Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Other
Use when wiring an Arduino, ESP32, ESP32-S3, Pico, or Pico W to sensors, LEDs, motors, relays, buses, or external supplies, especially when 5 V and 3.3 V logic, current limits, pull-ups, level shifting, inductive loads, or safe defaults matter.
Use when an Agent controls Xiaomi Home devices through xgg cloud or authors and debugs Central Hub Geek Edition rules, including offline dynamic lighting formulas, Mi Home QR authorization, automatic gateway login, cloud/local verification, household habit learning, all 25 cards plus nop, event/state semantics, variables, logs, and backups
When the user wants to pack 3D boxes into containers, plan how many containers to book, optimize 3D space utilization, or solve container loading problems, including loads where each purchase order, customer, or stop must stay together in one container. Also use when the user mentions "3D packing," "container packing," "load plan," "keep the PO whole," "box packing," "3D bin packing problem," "cube packing," "three-dimensional packing," "cargo loading," or "space optimization." For pallet-specific loading, see pallet-loading. For container logistics, see container-loading-optimization.
AI-powered stock and crypto analysis using the aipa CLI. Use this skill whenever the user asks to analyze a ticker, compare stocks, get technical analysis, or answer any financial market question about Vietnamese stocks (VIC, VCB, FPT...), cryptocurrencies (BTC, ETH...), or global assets. Also use for price action analysis, moving average analysis, support/resistance questions, sector comparison, Wyckoff analysis, or trading insights. Also handles fundamental analysis when the user explicitly asks for fundamentals, PE, ROE, NPL, CAR, valuation, or "phân tích cơ bản" — use `aipa fundamentals` commands to enrich technical analysis with financial ratios, company info, and fundamental screening/ranking. For raw price data without AI, use the aipa-data skill instead.
When the user wants to perform an internal audit, review controls, or prepare for an external financial audit. Also use when the user mentions "internal controls," "compliance check," "preparing for audit," "Sox compliance," "audit readiness," "checking for gaps," or "inventory audit." Use this for both operational and financial audits.
Resolve a named Arduino, ESP32, RP2040, or other embedded board to a source-backed exact profile, including pin/peripheral capability, voltage/current, buses, framework/core/toolchain, and variant or revision risks. Use this whenever a user asks for a board reference, pinout, GPIO restrictions, board capability, board profile, or safe handoff before pin assignment. Do not use it to choose a board from requirements; use board-selection for that decision.
When the user is making long-term investment, savings, or growth decisions and needs to understand the power of time and compounding, or is troubled by short-term fluctuations. Language signals: "how long should I hold", "what happens in ten years at X% annualized", "why is long-term holding better than frequent trading", "how do small gains become great wealth". Not applicable to: short-term trading decisions or analyses that do not need a time dimension.
When the user wants to balance demand and supply, resolve supply-demand mismatches, or optimize fulfillment allocation. Also use when the user mentions "demand-supply balancing," "ATP," "available-to-promise," "allocation," "supply rationing," "fulfillment optimization," "demand prioritization," or "supply allocation." For forecasting, see demand-forecasting. For S&OP, see sales-operations-planning.
When the user wants to optimize Direct Store Delivery (DSD) routes, plan delivery schedules for retail stores, or improve route efficiency for CPG distribution. Also use when the user mentions "DSD routing," "store delivery optimization," "retail route planning," "delivery windows," "merchandising routes," or "field sales routing." For general vehicle routing, see vehicle-routing-problem. For last-mile delivery, see last-mile-delivery.
Use when the user asks about Liuyao divination, Liuyao chart casting, Wenwang Najia, Jing Fang's Eight Palaces, three-coin casting, or manual entry of six line values, or asks Liuyao questions about career, relationships, wealth, or studies; English terms Liuyao, Six Lines Divination, Wenwang Najia, and I Ching coin casting should also trigger it. It performs deterministic chart casting, domain method loading, a complete integrated reading in the current conversation, a full HTML report containing the chart and reading, a standard share image, and fact consistency checks; for high-risk issues such as medical matters, life and death, fetal sex, or missing-person location, it provides only realistic help.
