Skills
101,174 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Shopee FirstMile logistics (in the same series as linkfox-shopee-store-auth), forwarding all 16 endpoints in the Shopee Open API FirstMile module via /shopee/developerProxy, including get_unbind_order_list, generate_first_mile_tracking_number, bind_first_mile_tracking_number, get_waybill, and get_channel_list. Trigger when the user mentions Shopee first-mile shipping, FirstMile, first-mile waybills, first-mile binding, first mile tracking, transit warehouses, or get_unbind_order_list. Even if “first mile” is not explicitly mentioned, trigger this skill for first-mile waybill binding or shipping labels for an authorized Shopee shop.
Shopee Follow Prize (in the same series as linkfox-shopee-store-auth), forwarding all 6 endpoints in the Shopee Open API Follow Prize module via /shopee/developerProxy: add_follow_prize, get_follow_prize_list, get_follow_prize_detail, update_follow_prize, end_follow_prize, and delete_follow_prize. Trigger when the user mentions Shopee Follow Prize, follow rewards, coupons for followers, add_follow_prize, campaign_id, or fan benefits. Even if “Follow Prize” is not explicitly mentioned, trigger this skill for managing Follow Prize campaigns for an authorized Shopee shop.
Shopee cross-border GlobalProduct (in the same series as linkfox-shopee-store-auth), forwarding all 34 endpoints in the Shopee Open API GlobalProduct module via /shopee/developerProxy, including get_category, get_global_item_list, add_global_item, create_publish_task, update_price, and update_stock. Trigger when the user mentions Shopee global products, cross-border products, GlobalProduct, global SKUs, publishing to sites, merchantId, global_item_id, get_global_item_list, or add_global_item. Even if “global products” is not explicitly mentioned, trigger this skill for global product management or cross-border publishing for an authorized Shopee merchant.
Shopee Media upload module (in the same series as linkfox-shopee-store-auth), forwarding all 6 endpoints in the Shopee Open API Media module via /shopee/developerProxy: upload_image, init_video_upload, upload_video_part, complete_video_upload, get_video_upload_result, and cancel_video_upload. The path is api/v2/media/... (module=130). Trigger when the user mentions Shopee media upload, v2.media.upload_image, or uploading images through the media module. The endpoint names match those in media_space (module=91), but the paths differ; select according to the gateway allowlist.
Shopee cross-border merchant information (in the same series as linkfox-shopee-store-auth), forwarding all 6 endpoints in the Shopee Open API Merchant module via /shopee/developerProxy: get_merchant_info, get_shop_list_by_merchant, get_merchant_warehouse_list, get_merchant_warehouse_location_list, get_warehouse_eligible_shop_list, and get_merchant_prepaid_account_list. Trigger when the user mentions Shopee merchants, merchantId, cross-border sellers, CNSC, a merchant’s shop list, get_merchant_info, merchant warehouses, or prepaid accounts. Even if “merchant” is not explicitly mentioned, trigger this skill for queries about an authorized Shopee cross-border merchant or their associated shop list.
Shopee Public module (in the same series as linkfox-shopee-store-auth), forwarding all 6 endpoints in the Shopee Open API Public module via /shopee/developerProxy: get_shops_by_partner, get_merchants_by_partner, get_access_token, refresh_access_token, get_token_by_resend_code, and get_shopee_ip_ranges. Trigger when the user mentions Shopee Public API, Partner shop lists, get_shops_by_partner, OAuth token exchange, refresh_access_token, or Shopee IP allowlists. Use linkfox-shopee-store-auth for routine authorization; trigger this skill when directly calling v2.public.* open endpoints.
Shopee SBS warehousing service (in the same series as linkfox-shopee-store-auth), forwarding all 5 endpoints in the Shopee Open API SBS module via /shopee/developerProxy: get_bound_whs_info, get_current_inventory, get_expiry_report, get_stock_aging, and get_stock_movement. Trigger when the user mentions Shopee SBS, warehouse inventory, bound warehouses, get_bound_whs_info, inventory aging reports, expiry reports, or stock movements. Even if “SBS” is not explicitly mentioned, trigger this skill for queries about SBS warehousing and inventory data for an authorized Shopee shop.
