Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Symbolic mathematics in Python with SymPy — solve equations algebraically, perform calculus (derivatives, integrals, limits), manipulate algebraic expressions, work with symbolic matrices, and generate executable code from formulas. Use when exact symbolic results are needed rather than numerical approximations, or for physics, number-theory, and geometry computations involving variables and parameters. Part of the AlterLab Academic Skills suite.
Provides LaTeX templates, formatting requirements, and submission guidelines for major scientific venues (Nature, Science, PLOS, IEEE, ACM, Cell Press), conferences (NeurIPS, ICML, ICLR, CVPR, CHI), research posters, and grant proposals (NSF, NIH, DOE, DARPA). Also covers venue-specific writing style (tone, abstract format, what reviewers prioritize). Use when preparing a manuscript, conference paper, poster, or grant proposal and you need the right template, page/word limits, citation style, figure specs, or venue conventions. For substantive prose/content development defer to alterlab-scientific-writing; for grant argumentation defer to alterlab-research-grants. Part of the AlterLab Academic Skills suite.
Plan and generate Amazon A+ Content / Premium A+ module images (970×600 header, 970×300 banner, 300×300 / 220×220 tiles, 350×175 comparison, 1464×600 premium) with a consistent campaign style lock across all modules. Use for A+ content, A+ 页面, EBC, brand story, enhanced brand content.
Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.
De-identify a session transcript (file or folder) by redacting PII LOCALLY before any sharing or cloud use. Produces a redacted GREEN copy with unique reserved-sentinel placeholders ([CONFIDE_PERSON_0001], [CONFIDE_EMAIL_0001], [CONFIDE_DATE_0002]...) plus a counts-only stats summary, and a local secret <name>.map.json (0600, gitignored) that enables confide:rehydrate to restore real values after a cloud analysis. Use when the user says "anonymize this transcript", "redact PII", "de-identify session", "make safe to share", "strip personal data", "anonymize notes before sending to an LLM", or points at a transcript/folder that should be scrubbed. Local-only by default — raw text never leaves the machine; the map is the only artifact with originals and stays local; nothing printed is PII; human review is still required before sharing.
Conducts comprehensive architecture design reviews including system design validation, architecture pattern assessment, quality attributes evaluation, technology stack review, and scalability analysis. Produces detailed review reports with findings, recommendations, and risk assessments. Use when reviewing software architecture designs, validating architecture decisions, assessing system scalability, evaluating technology choices, or when users mention architecture review, design assessment, technical review, or architecture validation.
Generate optimized Gemini prompts for `asc app-shots generate` by analyzing app screenshots. Reads the screenshot image, identifies the app's purpose, key features, color scheme, and most compelling UI elements, then outputs a ready-to-run `asc app-shots generate --prompt "..."` command that produces professional App Store marketing screenshots. Use this skill when: (1) User asks to "generate a prompt for my screenshot", "optimize my app-shots prompt" (2) User wants help making their `asc app-shots generate` output look better (3) User says "analyze this screenshot" or "create marketing screenshot" for an app (4) User mentions "app-shots prompt", "enhance screenshot prompt", or "ASO screenshot" (5) User has a composed screenshot and wants to improve it with AI
Astro framework patterns for Islands Architecture, client directives (client:load, client:visible, client:idle, client:only, client:media), integrations (MDX, Tailwind, React/Vue/Svelte), View Transitions API, and deployment strategies. Use when building content-focused sites, implementing partial hydration with islands, setting up multi-framework projects, optimizing performance with zero-JS by default, or deploying static/SSR sites.
Process, route, filter, and archive inbound email with Amazon SES Mail Manager. Use when building email ingress pipelines, spam/IP filtering, compliance archiving, SMTP relay forwarding, address allow/block lists, or any inbound email processing workflow. Covers ingress points, traffic policies, rule sets, relays, archives, and address lists.
Expert knowledge for Azure Durable Task development, including best practices, decision-making, architecture and design patterns, limits and quotas, configuration, integrations and coding patterns, and deployment. Use when building Durable orchestrations with Azure Storage/SQL/Netherite, versioning deployments, using instance APIs, or handling other Azure Durable Task-related development tasks. Not for Azure Functions (use azure-functions), Azure Logic Apps (use azure-logic-apps), Azure App Service (use azure-app-service), or Azure Service Fabric (use azure-service-fabric).
Drive and inspect iOS simulators with the `baguette` CLI: taps, swipes, buttons, typing, screenshots, the accessibility tree, logs, and the conditions an app runs under (location, network, appearance, push, UserDefaults), without opening Xcode. Use when an agent must act on or verify a running simulator — a UI flow, smoke test or demo, checking a code change on screen — or when the user names `baguette`. Not for installing Xcode or merely opening Simulator.app.
