Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Productivity
Schedule meetings, deployments, and events respecting Shabbat, Israeli holidays (chagim), and Hebrew calendar constraints. Use when user asks to schedule around Shabbat, "zmanim", check Israeli holidays, plan around chagim, set Israeli business hours, or needs Hebrew calendar-aware scheduling logic. Includes halachic times (zmanim) via HebCal API, full Israeli holiday calendar, and Israeli business hour conventions. Do NOT use for religious halachic rulings (consult a rabbi) or diaspora 2-day holiday scheduling.
Sweep the current conversation for durable knowledge - user preferences, project facts, operational gotchas, standing decisions, and unfinished next steps - and file each through explicit instructions, existing local conventions, or the private `.stow-notes.md` fallback, curating tiered, decaying destination files as it writes. Use when the user invokes /stow, asks to save or write down what was learned this session, or before a context reset or long break.
Full personal Telegram control over MTProto (Telethon) with the user's own account — list/search chats, read & summarize history, see unread, look up contacts & chat info, list a forum group's topics, download media, and send / reply / forward / edit / delete / react / send files / mark read / join & leave groups, including posting into a forum topic thread. Use when the user mentions Telegram, a Telegram chat/group/contact, "my Telegram", reading/replying/forwarding/summarizing Telegram messages, their unread Telegram, joining or leaving a Telegram group/channel, posting into a forum group's topic, or sending a file/message on Telegram.
Read and send email via IMAP/SMTP. Check for new or unread messages, fetch content, search mailboxes, mark messages as read or unread, and send emails with attachments. Supports multiple accounts. Works with any IMAP/SMTP server, including Gmail, Outlook, 163.com, vip.163.com, 126.com, vip.126.com, 188.com, and vip.188.com.
AI agent-focused RSS feed discovery tool with JSON output. Use when Claude needs to discover RSS/Atom feeds from websites for monitoring, aggregation, or content syndication purposes. Triggered by: "find RSS feed", "discover RSS", "find Atom feed", "get RSS URLs", "find feeds from [URL]", or when working with content aggregation, feed readers, or RSS monitoring workflows.
Evolve your brain's schema pack. Add page types, propose new ones from corpus scans, backfill page.type on existing pages, audit pack health. Triggers when an agent notices untyped pages, custom domains needing typed entities (researcher, contract, deposition), or wants to see what types the pack declares
Structured search data via 130+ engines — use INSTEAD OF web_search when you need: exact citations (google_scholar), local business details (google_maps), flight prices (google_flights), hotel rates (google_hotels), shopping prices (google_shopping_light), job listings (google_jobs), or any task where web_search gives approximate/unstructured results. Returns machine-readable JSON. Default engine: google_light.
Persistent TODO scratch pad for tracking tasks across sessions. Use when the user says “add to TODO,” “what's on the TODO,” “mark X done,” “show TODO list,” “remove from TODO,” or asks about pending tasks. Also triggers on heartbeat to remind about stale items.
Draft structured handover notes for transitioning a PostHog account from one TAM or CSM to another. Use this skill when a TAM needs to hand over an account, prepare a transition briefing, write handover notes, create an account summary for a new owner, or any request involving account transitions between TAMs or CSMs. Triggers on “hand over this account”, “transition account to”, “draft handover notes”, “account briefing for new TAM”, “prepare account transition”, or when a TAM names an account and says they're leaving or reassigning it.
Fetch and summarize recent AI news from curated RSS feeds (Hugging Face, VentureBeat, The Verge, OpenAI, Anthropic, DeepMind, etc.) and YouTube channels (Yannic Kilcher, Two Minute Papers, AI Explained, etc.). Also fetches full transcripts for specific YouTube videos. Use when the user asks about recent AI news, what's happened in AI lately, summaries of AI research or product announcements, or wants a digest of what's going on in the AI space
Guide for designing and planning Educates courses, which are structured collections of workshops for the Educates interactive training platform. Use this skill when the user asks to design a course, plan a course, extend an existing course, or organize topics into a multi-workshop curriculum. Do NOT use this skill when the user only wants to create a single standalone workshop; use the educates-workshop-authoring skill for that instead.