Filter independent Shopify stores by multiple dimensions, including store name/domain, country, age, product count, ad count, monthly visits, monthly orders, and social media followers. Trigger when the user mentions Shopify stores, Shopify store analysis, independent stores, Shopify seller, competing independent stores, Shopify monthly visits, independent store ad libraries, shopify stores, or Shopify store query. Even if the user does not mention the tool, trigger this skill when they want to find Shopify stores, filter store data, or analyze store performance.
Search locally synced Temu category data by keyword to find category names in Chinese and English and category IDs for filtering products or shops. Trigger when the user mentions Temu categories, Temu category ID, Temu category tree, Temu backend categories, temu product categories, looking up categories after syncTemuCategory (Temu category sync), or Temu category search. Even if the user does not mention the tool, trigger this skill when they want to find a category ID by keyword in the locally synced Temu category database.
Visual marketing asset creation for ads, social media, email, presentations, and brand collateral. Platform-specific dimensions, creative best practices, AI design tools, and conversion-focused visual hierarchy. Use when you need production-ready marketing visuals.
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
Moves an existing Playwright, Cypress, Selenium, Appium, Detox, Maestro, or TesterArmy suite to e2e one slice at a time, keeping the old suite running alongside the new one until each ported test is proven. Maintains a MIGRATION.md progress file so later sessions can resume where the last one stopped. Optionally plants a defect to show both suites catch it. Use for /migrate-to-e2e, “migrate our tests to e2e,” “port these Maestro flows,” “move our TesterArmy tests,” or when a project has an e2e config and an older suite still running.
Create and debug Minecraft 26.x and legacy 1.21.x world generation for datapacks, NeoForge, or Fabric, including biomes, dimensions, features, structures, and biome modifiers. Use for worldgen data or registration, not general gameplay systems.
MiniQMT quantitative trading interface, based on the XtQuant Python library (xtdata market data / xttrader trading), for external Python programs to connect to the MiniQMT client. Supports market data retrieval (K-lines, tick-by-tick data, financial data, etc.) and trade order placement (order submission, cancellation, and queries for assets, orders, and positions) for A-shares, futures, and options. Use when users mention miniqmt, xtquant, real-time market data retrieval, quantitative trade order placement, backtesting data retrieval, or need to connect an external Python program to the MiniQMT client for programmatic trading. To write or backtest built-in strategies inside the QMT client (ContextInfo/passorder), use the qmt-strategy skill.
Use for any question about Mux APIs, SDKs, the mux CLI, webhooks, assets, uploads, playback, live streaming, Mux Data, or Mux Robots. Finds the current Mux documentation — Mux publishes every docs page as LLM-ready markdown indexed at mux.com/llms.txt — so answers come from today's published docs instead of web search or model memory.
Bluetooth Low Energy (BLE) attack methodology — GATT enumeration, characteristic read/write without auth, pairing downgrade (Just Works forced), LE Secure Connections bypass, MITM via active relay, sniffing with Sniffle (TI CC1352) / Ubertooth / Frontline, encryption key extraction (LE Legacy Pairing crackable, LE Secure Connections strong), proximity authentication abuse (cars, locks), and companion-app trust analysis. Use for IoT BLE devices, smart locks, fitness trackers, medical devices, BLE beacons, or any device pairing over BLE.
Use when an agent is asked to draft, rewrite, edit, review, polish, copyedit, simplify, humanize, or create written prose, including creative writing, essays, posts, scripts, speeches, emails, documentation, product copy, and other style-sensitive text. Apply George Orwell's six rules and ASD-STE100 Simplified Technical English as a plain-English discipline while preserving the user's intended meaning, audience, tone, and explicit constraints
Complete browser automation with Playwright. Auto-detects dev servers, writes clean test scripts to /tmp. Test pages, fill forms, take screenshots, check responsive design, validate UX, test login flows, check links, automate any browser task. Use when user wants to test websites, automate browser interactions, validate web functionality, or perform any browser-based testing.
Use when creating a DeepSeek Harness plugin, choosing public names for a new external DSH plugin, validating a dsh-plugin.naming.json manifest, checking reviewed central registrations for known conflicts, or creating a workspace package inside the deepseek-harness repository. Covers the full workflow from repository-mode and plugin-form selection through separate offline naming validation, optional online registry lookup, and package validation. Routes tool, LLM adapter, hook, service, and configuration forms to their corresponding references while separating upstream-monorepo rules from external-package rules. For an existing plugin crossing Harness versions, use this Skill's built-in version-adaptation workflow before implementing against the exact target contract.