A viral-title generator for WeChat Official Accounts in tech/AI/internet, targeting 100k+ reads. Given an article, a piece of content or a topic, it first builds a content brief, then produces multiple candidate titles using several methods, scores each one, flags risks, recommends titles by role for different purposes, and gives A/B testing advice. Triggered when the user says 起标题, 想个爆款标题, 这篇文章叫什么好, 标题优化, 标题改写, 多组标题, 标题评分, or 10万+标题. The methodology is distilled from 100 real viral tech article titles.
Generates Xiaohongshu (Little Red Book) infographic series with 9 visual styles and 6 layouts. Breaks content into 1-10 cartoon-style images optimized for XHS engagement. Use when user mentions "小红书图片", "XHS images", "RedNote infographics", "小红书种草", or wants social media infographics for Chinese platforms.
Solve a hard problem by trying multiple approaches in parallel using isolated git worktrees. Each attempt runs in its own branch, and the best solution is selected. Use for complex refactors, tricky bugs, or architectural decisions where multiple strategies could work.
Better Auth (TypeScript authentication framework) v1.7 reference. Covers authentication and authorization, sign-up and sign-in, session management, OAuth, passkeys, two-factor authentication (2FA / TOTP), SSO / SAML, SCIM, OAuth Provider (OAuth 2.1 / OIDC), MCP authorization (@better-auth/mcp), infrastructure (dash / sentinel), and plugins (organization, admin, magic-link, anonymous, etc.). betterAuth, createAuthClient, signUp, signIn, getSession. Integrations with Next.js, Nuxt, SvelteKit, Hono, Express, Expo, TanStack, and Effect.
Use when the user asks for BingX perpetual futures trade review, performance analysis, PnL summary, win rate, trade journal, recent trading performance, trade tags, reflections, or weekly PnL. It fetches trade history from bingx-swap-account, computes statistics, generates local charts, and supports custom tags and review notes.
Query bioRxiv/medRxiv preprints via REST API. Search by DOI, category, or date range; retrieve metadata (title, abstract, authors, category, DOI, version history) and PDFs. No auth. For peer-reviewed biomedical use pubmed-database; broader scholarly search use openalex-database.
BlindPay integration for payins/payouts and stablecoin on/off-ramps (ACH, wire, SWIFT, Pix, SPEI, SEPA, USDC/USDT), customer KYC/KYB, bank and virtual accounts, managed or blockchain wallets, cross-chain transfers, payables (boletos, PIX QR codes, invoices), partner fees, or webhooks.
MANDATORY — invoke this skill BEFORE making any Blockscout MCP tool calls or writing any blockchain data scripts, even when the Blockscout MCP server is already configured. Provides architectural rules, execution-strategy decisions, MCP REST API conventions for scripts, endpoint reference files, response transformation requirements, and output conventions that are not available from MCP tool descriptions alone. Use when the user asks about on-chain data, blockchain analysis, wallet balances, token transfers, contract interactions, on-chain metrics, wants to use the Blockscout API, or needs to build software that retrieves blockchain data via Blockscout. Covers all EVM chains.
Feed and whole-publication ingestion: turn an entire blog, newsletter, or RSS/Atom archive into brain source pages. Covers feed discovery, pagination walking, normalization to a common article shape, canonical-URL dedup, idempotent re-runs, 429 pacing, and empty-husk repair. This is the PUBLICATION-scope skill — a single article URL routes to idea-ingest instead. Per-article enrichment hands off to the brain-ingest-gate skill; public posts only (gated content is skipped, never worked around).
Publish (with optional images), delete and read your own posts on Bluesky via the AT Protocol (XRPC). Use when the user wants to post to their Bluesky account (text or 带图 / with a picture), cross-post an article as a short dev-focused post, attach an image, delete a post, or list their own recent posts with engagement stats (reposts, likes, replies). Auth uses the user's handle plus an App Password.
Design and pressure-test useful nonfiction book promises, scopes, recommendation loops, and takeaway-first tables of contents before drafting. Use when planning, outlining, scoping, restructuring, validating, or testing a practical book, guide, manual, course-like book, or other reader-outcome-focused long-form nonfiction.
BRENDA Enzyme DB SOAP/REST queries: kinetic parameters (Km, Vmax, kcat, Ki), EC classes, substrate specificity, inhibitors, cofactors, organism data. 80K+ enzymes, 7M+ values. Free academic registration. For metabolic modeling use cobrapy-metabolic-modeling; metabolites use hmdb-database.
Use when automating a real, logged-in Chrome WITHOUT disturbing the user's open tabs — e.g. authenticated sessions like ChatGPT, LinkedIn, or any site needing a persistent login. Launches or reuses a dedicated debug Chrome instance per named profile that coexists with the user's main browser; it never quits or kills any browser (unlike real-browser, which closes Chrome Beta's tabs). Trigger on "automate this site without closing my tabs", "use my logged-in session", "open ChatGPT/LinkedIn in automation", or when a browser task must preserve the user's existing windows. macOS, requires the agent-browser CLI.
