Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Configures TYPO3 SEO for EXT:seo, metadata, hreflang, XML sitemaps, robots.txt, canonical URLs, structured data, Core Web Vitals, SEO extensions, and monitoring. Use when working on TYPO3 SEO, sitemap setup, meta tags, robots rules, Open Graph, schema.org, canonical URLs, hreflang, or search visibility.
Use this skill to reason about the three-piece ADB topology (client CLI, host server on TCP 5037, on-device daemon `adbd`), the lifecycle commands `adb start-server` / `adb kill-server` / `adb reconnect`, ADB environment variables (`ADB_TRACE`, `ADB_VENDOR_KEYS`, `ANDROID_ADB_SERVER_PORT`, `ANDROID_SERIAL`, `ADB_LOCAL_TRANSPORT_MAX_PORT`, `ADB_MDNS_AUTO_CONNECT`, `ADB_MDNS_OPENSCREEN`, `ADB_LIBUSB`, `ADB_BURST_MODE`), the host RSA key pair under `~/.android/`, the server log location, and version mismatches between Android Studio's bundled `platform-tools` and a system-installed `adb`. Use when the user mentions `daemon not running; starting now`, `server version doesn't match`, port 5037 collisions, ADB_TRACE, vendor keys, mDNS Openscreen vs Bonjour, libusb regressions, "adb is being weird", or asks "what does adb actually do".
Unity level design-to-code translation. Trigger & event architecture, encounter design contracts, checkpoint & respawn, cinematic & scripted sequences, environmental storytelling hooks, level streaming & loading seams. DESIGN INTENT format: INTENT/WRONG/RIGHT/SCAFFOLD/DESIGN HOOK. Based on Unity 6.3 LTS.
Unity physics query correctness patterns. Catches common mistakes with Raycast, SphereCast, OverlapSphere, NonAlloc allocation, LayerMask construction, trigger interaction, hit ordering, and query type selection. PATTERN format: WHEN/WRONG/RIGHT/GOTCHA. Based on Unity 6.3 LTS.
Use when starting a new feature branch, creating isolated development environments, or working on multiple tasks simultaneously without stashing or switching branches. Triggers: user says "worktree", "new branch for work", "parallel development", "isolated environment", needs to work on two things at once.
Neon is a serverless Postgres platform that separates compute and storage to offer autoscaling, branching, instant restore, and scale-to-zero. It's fully compatible with Postgres and works with any language, framework, or ORM that supports Postgres.
When the user wants to solve the Vehicle Routing Problem (VRP), optimize multi-vehicle routes, or plan fleet delivery routes. Also use when the user mentions "VRP," "fleet routing," "multi-vehicle routing," "delivery route planning," "vehicle dispatch," "fleet optimization," or "route assignment." For single vehicle, see traveling-salesman-problem. For time windows, see vrp-time-windows.
Design and build the visual layer of a long-form talking-head video as one persistent world the camera moves through, instead of a sequence of separate graphics. Use when asked to edit a video, add motion graphics, design the visuals for a script, plan an edit, or fix an edit judged confusing, text-heavy, hard to follow, or "clearly made by an AI". Covers the persistent world, camera grammar, the spotlight rule, spatial open loops, ornament and token discipline, transcript timing, and the verification gates.
Get current weather and forecasts via wttr.in or Open-Meteo. Use when: user asks about weather, temperature, or forecasts for any location. NOT for: historical weather data, severe weather alerts, or detailed meteorological analysis. No API key needed.
Develop, modify, review, debug, test, or deploy Webman PHP applications built on Workerman. Use when a project contains workerman/webman-framework or the task explicitly concerns Webman routing, controllers, middleware, configuration, long-lived workers, custom processes, queues, coroutines, databases, or plugins. Do not use for standalone Workerman or ordinary PHP, Laravel, or ThinkPHP projects without Webman.
WeChat official account topic and outline planning skill. Turns a rough idea, resource pack, voice draft, or interview transcript into 2-3 high-value topic angles, 1 recommended direction, 1 main outline, and 1 backup outline. Suited to the pre-writing planning stage: confirm the structure first, then hand off to the drafting skill.
Search WeRead, inspect books and reading data, manage the bookshelf, public-account subscriptions and reviews, read and write highlights and notes, build private article feeds and archives, ask WeRead AI, or import a personal book through the installed `weread-omni` JSON CLI. Use for requests involving 微信读书, WeChat Reading, a user's WeRead shelf, public accounts, articles, highlights, notes, reviews, reading statistics, recommendations, or book lookup.
