files with rendered previews: native Draw.io elements carry text and structure, SVG covers simple icons that match the reference, and cropped or transparent PNGs preserve complex visuals. Use when the user wants a diagram image, research figure, architecture diagram, slide, UI screenshot, or image folder turned into `.drawio` XML; batch requests use a manifest with bounded parallelism when available and a full-fidelity serial fallback otherwise.
Generate conference presentation slides (beamer LaTeX → PDF plus editable PPTX) from a compiled paper, with speaker notes and a full talk script. Use when the 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.
Generates UML diagrams, architecture diagrams and flowcharts for any project. After analyzing the codebase, asks the user which diagram type to generate, renders it as HTML+SVG with the architecture-diagram skill, and saves it to the docs/ directory. Suitable for documentation visualization of any software project.
Drafts publishable paper prose from the author's own materials, from a single paragraph to a full manuscript, across STEM and non-STEM fields. Every factual claim traces to user input, verified retrieval, or field common knowledge; citations pass an independent verification ladder; delivery is clean prose with zero placeholder tags. Use when the user asks to write a section, turn an idea or results into paper text, or draft a full paper.
Use this skill whenever the user wants to create, read, edit, or manipulate Word documents (.docx files). Triggers include: any mention of 'Word doc', 'word document', '.docx', or requests to produce professional documents with formatting like tables of contents, headings, page numbers, or letterheads. Also use when extracting or reorganizing content from .docx files, inserting or replacing images in documents, performing find-and-replace in Word files, working with tracked changes or comments, or converting content into a polished Word document. If the user asks for a 'report', 'memo', 'letter', 'template', or similar deliverable as a Word or .docx file, use this skill. Do NOT use for PDFs, spreadsheets, Google Docs, or general coding tasks unrelated to document generation.
Write competitive research proposals for NSF, NIH, DOE, and DARPA. Agency-specific formatting, review criteria, budget preparation, broader impacts, significance statements, innovation narratives, and compliance with submission requirements.
Guide the Amazon Working Backwards process from the 5 Questions through to a full PR-FAQ document. Use when the user wants to (1) draft answers to the Amazon 5 Questions for a proposal or idea, (2) refine or critique existing 5Q answers, (3) verify and challenge 5Q answers with probing questions, (4) generate a PR-FAQ document from 5Q answers, (5) review or critique an existing PR-FAQ against Amazon standards, or (6) clarify any element of the 5Q or PR-FAQ process. Triggers include mentions of "5 questions," "PR-FAQ," "PRFAQ," "working backwards," "press release FAQ," Amazon-style proposals, or requests to write/review product proposals in Amazon format.
Use when the user wants to share or hand off what was found in a video—for example, “send this analysis to my team,” “make a page I can share,” “export the findings,” or “give me something I can attach to the ticket.” Renders a self-contained offline HTML viewer page with the frames, transcript, and every cached answer with its evidence.
Create and edit Obsidian Flavored Markdown with wikilinks, embeds, callouts, properties, and other Obsidian-specific syntax. Use when working with .md files in Obsidian, or when the user mentions wikilinks, callouts, frontmatter, tags, embeds, or Obsidian notes.
Design, write, and validate a structured learning resource with chapters (<topic>-book/01-quickstart.md, 02-….md …) when a single quick-reference guide is not enough, tailoring it to the reader persona. Check the mapping between chapter learning objectives and comprehension checks, ensure concepts are not used before they are introduced, budget reading time per chapter, include exercises that fail when incomplete and pass when answered, and generate a chapter dependency diagram from book.json. Verify these with verify-book.mjs, and check each chapter’s output, diagrams, and HTML with explainer’s verify-doc.mjs. Use when the user asks for a book, tutorial series, course, “learning materials,” “tutorial,” “hands-on,” “compile it into a book,” “in chapters,” “starting with 01-quickstart,” or when an explainer crash course would take over ~20 minutes or needs exercises.
Parse, read, search, navigate, summarize, extract, or check images and documents for manipulation through xparse-cli. Use for document conversion and navigation, durable Task workflows, structured extraction, and domestic TextIn manipulation/AIGC detection of a local file or URL. Prefer it over raw PDF readers or custom OCR scripts.
