Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Lark Mail: Use when user mentions drafting emails, writing emails, drafts, sending/replying to/forwarding emails, reviewing emails, viewing emails, searching emails, email folders, email labels, email contacts, listening for new emails, email rules, etc.; use for mail/email intent only. Do not use for docs/sheets/calendar/auth setup/pure contact lookup/IM chat tasks.
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).
Lark Tasks: manage tasks, checklists, and task agents. Create to-do tasks, view and update task status, split subtasks, organize task checklists, assign collaborators, upload task attachments, register or unregister task agents, update task agent homepage data, and write agent task logs. Use when you need to create to-do items, view task lists, track task progress, manage project checklists, assign tasks to others, upload attachment files for tasks, register/unregister task agents, update agent homepage data, or write task logs.
Bridge THIS Claude Code or Codex session to Telegram, Discord, Feishu/Lark, QQ, or WeChat so the user can chat with Claude from their phone. Use for: setting up, starting, stopping, or diagnosing the claude-to-im bridge daemon; forwarding Claude replies to a messaging app; any phrase like "claude-to-im", "bridge", "消息推送", "消息转发", "桥接", "连上飞书", "手机上看claude", "启动后台服务", "诊断", "查看日志", "配置". Subcommands: setup, start, stop, status, logs, reconfigure, doctor. Do NOT use for: building standalone bots, webhook integrations, or coding with IM platform SDKs — those are regular programming tasks.
Feishu / Lark contacts: resolve a name/email to an open_id, or look up a name/department/email/contact details/personal status/signature by open_id; also search by keyword for bots/agents visible to the current user. Use when a user mentions a name and wants to message them or schedule something next, or has an open_id and wants specific information. Does not handle department tree traversal, listing employees by department, or organization charts; use the native OpenAPI for these.
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/Feishu real-time event listening / subscribing / consuming: stream events as NDJSON via `lark-cli event consume <EventKey>` (covers IM messages/reactions/chat changes, Approval status changes, Task updates, VC meeting started/joined/ended, Minutes generated, Whiteboard updated, etc.). Use for Lark bots, real-time message processing, long-running subscribers, and streaming webhook/push handlers. Supports `--max-events` / `--timeout` bounded runs and a stderr ready-marker contract—designed for AI agents running as subprocesses.
Meeting notes organization workflow: Consolidate meeting notes within a specified time range and generate structured reports. Use when users need to organize meeting notes, generate weekly meeting reports, or review meeting content over a period of time.
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).
Lark OKR: manage objectives and key results. View and edit OKR cycles, objectives, key results, alignment relationships, quantified metrics, and progress records. Use when users need to view or create OKRs, manage objectives and key results, or view alignment relationships. Does not handle: to-do task management (lark-task), scheduling/meetings (lark-calendar), performance reviews.
Intelligently organizes your files and folders across your computer by understanding context, finding duplicates, suggesting better structures, and automating cleanup tasks. Reduces cognitive load and keeps your digital workspace tidy without manual effort.
Explain research papers to readers without a specialist background: what the paper studies, what the authors contribute, how the findings follow, and what the evidence does not establish. USE WHEN the user shares an arXiv link, paper URL, PDF, local paper, or paper title, or asks to read, explain, analyze, or understand a paper. Defaults to a saved Markdown note. NOT FOR reproduction, formal peer review, benchmark tables, or literature surveys.
Find the cheapest hotel deal by comparing live prices across Booking.com, Agoda, Google Hotels, and OpenTravel for any city worldwide and any travel dates. One command returns ranked best-value, cheapest, and quality picks with direct booking links, all normalized to USD. Use whenever someone asks for hotel prices, hotel deals, the cheapest room or rate, best hotel rates, a hotel price comparison, or which OTA is cheaper—for example, “is Booking or Agoda cheaper for Tokyo,” “find me a hotel in Bangkok under $100,” “compare hotel prices for 12–15 Aug,” or “cheapest hotel near Shinjuku.”
Search Korean scholarship announcements across official KOSAF, university, foundation, company, and public-sector sources, extract amount and eligibility, and filter results by school, income band, student level, and organization type. Users may invoke it with the phrase 장학금 검색 및 조회. In Dolsoe, it also carries out follow-up actions through official surfaces.
One topic, one roundtable: a host invites 3–5 real people, sets the opening, and moderates round-by-round exchanges, capturing an ASCII structure diagram each round. The user controls the pace with commands (go / stop / go deeper on this section / introduce a new person). Afterward, the full text is saved in a Markdown note. Use when the user says “圆桌讨论”, “圆桌”, “roundtable”, “辩论”, or wants to explore a topic through structured debate from multiple perspectives.