Create professional PowerPoint presentations from outlines, data sources, or AI-generated content. Supports custom templates, style presets, charts/tables from data, and AI-generated images. Use when asked to create slides, pitch decks, reports, or presentations.
Philosophy-aware PR reviews checking alignment with amplihack principles. Use when reviewing PRs to ensure ruthless simplicity, modular design, and zero-BS implementation. Suggests simplifications, identifies over-engineering, verifies brick module structure. Posts detailed, constructive review comments with specific file:line references.
Discover and install related skills from inference.sh skill registry. Helps find complementary skills for your AI workflow. Use for: skill discovery, workflow expansion, capability exploration. Triggers: related skills, find skills, skill discovery, complementary skills, expand workflow, more capabilities, similar skills, skill suggestions
Synthesize user research into actionable insights using atomic research methods. Use when asked to synthesize research, organize user feedback, find patterns in interviews, summarize customer discovery, or turn raw notes into insights and recommendations.
Acquire a page or site into the shared PageSnapshot every audit module reads — real HTTP status chain, headers, robots directives, raw HTML on disk, parsed document, optional headless-Chrome render with a raw-vs-rendered delta, and once-per-run site artifacts (robots, sitemaps, AI discovery files). Acquisition is done by the bundled scripts (snapshot.mjs / crawl.mjs), never by WebFetch. Records the data tier reached.
Audit and generate Local SEO signals for local-business pages — verify LocalBusiness JSON-LD, NAP consistency, geo coordinates, openingHoursSpecification, and service-area, advise on Google Business Profile alignment, and produce ready-to-inject LocalBusiness JSON-LD. Module M19 (conditional). Feeds both the Search SEO and AI Visibility scores.
Orchestrates a full SEO + AI-search audit — acquires the site with the bundled scripts (crawl/snapshot), detects platform and vertical, runs the deterministic checks, dispatches the read-only specialist subagents in parallel with a dispatch envelope, merges their findings into a persisted report, and presents the two scores. Invoked by the `audit` and `geo` commands; not called directly.
Scaffold production-ready React Native apps using the @codewithbeto/ship CLI. Use when the user wants to create a new app from a Code with Beto template, scaffold a project with Platano, or run `bunx @codewithbeto/ship`. Always use flag-based (non-interactive) mode — the interactive TUI requires a terminal
Manually invoked skill that makes the agent compress its current answer — remove filler, simplify wording, and cut length while preserving the substance. Use when the user says "short", "shorter", "simpler", "too long", "tl;dr", or asks for a more concise version of the previous response.
Search, rent, manage, and release phone numbers with the Sinch Numbers API. Use when listing active numbers, searching available numbers, renting or releasing numbers, updating number configuration (SMS/voice/callback), managing emergency addresses, or checking available regions
Implements Syncfusion .NET MAUI ComboBox (SfComboBox) control. Use when working with ComboBox, dropdown selection, editable dropdown, searchable dropdown, or filterable dropdown in .NET MAUI. Covers basic ComboBox setup, editable/non-editable modes, single/multiple selection, filtering and searching, custom UI styling, and AI-powered smart search.
Technical blog post writing with structure, code examples, and developer audience conventions. Covers post types, code formatting, explanation depth, and developer-specific engagement patterns. Use for: engineering blogs, dev tutorials, technical writing, developer content, documentation posts. Triggers: technical blog, dev blog, engineering blog, technical writing, developer tutorial, tech post, code tutorial, programming blog, developer content, technical article, engineering post, coding tutorial, technical content
Migrates and converts test automation scripts between Selenium, Playwright, Puppeteer, and Cypress. Use when the user asks to migrate, convert, or port tests from one framework to another; rewrite tests in a different framework; or switch from Selenium to Playwright, Playwright to Selenium, Puppeteer to Playwright, Cypress to Playwright, or vice versa. Triggers on: "migrate", "convert", "port", "selenium to playwright", "playwright to selenium", "puppeteer to playwright", "cypress to playwright", "rewrite tests in", "switch from [framework] to [framework]".
