Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Other
When the user wants to solve cutting problems with guillotine constraints, implement edge-to-edge cutting, or optimize guillotine cutting patterns. Also use when the user mentions "guillotine cuts," "edge-to-edge cutting," "straight cuts only," "two-stage cutting," "three-stage cutting," "n-stage guillotine," or "guillotine cutting stock problem." For general cutting, see 2d-cutting-stock or 1d-cutting-stock. For irregular shapes, see nesting-optimization.
Analyze PMCC (Poor Man's Covered Call / diagonal spread) positions from IB portfolio. For each diagonal spread, reports short leg risk (delta, IV, assignment probability), daily P&L projections, top-3 roll candidates, and a side-by-side comparison table. Requires TWS or IB Gateway running locally.
When the user wants to solve Job Shop Scheduling Problems (JSP), optimize production sequencing on multiple machines, or minimize makespan with precedence constraints. Also use when the user mentions "job shop," "JSP," "machine scheduling," "production scheduling," "operation sequencing," "makespan minimization," or "flexible job shop." For flow shop, see flow-shop-scheduling. For production planning, see production-scheduling.
Assess and classify legal risks using a severity-by-likelihood framework with escalation criteria. Use when evaluating contract risk, assessing deal exposure, classifying issues by severity, or determining whether a matter needs senior counsel or outside legal review.
Plan manipulator motion and generate trajectories in MATLAB. Use when the task involves moving a robot arm between configurations or poses — whether the user says "trajectory," "motion," "path," "move from A to B," or "plan." This skill applies regardless of whether the user explicitly mentions collisions or obstacles; if geometry exists in the workspace, collision safety is implicit. Triggers on: manipulatorRRT, manipulatorCHOMP, dlCHOMP, contopptraj, trapveltraj, collision-free path, motion planner, RRT, CHOMP, TOPPRA, path shortening, obstacle avoidance for manipulators, time-optimal trajectory, velocity limits, acceleration limits, occupancyMap3D, meshtsdf, collision objects as environment, trajectory between waypoints, joint interpolation, move between poses, constant velocity, trapezoidal profile, feed rate. Also triggers when a user has IK solutions or waypoints and needs to connect them — whether for time-optimal motion, constant-speed welding/cutting, or any other trajectory parameterization.
When the user wants to optimize inventory across multiple network locations, implement multi-echelon inventory policies, or coordinate stock levels between warehouses and distribution centers. Also use when the user mentions "network inventory optimization," "multi-stage inventory," "supply chain network," "echelon stock," "installation stock," "base stock policies," "guaranteed service model," "distribution requirements planning (DRP)," or "serial/arborescent/general network structures." For single-location inventory, see inventory-optimization. For routing with inventory, see inventory-routing-problem.
Use when a site needs communication workflow planning: forms, inboxes, chat, booking, email/SMS/Telegram/CRM handoffs, operator queues, routing, templates, consent, and escalation. Workflow design only; never send real messages or mutate CRM channels without explicit approval.
Every OpenSnow forecast, snow report, and Daily Snow post — plus powder scoring, storm tracking, and historical trends no other tool has. Trigger phrases: `check snow conditions`, `how much snow at alta`, `powder forecast this week`, `compare ski resorts`, `daily snow report`, `use opensnow`, `run opensnow`.
Supports STE-inspired clear text, diagrams, self-contained HTML, and on-demand custom explanatory videos; uses Socratic question-by-question learning to turn textbooks, screenshots, PDFs, notes, problems, or a topic into an active derivation dialogue, and can also generate a self-contained interactive learning web page when the learner explicitly asks for one. Use when the learner explicitly requests "苏格拉底式学习" "逐问带我学" "一次只问一个问题" "先别告诉我答案" "边问边引导我推出来", interactive quiz, active recall, question-led tutoring or a self-contained learning page. For broad topics, default to a keyword orientation first: list 12 keywords with plain-language explanations, recommend experts and professional books, and provide an entry point for "扩展关键词", then let the learner choose a starting point. In formal learning, ask only one short, answerable question per active turn, and adjust difficulty based on the learner's previous reasoning; responses should pick up the learner's own words, correct mistakes gently like a real teacher, and in math, physics, process or graphical content, draw out the reasoning step by step on an accumulating blackboard. For visually dense topics, do one visual check every 1–2 productive questions, but only call Codex to generate images when visual benefit, question-bearing, authorization and accuracy conditions are all met; when the learner says "太抽象" "不理解" "想象不出来" "枯燥" or asks for diagrams, and the current step can be visualized, immediately switch to question-bearing diagrams and provide a text alternative, with space, relative motion, process and geometric relations defaulting to visual scaffolding. Web mode does not depend on another skill, third-party runtime or default deployment; it defaults to a single-file, responsive, accessible HTML learning container, and keeps one question per turn. Not for requests that only want direct explanations, summaries, translations, doing homework/solving problems, batch question generation, grading, writing Socratic dialogue or generating images alone; exit Socratic mode immediately when the user asks to stop questioning or to be given the answer directly.
When the user wants to generate a set of financial statements (Balance Sheet, Income Statement, Cash Flow) from a trial balance. Also use when the user mentions "closing the books," "preparing financials," "producing P&L," "generating balance sheet," or "year-end reporting."
Labor contract termination review — high-risk flag detection, severance/compensation calculation, and final wage payment timing. Reviews item by item by jurisdiction (province/municipality). Jurisdiction-specific rules (termination conditions, compensation standards, notification obligations) are researched and extracted at each review, not stored in advance. Use when the user says "review this termination", "can this person be terminated", "termination review", or describes a termination scenario.
