Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Other
Safe Windows C: drive space analysis and cleanup workflow. Use when a user asks Codex to scan, diagnose, clean, free space, remove large files, identify uninstall candidates, or troubleshoot low disk space on a Windows system drive, especially C:\. Emphasizes read-only analysis first, risk classification, explicit user approval before deletion or uninstalling, privacy-preserving local-only scans, and safe handling of Windows Installer, WinSxS, AppData, ProgramData, caches, personal files, and large application data.
Operate YouTube Music via natural language. Search songs, artists, albums, playlists, lyrics, charts, recommendations, and control playback. Browse personal library, manage playlists, rate tracks, and inspect account info. Use this skill whenever the user asks about YouTube Music, wants to play music, manage playlists, search by song or artist name, inspect lyrics, or control playback.
Answer questions from Zhuangzi's perspective — wandering freely among all things, dissolving binary oppositions through the Equality of Things, and revealing what is true through fables and absurd metaphors. Use when the user explicitly asks for this figure's perspective, mentions "zhuangzi-perspective", or wants to apply its core method to analyze a problem; do not trigger automatically for general questions.
Use when deciding whether an AI-enabled workflow should be adopted, scaled, constrained, redesigned, or retired, and the decision must connect business outcomes, worker or user effects, quality guardrails, full operating cost, telemetry, uncertainty, and accountable governance. Do not use for a standalone financial model, infrastructure cost calculation, agent evaluation design, runtime operations, or general AI governance; route those details to the neighboring specialist skills.
Comprehensive one-click analysis of a stock or company. Parallel subagents collect data across five dimensions at once — stock price, news sentiment, industry comparison, market environment, and the company's official website — then the main thread performs cross-analysis, causal attribution, and trend forecasting, and outputs a standardized HTML analysis report (including the day's quotes and a 7-day trend). Trigger phrases: analyze XX stock, analyze TICKER, how is XX doing, is XX worth buying. Supports A-shares, Hong Kong stocks, and US stocks.
Build, fill, stress-test, and iterate on a Business Model Canvas for a solopreneur. Use when designing or redesigning how a business creates, delivers, and captures value — covering all nine BMC blocks plus solopreneur-specific adaptations like the "Time & Energy" block and unit economics validation. Trigger on "business model canvas", "design my business model", "how will I make money", "business model", "BMC", "value proposition canvas", "how does my business work", "monetize my idea".
AI-powered clinical decision support tool that helps generate comprehensive differential diagnoses based on patient symptoms, lab results, and medical history. Integrates evidence-based clinical reasoning and medical literature.
When the user wants to implement or optimize cycle counting programs, improve inventory accuracy, or design physical inventory processes. Also use when the user mentions "inventory accuracy," "physical inventory," "stock counting," "ABC cycle counting," "perpetual inventory," "inventory reconciliation," or "variance analysis." For inventory optimization, see inventory-optimization. For warehouse operations, see warehouse-design.
A mental model that takes Duan Yongping's philosophy of benfen (staying true to one's role) and value investing wisdom as its perspective. Use when the user explicitly asks for this figure's perspective, mentions "duanyongping-perspective", or wants to apply its core method to analyze a problem; do not trigger automatically for general questions.
Expert in course platform selection and implementation - comparing Teachable, Kajabi, Thinkific, and custom solutions. Covers LMS selection criteria, platform migrations, tech stack decisions, and building vs buying. Use when "course platform, lms, teachable, kajabi, thinkific, course hosting, learning management system, which platform" mentioned.
Power systems engineering covering grid modeling, power flow analysis, energy storage dispatch, demand response, and electricity market economics. Spans transmission/distribution planning to real-time operations. Use when "power flow|load flow|grid model, energy storage|battery dispatch|ESS, demand response|load management|peak shaving, electricity market|LMP|locational marginal price, grid stability|frequency|voltage, capacity planning|resource adequacy, unit commitment|economic dispatch, transmission|distribution|power system, " mentioned.
Use when the user faces extreme market sentiment and needs to make a contrarian decision — when everyone is buying/selling and the market is extremely optimistic/pessimistic. Language signals: "everyone is making money" / "this time it's different" / "the market is about to crash, should I sell everything" / "if I don't buy now it'll be too late". Not applicable to: investment decisions in normal market conditions, or purely fundamental analysis.
