Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Documents
Lark Wiki: manage knowledge spaces, space members, and document nodes. Create and query knowledge spaces, view and manage space members, manage node hierarchy, organize documents and shortcuts in the knowledge base. Use when users need to find or create documents, browse knowledge space structure, view or manage space members, or move or copy nodes. When users provide a doubao.com /wiki/ URL/token, use this skill directly without falling back to WebFetch due to domain name; routing is based on URL path pattern and token, not domain name. Not responsible for: uploading files to knowledge base nodes (use lark-drive), editing document/sheet/Base content (use lark-doc / lark-sheets / lark-base).
Feishu Slides: Create and edit slides. Create presentations, read slide content, and manage slide pages (create, delete, read, and partially replace). Use when users need to create or edit slides, or read or modify an individual page. Also use this skill directly when users provide a doubao.com /slides/ URL/token; do not fall back to WebFetch just because the domain is not Feishu. Route based on the URL path pattern and token, not the domain. Not responsible for: editing cloud document content (use lark-doc), standalone whiteboard objects in cloud documents (use lark-whiteboard), or uploading and downloading ordinary files (use lark-drive).
Feishu Markdown: view, create, upload, edit, and compare native Markdown files in Feishu. Use when users need to operate on Feishu Markdown files or compare their remote versions with local drafts. Purely local Markdown file operations do not trigger this skill. Does not handle importing Markdown as Feishu online documents or cloud storage management such as file search, permissions, comments, moving, or deleting.
Lark Whiteboard: query and edit whiteboards in Lark Cloud Documents. Supports exporting whiteboards as preview images, exporting raw node structures, and updating whiteboard content using multiple formats. Use this skill when users need to view whiteboard content, export whiteboard images, or edit whiteboards. Not responsible for: Lark Cloud Documents content editing (lark-doc), embedded spreadsheets/Base in documents (lark-sheets / lark-base).
Draft, promote, archive, and supersede ADR-style decision records (types are open: architecture, product, security, policy, legal, …) and keep INDEX.md and cross-links generated, via the bundled scripts/decisions.py tool. Use when creating or promoting decision drafts, superseding or archiving a decision, fixing a promotion breach, flattening the old per-type accepted/ layout, or running build, check, promote, rename-draft-id, migrate-layout, or install.
Create and edit draw.io/diagrams.net diagrams as editable `.drawio` files. Covers architecture, UML/ERD/sequence, BPMN, network, and swimlane views authored from a description or converted from code, IaC, SQL, and API schemas, plus sync, query, test, review, export, and publish of existing diagrams. Use when the user asks for draw.io/diagrams.net or an editable diagram; prefer Mermaid/PlantUML when diagrams-as-code is enough.
Prepare to obtain corporate or real estate registry certificates (certificates of registered matters) from the Internet Registry Office (IROS), and safely assist with the cart, viewing, and saving within a browser flow where the user logs in and pays directly. In 돌쇠, prepare up to the closest possible lawful official step.
A thin wrapper skill built around the kimlawtech/korean-jangbu-for (Apache-2.0) upstream, covering bookkeeping automation and business tax document organization for Korean startups, one-person corporations, freelancers and sole proprietors: importing original data, tagging accounts, CSVs for tax accountants, and generating management reports. In Tols it carries on to follow-up actions through the official interface.
Create polished design artifacts as self-contained HTML: UI mockups, interactive prototypes, wireframes, landing pages, dashboards, app screens, mobile apps, slide decks (a.k.a. PPT / PowerPoint presentations), documents and résumés, animations, 3D objects, research reports, HTML email, diagrams, fliers, and visual explorations. Use whenever the user asks to design, mock up, prototype, wireframe, visualize, explore, or make a PPT/deck for an interface, product screen, user flow, content layout, visual artifact, or pitch/deck concept, even if they do not say "design". Also use to export a deck built with this skill to PowerPoint (PPT/PPTX) — but only decks authored here (deck-stage / this skill's slide-structured HTML), NOT arbitrary HTML, so confirm the target is such a deck first. Also use for setting up, importing, or authoring reusable design systems, UI kits, brand tokens, or component libraries. Harness-agnostic for Claude Code,Cursor, Codex Agent, and similar file-capable agents.
Interactive PDF viewer. Use when the user wants to open, show, or view a PDF and collaborate on it visually — annotate, highlight, stamp, fill form fields, place signature/initials, or review markup together. Not for summarization or text extraction (use native Read instead).
Layered technical-writing standard: Diátaxis structure, Google developer style sentences, STE instruction rules, Global English syntax. Use for /technical-writing or when writing or reviewing docs, RFCs, readmes, PR descriptions, or commit messages.
Generate, edit, and read PowerPoint presentations. Create from scratch with PptxGenJS (cover, TOC, content, section divider, summary slides), edit existing PPTX via XML workflows, or extract text with markitdown. Triggers: PPT, PPTX, PowerPoint, presentation, slide, deck, slides.
Handle PowerPoint (.pptx) creation, design, and analysis. Use for pitch decks, status updates, and visual storytelling. Use proactively when precise layout positioning and design principles are needed. Examples: - user: "Create a 10-slide deck for the board meeting" -> use design principles + html2pptx - user: "Convert this report into a presentation" -> extract text and map to template - user: "Audit this deck for layout issues" -> generate thumbnail grid for inspection
Turns an answer into a one-page visual HTML explainer: the model writes a short Markdown draft and the bundled CLI builds one page. Use it proactively and liberally, without being asked, whenever a page would help the reader more than plain text, even if plain text would also work: any explanation of how something works or how parts relate (flow, request path, architecture, code or folder structure, state machine, lifecycle, history); any comparison, trade-off or decision with pros and cons; any diagnosis, review or investigation, especially with several causes or findings to rank; any answer with a table, a numbered or ranked list, steps, branches or several sections; or when the user says "I don't get it / draw it / explain visually / 讲讲原理 / 没看懂 / 画个图". When in doubt, use it: a page is quick and cheap to make. Also for explainer videos ("make a video", "做个视频") and for changing its settings. Skip only for small talk, a trivial one-line answer, or when the user asks for plain text.
