Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Other
When the user wants to solve VRP with Backhauls (VRPB), optimize routes with both deliveries and pickups, or handle reverse logistics. Also use when the user mentions "VRPB," "backhaul optimization," "linehaul and backhaul," "delivery and pickup routes," "reverse logistics," or "return pickups." Backhauls are pickups that occur AFTER all deliveries on a route. For paired pickup-delivery, see pickup-delivery-problem.
The user is analyzing a stock or investment opportunity and needs to evaluate it from a "buying a business" rather than "buying a stock" perspective. Language signals: "how do this stock's technicals look" / "will the share price go up" / "what stock should I buy". Not applicable to: purely business management questions (when valuation is not involved).
Cancel an existing hotel booking. Use this skill when the user explicitly wants to cancel their reservation — phrases like "cancel my booking", "cancel reservation BK_xxx", "I don't need the hotel anymore", "refund my booking". This is a destructive action; always confirm with the user before calling, and warn if the cancellation is past the free-cancellation deadline.
Use the `catena` CLI for every Catena operation — moving money, reading accounts and balances, managing counterparties, linking an agent, or anything else involving a Catena account. Before acting, run `catena guide` for instructions unless you have already read it for the installed CLI version.
When the user wants to optimize container loading, load shipping containers efficiently, or maximize container utilization. Also use when the user mentions "container packing," "FCL optimization," "LCL consolidation," "container stuffing," "cargo optimization," "shipping container loading," or "container utilization." For pallet-level optimization, see pallet-loading. For general 3D packing, see 3d-bin-packing.
Verify customer support work against the selected customer-case flow, full-thread evidence, account and canonical-thread matching, authority, financial approval, customer communication, eligible optional Trustpilot review-request rules, post-action read-back, send confirmation, thread-wide archive, and closure requirements. Use after every SaaS support triage, account/access or unsupported-platform response, duplicate or resolved acknowledgement, positive-confirmation closure reply, cancellation, failed-payment cancellation, refund, accidental-renewal case, support handoff, draft, send, or archive task before reporting completion. Triggers on: verify support case, support closure check, cancellation verification, refund verification, accidental-renewal case, duplicate/resolved acknowledgement, account-access ticket, Trustpilot eligibility, thread read-back before marking done.
The user needs to assess a company's long-term competitiveness and pricing power — whether it can keep growing profits with very little additional capital. Language signals: "does this company have a moat" / "where is the competitive advantage" / "why can this company keep making money long term" / "how much is the brand worth". Not applicable to: purely industry analysis (when individual company competitiveness is not being assessed).
Automated email sending tool supporting SMTP and API, with a built-in Jinja2 template engine, suited to automated workflows, bulk email sending, system notifications and similar scenarios. Supports enterprise-grade features such as HTML emails, multiple attachments, template variables and error retries.
Personal fashion expert and stylist for any gender. Use this skill whenever the user wants outfit recommendations, wants to track what they own, build their style profile, get honest opinions on pieces they're considering, or generate occasion-specific outfits from their wardrobe. Also use when they want to import purchases from Zalando or Amazon (via Chrome), get shopping suggestions with links, trend advice, seasonal wardrobe updates, feedback logging, weekly outfit planning from their calendar, a fast wardrobe logging sprint, sell items on Vinted, set up Zalando price alerts, visualize their wardrobe, see their color palette, get new arrivals alerts from any brand website, or visualize an outfit as a flat-lay builder. Use for "what should I wear tomorrow?", "will this shirt work?", "what's trending?", "find me this on Zalando", "I wore X and felt great", "pre-purchase check", "build my style profile", "import my recent purchases", "plan my week", "what do I wear this week?", "log my wardrobe", "show my wardrobe", "show my color palette", "what colors work for me", "new arrivals", "watch this brand for me", "alert me for new shoes", "sell this on Vinted", "list this", "price alert", "show me this outfit", "flat lay", "visualize outfit", or "what should I add for summer?". Works in Claude Code CLI, Claude Code desktop app, and Claude Cowork.