Use when the user asks to search Korean library books, book details, library holdings, or whether a Korean public library owns a book via k-skill-proxy Data4Library routes. In Dolsoe, it also carries out follow-up actions through the official interface.
Send emails through SMTP with optional local attachments and optional IMAP APPEND sync to the Sent mailbox. Use when tasks need reliable outbound email delivery, attachment sending, SMTP connectivity checks, or cross-client sent-mail visibility (for example, appending to "Sent Items" after an SMTP send).
Academic research assistant for literature reviews, paper analysis, and scholarly writing. Use when: reviewing academic papers, conducting literature reviews, writing research summaries, analyzing methodologies, formatting citations, or when the user mentions academic research, scholarly writing, papers, or scientific literature.
Customize cmux for an end user, including terminal, browser, Markdown, diff, file preview, notes, HTML, and right-sidebar viewers. Use when changing cmux.json actions, custom commands, workspace layouts, plus-button behavior, surface tab bar buttons, Command Palette entries, Dock controls, sidebar and app settings, shortcuts, notifications, browser routing, examples-library presets, or Ghostty-backed terminal preferences.
Official Salesforce documentation retrieval skill. Use when you need authoritative Salesforce docs from developer.salesforce.com, help.salesforce.com, architect.salesforce.com, admin.salesforce.com, or lightningdesignsystem.com, especially when pages are JS-heavy, shell-rendered, or hard to extract with naive fetching. Use to ground answers in official Salesforce sources instead of third-party blogs or summaries. TRIGGER when: user asks for official Salesforce documentation, Apex or API reference, LWC docs, Agentforce docs, setup or help articles, or any doc from a Salesforce-owned domain. DO NOT TRIGGER when: user is asking for a code change, deployment task, or anything not requiring documentation retrieval — use the appropriate sf-* skill instead.
Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or idea. Triggers on “解剖概念”, “概念解剖”, “explain concept”, “learn concept”, “/ljg-learn”. Produces markdown output.
Find web sources with query-relevant page excerpts and optional full-page content, and discover workflows, data APIs, and indexes. Use for web research or finding structured records, listings, transcripts, and datasets. Supports semantic tool discovery, domain matching, and progressive catalogue browsing.
Systematic literature-review workflow for academic, biomedical, technical, and scientific topics, including search planning, source screening, synthesis, citation checks, and evidence logging. Use when the task is to find, screen, synthesize, and cite a body of academic or technical literature.
Plan and ship a game under a jam deadline: lock scope to the clock, schedule the hours, cut features, and submit on time. Use for a game jam (Ludum Dare, GMTK Jam, Global Game Jam), a 48-hour or weekend build, or scoping and submitting a jam entry.
Given a domain, find the few independent forces that truly hold it up. A generator that reduces a dozen phenomena to the fewest possible terms — and can regenerate each phenomenon one by one — only then does it count. Use when user says '降秩', '找秩', '秩是什么', '这个领域靠什么撑着', '背后是什么', or wants to decompose any domain to its irreducible generators.
Freely queries the public Google Flights search surface to conservatively provide flight candidates, booking search links, and lowest/average price comparisons by date, month, and year. In 돌쇠, it also carries out follow-up actions through the official surface.
Find product candidates through Danawa's public search and price-comparison surface, and conservatively compare per-store lowest prices, real purchase price including shipping, card installment discounts, and interest-free installment info across shopping malls. In 돌쇠 it also proceeds with follow-up actions through the official surface.
Guide and apply cmux keyboard shortcut customization. Use when the user asks to customize, rebind, unbind, reset, audit, or create shortcut templates for cmux, including tmux-style, Vim-style, terminal-first, browser-heavy, iTerm/Terminal-like, or agent-triage layouts.
Door-to-door public transit routing in Korea (subway, bus, and walking) via the ODsay LIVE API with Kakao geocoding for address-to-address queries. Use when the user asks for subway, bus, or public transit directions, transfer routes, travel time, or transit directions between two places in Korea.
Trace the origins of theories and reinterpret cases. Review experiential judgments in presentations, courses, copy, or methodologies: first determine whether the proposition holds, then identify and verify credible theories, reinterpret the case through those theories, and state their limits. Use to find support for an original theory, add theoretical sources to a presentation, assess whether a statement can be elevated to a theory, or check for forced attribution to a famous person. Focuses on a single theoretical anchoring and does not default to broader historical analogy research.
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.