Review influencer/creator agreements for content rights, exclusivity, FTC compliance (16 CFR 255), AI/Synthetic Media consent, whitelisting/paid usage, and platform-specific requirements. Covers: Instagram, TikTok, YouTube. Includes AI Influencer/Virtual Influencer guidance. Triggers: (1) 'check contract' → checklist review, (2) 'advise' / 'review' → full consultation with playbook, (3) 'generate' / 'template' → Skala template URL. Jurisdiction: New York, USA.
LetsFG — Agent-native flight and hotel search and booking API. Every airline in the world plus the major booking sites (Google Flights, Skyscanner, Kiwi, Kayak, Momondo), with per-flight reliability history and instant booking. Plus real bookable hotel rates, refundable and non-refundable: the price is held on the connected card and charged only once the hotel confirms. letsfg.co
PancakeSwap V3 CLMM farming plugin. Stake V3 LP NFTs into MasterChefV3 to earn CAKE rewards, harvest CAKE, collect swap fees, and view positions across BSC, Ethereum, Base, and Arbitrum. Trigger phrases: stake LP NFT, farm CAKE, harvest CAKE rewards, collect fees, unfarm position, PancakeSwap farming, view positions.
Use when assigning Arduino, ESP32, ESP32-S3, Pico, or Pico W pins; creating a GPIO map; assigning buttons, LEDs, sensors, buses, or actuators; migrating a pin map; or generating constexpr int declarations. Check the exact board and physical pin constraints before emitting the user's ordered raw declaration format.
Comprehensive guide for PySCF - Python-based Simulations of Chemistry Framework. Use for ab initio quantum chemistry calculations including Hartree-Fock, DFT, MP2, CCSD, geometry optimization, excited states, and molecular properties. Industry-standard library for electronic structure calculations.
When the user wants to optimize seasonal planning, manage seasonal buy decisions, or plan for seasonal demand. Also use when the user mentions "seasonal planning," "seasonal buy," "holiday planning," "back-to-school," "spring/fall collection," "seasonal inventory," "peak season," or "seasonal assortment." For demand forecasting, see demand-forecasting. For retail allocation, see retail-allocation.
Routes a request to Slop or Not Pro's on-device tools: detect whether text or an image is AI-generated, clean AI artifacts out of text, and score readability with each language's native formula (Flesch-Kincaid for English). Runs locally on a Mac via the SlopOrNot MCP server or the slop CLI. Use when the user asks "is this AI", "did a bot write this", "is this image AI generated", "clean the invisible characters out of this", "what reading grade is this", or invokes /slop-check. Not for rewriting or humanizing text; that is the agentic-humanizer skill.
Search products, suppliers, and get detailed product info from Made-in-China.com via MCP server. Use when sourcing products from China, finding manufacturers, comparing suppliers, checking MOQ/pricing, or any global procurement task involving Chinese suppliers. Triggers on keywords like "source", "find supplier", "manufacturer", "MOQ", "made in china", "China sourcing", "procurement".
SupSub CLI authentication management — login / logout / check login status. Login uses OAuth browser device authorization; the CLI does not support API Key login. Matches 「supsub 登录」「supsub 登出」「查看我在 supsub 的登录状态」「我现在 supsub 用的是哪个账号」「supsub auth login / logout / status」. Before calling other supsub subcommands, if you are unsure of the credential status, run `supsub auth status` with this skill first.
Overview of Tavus, the AI research lab pioneering human computing. Use when you need context about what Tavus is, their mission, core concepts like CVI and Human Computing, the model stack (Phoenix, Raven, Sparrow), or links to docs/platform/resources.
Cast and interpret a question-time Vedic Prashna chart for one concrete question using the exact asking time and place. The Shatpanchasika-rooted classical standard layer runs first; Tajika contact and KP 1-249 remain isolated optional stacks. Use for 'Prashna', 'horary chart', 'cast a chart for this question', 'will this specific matter work out'; Chinese triggers such as '即时盘', '时盘', '卜卦', and '起一卦'; Japanese triggers such as 'プラシュナで見て', '質問時刻図を立てて', and 'ホラリーで判断して'; or follow-ups about an existing Prashna result. Not for natal life-trend analysis. / 吠陀提问盘与时盘分析引擎。
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.