Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Documents
Convert files and documents to Markdown for LLM consumption using Microsoft’s markitdown tool. Use whenever the user wants to turn a PDF, Word/Excel/PowerPoint file (.docx/.xlsx/.pptx), HTML page, CSV/JSON/XML, Jupyter notebook, EPUB, Outlook .msg, ZIP archive, audio file, or YouTube URL into Markdown or plain text—for example, “convert this PDF to markdown,” “extract the text from report.docx,” “turn this spreadsheet into markdown,” “markdownify this folder of documents,” or “pull the transcript from this audio.” Also use for batch-converting a directory of documents, feeding office/PDF content into a prompt or RAG pipeline, or building a doc-to-markdown step in a Python script. Trigger even if the user names a file type without saying “markitdown.” Not for plain .txt/.md/source files, which can be read directly.
Read or write data files in MATLAB. Use when the task involves tables, spreadsheets, delimited text, or structured files in CSV, Excel, Parquet, JSON, or XML format — including but not limited to importing, exporting, loading, parsing, converting, validating, configuring import options, reading from URLs, handling locales or encodings, diagnosing file errors, and modernizing legacy file I/O code. MATLAB provides built-in functions for these workflows with no additional products required.
Converts long-form markdown (specs, RFCs, reports, plans, explainers) into a single-file, lightly-interactive HTML document with sticky TOC, scrollspy, search filter, code-copy buttons, and design-system-driven brand tokens. Triggers when the markdown-html-orchestrator classifies an input as DOCUMENT, or when invoked directly via /cs-md-document. Reads the design-system config via config_loader.py and inlines the user's 12 derived CSS custom properties; refuses to render if onboarding hasn't run. Single-file output — Google Fonts + Prism.js CDN are the only externals; no framework runtime, no build step. Use after orchestrator routing or after design-system onboarding is confirmed.
Generate Mermaid diagrams for chatbot flows that render in Markdown, including choosing diagram types, producing valid Mermaid code blocks, and validating or rendering diagrams locally via the bundled scripts. Use when a user asks for chatbot flowcharts/sequence/state diagrams, wants Mermaid syntax, or needs to verify/render Mermaid without a web service.
Convert PDFs to Markdown using Mistral OCR API with image extraction. Use when you need to extract structured text and images from PDFs, especially for scanned documents or documents with complex formatting. Outputs Markdown with embedded images.
Prepares meeting materials by gathering context from Notion, enriching it with Claude research, and creating both an internal pre-read and an external agenda saved to Notion. Helps you arrive prepared with comprehensive background and structured meeting docs
Use when writing or revising actual paper prose — sections, result narratives, venue-aware style, provisional metrics. Not for planning the writing contract before drafting (use paper-writing-contract-planner). Not for tracking section status or edit-state across drafting sessions (use paper-writing-memory-manager).
Make PDF documents look like they were scanned on a physical scanner. Applies realistic effects: grayscale conversion, Gaussian noise, slight rotation, blur, edge shadows, and random offset. Optionally extract real handwritten signatures from a source PDF (or user-provided images) and replace digital signatures on specific pages. Use when the user asks to: make a PDF look scanned, give a PDF a scanned appearance, replace digital signatures with real/handwritten ones, fake a scan, add scan effects to a document, or make a document look printed and scanned.
Use when organizing legal PDFs: detect the text layer, generate a page index, organizing drafts, and downstream handoff files; split, merge, or directly rename OCR'd double-layer scans by content and normalize naming; supports cross-source page reference stitching and page coverage audits (orphan pages/duplicate references); can do rotation and deskew correction, but not OCR or compression.
Create, edit, and analyze presentations. Use when Claude needs to work with presentations (.pptx files), including: (1) creating a new presentation, (2) modifying or editing content, (3) handling layouts, (4) adding comments or speaker notes, or any other presentation task
Prepare organized packages of project files for sharing at different levels - from summary PDFs to fully reproducible archives. Creates copies with cleaned notebooks, documentation, and appropriate file selection. After creating sharing package, all work continues in the main project directory.
Adversarial Quarto-vs-Beamer parity QA. A critic agent compares the Quarto HTML render to the Beamer PDF benchmark for content/visual parity; a fixer agent applies fixes; loops until APPROVED or two consecutive rounds turn up nothing new (fallback cap 5 rounds). Use when user says "qa the quarto", "check parity", "does the html match the pdf?", "quarto matches beamer?", or after a translate-to-quarto run. Requires both the `.qmd` rendered and a `.pdf` benchmark.