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", "专利申请", "draft patent", "写权利要求书", or wants to draft a complete patent application.
Convert Mermaid diagrams and Markdown tables to images (PNG) for platforms that don't support rich formatting. Use when user asks to "convert to image", "export as PNG", "make this an image", or has content for X/Twitter that needs visual exports.
Convert Markdown documents to professionally typeset PDF files with reportlab. Handles CJK/Latin mixed text, fenced code blocks, tables, blockquotes, Obsidian callouts, inline images, emoji fallback, LaTeX-style formulas, cover pages, clickable TOC, PDF bookmarks, watermarks, and page numbers. Supports multiple color themes (Warm Academic, Nord, GitHub Light, Solarized, etc.) and is battle-tested for Chinese technical reports. Use this skill whenever the user wants to turn a .md file into a styled PDF, generate a report PDF from markdown, or create a print-ready document from markdown content — especially if CJK characters, code blocks, or tables are involved. Also trigger when the user mentions "markdown to PDF", "md2pdf", "any2pdf", "md转pdf", "报告生成", or asks for a "typeset" or "professionally formatted" PDF from markdown source.
Guides self-review of YOUR OWN academic paper before submission with adversarial stress-testing. Core method: three passes (adversarial deep read; 5-aspect checklist — contribution sufficiency, writing clarity, results quality, testing completeness, method design; mechanical consistency scans and experimental protocol audit of data flow, assumptions, leakage), counterintuitive protocol (reject-first simulation, delete unsupported claims, score trust, promote limitations, attack novelty), reverse-outlining, and figure/table quality checks. Use when: user wants to self-review or self-check their own paper draft before submission, stress-test their claims, prepare for reviewer criticism, or mentions 'self-review', 'check my draft', 'is my paper ready'. Do NOT use for writing a peer review of someone else's paper, and do NOT use after receiving actual reviews (use paper-rebuttal instead). Also runs as a background expert: dispatch it async with a draft path and it reviews end-to-end while you keep working.
Workflow 4: submission rebuttal pipeline. Parses external reviews, enforces coverage and grounding, drafts a safe text-only rebuttal within venue limits, and manages follow-up rounds. Use when the user says “rebuttal,” “reply to reviewers,” “ICML rebuttal,” “OpenReview response,” or wants to answer external reviews safely.
Build and maintain an explorable, progressively disclosed isometric “atlas” of a system's architecture — an interactive page (hover to read, click to pin, go inside for steps, inspect moving data packets, and chapters that reveal the system a few structures at a time) plus a generated text twin (SYSTEM.md) and question tracking by ID, all from one data file in the repo. Use whenever someone wants to discuss, design, review, or explain an architecture visually — “make an atlas”, “map the system”, “make the architecture explorable”, “visualize the codebase/agent/pipeline so we can talk about it”, “a diagram I can click around”, “walk me through how it fits together” — or when an architecture discussion produces open questions that need tracking across feedback rounds. Also use it to update an existing atlas after decisions change.
You are a documentation expert specializing in creating comprehensive, maintainable documentation from code. Generate API docs, architecture diagrams, user guides, and technical references using AI-powered analysis and industry best practices.
Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.
Generate and edit PowerPoint presentations using 21 built-in Chinese PPT templates or user-provided .pptx templates. Replace text without disrupting the original layout, colors, or font sizes. Includes text-box overflow detection and checks that headings at the same level use consistent font sizes. Also supports fully original, simple layouts. Use when the user wants to create or edit a PPT, presentation, slides, or .pptx, or needs a finished deck for work reports, annual or quarterly reviews, promotion presentations, project retrospectives, proposal defenses, business proposals, teaching materials, data visualization, and more. Use when the user wants to create or edit a PowerPoint / PPT / slides / .pptx deck, choose from built-in templates, or apply their own template without breaking the layout.