When a user pastes a BSC mint URL or contract address (CA), run fast, read-only mint identification and preflight: detect the mint contract, function, price, eligibility, quota, and open status via experience DB, verified ABI/proxy, and parallel RPC; perform risk checks and optionally preview baw; never auto-sign.
Create or edit a PostHog freeform canvas — a sandboxed browser application (data board, document, form, small tool, graphics experiment) stored in PostHog and rendered by the desktop/web app. Use when a task asks to build, generate, update, or fix a standalone canvas app, or when a freeform canvas id is given as the publish target. For grid/home canvases, widget placements, or reusable components, use composing-grid-canvases instead. Covers resolving or creating the target canvas, choosing an implementation approach (React + Quill vs plain HTML/browser APIs), the read → edit → validate → publish → build loop, and which companion canvas skills to load for the details.
Transforms technical work into persuasive business-language documents for non-technical stakeholders, including internal announcements, approval proposals, incident explainers, technical-debt cases, product explainers, and investor or partner memos. Use when the user asks to present technical work to the company, explain software to business teams, write a business case, make an approval document, or convert a technical artifact into stakeholder communication in the requested language. Do not use for READMEs, specs, ADRs, external marketing pages, or customer-facing sales copy.
Generates 15-25+ cold outbound campaign ideas with targeting strategies, AI personalization approaches, and value propositions. Use when planning campaign experiments for a client, given their website or business context.
Official CCXT MCP (Model Context Protocol) server — connect an AI agent to 100+ cryptocurrency exchanges and prediction markets for market data, balances, and opt-in trading. Covers installing the server in Claude Desktop/Code, Cursor, VS Code and other MCP hosts; configuring named accounts and API keys (kept local, never seen by the model); the capability tiers and safety rails; sandbox/testnet trading; and how to drive the tools. Use when the user wants an agent to fetch prices/order books/candles, check balances/orders/positions, place or cancel orders, or explore prediction markets across exchanges.
Use when writing Java (or other JVM language — Kotlin, Scala) application code that connects to a data source through a CData driver, after the connection and SQL have been validated with the cdata-cli discovery skill. Covers the CData JDBC Driver edition: reusing the same jar cdata-cli already downloaded and activated, putting it on the classpath (or adding it as a Maven/Gradle dependency), and connecting via JDBC (DriverManager, the jdbc:<source>: URL, PreparedStatement). This is the JVM build-phase companion to cdata-cli.
Use when reviewing a set of changes before they merge — a PR, a branch diff, or the working-tree changes you just made — in a Repowise-indexed codebase (.repowise/ directory exists). Activates for "review this PR", "is this safe to merge", "what's the blast radius of these changes", "did I miss anything", or "what else should change with this".
Assess an A-share portfolio company's AI readiness for China-focused private equity investments. Evaluates data infrastructure, technology stack, talent, and AI adoption opportunities in the Chinese market context. Triggers on "A股公司AI评估", "AI readiness China", "AI assessment portfolio company", "AI转型评估", or "artificial intelligence readiness [company]".
Structure and draft Confidential Information Memorandums (CIMs) for A-share sell-side M&A processes. Organizes company information into professional, investor-ready documents with Chinese market context. Triggers on "A股CIM", "保密信息备忘录", "CIM China", "confidential memorandum A-share", or "offering memorandum [company]".
Track A-share sell-side M&A and deal pipeline with milestones, deadlines, and action items. Adapted from the original deal-tracker skill for Chinese market deal processes. Triggers on "A股交易跟踪", "并购进度", "deal tracker China", "M&A pipeline A-share", or "track progress on [deal]".
Refresh and update existing A-share investment presentation decks with latest data. Adapts the original deck-refresh skill for Chinese presentations, A-share data updates, and domestic market conventions. Triggers on "更新PPT", "刷新演示", "refresh deck China", "update presentation", "更新演示文稿", or "refresh slides [company]".
Draft process letters and bid instructions for A-share sell-side M&A processes. Covers indication of interest (IOI) instructions, final bid procedures, and management meeting logistics adapted for Chinese market conventions. Triggers on "A股流程函", "投标函", "process letter China", "bid instructions A-share", or "IOI instructions [company]".
Tax-loss harvesting strategies for A-share portfolios. Adapts the original tax-loss-harvesting skill for Chinese tax rules, A-share market conventions, and domestic tax treatment. Triggers on "A股税务亏损抵扣", "亏损抵扣", "tax loss harvesting China", "税务优化", "亏损抵扣策略", or "harvest tax losses [portfolio]".
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.