Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Other
When the user wants to design or optimize a supply chain network, determine facility locations, or configure distribution strategies. Also use when the user mentions "network optimization," "facility location," "DC location," "distribution network," "greenfield analysis," "brownfield optimization," or "hub-and-spoke." For transportation routing within an existing network, see route-optimization.
Integrate with Octav API for cryptocurrency portfolio tracking, transaction history, and DeFi analytics across 50+ blockchain networks. Use when building applications that need to: (1) Track wallet balances and net worth across multiple chains, (2) Query transaction history with filtering and search, (3) Monitor DeFi protocol positions (Aave, Uniswap, etc.), (4) Access historical portfolio snapshots, (5) Analyze token distribution and holdings, (6) Pay per request as an autonomous agent via x402. Triggers on: "Octav API", "crypto portfolio API", "blockchain portfolio tracking", "DeFi analytics API", "wallet balance API", "transaction history API", "multi-chain portfolio", "Octav x402".
End-to-end hotel booking with USDC wallet payment. Use when the user wants the agent to search, book, and pay for a hotel in one autonomous flow — phrases like "book me a hotel in Tokyo and pay with USDC", "find a place in Paris and pay from my wallet", "handle the whole booking for next week". Orchestrates: search → select → authenticate wallet → fund if needed → pay via x402 → confirm. Do NOT use for search-only, payment-only, or non-hotel bookings.
Comprehensive expertise in decentralized perpetual futures protocols, including GMX, dYdX, Hyperliquid, and similar platforms. Covers funding rate mechanics, liquidation engines, position management, oracle integration, and protocol risk management. Use when "perpetual futures, perps, funding rate, liquidation, GMX, dYdX, Hyperliquid, leverage trading, margin trading, long position, short position, mark price, index price, open interest, basis trading, " mentioned.
Slickdeals live RSS surface (hot deals, frontpage, search, category, coupons) plus local-snapshot transcendence (watch/digest/deals/analytics) — agent-native, MCP-compatible, SQLite-backed. Trigger phrases: `slickdeals frontpage`, `slickdeals hot deals`, `slickdeals missed deals`, `slickdeals coupons`, `slickdeals category`, `use slickdeals-pp-cli`, `run slickdeals`.
Use when the main problem is a noisy or aliased analog/ADC signal and the task needs signal-chain diagnosis or filter-path selection across sampling, anti-aliasing, RC/input conditioning, ADC source impedance/settling, latency, startup, saturation, or raw/fault observability. Apply it when software filtering and hardware signal conditioning interact, even when the request only says that an analog sensor is unstable. Hand reusable Arduino snippets to arduino-code-generator, board facts to board-support, voltage/pin/rail safety to wiring-safety-check or circuit-debugger, and calibration after detection to sensor-calibration-workbench.
Fetch announcements from A-share listed companies (real data). Based on AkShare, retrieves all announcements of the day from East Money, with filtering by stock code and keyword. Suitable for monitoring key information for investment decisions such as major events, earnings flash reports, shareholder changes and restructuring announcements. Data source: East Money (stable and reliable).
When the user is assessing the long-term value of different asset classes (currency/gold/real estate/stocks/crypto, etc.), or needs to understand the fundamental economic properties of a given asset class. Language signals: "is gold worth investing in" / "does Bitcoin have value" / "which is better, real estate or stocks" / "why does holding cash lose money" Not applicable to: pure single-stock analysis that does not require cross-asset-class comparison.
Call when the user needs to assess whether an investment, acquisition target, business opportunity, or major resource commitment is "worth it". Typical trigger signals: decisions involving "intrinsic value", "margin of safety", "moat", "pricing power", "to buy or not to buy". Not applicable to purely psychological bias analysis (use misjudgment-checklist) or economies-of-scale judgements (use scale-advantage-analysis).
When the user wants to optimize truck loading, load delivery vehicles, or plan vehicle capacity utilization. Also use when the user mentions "truck loading," "delivery vehicle optimization," "van loading," "cargo van packing," "multi-drop vehicle loading," "delivery route loading," "axle weight distribution," or "vehicle utilization." For container loading, see container-loading-optimization. For route optimization, see route-optimization.
When the user wants to solve VRP with time windows (VRPTW), optimize routes with delivery time constraints, or handle appointment scheduling. Also use when the user mentions "VRPTW," "time window routing," "scheduled deliveries," "appointment routing," "delivery windows," "earliest/latest delivery," or "hard/soft time windows." For basic VRP, see vehicle-routing-problem.
When the user needs to assess the value of an asset/investment/project, or is torn over whether something is "worth it." Applies to any asset valuation that generates (or does not generate) cash flow. Language signals: "how much is this worth" / "is this stock expensive" / "is this project worth investing in" / "should I use PE or PB for valuation." Not applicable to: purely emotional/aesthetic decisions that require no valuation analysis.
When the user wants to create a budget, forecast future performance, or perform variance analysis. Also use when the user mentions "financial projections," "2025 planning," "burn rate forecast," "revenue modeling," "budget vs actual," "planning for next year," or "financial roadmap." Use this for operational planning and strategic forecasting.
Performs arbitrary-precision arithmetic calculations including addition, subtraction, multiplication, division, and exponents. Use when the user asks to calculate, compute, or evaluate math expressions, or when precise decimal arithmetic is needed to avoid floating-point errors.
Chinese calendar query tool — retrieves comprehensive traditional calendar information for any date, including lunar calendar, Heavenly Stems and Earthly Branches (干支), solar terms (节气), festivals, auspicious/inauspicious activities (宜忌), zodiac (生肖), constellation (星座), fetal god (胎神), Peng Zu's hundred taboos (彭祖百忌), 28 mansions (星宿), Buddhist/Taoist calendar, and more. Triggered whenever the user asks about the Chinese calendar: "what's the lunar date today", "today's 宜忌", "what solar term is it", "is today auspicious", "Chinese zodiac for this year", "constellation", "今天农历几号", "今天宜做什么", "黄历", "万年历", "今天什么节气". Trigger even for casual one-line questions.
Design an employee engagement survey and analyse results. Use when asked to create an employee survey, engagement questionnaire, pulse survey, or eNPS survey. Also use when asked to analyse survey results. Produces a complete survey with questions, rating scales, and an analysis framework.
When the user is making capital allocation decisions: buybacks, dividends, acquisitions, reinvestment. The key judgment is "is this action smart or foolish at the current price". Language signals: "the company is going to buy back stock" / "should we pay dividends or reinvest" / "is this acquisition price reasonable" / "can retained earnings create value". Not applicable to: pure operating decisions that do not involve price.
When the user is considering whether to sell a position, evaluating a holding period, or struggling with "when to sell." Language signals: "when should I sell" / "how long is the right holding period" / "it's already up, should I sell" / "when should I take profit." Not applicable to: sell decisions for short-term trades or speculative positions.
Evidence-based muscle hypertrophy training, nutrition, exercise selection, periodization, recovery, supplements, and progress tracking. Use when Codex needs to build strength-training programs, set volume or RIR targets, choose exercises, troubleshoot plateaus, calculate macros/TDEE, or answer bodybuilding and muscle-growth questions.
When the user is analyzing management decisions or corporate governance issues, or finds that they or their organization are making decisions "because everyone else does it". Language signals: "why does the CEO make such stupid decisions" / "all our peers are doing it" / "why isn't the board stepping in" / "why do large companies fail at acquisitions". Not applicable to: purely personal choices that do not involve organizational decisions.
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.