Guides writing academic papers section by section using an 11-step workflow with LaTeX templates and counterintuitive writing tactics. Covers Abstract, Introduction, Method, Experiments, Related Work, Conclusion, and Supplementary. Use when: user asks to write or draft a paper section, needs LaTeX templates, wants to improve academic writing quality, optimize novelty framing, or mentions 'write introduction', 'draft method', 'paper writing'. Do NOT use for pre-submission review (use paper-review), experiment execution (use experiment-pipeline), or paper planning/story design (use paper-planning).
Transform a PRD into a technical SPEC document covering architecture, API design, data model, error handling, and implementation contracts. Triggers on: prd-to-spec, prd to spec, prd转spec, 需求转设计, 需求转规格, generate spec from prd, design from prd, 技术方案, 设计方案
Formats plain text or markdown files with frontmatter, titles, summaries, headings, bold, lists, and code blocks. Use when user asks to "format markdown", "beautify article", "add formatting", or improve article layout. Outputs to {filename}-formatted.md.
Pitch-book company profile page via Longbridge — generates a professional company profile for trading materials and client presentations: positioning quadrant (market position / growth), business highlights, key financial matrix (revenue / EBITDA / net income / EPS / PE / EV), price trend description, major shareholders and management, recent catalysts. More presentation-focused and investment-banking oriented than longbridge-company-tearsheet. Triggers: 公司画像, 公司简介页, 投行公司页, 公司展示, 公司描述, 公司介绍页, 公司信息页, 公司畫像, 公司簡介頁, 投行公司頁, pitch book, company profile page, company profile, company description, investor profile, company slide, company overview page, pitch book company page.
Use when the user wants visually striking, shareable slide-deck IMAGES from any content — an article, blog post, topic, or paper — where look-and-feel matters more than editable precision (风格化幻灯/小红书配图/公众号配图/视觉化海报), optimized for reading and social sharing rather than live presentation. Offers 17 T2I aesthetic styles (watercolor, sketch-notes, pixel-art, editorial, chalkboard, etc.); each slide is an AI-generated image (Gemini/Nano Banana), so the look is distinctive but text/math/data are baked into the image (not editable). NOT for a faithful academic talk where equations, numbers, tables, and citations must stay exact, editable, and projector-ready (组会/答辩/thesis defense/conference/results-heavy talks) — for that use scholar-slides instead, since text-to-image will garble math and data.
Clean and finalize authorized natural-language text for readers by auditing suspicious invisible Unicode and rewriting prose while preserving facts, meaning, and the writer's voice. Use when the user asks to clean, humanize, polish, or finalize articles, manuscripts, reports, documentation, emails, product copy, UI text, Markdown, or HTML prose, or when a project rule or instruction file explicitly requires this workflow. Don't use for code-only tasks or undisclosed authorship evasion; leave code, commands, identifiers, paths, APIs, formulas, citations, required disclosures, and verbatim quotations unchanged.
Feishu video meetings and Minutes operations. Search past meetings across multiple dimensions, get meeting notes / AI artifacts / transcripts, query meeting recordings, download Minutes media files, and handle meeting bot join / leave / meeting events. Supports three entry paths: meeting-ids / minute-tokens / calendar-event-ids. Use when the user asks to "搜索会议", "会议记录", "会议纪要", "逐字稿", "妙记", "meeting", "vc search", "vc recording", "minutes", "下载妙记", "妙记视频", "会议录制", "会议机器人", "机器人入会", "vc bot", "从日程找会议".
Company tear sheet / one-pager via Longbridge Securities — generates a high-density 1–2 page company snapshot: business overview, key financials (revenue / net income / EPS / ROE), valuation multiples (PE / PB / EV-EBITDA), price performance, major shareholders, and recent catalysts. Triggers: "公司单页", "公司快照", "公司简报", "公司画像", "一页纸分析", "公司概要", "股票简报", "公司單頁", "公司快照", "公司簡報", "公司畫像", "一頁紙分析", "company tearsheet", "company profile", "company snapshot", "one-pager", "company brief", "stock summary", "company factsheet".
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 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.
This skill should be used when the user asks to "write an experiment report", "summarize experimental results", "do experiment retrospection", "write a results report", "写实验总结报告", "写实验复盘", or mentions turning completed experiment artifacts into a structured, decision-oriented research report. It assumes strict analysis should come from `results-analysis` first.
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.