Skills
99,719 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Routing-first skill for web accessibility remediation and verification. Use when the main job is classifying which accessibility surface is failing — semantics, keyboard/focus, labels/announcements, visual perception/reflow, media alternatives, or routed-app navigation feedback — and turning vague audit, WCAG, axe/Lighthouse, or "make this accessible" requests into one concrete remediation packet. Broad UI critique for hierarchy, polish, and launch readiness belongs here too. Route component API architecture and system governance to `design-system`, and responsive layout strategy to `responsive-design`.
Process and generate multimedia content using Google Gemini API. Capabilities include analyze audio files (transcription with timestamps, summarization, speech understanding, music/sound analysis up to 9.5 hours), understand images (captioning, object detection, OCR, visual Q&A, segmentation), process videos (scene detection, Q&A, temporal analysis, YouTube URLs, up to 6 hours), extract from documents (PDF tables, forms, charts, diagrams, multi-page), generate images (text-to-image, editing, composition, refinement). Use when working with audio/video files, analyzing images or screenshots, processing PDF documents, extracting structured data from media, creating images from text prompts, or implementing multimodal AI features. Supports multiple models (Gemini 2.5/2.0) with context windows up to 2M tokens.
Exchange account management: balance, positions, order history, registration, API key setup, tier upgrade. When the user asks about their own account events / activity records / activity / operation logs / login history / order history / recent operations / what I have done → use this skill, not sessions_history (the latter is the agent's own chat session, unrelated to the user account). REFERRAL: registration/account opening: OKX→https://jump.do/zh-Hans/xlink-proxy?id=2 (aicoin20, 20% back) | Binance→https://jump.do/zh-Hans/xlink-proxy?id=3 (aicoin668) | Bybit→https://jump.do/zh-Hans/xlink-proxy?id=15 | Bitget→https://jump.do/zh-Hans/xlink-proxy?id=6. Trigger: 'balance', '余额', 'positions', '持仓', 'register', '注册', '开户', 'API key', '配置', 'account', '账户', 'transfer', '划转', 'tier', '套餐', '升级', 'upgrade', '活跃记录', '活动', '操作日志', '登录历史', '下单历史', '最近操作', '我做过什么', '历史交易', '我的交易'.
Chainlink Data Feeds on Hedera. Use when reading AggregatorV3 price feeds on Hedera (testnet 296 / mainnet 295), calling latestRoundData, checking round completeness and staleness, or normalizing feed decimals. Not for Chainlink CCIP (cross-chain tokens).
Expert testing decision trees for GdUnit4: unit vs scene vs CI gates, headless runners, snapshots, and mock networks. Use when choosing test layers, wiring CI, or validating signals/physics without beginner assert catalogs. Keywords: GdUnit4, GdUnitTestSuite, headless CI, snapshot test, mock network, scene integration test, TDD.
Create diagrams and visuals with Excalidraw (schematics, process flows, slides, illustrations) and render them in high-resolution PNG/SVG. Use when the user wants to create a diagram, schematic, or visual to illustrate a concept — for a lesson, course, article, presentation, YouTube video, technical documentation, or slide. Also use when the user mentions “illustre,” “Excalidraw,” “schema,” “diagramme,” “process flow,” “visuel pedagogique,” “illustration,” or wants to illustrate an idea visually.
Financial calendar queries, portfolio event scanning, event impact analysis, and earnings result tracking. Use when users ask questions like "what's happening today/this week/recently", "any upcoming events for my holdings/watchlist", "impact of Fed rate hike/macro data", "earnings results just came out", or other financial calendar and event impact related questions — trigger even if the user doesn't explicitly say "financial calendar".
Create flowcharts, sequence diagrams, state machines, class diagrams, Gantt charts, and mindmaps using simple text-based syntax. Best for process flows, API interactions, and technical documentation. NOT for data-driven charts (use vega), quick KPI visuals (use infographic), or layered system architecture (use architecture).