When the user wants to investigate financial discrepancies, fraud, or hidden assets. Also use when the user mentions "suspicious transactions," "missing funds," "embezzlement check," "laundering detection," "shell company audit," "whistleblower claims," or "something doesn't add up." Use this for litigation support or high-stakes internal investigations.
KODIAK v7.0.0 — SOL alpha hunter, senpi_runtime_helpers migration. Plumbing-only flip from openclaw-CLI subprocess + mcporter subprocess to in-process SenpiClient (direct HTTPS for MCP, direct HTTP POST to runtime /signals, long-lived producer_daemon). Thesis preserved verbatim from v6.0.1: SOL alpha hunter, single-asset focus, v5.1 base-tech-score floor with multi-factor scoring (SM consensus, trend structure, momentum, funding, OI, BTC correlation, RSI), conviction-tiered leverage (5x default, 6x conviction at score 11+, 7x apex at score 13+), 240-min asset cooldown.
Analyze contract fundamentals including formation requirements (offer, acceptance, consideration), essential clauses, and common risk areas. Use this skill when the user needs to review a contract, understand contract terms, identify risky clauses, or draft contract provisions — even if they say 'review this agreement', 'what should I watch out for in this contract', or 'is this clause standard'.
Analyze macOS performance — CPU, memory, swap, processes, browsers, containers — and battery drain, then provide actionable optimization recommendations. Use when the user asks to check Mac performance, optimize their system, diagnose slowness, audit running processes, or asks why the battery drains fast.
Mall skill: recognizes shopping/buying/product-selection intent, displays the product catalog, guides the user to choose products and quantities, and after summarizing the order calls the payment skill to complete payment. TRIGGER when: the user says "买东西", "购物", "我想买", "有什么可以买", "看看商品", "买手机", "买水果", "买菜", "逛商场", "下单", "选购", etc., indicating shopping-related intent. DO NOT TRIGGER when: the user only says "支付", "付款", "打赏", etc., without any intent to select products.
Configure, simulate, debug, and analyze radarDataGenerator within radarScenario. Use for: interactively building radar detection scenarios from datasheets or performance requirements; diagnosing missed detections and configuration errors; interpreting sensor spherical, body, and scenario-frame outputs; deriving ReferenceRange from hardware specs via link budget; scan mode configuration (mechanical, electronic/AESA, hybrid); and validating simulation results against analytical predictions.
The user is considering using leverage (margin/loans/financing) to amplify investment returns, or assessing financial safety. Language signals: "should I use leverage" / "buy on margin" / "is investing with a loan worth it" / "financing rates are low, should I borrow to invest". Not applicable to: purely operational decisions not involving leverage/financing.
Fiat → crypto onramp through OpenFinance. Smart-routed across **Moonpay** (cards / Apple Pay / Google Pay / SEPA / bank — global, non-INR) and **Onramp.money** (UPI / IMPS — INR only). Default to POST /agent/onramp (smart router; `baseCurrency:"inr"` → Onramp.money, anything else → Moonpay). Use POST /agent/onramp/moonpay or /onrampmoney to force a provider. Triggers — "buy USDC with my card", "Apple Pay", "deposit fiat", "fund my wallet", "I have no crypto, how do I start", "buy ETH on Base with USD"; INR triggers — "buy USDC with INR", "deposit ₹1000", "top up with UPI / IMPS", "India onramp". The agent never signs an on-chain tx — user opens the returned URL to complete KYC + payment in the provider's UI; funds land in the user's OpenFinance-managed wallet for the chosen chain. Onramp.money has a **fixed (coin × network) matrix** (usdt:bep20|matic20|erc20|trc20, usdc:bep20|matic20 ONLY, busd:bep20, matic:matic20, bnb:bep20, eth:erc20|matic20, sol:spl); calls outside it throw — propose a supported pair instead. Pair with openfin-relay (bridge after onramp) and openfin-setup (API key).
