Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Documents
Draft or revise the abstract and introduction of a research paper. Use whenever the user needs to write or improve these sections — including phrasings like "write my abstract", "improve my intro", "draft the introduction", "my abstract is weak", "how should I open the paper", "the intro is too long", "I need a hook", "write a one-paragraph summary", or "my introduction doesn't sell the contribution". Also use when the user has a paper plan or results but no prose yet for the opening. The abstract and introduction have distinct structures and reviewer conventions that differ from the rest of the paper; this skill handles both as a pair since the intro must match and extend the abstract's promises. If the contribution or paper spine is not yet stable, use paper-argument-planner first.
Turn meeting audio into three artifacts (a corrected transcript, an HTML visual canvas, and a Markdown summary with AI insights), transcribed locally with Whisper on any platform: no cloud, no external transcription app. Use when the user provides a meeting recording or wants meeting notes from one ("处理这个录音", "会议纪要", "把录音转成文字", or an audio file lands in the configured drop-zone), wants an existing transcript corrected or cleaned ("处理 transcript", "转录纠错", "转写文本", or a .txt lands in the drop-zone), wants a recording pulled from their connected PLAUD account ("process my Plaud recording", "从 Plaud 拿"), asks for edits to a transcript, canvas, or summary this skill just produced, or requests cross-meeting Insights on communication patterns instead of processing one recording ("analyze my meetings", "how do I come across in meetings", "分析我的沟通模式", "复盘我最近的会议", "跨会议分析").
Run a structured business analysis workflow: requirements elicitation with stakeholder interviews and MoSCoW prioritization, as-is/to-be process mapping with BPMN notation, data-driven analysis (CBA, SWOT, root cause), and production-ready documentation (BRD, FRD, user stories with INVEST acceptance criteria). Triggers on "gather requirements", "write user stories", "map business process", "BRD", "FRD", "gap analysis", "cost-benefit analysis", "facilitate workshop", "business requirements", "process mapping", "as-is to-be", "stakeholder interview", or "business analyst". For management consulting (issue trees, steerCo business cases, operating model), use business-consultant—not business-analyst. For business model canvas, market sizing, and unit economics research, use business-model-researcher. Human data / labeling platform PRDs: product-management-human-data-platform. Monetization PRDs and packaging: product-management-monetization.
A complete workflow that turns descriptive text into comic pages. Supports two styles, sketch (black-and-white line art) and colored (color comics), reads text from direct input or files (.docx, .txt), allows editing individual pages after generation, and outputs the final result as a PDF document.
This skill should be used when the user asks to "create a deck", "make a presentation", "build slides", "pitch deck", "investor deck", "sales presentation", "design a deck", "interactive presentation", "presenter mode", "HTML slides", "video background deck", "deck playground", "visual deck editor", "deck builder UI", "publish deck link", or needs to generate a complete deck with minimal friction. Handles low-question discovery, early Deck Creator UI launch, theme selection, copywriting, parallel slide generation, PDF stitching, optional HTML presenter, and publishing workflows.
Synthesize a fragmented academic conversation into a cohesive, structured markdown report. Use this skill whenever the user has asked many disconnected questions about a topic in one session and now wants a unified write-up that captures what was discussed. Trigger phrases: write a report on our conversation, summarize this discussion into a document, turn this into a readable report, capture everything we talked about, make a note of this whole conversation, write up what we covered. The skill scans the full conversation, groups ideas into themes, identifies gaps, asks 2–4 targeted clarifying questions to fill them, then drafts the report. It does NOT write experimental results sections (use results-writeup), Related Work prose (use related-work-writer), or paper section drafts (use method-section-writer or abstract-and-intro-writer).
Diátaxis Documentation Expert. An expert technical writer specializing in creating high-quality software documentation, guided by the principles and structure of the Diátaxis technical documentation authoring framework. Templates for tutorial / how-to / reference / explanation live under templates/.
Convert self-contained SVG scientific flowcharts and architecture diagrams into vector PDFs that preserve real text, as well as natively editable PowerPoint PPTX. Use when asked to convert SVG/PDF figures to editable PDF/PPTX, preserve editable text and vector shapes, or avoid a slide that is only a screenshot. Includes a tested SVG→PDF→text-template→native DrawingML workflow; the PPTX helper targets flattened path-based SVGs, not arbitrary SVG artwork.