Publish quantitative analysis or existing JPG/PNG, HTML, PDF as a Quant Buddy shareable live page or real-time dashboard, supporting creation, update, reuse, acceptance and public link delivery. Applies to pages such as single-stock profiles, valuation and financials, index moves, multi-factor screening, commodity daily reports, templates, sharing shells and cards. Also use when the user provides a QuantBuddy live page URL and asks for interpretation. When /quant-buddy-view, /qbv, qbv or QBV is explicitly invoked and the request is not purely consultation, code maintenance or documentation explanation, treat it by default as a shareable live page task. Inputs that uniquely identify an A-share name, short name or code, or a simple request for single-stock comprehensive analysis (such as "贵州茅台", "600519", "分析一下贵州茅台") all default to a single-stock quick page; first verify via QBS and reply with the complete single-stock analysis, then new_asset_page in the same round, without the user needing to add "generate a page". When a WebAgent host requires financial questions to deliver both Q&A and a live page uniformly, one-off quotes, price changes, valuation, concept explanations and colloquial status questions are also handed off to this skill after the first QBS answer. Without such a host agreement, one-off questions are answered by QBS; operations such as review, monitoring, charting, backtesting and K-line still default to live page intent. Do not create a page when the user explicitly does not want a web page or wants text only.
Write and edit human-facing project technical text for scanning, wherever it lives — README, specs, design notes, plans, reports, runbooks, changelogs, and project memory, not only docs/ or StrictDoc. Use whenever creating or revising these records, without waiting for an explicit style request; also for 说人话、去 AI 味、精简文档、短语分点、PPT 式表达. Prefer Chinese phrases, lists, and compact comparison tables while preserving facts, conditions, evidence, and required structure. Not a detector-evasion or creative-writing skill.
Write a structured research protocol or study design document. Use when asked to write a research protocol, study protocol, research plan, methodology section, or research proposal. Produces a complete protocol with objectives, methodology, ethical considerations, and analysis plan.
Create publication-quality scientific diagrams, flowcharts, and schematics using Python (graphviz, matplotlib, schemdraw, networkx). Specialized in neural network architectures, system diagrams, and flowcharts. Generates SVG/EPS in figures/ folder with automated quality verification.
Mechanize Pattern 15 — the seven-pass adversarial review protocol for academic manuscripts. Spawns 7 fresh-context subagents in parallel (abstract, intro, methods, results, robustness, prose, citations), then synthesizes a prioritized revision checklist. Use for submission-ready or R&R-stage papers where single-pass review isn't enough.
Write or rewrite Chinese technical content in Simplified Technical Chinese (STC): procedures, installation and deployment, troubleshooting, interface and parameter descriptions, technical concept explanations, and explanatory answers for readers. Use when the user mentions “简明技术中文”, “STC”, “受控中文”, “像 ASD-STE100 那样写中文”, or “一词一义”; also use when the user asks to make Chinese technical instructions clear or unambiguous. Not for marketing copy, narratives, legal originals, or code.
Compact an active task file without changing meaning. Use when converting a no-subtask task to subtask form, when adding a new subtask after earlier subtasks already contain full section content, when duplicated section content should be compacted before approval seeking, or when a task file has become too large to use safely.
Implements Syncfusion Flutter SignaturePad (SfSignaturePad) for capturing handwritten signatures and drawings in Flutter apps. Use when implementing digital signatures, document signing, e-signature fields, or touch/stylus drawing surfaces. This skill covers stroke customization, background color, saving signatures as images, and clearing the pad.
Provides paragraph-level structural blueprints for 10-12 page systems papers targeting OSDI, SOSP, ASPLOS, NSDI, and EuroSys. Covers page budgets per section, writing patterns (gap analysis, observation-driven, contribution list, thesis formula), evaluation structure, venue checklists, reviewer guidelines, deadlines, and LaTeX templates for OSDI, NSDI, ASPLOS, and SOSP. Use when planning the section and page layout of a systems paper. Use when drafting an introduction, motivation, design, or evaluation section. Use when checking a draft against venue page limits and a pre-submission checklist. Use when anticipating how systems reviewers will assess a paper. Use when looking up conference formats or deadlines. For NeurIPS/ICML/ICLR papers or citation verification, use ml-paper-writing instead
Analyze any TRES Finance report XLSX and produce an automatic findings summary. Trigger this skill whenever a user uploads a .xlsx file that came from TRES Finance and asks to "analyze", "summarize", "review", "check", "audit", "look at", "what does this show", "any issues", "anything interesting", or "walk me through" the report. Also trigger when the user uploads an Excel file and mentions TRES, reconciliation, balances, transactions, cost basis, roll forward, or ERP sync. The skill identifies the report type from the file structure, runs targeted analysis based on report-specific logic, and produces a clear findings summary highlighting anomalies, key metrics, and action items.