Augment a Wren project with business context that DB schema cannot carry — enum value meanings, units (USD vs cents, ms vs sec), NULL semantics, magic sentinels (-1 = unknown), soft-delete default filters, business synonyms, time-grain / TZ conventions, cross-system identifiers, currency rules, canonical-table preferences, AND named aggregation metrics (ARR, churn, DAU, WAU, NRR) proposed as cubes. Runs in one of two modes selected at session start: `grill` (one question at a time, user-driven) or `auto-pilot` (agent infers and applies, escalates only on conflicts and high-blast-radius additions like new cubes / views / relationships). Reads everything under <project>/raw/ (PDFs, glossaries, handbooks, code, data dictionaries) and optionally samples low-cardinality columns from the live DB (grill mode), compares against the current MDL / cubes / instructions.md / queries.yml / memory pairs, then fills gaps via the ten-category gap catalog and the cube proposal flow. Confirmed findings are written back to the right sink. Use when: user says 'enrich context', 'augment my project', 'grill me on this project', 'auto-fill my context', 'agent doesn't understand our docs / enum values / units / null meanings', 'business context is missing', 'what does status=A mean', 'is this amount in USD or cents', 'we keep getting wrong aggregations', 'add cubes for ARR / DAU / churn', 'we have a handbook / glossary / data dictionary the agent should know'; or after generating an MDL and noticing the agent lacks business semantics.
Runs a comprehensive six-section quality checklist (content, structure, clarity, style, polish, final tests) before writing is shared or published, catching issues that revision and stickiness enhancement might miss. Use when performing final quality checks before sharing, publishing, or submitting writing, or when user mentions pre-publish, final check, ready to publish, last review, quality check, or about to share.
Applies the Heath brothers' SUCCESs model (Simple, Unexpected, Concrete, Credible, Emotional, Stories) to make messages memorable and persuasive, with systematic analysis, targeted improvements, and scoring (0-18 stickiness scorecard). Use when making messages more memorable or compelling, preparing presentations, crafting pitches or campaigns, or when user mentions stickiness, making ideas stick, persuasion, SUCCESs framework, or Heath brothers.
Search recent X/Twitter posts by query. Returns raw tweets (last 7 days). Use when user asks "search X for", "find tweets about", "what are people saying about", "Twitter search", "raw tweets about". For AI summaries/sentiment, use x-research instead. Requires X_BEARER_TOKEN.
Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas
Orchestrates keyword-driven searches across public web pages, the latest AI developments (including curated picks, daily reports, and categorized items explicitly requested by the user as AI HOT), verticals, and social platforms, returning standardized candidates. Supports bounded X Research, explicit site Maps, and lightweight verification of candidates found in the current search. Not for reading or downloading known URLs provided directly by the user; use yichen-content-archive for those tasks.
Orchestrates multi-stage internet research requiring search, source verification, and synthesis (such as searching before archiving or compiling cross-platform evidence), including research that combines historical evolution with the current landscape, as well as pre-research offline checks across multiple backends. Handle one-off searches, reading known links, exporting bookmarks, audio/video transcription, and summarizing provided full text directly or with the relevant Skill.
Guides use of Zarr-Python 3 for storing chunked, compressed N-dimensional arrays and groups, with local, in-memory, ZIP, and fsspec-backed S3/GCS/HTTP stores, plus NumPy, Dask, and Xarray integration. Covers array creation, resizing and appending, attributes, chunk and shard sizing, codecs, consolidated metadata, and v2-to-v3 migration. Use when creating or opening Zarr arrays or groups, choosing chunk sizes or compression for large datasets, reading or writing arrays on S3 or GCS, appending to time-series arrays, or migrating code from Zarr-Python 2 to 3. Use when setting up parallel I/O with Dask or Xarray. For labeled multi-dimensional datasets, use Xarray instead.
Official Zernio API reference for scheduling posts across 15 social media platforms and running paid ads on 7 ad networks. Covers authentication, endpoints, webhooks, ads, and platform-specific features. Use when building with the Zernio Social Media Scheduling API.
Manage the Yandex KIT store catalog over its REST API: products, variants (SKUs, prices, stocks), bulk price/stock sync, variant documents (attachments), categories, characteristics (including groups and colors), product videos, collections, context collections and badges. Use when creating, updating, archiving or querying catalog entities in a Yandex KIT store, or when exporting storefront links of products to a CMS, PIM or feed. Russian triggers include: «заведи товар», «обнови цены», «загрузи остатки», «поменяй категорию», «добавь видео к товару», «синхронизируй каталог», «дай ссылку на товар», «выгрузи ссылки на товары».
Manage orders in a Yandex KIT store over its REST API: orders and their statuses, customers, gift cards, additional services (addons) and delivery documents (waybills, parcel labels). Use when listing, confirming or cancelling KIT orders, printing delivery labels, or when looking up customers, their orders or gift cards. Russian triggers include: «покажи заказы», «подтверди заказ», «отмени заказ», «что с заказом», «найди клиента», «выгрузи заказы за неделю», «распечатай ярлык».
Manage promotions in a Yandex KIT store over its REST API: discounts, promo codes, promocode groups (shared codes and single-use coupon batches) and gifts. Use when creating or updating discounts, promocodes, promocode groups or gifts, or when binding them to products, categories or collections. Russian triggers include: «создай скидку», «сделай промокод», «выпусти партию промокодов», «добавь подарок к товару», «останови акцию».
Manage Yandex KIT store-level resources over its REST API: store profile, warehouses, users, geo regions, file uploads, redirects, blog/news posts and system alerts. Use when reading store metadata, managing warehouses or redirects, uploading files, publishing news or triaging store alerts in a Yandex KIT store. Russian triggers include: «покажи склады», «создай склад», «загрузи файл», «опубликуй новость», «какие алерты у магазина», «настрой редирект».
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.