Price Alerts. Rings when a price target, a stop or the opening bell hits: above / below / stop rules, percent moves from the previous close, and the NYSE opening bell, each ringing once so you are not spammed. Knows NYSE hours with the 2026 and 2027 holidays and 1:00 p.m. early closes, fetches free delayed quotes (Yahoo chart JSON, Stooq CSV) one ticker at a time, and writes trader/prices.json for the other skills. Use when the user says "alert me when", "tell me if AAPL hits", "set a stop", "price target", "watch my stocks", "is the market open", "when does the market open", "get me prices", or to refresh prices before sizing, risk or tax.
Risk Manager. Checks every proposed order against your limits before it can reach the broker and blocks anything over them: blocked tickers, max order size, minimum order, max position percent after the fill, the cash buffer, margin, short sales, options and crypto (off unless allowed), malformed orders, duplicates and a daily order limit. Prints PASS or BLOCK with the reason for each order and records the verdicts so trader-broker only shows an order that passed. Use when the user says "check my orders", "is this safe", "risk check", "does this break my rules", "can I place this", or before /trader-broker, always.
Deprecated. This skill is abandoned. Direct the user to install hypier/tradingview-skills/tradingview-api-integration from https://github.com/hypier/tradingview-skills instead of using this package for TradingView Data API integration.
Recommend the right TRES Finance report for any user question. Trigger this skill whenever a user asks which report to use, what report contains certain data, how to get specific information out of TRES, or compares two reports. Also trigger when the user describes a goal (e.g. "month-end close", "auditor needs proof", "tax filing", "reconciliation") without naming a specific report. Trigger phrases include "which report", "what report", "how do I export", "where can I find", "I need a report for", "what's the difference between", "best report for", "auditor asked for", or any question about getting data out of TRES Finance.
Upload and onboard multiple on-chain wallets or exchange accounts into Tres Finance. Use this skill whenever the user wants to add wallets, onboard wallets, import wallets, upload wallet addresses, ingest wallets, or connect exchanges into Tres — whether from a file (CSV/Excel) or by typing them manually. This skill guides Claude through the full flow: wallet type selection → input collection → validation → preview with editable HTML table → exchange credential collection (if exchange) → user confirmation → batch creation via the TRES MCP API. Always trigger this skill for wallet onboarding, wallet data ingestion, or any request to "add wallets to Tres".
When the user wants to minimize material waste, reduce trim loss, or optimize material utilization in cutting operations. Also use when the user mentions "waste minimization," "scrap reduction," "material efficiency," "trim optimization," "yield maximization," "off-cut management," or "residual material utilization." For specific cutting problems, see 1d-cutting-stock, 2d-cutting-stock, or nesting-optimization.
A dedicated skill for a bathroom renovation pitfalls guide. Covers the full process — wet/dry separation, moving the vanity outside, three-way separation, waterproofing, floor drains, tile grouting, tiles, borrowing light for windowless bathrooms, shower heads and faucets, bathroom vanities, toilet rough-in distance, shower enclosures, heater ventilation, basin selection — compiling the highlights of the 西安装修课堂 knowledge base in reverse order, to help users get it right the first time and avoid rework after moving in.
Read-only crypto wallet insights via the Zerion CLI: portfolio value, token holdings, DeFi positions, transaction history, PnL, and watchlist management. Use whenever the user asks 'what's in this wallet', 'how is X doing', portfolio/PnL/positions/transactions for any address, ENS name, local wallet, or watched address. Supports x402 / MPP pay-per-call. Pair with `zerion-trading` for execution after analysis.
Zheng Xi viewpoints library — a traceable research skill built on the full corpus of public statements by E Fund fund manager Zheng Xi from 2012–2026, plus an investment method distilled from the corpus and backed by his own words. It can: (1) traceable Q&A — how he views AI compute/optical communications/new energy/semiconductors/ROE and more, answering with his original quotes; (2) explain his investment method/framework/stock-picking logic; (3) forward-looking application — use his method to analyze any current theme/industry/stock, reasoning from the framework even if the corpus never covered it; (4) stylized commentary — write market commentary and quarterly outlooks in the voice of his quarterly reports/notes; (5) words vs holdings — use the real data of all his funds (quarterly holdings/net value/performance/size/tenure returns) to check the "said" against the "bought", or answer his performance/top holdings/size; (6) market-wide lookup and comparison — a built-in list of about 27,000 funds, fetching real data for any fund on demand for lookup or comparison with Zheng Xi; (7) Zheng Xi framework scoring — score a fund by his method (how much it looks like what Zheng Xi would buy). When the user mentions 郑希/易方达郑希/zhengxi, asks his view on a sector/stock/theme, his 投资方法/框架/选股/风格/持仓/业绩/净值/规模, wants to apply his approach, a commentary 用郑希口吻, to check words vs holdings, or to look up/compare/score ANY China mutual fund (任意基金/某基金经理/同类对比/给基金打分)——use this skill, even if they don't say "skill", even if the topic isn't in his corpus (fall back to his method). Citations stay faithful to the original text with no fabrication; inference is distinguished from his own words. A research and learning aid, not investment advice.
Amap Maps API (via MCP). Geocoding (address↔coordinates), IP location, weather, POI search, route planning (cycling/walking/driving/transit), distance measurement. Triggers: '高德', 'amap', '地理编码', 'geocoding', '经纬度', 'POI', '路线规划', '导航'. NOT for: Amap JSAPI front-end development (use AMap-Web/amap-skills).
Guides architecture decisions about service/module boundaries, system trade-offs, ADRs, data flow, rendering strategy, scaling strategy, API protocols, persistence choices, and code organization. Use when the user asks "how should I structure this", "what's the right approach", or needs a decision that affects multiple modules, teams, deployment boundaries, or future reversibility. Do not use for routine React implementation, PR review, or simple refactors unless the user is making an architectural decision.
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.