Everything In Its Right Place. The universal post-work organizer. After any significant work session, EIIRP runs a 7-phase audit: (1) inventory every output, (2) walk taxonomy to decide where each lands, (3) check schema-pack consistency against the brain's actual shape, (4) file enriched brain pages, (5) audit the skill graph for DRY+MECE, (6) verify resolvability, (7) report. Named after the Radiohead song. Nothing produced during significant work lives only in chat — knowledge becomes permanent, patterns become reusable. Also carries the always-on auto-fire gate: when >=500 words of structured analysis on a user-shared document is about to be delivered, file the brain page first, then deliver the analysis with the link in that same reply.
Create, retrieve, update, and manage GitHub issues with full context collection. Use when the user wants to create a new issue, view issue details, update existing issues, list project issues, add comments, or manage issue workflows on GitHub (github.com, gh CLI). If the user does not specify a platform, refer to the repository's git remote: use this skill only if the remote is GitHub — otherwise see gitlab-issue
Orchestrates reliable multi-step workflows with the Upwork MCP server for clients, freelancers, and agencies. Use when a task requires selecting an account, discovering tools, chaining reads and writes, handling drafts and confirmation, paginating results, uploading files, or recovering from Upwork tool errors.
Creates user-specific one-click action templates that execute email operations when clicked in the chat interface. Use when the user wants reusable actions for their specific workflows (send payment reminders to ACME Corp, forward bugs to engineering, archive old newsletters from specific sources)
Work with the user's Discord account. Two modes, auto-selected by how they connected — OAuth (read-only identity and server list) or User Token / BYOC (full personal-account actions — list channels, read messages, send and reply). Use when the user mentions Discord, asks which servers they are in, or wants to read/post in a channel as themselves.
A guide to writing NSFC applications. Covers writing tips and templates for each section, including topic selection, abstract, rationale, research content, research plan, innovation, and feasibility analysis. Suitable for project types such as Young Scientists Fund C, General Program, and Key Program.
Extract structured fields, sections, figures and tables, source locations, missing items, and supportable conclusions from paper PDFs and supplementary materials. Can also create a Paper Case with a hash and a phased in-depth reading report. Use when the user asks to “extract this paper,” “extract information from papers in bulk,” “make a paper card,” “read a PDF in depth,” “extract figures and tables,” or create a “phased in-depth reading report.” Runs without a private local workspace or preset research lab; use user-provided material and bundled public-source methods.
Migrate a brain from gbrain-base (or any pack) to gbrain-base-v2's 14-canonical-type taxonomy via gbrain onboard --check + the unify-types Minion handler. Collapses 94 noisy types to 15 canonical with subtypes, alias rows, and link rows. Triggers when an agent notices pack_upgrade_available, type_proliferation, or asks "what is the canonical taxonomy / how do I clean up my page types".
DingTalk AI Minutes. Use when querying or modifying minutes summaries, full transcripts, keywords, tags, action items, recordings, uploads, mind maps, speaker insights, ASR hot word/recognition word configuration, or sharing permissions. Use dingtalk-doc for writing documents; dingtalk-todo for creating to-dos; dingtalk-calendar for schedules. Command prefix: dws minutes.
DingTalk knowledge base and space management. Use when the user explicitly says 知识库/wiki/create, find or list knowledge bases/named team knowledge spaces/personal knowledge bases/knowledge base members/node creation, listing, search, copy, move or deletion within a knowledge base/knowledge base activity. Saying only "文档空间/我的文档" does not trigger it: general storage management and global file search go to dingtalk-drive; node body read/write goes to dingtalk-doc. Command prefix: dws wiki.
Use Exa Agent for multi-step web research, list-building, enrichment, structured output, run continuation, and coverage validation. Exa Agent can access additional data providers: fiber, financial_datasets, similarweb, baselayer, affiliate, particle, and jinko.
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.