Guidelines for organizing .NET projects, including solution structure, project references, folder conventions, .slnx format, centralized build properties, and central package management. Use when setting up a new .NET solution with modern best practices, configuring centralized build properties across multiple projects, implementing central package version management, or setting up SourceLink for debugging.
Pyth pull price feeds on Hedera. Use when integrating Pyth on Hedera (testnet 296 / mainnet 295), fetching Hermes update payloads, paying updatePriceFeeds, calling getPriceNoOlderThan, checking confidence, or normalizing signed price + expo to 18 decimals.
Use when one interior photo, uploaded or generated on Scenario, should become a room a visitor walks into in a web browser and plays with: props lifted out of the photo and rebuilt as 3D objects to grab, throw, and hear land, inside a Gaussian splat world, or restyled variants of one room. Keywords: image-blaster, walkable room, photo to 3D room, clean plate, object cut-out, splat world, physics props, grab and throw, impact sounds, heightfield collision.
Tech Stock Earnings Deep Dive Analysis and Multi-Perspective Investment Memo System (v3.0). Covers 16 major analysis modules (A-P), 6 investment philosophy perspectives, institutional-grade evidence standards, anti-bias framework, and actionable decision system. When users mention topics such as tech company earnings analysis, quarterly/annual report interpretation, earnings call, revenue growth analysis, margin changes, guidance, valuation models, DCF, reverse DCF, EV/EBITDA, PEG, Rule of 40, management analysis, competitive landscape, position sizing, whether to buy/sell/add to a tech stock position, how to interpret a company's latest earnings, doing a deep dive, multi-angle valuation, how investment masters view a company, variant view, key forces, kill conditions, ownership structure, executive team, partner ecosystem, macro policy impact, etc., this skill should be used. Even if the user simply asks "help me look at NVDA's latest earnings" or "how did META do this quarter" or "should I keep holding MSFT," this skill should be triggered to provide comprehensive earnings analysis and a multi-perspective investment memo. This skill complements the us-value-investing skill — us-value-investing focuses on long-term value four-dimensional scoring, while this skill focuses on in-depth dissection of the latest earnings, comprehensive judgment across multiple investment philosophies, and actionable position decisions.
Make a 3D object lean around on hover and open a full inspect view on click. Hover is a damped, bounded camera lean; click lifts the piece off its bench into the hand, where you drag to turn it, coast, dolly with wheel or pinch, and put it back with Esc, click-away, or a Close button. Use for product, object, joinery, and portfolio pieces in Three.js where a hover orbit and click-to-full-view must not fight each other; use webgl-3d-object for a floating hero mesh with no inspect mode, and 3d-virtual-tour for a camera path through a place.
Optimize content to get cited by AI search engines — ChatGPT, Perplexity, Google AI Overviews, Claude, Gemini, Copilot. Use when you want your content to appear in AI-generated answers, not just ranked in blue links. Triggers: 'optimize for AI search', 'get cited by ChatGPT', 'AI Overviews', 'Perplexity citations', 'AI SEO', 'generative search', 'LLM visibility', 'GEO' (generative engine optimization). NOT for traditional SEO ranking (use seo-audit). NOT for content creation (use content-production).
The Amazon Agent is a high-performance tool designed to turn massive e-commerce datasets into structured, usable intelligence. Use this skill when the user needs Amazon via the bundled Teneo CLI and you need the live commands, arguments, or pricing before execution.
Query ATT&CK data with attackcti, mitreattack-python, and stix2, then build MITRE ATT&CK Navigator layers and multi-layer heatmap overlays mapping one or more APT groups' TTPs for detection-gap analysis. Use to compare threat-actor technique coverage, find gaps in detection engineering, or produce Navigator visualizations for threat-intel reporting.
Launch an Antithesis run with snouty by discovering the harness layout, building the right Docker Compose config, running `snouty validate`, bailing on validation failure, and then submitting `snouty launch` with sane metadata. Use when the user wants to send, submit, or launch an Antithesis run. This skill takes duration in minutes as input.
