Skills
100,928 packaged capabilities and playbooks for agents. Install any of them with one command.
All
ShipSwift skill library — 118 production-ready SwiftUI skills for iOS/macOS covering animations (view transitions, particle transitions, change effects, shimmer, confetti, typewriter, 28 Metal shaders), charts (line, bar, donut, radar, heatmap, 3D network graph), UI components (onboarding, alert, stepper, search bar, cached remote images), and full-stack modules (Cognito/Supabase auth, camera, chat, StoreKit subscriptions, CDK infra). Use when building SwiftUI features, adding animations/charts/components, or when the user mentions ShipSwift.
Use when turning local, private, or personal Agent Skills into publishable skills for GitHub, marketplaces, teams, or public sharing, especially when private paths, personal habits, credentials, internal hosts, or user-specific context must be removed
Semantic Design System Skill for Google Stitch. Generates agent-friendly DESIGN.md files that enforce premium, anti-generic UI standards — strict typography, calibrated color, asymmetric layouts, perpetual micro-motion, and hardware-accelerated performance.
Always invoke when the user's message includes 'tailwind' in any form. Also invoke for: building responsive grid layouts (multi-column card grids, product grids), flex/grid page structures (dashboards with sidebars, fixed topbars, mobile-toggle navs), styling UI components (cards, tables, navbars, pricing sections, forms, inputs, badges), adding dark mode variants, fixing spacing or typography, and Tailwind v3/v4 work. The core use case: writing or fixing Tailwind utility classes in HTML templates (Blade, JSX, Vue). Skip for backend PHP logic, database queries, API routes, JavaScript with no HTML/CSS component, CSS file audits, build tool configuration, and vanilla CSS.
Analyze traditional Chinese medicine constitution data, identify constitution types, assess constitution characteristics, and provide personalized wellness recommendations. Supports correlation analysis with health data such as nutrition, exercise, and sleep.
Reports how hardcoded style values on a page, file or diff map onto a project's existing design tokens, purpose first, then value. Use for "are we using our tokens here", "which hardcoded colors map to which tokens", a token audit or planning a token migration. It never edits and never creates or renames tokens. Fixes and whole-app consistency go to design-system-boss
End-to-end drug safety review integrating FDA labels, FAERS adverse event reports, PRR/ROR disproportionality, pharmacogenomic biomarkers, clinical trial data, and published literature. Use for regulatory drug safety reviews, comprehensive pharmacovigilance reports, label-vs-real-world AE comparison, and clinical decision support for drug safety.
Style thiết kế Supademo cho in-app product tour (dùng kèm skill tour-guide — component gốc 0 dependency): blinker hotspot pulse, tooltip card, step counter + nav buttons, progress bar, theme tokens — quy ra recipe Tailwind/CSS dùng ngay. Trigger: "/tour-guide-supademo", "tour kiểu Supademo", "style supademo", "blinker hotspot". Quy ước: style distill từ sản phẩm khác sẽ là skill riêng /tour-guide-<tên>.
Extract transcript or subtitles from a local video file. Use this skill whenever the user asks to transcribe a video, extract speech-to-text, get subtitles, or wants a text version of what's said in a video. Also trigger on "提取字幕", "视频转文字", "语音转文字", "transcribe", "extract audio text", or when the user references getting a script/transcript from any video file (mp4, mkv, mov, avi, webm). This skill is for LOCAL video files — for YouTube or other online URLs, use the download-video skill first to get the file, then transcribe it.
Treasures Finance: tokenized stocks (xStocks / Ondo) trading, USDC bridging, and delegated wallet ops on Solana and Ethereum. Use when running Treasures-routed finance ops (e.g. discover tokenized stocks, quote/execute a trade, bridge USDC across chains, check a delegated wallet's portfolio). Base URL needs the `/public/v1` prefix (bare host 404s). Trade paths (`/quote/*`, `/trade/submit`, `/bridge/quote`) are geo-fenced at the AWS load balancer → 451 from US and GB, before auth — route those calls through the `sc-vpn` skill with a per-request proxy (DE/NL/SE/CH/SG/HK/JP are clear); reads work from anywhere. A 451 is never a signing problem. See the "Read this before any trade attempt" section. Wallet: DEFAULT to the user's Privy wallet via `treasures-b2b-api` (the wallet signs `ownership_proof` for quotes + per-leg signed payloads for `/trade/submit` — use the `wallet` skill to sign). Route by where the assets live: assets in the Privy/EOA wallet → `treasures-b2b-api`; only use the `treasures-wallet` delegated skill when the user explicitly asks for the Treasures-provisioned wallet or the assets sit in it.
Plan videos and prepare publishing materials for YouTubers/UP主. Use when user wants to plan a video, write a script (口播稿) with on-screen / screen-share cues, generate video title, description, tags, or YouTube chapter timestamps. Triggers on "策划视频", "写视频脚本", "视频口播稿", "video planner", "video script", "prepare video", "视频发布素材", or mentions creating content for YouTube/Bilibili.