Plan, audit, or revise the figures, tables, captions, and visual evidence for a research paper. Use this skill whenever the user asks what figures or tables they need, whether a result should be a plot or table, how to present experiments, how to design ablation tables, how to make captions self-contained, what belongs in the appendix, or whether the current visual evidence supports the paper's claims. This skill is especially useful after experiment design and before writing the Results section.
An intelligent formula normalization skill for standardizing mathematical formula formatting, checking symbol consistency, and converting formula styles. It also generates general templates for describing comparisons of classic algorithms in academic theses. Use for normalizing formulas in Markdown documents, checking symbol consistency throughout a document, and academic writing such as algorithm comparisons.
Extract answer keys from Chinese Gaozhong-style English exam papers (PDF or image) and format them into a standardized structured output. Trigger when the user sends an English exam paper, answer key, mock test answer sheet, or similar file and asks to extract, organize, or structure the answers. Trigger even for casual requests like "look at the answers", "extract answers", or "organize this".
Official skill for recognizing and extracting mathematical formulas from images and PDFs into LaTeX format using ZhiPu GLM-OCR API. Supports complex equations, inline formulas, and formula blocks. Use this skill when the user wants to extract formulas, convert formula images to LaTeX, or OCR mathematical expressions.
Write or improve a README.md for an open source project. Use this for any request to create, rewrite, review, or polish a README, project description, or "getting started" docs for a library, framework, or tool, or to make an open source project more popular or attractive to users. Do NOT use for internal/private repo docs, API reference generation, or CHANGELOG/CONTRIBUTING files.
HTML PPT refined presentation designer - turns user content into polished HTML presentation pages, with LLM-driven design as the priority and support for multiple visual styles, motion design, and a color cognition system. Trigger words: PPT, presentation, HTML slides, slide, presentation, make a PPT, create a presentation.
Produce institutional-grade research reports and academic papers — industry reports, white papers, annual surveys, data insights, arXiv papers, and also 16:9 consulting deck-style reports (one conclusion per page). Define structure, write findings, build a chart and visual system. The standards are distilled from real-world testing of 2026 top-tier institutional reports. Not suitable for single articles or pure presentation PPTs (use design/slides instead).
Investment-banking pitch book for strategic alternatives — trading comps, precedent transactions, valuation football field, DCF sensitivity, strategic-options matrix, process recommendation. Built by adapting `assets/template.html` so IB-specific chrome, disclosure bands, and source labels are preserved. Use for Board / sell-side discussion materials. Not a VC fundraising deck (see html-ppt-pitch-deck). Workflow adapted from Anthropic financial-services Pitch Agent (Apache-2.0).
A set of resources to help me write all kinds of internal communications, using the formats that my company likes to use. Claude should use this skill whenever asked to write some sort of internal communications (status reports, leadership updates, 3P updates, company newsletters, FAQs, incident reports, project updates, etc.).
Convert various file formats (PDF, Office documents, images, audio, web content, structured data) to Markdown optimized for LLM processing. Use when converting documents to markdown, extracting text from PDFs/Office files, transcribing audio, performing OCR on images, extracting YouTube transcripts, or processing batches of files. Supports 20+ formats including DOCX, XLSX, PPTX, PDF, HTML, EPUB, CSV, JSON, images with OCR, and audio with transcription.
Create stunning, animation-rich HTML presentations from scratch or convert PowerPoint files (.ppt/.pptx) to beautiful web slides. Use when the user wants to build a pitch deck, presentation, slideshow, or slide deck — or convert an existing PPT to a web presentation. Generates zero-dependency single HTML files with keyboard/touch navigation and scroll-triggered animations. Style options include Neon Cyber, Bold Signal, Swiss Modern, Paper & Ink, and 8 more curated presets.
Convert entire PDF documents to clean, structured Markdown for full context loading. Use this skill when the user wants to extract ALL text from a PDF into context (not grep/search), when discussing or analyzing PDF content in full, when the user mentions “load the whole PDF”, “bring the PDF into context”, “read the entire PDF”, or when partial extraction/grepping would miss important context. This is the preferred method for PDF text extraction over page-by-page or grep approaches.