Enforces the non-happy paths every screen owes the user — loading/empty/error/content resolved in ONE switch over an AsyncValue or sealed view state, never an isLoading+error+data bool triple; a delayed skeleton shaped like the result instead of a spinner that flashes; a refresh that keeps stale content on screen; "nothing yet" distinguished from "nothing matches this filter", each with its own action; error text from a typed Failure code (never e.toString()) plus a retry that invalidates the provider; the surface ladder inline, snackbar, banner, dialog, with a modal earned only by a decision that must resolve now; soft-delete + Undo over a confirmation; showDialog's null dismissal handled as its own outcome; ScaffoldMessenger captured before an await; and announcements for eye-only changes. Use when writing loading, empty, error, or offline UI, calling AsyncValue.when, showDialog, showModalBottomSheet, showSnackBar or showMaterialBanner, or adding a confirmation, Undo, or retry
Search Zhihu & the web, get trending topics, and read/publish on Zhihu (知乎) — search Zhihu content or the entire web via the official Developer Platform API, get hot topics (热榜), list published articles & answers with stats, inspect content, publish articles, and answer questions. Use when the user mentions 知乎 / Zhihu, 搜索知乎, 全网搜索, 热榜, "我的知乎文章/回答", reading stats, 发文, or 回答问题.
Enforces adapting layout by available CONSTRAINTS/size, never device or platform checks — LayoutBuilder + MediaQuery.sizeOf/paddingOf/viewInsetsOf (not .of) for narrow rebuilds, Material 3 window size classes (compact <600, medium 600-840, expanded 840-1200, large >1200) as the breakpoint vocabulary, navigation affordance chosen by width (NavigationBar → NavigationRail → NavigationDrawer), list-detail single-pane-vs-two-pane, readable max-width via ConstrainedBox, Flexible/Expanded/FractionallySizedBox over fixed widths, SafeArea + display cutouts + keyboard insets, never lock orientation, foldable/hinge awareness via MediaQuery.displayFeatures, and golden-matrix verification across sizes. Use when building responsive or adaptive UI, tablet/desktop/foldable support, master-detail or two-pane screens, a NavigationRail-vs-BottomNav shell, breakpoints, LayoutBuilder, MediaQuery sizing, SafeArea/cutouts, or fixing overflow at large widths.
Use when the user asks about personal notes or personal notebooks without naming another storage target, including “最近的笔记” or “列出我的笔记本”, or wants to search, read, export, create, organize, move, or auto-classify notes and view 总结、大纲、全文、划线、批注 or 我的记录. These requests target the user's external note library, not agent memory and not Claude memory. Also use when Ai好记 / AI好记 is named. Do not use for explicit 本地文件 or Markdown, 代码仓库, Obsidian, Notion, 有道云笔记 or 其他服务.
Alibaba Cloud KMS Secret Management Skill. Used for managing secrets in KMS, supporting create, delete, update, query operations, version management, and rotation policy configuration. Trigger words: "KMS secret", "secret management", "create secret", "delete secret", "secret rotation", "get secret value"
Animation and motion design patterns using Motion library (formerly Framer Motion) and View Transitions API. Use when implementing component animations, page transitions, micro-interactions, gesture-driven UIs, or ensuring motion accessibility with prefers-reduced-motion.
Transform AI-assisted drafts into authentic, human-sounding content. This skill provides patterns to detect and eliminate AI tells, frameworks for natural writing, and techniques for creating prose that reads as genuinely human. Use when reviewing any AI-generated content or when writing content that must not appear AI-assisted.
Expert knowledge for Azure Policy development, including troubleshooting, best practices, decision-making, architecture and design patterns, security, configuration, integrations and coding patterns, and deployment. Use when authoring JSON policies, Machine Configuration, DevOps policy-as-code, Terraform/Gatekeeper, or CI/CD governance, and other Azure Policy-related development tasks. Not for Azure Blueprints (use azure-blueprints), Azure Resource Manager (use azure-resource-manager), Azure Role-based access control (use azure-rbac), or Azure Security (use azure-security).
Build and deploy applications on inference.sh. Use when getting started, understanding the platform, creating apps, configuring resources, or needing an overview of inference.sh app development. Supports both Python and Node.js. Triggers: inference.sh app, belt app, inf.yml, inference.py, inference.js, deploy app, app development, build app, create app, GPU app, VRAM, app resources, app secrets, app integrations, multi-function app
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.