Generate and deliver Vidu videos, images, and speech through vidu-cli; manage generation tasks, reference assets, creations, personal cloned voices, and credit quotes. Use for Vidu generation, lip-sync, timeline composition, video extension or upscaling, and related Vidu account workflows. Requires VIDU_TOKEN and vidu-cli v0.2.36 or newer
Write a blameless incident postmortem under postmortems/ following the Google SRE shape — evidence-based timeline, trigger vs root cause vs symptom, contributing factors, what went well, and owned, dated, verifiable action items. Read when asked to write a postmortem, do an incident review, run a root cause analysis, write up the outage, retro on the outage, or when the user says there was an incident and wants it documented. Do NOT read to frame a proposal (use frame-a-proposal), write a spec (use write-a-spec), record a decision (use record-a-decision), or review a design (use review-a-design) — a postmortem documents an incident that already happened; it does not propose, specify, decide, or critique future work.
Search the live web and read full pages with You.com. Use whenever a task needs information newer than training data or from outside the codebase: current library docs and API references, changelogs and release notes, breaking changes, error messages, package versions, pricing, news, or any claim to verify with cited sources. Works keyless through the free MCP profile when no You.com credentials are configured.
Audit MCP servers for tool poisoning, tool shadowing, rug pulls, SSRF, and unauthenticated exposure using Invariant Labs' mcp-scan for static/runtime scanning plus manual SSRF/auth checks and description pinning. Use before adding a new MCP server to an agent stack, when reviewing an internal MCP server, detecting rug pulls, or investigating an agent's unexpected tool-driven behavior.
Use Naval Ravikant-style reframing, desire audits, specific knowledge, and leverage frameworks to clarify career, entrepreneurship, wealth, happiness, freedom, and life choices. Use to identify the wrong questions, conflicting desires, unique competitive advantages, AI replacement risks, dependence on permission, marginal costs, and directions for long-term compounding.
Use when working inside the bagisto-api package: installing or removing it, adding or changing a REST or GraphQL endpoint or resource, building an admin menu's API, or fixing package behavior. Install and removal happen only on explicit request, never automatically. Trigger phrases include “ApiResource,” “Provider,” “Processor,” “DTO,” “resolver,” “install the bagisto-api package,” “remove the package,” “add an endpoint,” and “extend an endpoint.”
A skill for starting the ByteHouse MCP Server locally and invoking its tools. Use it to connect to a ByteHouse database and query data, interact with ByteHouse via the MCP protocol, and generate data asset catalogs and lineage analyses. Use this skill when users need to connect to a ByteHouse database, query data, interact with ByteHouse via MCP, or generate data asset catalogs and lineage analyses.
Generates Codeception tests in PHP covering acceptance, functional, and unit testing. BDD-style with Actor pattern. Use when user mentions "Codeception", "$I->amOnPage", "$I->see", "Cest". Triggers on: "Codeception", "$I->amOnPage", "AcceptanceTester", "Codeception PHP", "Cest"
Build an interactive “cursor-animated walkthrough” page on top of the /docs-site-macos glass theme — a narrow LEFT step-list + wide RIGHT animated folder-tree where an arrow cursor sits in the gutter at the start of each line and moves controller→file per step, files TYPE IN like a transcript exactly when they are created (absent before), nodes are colored BY ROLE (source/read vs dest/write vs pass vs verdict) with text tags, each step has its own accent, there is a manual “step” mode and an auto-play mode, and a caption under the frame narrates the current frame. Use for explaining install→runtime lifecycles, sequences, data-flow, or any “how it works, step by step” walkthrough where the viewer must SEE which file each action touches. Hooks /docs-site-macos for the base glass design system.
Search API configuration, boosting strategies, and processor patterns for Drupal. Covers index field types, custom boost processors, number-field and engagement-metric boosting, Solr field-type drift on config export, and reindexing workflows. Use when configuring or debugging a Search API index, tuning relevance or result ranking, writing a custom search processor, or when search results are missing, stale, or ordered unexpectedly.
Expert blueprint for MOBA games including lane logic (minion wave spawning every 30s), tower aggro priority (hero attacking ally over minion over hero), click-to-move controls (RTS-style raycasting), hero ability systems (QWER cooldowns, mana cost), fog of war (SubViewport projections), and authoritative networking (server validates damage). Use for competitive 5v5 or arena games. Trigger keywords: MOBA, lane_manager, minion_waves, tower_aggro, click_to_move, ability_cooldowns, fog_of_war, comeback_mechanics.
Generate HTML entity-relationship diagrams (ERDs) and database schema visualizations with clickable tables, relationship paths, and migration before/after views. Use whenever the user has a database schema, data model, or table structure to document, explain, migrate, or explore — even when they call it a “data model,” “schema diagram,” or just “the tables.” Reach for this any time the conversation touches database structure with more than ~3 tables.