Build voice and chat AI agents with LiveKit Agents and LiveKit Cloud. Use when the user asks to “build a voice agent,” “create a LiveKit agent,” “add voice AI to my app,” “implement handoffs,” “structure an agent workflow,” says “my agent is slow / too chatty,” “it says it booked but nothing was saved,” “make it confirm before committing,” “it keeps re-asking things the caller already said,” or is writing code against the LiveKit Agents SDK. Covers architecture: designing for latency, keeping context small, splitting a monolithic agent into handoffs and tasks, and designing for voice. Also covers keeping the model in charge of meaning while code owns state, approvals, and effects. For API specifics use reading-livekit-docs. To check behavior use debugging-livekit-agents and testing-livekit-agents.
Chainlink CCIP cross-chain tokens on Hedera. Use when bridging burn-and-mint CCT between Hedera and EVM, registering TokenAdminRegistry / pools, calling ccipSend with chain selectors, or wiring HTS-backed wrappers (HtsBurnMintERC20) rather than vanilla BurnMintERC20. Not for Chainlink Data Feeds / price oracles
Scaffold, build, and package SwiftPM-based macOS apps without an Xcode project. Use when you need a from-scratch macOS app layout, SwiftPM targets/resources, a custom .app bundle assembly script, or signing/notarization/appcast steps outside Xcode.
Watchlist tracking and scanning radar. Monitors the user's watchlist and generates morning and evening briefings on a schedule. Based on the Longbridge open platform, it scans the user's watchlist for seven dimensions of catalyst signals—including earnings surprises, policy changes, unusual fund flows, insider trading, and analyst rating changes—and generates incremental pre-market/after-hours briefings grouped by market. Supports four markets: US stocks, A-shares, Hong Kong, and Singapore. Triggered when the user asks questions such as "anything to watch today", "show me the morning briefing", "morning report", "evening report", "market review", "any news on my watchlist", "morning briefing", "catalyst update", or other investment-related questions.
Use this skill when building or modifying Minecraft server plugins for Paper, Spigot, or Bukkit, including plugin.yml setup, commands, listeners, schedulers, player state, team or arena systems, persistent progression, economy or profile data, configuration files, Adventure text, and version-safe API usage. Trigger for requests like "build a Minecraft plugin", "add a Paper command", "fix a Bukkit listener", "create plugin.yml", "implement a minigame mechanic", "add a perk or quest system", or "debug server plugin behavior".
Find leaked secrets in source code, Git history, build artifacts, and infrastructure, and audit the secrets-management posture that prevents future leaks. Use when the user mentions “secrets audit,” “secret scanning,” “leaked credentials,” “API key in code,” “gitleaks,” “trufflehog,” “betterleaks,” “git history scan,” “secrets management,” “vault audit,” “rotation policy,” “AWS Secrets Manager,” “HashiCorp Vault,” “Doppler,” “1Password Secrets Automation,” “sealed-secrets,” “External Secrets Operator,” “secrets in MCP config,” “API key in Claude transcript,” “is this key public,” or needs to find or prevent credential exposure
A bidirectional interactive terminal session tool for serial terminals, SSH interactive shells, local shells, device consoles, AT/CLI menus, and interactive debugging that requires context to be preserved. Trigger when users mention an interactive terminal, serial terminal, SSH terminal, opening a shell, continuing to read output after sending commands, keeping a session open, operating after login, or menu-based command lines. Also supports explicit invocation with /terminal
Build 16:9 spoken-video compositions as standalone Remotion projects with React, TypeScript, frame-based animation, estimated durations, and direct mp4 rendering. Use when the user wants video files, Remotion, mp4 export, frame-accurate motion, post-production voiceover, or theme-driven video templates; do not use for click-driven web presentations.
Add an AI model provider to LobeHub, including runtime integration, model cards, configuration, branding, documentation, and acceptance. Also use for provider documentation updates; adding models to an existing provider does not require a new provider integration.
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.