Stock analysis and price movement prediction. Triggered when the user expresses intent to analyze, judge, or predict, such as "analyze Tencent", "how has 0700 been trending lately", "should I buy XX", "predict the trend going forward", "generate an analysis report", etc. Supports Hong Kong stocks, A-shares, and US stocks, integrating multi-source data (including news, fundamentals, technicals, capital flows, and macro information) for multi-dimensional comprehensive analysis, and outputs structured analysis reports combining text and images with visual charts. For simple lookup requests (such as "what is Tencent's current price" or "what is Moutai's ticker"), this skill is not triggered; use the web_search capability to search and summarize directly. ⚠️ Requires support from a multimodal main model (such as glm-5v-turbo); the main model must be able to read images.
Deep-dive English word mastery tool. Deconstructs a single English word into core semantics and epiphany. Use when user asks to explain/master a specific English word. Do NOT use for Chinese concepts or multi-word ideas (use ljg-explain-concept).
The user is about to make a major decision (investment/acquisition/commitment) and needs to assess whether downside protection is sufficient, or is deciding whether to act when valuation is uncertain. Language signals: "is this price low enough" / "what if I'm wrong" / "how much loss can I bear" / "how much downside is there". Not applicable to: everyday low-risk decisions, or purely upside analysis (when downside protection is not a concern).
Terminal client for meatproxy.me. Run the official Meat Scan inside the agent, refer someone as a meat proxy and get their case-file link, claim a Certified Thinker certificate, generate badges and share links, and read live stats. Triggers on "meat proxy", "meat scan", "refer X as a meat proxy", "am I a meat proxy", "certified thinker", "meatproxy.me link", or "meat proxy badge".
Payment Skill — recognises user payment/checkout intent, or receives calls from other skills (such as the tip skill), runs scripts/payment_api.js to call the payment QR code API, obtains the tradeCode and prominently displays it to the user. TRIGGER when: the user says "我要支付", "我要付款", "去支付", "帮我支付", "结账", "付钱", "买单", or is called by another skill carrying an amount parameter. DO NOT TRIGGER when: the user expresses tipping/gifting/appreciation intent (handled by the tip skill).
Polymarket prediction markets at your fingertips - check odds, track portfolios, research markets with AI-powered analysis, compare markets, and trade. Covers all 4 Polymarket APIs: Gamma, CLOB, Data API, RTDS WebSocket, and Bridge. Read-only works instantly (no setup). The most comprehensive prediction markets skill on ClawHub.
When the user wants to optimize manufacturing processes, improve throughput, reduce cycle times, or simulate process performance. Also use when the user mentions "process improvement," "bottleneck analysis," "simulation," "discrete-event simulation," "throughput optimization," "cycle time reduction," "process efficiency," "queuing theory," "process mapping," or "capacity analysis." For lean methods, see lean-manufacturing. For scheduling, see production-scheduling.
Find the angriest or funniest prompt the user has sent to local AI agents using this skill's bundled scripts and the active LLM; collect Claude, Codex, Cursor, Gemini CLI, OpenCode, Aider, Windsurf, Trae, Continue, Cline/Roo, and Copilot-style local history, judge it in this chat, then upload the winning prompt plus leaderboard metadata to rageprompt.com without relying on npm or npx.
When the user wants to plan renewable energy supply chains, optimize wind or solar logistics, or manage clean energy operations. Also use when the user mentions "solar logistics," "wind farm operations," "renewable energy supply chain," "green energy planning," "battery storage," "solar panel distribution," "wind turbine logistics," or "clean energy optimization." For power grids, see power-grid-optimization. For energy storage, see energy-storage-optimization.
Unified swap + bridge router combining WOOFi (best-price meta-aggregator on 14 EVM chains) and the LayerZero Value Transfer API (broad multi-chain bridging incl. Solana, Aptos, TON — discover supported chains/tokens dynamically). One workflow: classify the request, validate the wallet can actually execute, quote, compare complete routes, approve-then-requote-then-execute, and verify destination receipt.
Billing and payment operations for Stripe: customers, products, prices, invoices, payment links, subscriptions, refunds, disputes, balance. Triggers: create customer, create product, create invoice, generate payment link, query transactions, process refunds, manage subscriptions, view disputes, check balance. Money operations require confirmation. MCP is optional — works with Dashboard/CLI too.
Comprehensive structural systems knowledge for architects covering structural typology selection, grid design and spacing, lateral stability systems, foundation types, span-to-depth ratio tables, load path narratives, and architect-engineer coordination strategies. Provides decision frameworks for selecting structural systems based on span, height, program, cost, construction speed, and sustainability targets.
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.