English LaTeX assistant for existing .tex journal or conference papers. Use for compile repair, venue formatting, bibliography/citation checks, section writing, logic, related work, tables, pseudocode, de-AI polish, claim-forward (self-weakening) fixes, translation, adaptation, and submission readiness; use latex-thesis-zh for Chinese theses and paper-audit for critique.
Write the hackathon challenge document teams read before they build - problem statements sized to the time box, thematic challenge tracks, the published rules and eligibility text, the submission-artifact checklist, sponsor-challenge framing, and naming (never weighting) the evaluation categories. Use whenever the user mentions a hackathon brief, challenge or track prompts, hackathon rules or eligibility, submission guidelines, or turning a sponsor's API into a challenge - even if they never say "brief". Challenge tracks here are thematic categories a team enters, not parallel session streams. Do NOT use for rubric weights and judging mechanics - use samber/dev-event-organizer-skills@hackathon-judging instead.
Salesforce architecture diagrams using Mermaid with ASCII fallback. Use this skill when generating text-based diagrams for Salesforce architecture, OAuth flows, ERDs, integration sequences, or Agentforce structure. TRIGGER when: user says “diagram”, “visualize”, “ERD”, or asks for sequence diagrams, flowcharts, class diagrams, or architecture visualizations in Mermaid. DO NOT TRIGGER when: user asks about non-Salesforce systems.
Turn a sold event sponsorship into a term sheet a lawyer can review — never a signable contract or legal advice. Covers the clause checklist an organizer hands to counsel — a deliverables schedule mirroring the sold tier, payment and late-fee terms, sponsor-withdrawal refunds plus the narrower organizer-cancels remedy, a force-majeure remedy, category exclusivity bounded by published caps, liability and insurance, a code-of-conduct clause with an ejection right, an editorial-independence clause denying sponsors program control, mutual logo licensing, term and renewal. Use whenever the user mentions a sponsorship agreement or contract, sponsor payment or cancellation terms, exclusivity, or a force-majeure clause — even if they never say “agreement”. Do NOT use to set prices — use samber/dev-event-organizer-skills@event-sponsor-pricing.
Assemble a technical event's sponsorship prospectus - the published document packaging an existing sponsor value proposition and rate card into a credibility-before-price section anatomy, a checkmark tier table with real disclosed caps, named per-tier perks and add-on packages, an audience-demographics evidence section, and a distribution format (web page or PDF kit) refreshed every edition. Use whenever the user mentions a sponsor deck, a sponsorship kit, a sponsor packages document, a prospectus, or a sponsor page for a conference, meetup or hackathon - even if they never say "prospectus". Never prints guarantees, invented scarcity, or lead-list benefits the event cannot deliver. Do NOT use to set prices - use samber/dev-event-organizer-skills@event-sponsor-pricing instead.
Create world-class PowerPoint presentations with professional design, consistent branding, sophisticated animations, and polished visual hierarchy. Use when users request presentations, slide decks, pitches, reports, or want to convert markdown to professionally designed PowerPoint with Apple/Microsoft/Google-level quality.
Automatically organizes invoices and receipts for tax preparation by reading messy files, extracting key information, renaming them consistently, and sorting them into logical folders. Turns hours of manual bookkeeping into minutes of automated organization.
Unix-flavored presentation design and fidelity typography. Turns an Org/Markdown outline or an authorized distilled script into a single-file offline HTML page, selecting the layout per semantic role: statement, contrast, Unicode relationship diagram, evidence, section. Dark by default, with presenter layer, native charts and page-flip controls. USE WHEN present, giving a talk, slides, beautifying an outline, or putting the essence of a talk on screen. NOT FOR rewriting an author's content without authorization or generating corporate PPT.
A retrieval and Q&A assistant for local knowledge base directories. Core flow: (1) navigate the layered index (2) when encountering PDF/Excel, first read references to learn the handling method (3) retrieve after processing the file. Combine grep, Read, pdfplumber and pandas by file type for progressive retrieval to avoid loading whole files. Use when the user's question involves "answering questions/retrieving information/looking up material from a knowledge base directory".
Guides creation of comprehensive Product Requirement Documents (PRDs) for software projects through structured questioning and validation, then generates implementation task lists in JSON format. Use when users want to document a software idea, create specifications for development, plan a new application feature/bug, or break down requirements into actionable tasks. Transforms ideas into implementation-ready documents with verifiable pass criteria.
Project wiki lifecycle — create pages, track source changes with ingest, update stale pages, lint structural integrity, detect code-to-doc drift with reconcile, and manage search indexes. A runbook for navigating and maintaining the wiki as an agent.
A skill for writing and editing Japanese business documents in natural, readable, and clear Japanese. Use it to create or refine meeting minutes, research reports, customer-facing reports, internal guides, technical articles, PR copy, research notes, proposals, emails, slide structures, as well as notes, blog posts, and essays. It can also create meeting minutes from transcripts. Use it for requests to make writing sound natural, readable, concise, or lead with the conclusion, and for feedback that text is hard to read or understand, unclear, AI-like, smells of AI, reads like a literal translation from English, sounds unnatural in Japanese, or feels off. It can also assess or score how AI-like text is without rewriting it, and learn the user's writing style.
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.