Discover a single-page app's hidden backend API from its public JS bundle, then test that API for broken access control or missing authentication. One of the highest-yield web plays in modern recon: SPAs ship their entire backend route map to the browser, and the API behind them frequently lacks the authentication middleware implied by the login page. Built from an authorized engagement where this play found an unauthenticated financial API that an ASM scan reporting hundreds of "Criticals" completely missed. Use whenever a target serves a JS-heavy SPA (React/Vue/Angular/Next), an "app"/"console"/"dashboard"/"portal" subdomain, or any `*api*` host appears in recon. Leaked build artifacts (source maps / .env / .git / asset-manifest) are handled by hunt-source-leak; API version inventory and behavioral diffing by hunt-shadow-api; this skill maps a live SPA's backend routes from its JS bundle and tests them for broken access control or missing authentication.
Elite website image-to-code skill for Codex. For visually important web tasks, it must first generate the design image(s) itself, deeply analyze them, then implement the website to match them as closely as possible. In Codex, it must prefer large, readable, section-specific images instead of tiny compressed boards, generate fresh standalone images for sections or detail views instead of cropping old ones, avoid lazy under-generation, avoid cards-inside-cards-inside-cards UI, and keep the hero clean, spacious, readable, and visible on a small laptop.
Raw mechanical interfaces fusing Swiss typographic print with military terminal aesthetics. Rigid grids, extreme type scale contrast, utilitarian color, analog degradation effects. For data-heavy dashboards, portfolios, or editorial sites that need to feel like declassified blueprints.
Audits an Infrahub repository against best practices and rules, producing a structured compliance report. TRIGGER when: reviewing repo for compliance, onboarding to existing project, pre-deployment validation, catching issues. DO NOT TRIGGER when: creating schemas, writing checks/generators, querying live data, populating objects, planning an Infrahub version upgrade (use infrahub-planning-upgrades).
Creates, modifies and debugs Infrahub custom navigation menus for the web UI sidebar, organizing node types into logical groups. TRIGGER when: designing sidebar menus, grouping node types in UI, customizing Infrahub web interface navigation, modifying or extending an existing menu, changing the order, nesting, or icons inside a menu file, debugging why a menu item does not appear or lands in the wrong group. DO NOT TRIGGER when: designing or modifying schemas, including setting menu_placement, icon, or order_weight on a schema node (use infrahub-managing-schemas), writing checks or transforms, populating data objects.
Creates, modifies and manages Infrahub object data YAML files for populating infrastructure instances — devices, locations, organizations, and modules. Trigger when: creating device instances, populating data files, defining locations or organizations, adding infrastructure objects, modifying or extending an existing data file, updating attribute values or relationship links on objects already defined in a data file, debugging why an object fails to load. Do not trigger when: designing or modifying schemas, including changing an attribute or relationship definition on a node kind (use infrahub-managing-schemas), writing Python checks/generators, querying live data.
Use SellerSprite data to find and analyze competitors on Amazon across 12 marketplaces, including product metrics such as sales, BSR, pricing, ratings, and growth trends. Trigger when users mention competitor lookup or analysis, ASIN reverse lookup, competitive product research, finding similar products, market competitor discovery, product benchmarking, competitor sales estimates, analyzing competing listings, competitor analysis, ASIN reverse lookup, competitor sales, competitor research, SellerSprite, market competitor discovery, or competitor trends. Also trigger even without explicitly mentioning “SellerSprite” or “competitor lookup” if the request involves discovering and analyzing Amazon competitors using ASINs, keywords, seller names, brands, or categories.
Use when the user explicitly asks to “write/revise the research foundation” or “organize the research foundation, working conditions, and risk responses.” Write or restructure “(III) Research Foundation” in the NSFC main text, while also organizing “Working Conditions” and “Research Risk Responses.” Use an evidence chain to demonstrate project feasibility, alignment between resources and research content, and the feasibility of risk mitigation plans.
Guide for migrating OCaml projects, libraries, modules, and test suites to idiomatic MoonBit. Use when translating OCaml code to MoonBit, planning a large OCaml-to-MoonBit port, preserving byte/string-heavy behavior, replacing OCaml variants/records/exceptions/refs/arrays, mapping OCaml APIs to MoonBit packages, or building verification and test strategy for a migration.
Use when working with Payload CMS projects (payload.config.ts, collections, fields, hooks, access control, Payload API). Triggers on tasks involving collection definitions, field configurations, hooks, access control, database queries, custom endpoints, authentication, file uploads, drafts/versions, live preview, or plugin development. Also use when debugging validation errors, security issues, relationship queries, transactions, or hook behavior.
Data fetching layer for Vue built on Pinia. Use when writing, debugging, or reviewing code that imports @pinia/colada (pinia colada), including useQuery, useMutation, useInfiniteQuery, defineQuery, query cache invalidation, optimistic updates, plugins, SSR, or migrating from older versions. Provides current 1.4.x APIs, patterns, and migration rules.
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.