OWL v8.0 — Pure contrarian crowding-unwind hunter (senpi_runtime_helpers). Wait for the crowd to overcommit. Wait for them to exhaust. Then eat their liquidations. Producer pushes signals to the runtime via direct HTTP POST; runtime LLM gates them (pass-through), executes via FEE_OPTIMIZED_LIMIT (maker-first), and manages DSL exits autonomously. Conviction-scaled leverage (7/8/10 by score) per the fleet Polar v2.4 / Bald Eagle v3.0 pattern. Entry direction is OPPOSITE of crowd direction — Owl is the only Senpi agent that fades crowding.
An agent-native CLI for SEC EDGAR — six sanctioned endpoints, SQLite-cached filings with FTS5, and LODESTAR-shaped... Trigger phrases: `primary sources for <ticker>`, `insider summary <ticker>`, `recheck delta for <ticker>`, `eightk items <ticker>`, `xbrl pivot`, `use edgar-pp-cli`, `run edgar`.
Rough cycle time and cost estimation for CNC machined parts. Uses MNMUK plant capabilities and standard estimating factors. USE WHEN user says 'quote', 'estimate', 'cycle time', 'how long', 'cost estimate', 'pricing', 'how much to make', or describes a part needing a rough quote.
Provides guidance on Regulation S offerings of securities under U.S. law. Helps determine eligibility for Regulation S exemption, identify applicable transaction categories (1, 2, or 3), understand safe harbor requirements under Rules 903 and 904, and navigate distribution compliance periods. Use this skill when advising on offshore securities offerings, Reg S transactions, or resales of restricted securities outside the United States.
When the user wants to optimize retail allocation, distribute inventory to stores, or perform initial merchandise allocation. Also use when the user mentions "store allocation," "assortment planning," "size curve," "cluster allocation," "pre-pack," "store grading," or "initial allocation." For ongoing replenishment, see retail-replenishment. For markdown decisions, see markdown-optimization.
Use to enable Command Center for Service V2 and configure its supported supervisor controls through the OmniChannel Settings Metadata API while preserving unrelated settings. Requires explicit consent to apply, refuses production customer orgs, and verifies the seeded V2 page and tab. Trigger when enabling Command Center V2, configuring conversation monitoring, enabling agent sneak peek or customer sneak peek, configuring whisper messaging, or enabling queues and skills actions. Do not use to assign supervisor permissions or configure classic OmniSupervisorConfig metadata
Use this skill when working with symbolic mathematics in Python. This skill should be used for symbolic computation tasks including solving equations algebraically, performing calculus operations (derivatives, integrals, limits), manipulating algebraic expressions, working with matrices symbolically, physics calculations, number theory problems, geometry computations, and generating executable code from mathematical expressions. Apply this skill when the user needs exact symbolic results rather than numerical approximations, or when working with mathematical formulas that contain variables and parameters.
Query hyper-local weather from a WeatherFlow Tempest station over its REST API and the hub's local UDP broadcast: current conditions, forecast, historical observations, and real-time decoded datagrams (obs_st, rapid_wind, evt_precip, evt_strike, hub_status). Use when the user asks about weather, temperature, rain, wind, humidity, or forecast data from their own Tempest/WeatherFlow station, or wants to parse the hub's UDP port 50222 broadcast. Do not use this skill for generic or city forecasts without a Tempest station (public weather services serve those), for Shakespeare's play The Tempest or other literature questions, or for weather hardware from other vendors - the REST endpoints require a personal-use token and the UDP broadcast only exists on a Tempest hub's LAN.
Query travel promotions from Argentina using the Anduin Promos API. Use when the user asks for travel promos in Argentina, flight, hotel or package promotions, the day's best deals, promos to Brazil/USA/Europe, rankings by score, or the latest promos from promociones-aereas.
Build a Two-Headed Giant (2HG) sealed prerelease cheat sheet for a new MTG set — what's winning (Arena Early Access stats + paper prerelease reports), team pairings, every card that doubles against two opponents, partner-hitting gotchas, rules that change in 2HG, bombs, removal, and a build-hour checklist — published as a private artifact page with card-image hovers.
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.