Plan and write responses to peer review, including journal “response to reviewers” letters for revise-and-resubmit, conference rebuttals under strict length limits (OpenReview/ICLR, NeurIPS, ICML, ACL ARR, CVPR), author responses to meta-reviews, and appeals. Use when a user receives reviews, must triage reviewer comments, draft point-by-point replies, decide what new experiments to run, disagree respectfully with a reviewer, or track manuscript changes for a revision. For authors answering reviews of their own manuscript; to write a review of someone else's paper, use peer-review instead.
Refine an existing written artifact for clarity, structure, tone, and readiness while preserving intent and scope. Use when the user asks for open-ended, artifact-wide polishing or improvement. For exact edits or shortening only, follow the request directly without this skill.
Plan and structure a research talk (conference presentation, seminar, invited talk, or job talk) from a paper, set of results, or research overview. Use whenever the user needs to turn a paper into slides, structure a 15/20/30/45/60-minute talk, decide what to cut for a short slot, plan a job talk narrative, or figure out how to present technical content to a mixed audience. Also use when the user asks "how do I present this paper", "what should my slides cover", "how long should each section be", or "I only have 15 minutes". A talk is not a paper read aloud — the narrative arc, pacing, and depth of detail must be rebuilt from scratch for a listening audience.
Review Supabase docs changes locally in your `supabase/supabase` checkout — either an open PR (triage, classify, verify) or your own branch before opening a PR (local self-review). Covers markdown pipeline, MDX content, tutorials, examples, Studio links, and docs tooling. Use when asked to review docs PRs, self-review a draft branch, check who has approved, verify build output, or evaluate supabase/supabase documentation changes.
Two-stage academic paper polishing skill. Stage A reduces AI detection traces (targeting GPTZero, Turnitin, Originality.ai). Stage B performs 8-dimension quality improvement (grammar, tone, coherence, conciseness, terminology, structure, argument clarity, journal compliance). Use whenever the user asks to polish, proofread, humanize, reduce AI rate, improve writing quality, or prepare a paper for submission.
Multi-agent comprehensive slide review (visual + pedagogy + proofreading, plus TikZ / parity / substance conditionally). Use when user says "full review", "excellence pass", "comprehensive check", "review everything", "pre-release review", "slide excellence", or before teaching / shipping a deck. Fanout wrapper — for a single lens, use `/visual-audit`, `/pedagogy-review`, or `/proofread` directly.
Help set up and troubleshoot rendering for task files and glossary files. Use when the user asks about PlantUML, AsciiDoc, VS Code, Cursor, other VS Code-based IDEs, JetBrains, preview rendering, Java, or Graphviz needed to review rendered task or glossary files.
Create WinForms applications featuring the Syncfusion WinForms PDF Viewer, customized to meet specific user requirements. It supports essential PDF operations such as loading, saving, printing, text search, text extraction, and bookmark or hyperlink navigation. Additional capabilities include zooming, interaction modes, localization, theming, rendering engine selection, and robust error handling, enabling the creation of tailored and fully functional PDF viewing solutions.
A tool for extracting video screenshots, scrolling text, and carefully filtering evidence clues. Extracts keyframes from screen recordings of WeChat, Xiaohongshu, web pages, meetings, and more with bounded high recall, controls screenshot density, and filters transition states. Uses local OCR multi-anchors and image subjects without text to generate an evidence-clue index without saving original text. Anonymous annotations on private corpora can establish a desensitized dual-path baseline. It also provides budget-constrained, closed-category, non-destructive classification/summary bundles, and deduplication audit bundles that only reduce items and enforce a coverage-survival gate. Explicit scrolling-text mode uses local OCR and a conservative body-text crop to output copyable TXT/Markdown, original OCR, and source references; this mode saves original text and has a different privacy policy from the clue index. Frame extraction, OCR, and body-text stitching run locally. Trigger terms: video screenshots, screen-recording screenshots, chat-record screenshots, evidence screenshots, video evidence clues, frame-extraction deduplication, keyframe extraction, screenshots too dense, transition frames, page changes, screenshot audit, scrolling-text extraction, screen recording to text, transcript page extraction. Do not use for video compression, video editing, legal determination of evidentiary weight, or audio extraction
Convert Markdown articles into inline-styled HTML usable in WeChat Official Accounts, using the kami paper-feel theme by default, with support for switching among multiple themes (kami, magazine-ink, magazine-indigo, magazine-forest, magazine-kraft, magazine-dune, elegant, modern, minimal) and configuration of parameters such as font, font size, accent color, background color, and output path. Used for Official Account layout, article HTML generation, replacing unstable external layout services, and especially suited to converting articles in this vault into a format that can be pasted into the WeChat Official Account editor.