Strip multi-vendor AI provenance marks from text and files using the guillaumemeyer/watermarks-remover Python toolkit: invisible Unicode/space homoglyphs (Layer A, deterministic), statistical token-sampling watermarks via agent-guided rewrite (Layer B, best-effort), and C2PA/EXIF/XMP/doc-props metadata on PNG, JPEG, SVG, PDF, DOCX, ODT, HTML, and Markdown. Covers Claude, Gemini/SynthID-Text, OpenAI provenance surfaces, and open-LLM Kirchenbauer-style marks, plus optional external backends for SynthID pixel scoring and CtrlRegen pixel-domain removal. Use when the user wants to strip AI watermarks, remove C2PA / Content Credentials, clean AI metadata from a file, remove invisible Unicode / zero-width characters from AI-generated text, or audit a directory/website for AI provenance signals. Triggers on: "remove watermark", "strip C2PA", "remove AI metadata", "clean invisible unicode", "remove-ai-marks", "SynthID removal", "audit_dir.py", "Layer A / Layer B watermark removal".
WeChat Official Account article publishing tool. Use the wxgzh CLI to publish Markdown articles to the Official Account drafts. Triggered when the user wants to publish an Official Account article, configure AppID/AppSecret, generate a cover image, convert Markdown to HTML, or manage multiple accounts.
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualisation. Use when working with spreadsheets (.xlsx, .xlsm, .csv, .tsv) for creating new spreadsheets with formulas and formatting, reading or analysing data, modifying existing spreadsheets while preserving formulas, data analysis and visualisation, or recalculating formulas. Do NOT use for plain CSV/TSV manipulation when no formulas, formatting, or multi-sheet workbook structure is needed - plain text tooling is faster. Do NOT use for BigQuery or warehouse-scale SQL analysis.
Use when an author has received peer-review comments and scores for an academic paper and needs to diagnose underlying reviewer concerns, decide whether a rebuttal is worthwhile, plan rebuttal experiments, or prepare evidence-grounded response material and revision plans for the author to review and finalize. Produces author-review material, never submission-ready rebuttals; venue generative-AI policies must be checked before use. Never fabricate results, reviewer intent, citations, or manuscript locations.
This skill should be used when the user asks about "film pitch", "treatment writing", "pitch deck", "lookbook", "mood board", "film proposal", "funding application", "act as a film pitch developer", "film pitch mode", "pitch package", "film financing", "producer pitch", "story treatment", "concept development", "film grant application", or needs expertise in film treatments, pitch packages, lookbooks, mood boards, and funding proposals for film projects. Part of the AlterLab FC Skills collection (Cinema & Digital Media department).
This skill should be used when the user asks about "thesis structure", "dissertation", "thesis writing", "chapter organization", "research proposal", "thesis outline", "defense preparation", "thesis defense", "committee management", "thesis timeline", "writing productivity", "argument architecture", "thesis introduction", "literature review structure", "methodology chapter", "findings chapter", "discussion chapter", "thesis conclusion", "act as a thesis architect", "thesis architect mode", "dissertation proposal", "thesis pipeline", "academic writing structure", "thesis formatting", "thesis revision", "writing schedule", "thesis advisor", "research proposal writing", "thesis planning", "chapter drafting", "thesis feedback", "defense slides", "viva preparation", or needs expertise in structuring, planning, writing, and defending a thesis or dissertation. Part of the AlterLab FC Skills collection (Research Methods & Academic Writing department).
Create, adapt, or revise practical community guides with locally grounded activities, participant worksheets, facilitator instructions, and maintenance plans. Use for neighborhood preparedness, mutual support, shared projects, and community learning programs. Do not use for travel guides, promotional brochures, standalone policies, simple document formatting, or live incident response.
Write journal submission cover letters, presubmission inquiries, transfer requests, and reviewer suggestion or exclusion lists that help a manuscript get past editorial triage. Use when submitting a paper to a journal, pitching a manuscript to an editor (presubmission enquiry), transferring after rejection, explaining a resubmission or appeal, or preparing the editor-facing parts of a submission such as the significance pitch, suggested reviewers and conflicts. Not for job or fellowship application letters.
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.