Ingest sources into WikiContext, synthesize and publish cited knowledge pages, answer questions from its authenticated SQL evidence, maintain authoritative repository files and their GitHub destinations, and export a reproducible Obsidian vault. Use for WikiContext knowledge operations, including text, PDF, reviewed images, external transcript bundles and authorized Gemini audio ingestion; Markdown exports are presentation only.
Guide for working with zip files. Use when you need to create/compress a zip file from files or folders, extract/unpack/decompress a zip file, zip, compress, or archive files, make changes to files within a zip archive. Trigger words include; zip, unzip, compress, archive, extract, pack, unpack
Multi-perspective academic paper review with dynamic reviewer personas. Simulates 5 independent reviewers (EIC + 3 peer reviewers + Devil's Advocate) with field-specific expertise. Supports full review, re-review (verification), quick assessment, methodology focus, and Socratic guided modes. Triggers on: review paper, peer review, manuscript review, referee report, review my paper, critique paper, simulate review, editorial review.
Use this skill any time the user wants in-depth research or comprehensive analysis on any topic. This includes: industry analysis, competitive landscape mapping, market sizing, trend analysis, technology reviews, investment research, sector overviews, due diligence, benchmark studies, patent landscape analysis, regulatory analysis, and academic surveys. Also trigger when: user says 帮我调研一下, 深度分析, 行业研究, 市场规模分析, 竞争格局, 技术趋势, 做个研究报告. If deep research or comprehensive analysis is needed, use this skill.
Use when the user wants a cited, structured read of local documents and project knowledge. Triggers on: "analyze these docs", "scan my project for context", "read the docs folder", "summarize what's in .beagle/concepts/", "extract context from docs/", "what's in this folder", "go read everything in X and tell me what's there". Also invoked programmatically by other beagle skills (prfaq-beagle Ignition, brainstorm-beagle reference points, strategy-interview context grounding) via the companion contract. Does NOT trigger on codebase lookups ("find this function", "search the repo"), web research (use web-research), LLM-as-judge evaluation (use llm-judge), or document editing (use humanize-beagle). Produces a written scan plan, parallel-subagent findings, and a cited synthesis report on disk — never inline prose, never unsourced claims.
Build the storyline and slide structure for a board presentation. Use when asked to create a board deck, board presentation narrative, board meeting slides, or quarterly board update. Produces a complete slide-by-slide structure with narrative beats, talking points, and slide content guidance.
Turn a lesson plan into a teaching slide deck in Canva. Use when the user asks to build classroom slides from a lesson plan, convert a lesson plan into a presentation, make a teaching deck, create school slides from an outline, or generate a lesson deck for students. Input can be a lesson plan pasted in the message, a Canva design ID, a Canva doc or design by name, or a Canva design link (e.g., https://www.canva.com/design/...).
Turn a topic or existing document into an interactive Concept Atlas explainer — AI-editable MDX compiled to standalone HTML with concept nodes, relation graphs, math, charts, figures, citations, and reading aids. Use for technical explanations, concept maps, layered knowledge pages, dense explainers, or interactive teaching pages; also 概念图 / 知识地图 / 分层讲解
Adversarial 5-7 question challenge to a deck's pedagogical choices — ordering, prerequisites, cognitive load, motivation. Use when user says "devil's advocate", "poke holes in this deck", "push back on my slides", "stress-test the design", "what would a skeptical student ask?". Read-only; surfaces questions to force rethinking. Lighter than `/pedagogy-review`.
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.