Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Other
Knowledge Q&A Skill for Huawei Cloud ICP filing. Includes a built-in ICP filing knowledge base (./kb/) and works out of the box. Trigger when users mention Huawei Cloud, ICP filing, website filing, or App filing together with processes, materials, requirements, questions, rejection, authorization codes, or review. Answer only ICP filing-related questions and politely decline others.
(forwward) Interprets medical records, clinical notes, FHIR data, and advises on medical data UI with OCR interpretation, clinical summarization, and drug interaction flags. Triggers on patient records, clinical data, medical PDFs, health-tech products, or medical data presentation.
Analyze stocks and cryptocurrencies using Yahoo Finance data. Supports portfolio management (create, add, remove assets), crypto analysis (Top 20 by market cap), and periodic performance reports (daily/weekly/monthly/quarterly/yearly). Includes 8 analysis dimensions for stocks and 3 for crypto. Use for stock analysis, portfolio tracking, earnings reactions, or crypto monitoring.
Subscribe to BingX spot WebSocket account data streams, including order updates and balance changes. Also manages the Listen Key lifecycle (generate, extend, delete). Use when the user asks about real-time spot account updates, live spot order status, streaming spot balance changes, or WebSocket account subscriptions for spot trading.
Every Twilio Core feature, plus offline message and call history, FTS, and SQL-grade analytics no other Twilio tool... Trigger phrases: `send an SMS via Twilio`, `list Twilio messages`, `Twilio call recordings`, `Twilio usage cost`, `Twilio opt-out audit`, `use twilio`, `run twilio`
Auto-mirror top Discovery traders on Hyperliquid. Scans top 50 traders, scores on PnL rank (35%), win rate (25%), consistency (20%), hold time (10%), drawdown (10%). Creates 2-5 mirror strategies with overlap checks. Daily rebalance with 2-day watch period before swaps. Use when setting up trader mirroring, copy trading, or portfolio auto-rebalancing based on Discovery leaderboard performance.
Manage virtual Visa cards for AI agents with AgentCard. Fund a wallet with Apple Pay or Google Pay, create single-use or multi-use cards, check balances, view credentials, pay for things, shop and check out at merchants like DoorDash, close cards, manage plans, and get support. Use when the user wants to create or manage virtual payment cards for AI agents, fund their AgentCard wallet, pay for online purchases, shop on their behalf, set up agent spending, or configure card billing and limits.
Build a five-level rubric with coherent logic for a learning target within a developmental band. Use for Manning methodology programmes where Competent = success. For general curriculum rubrics, use criterion-referenced-rubric-generator instead.
High-level overview of DeepBook V3 on Sui — architecture, key concepts, integration models, contract addresses, supported coins, and pool information. Use when explaining DeepBook to someone new, comparing integration approaches (Move vs SDK vs read-only), looking up mainnet/testnet contract addresses, or understanding the Pool/Book/State/Vault design. For TypeScript SDK usage and trading, see the `deepbook-sdk` skill. For Move smart contract integration, see the `deepbook-move` skill.
Every Discovery v2 endpoint plus offline search, multi-venue watchlists, residency dedup, and on-sale tracking no API call exposes. Trigger phrases: `what concerts in <city> this weekend`, `what's playing at <venue>`, `where is <artist> playing`, `presale watch`, `ticketmaster events`, `use ticketmaster`, `run ticketmaster`.
HOWL v2 — Hunt, Optimize, Win, Learn. Nightly self-improvement loop for the WOLF autonomous trading strategy. Runs once per day (via cron) to review all trades from the last 24 hours, compute win rates, analyze signal quality correlation, evaluate DSL tier performance, identify missed opportunities, and produce concrete improvement suggestions for the wolf-strategy skill. v2 adds fee drag ratio (FDR) analysis, holding period bucketing, LONG vs SHORT regime detection, rotation cost tracking, cumulative drift detection, and gross vs net profit factor separation. Use when setting up daily trade review automation, analyzing trading performance, or improving an autonomous trading strategy through data-driven feedback loops. Requires Senpi MCP connection, mcporter CLI, and OpenClaw cron system
Read-only public market data for Bithumb: prices, ticker, order book, candles (minute/day/week/month), recent trades, market list, virtual asset warnings, notices, and fees. No API credentials required. Do NOT use for wallet/blockchain status or deposit-withdrawal availability — use bithumb-account. 빗썸 시세·호가·캔들·체결 내역·마켓 목록·유의 종목·경보제·공지사항·수수료 등 공개 시장 데이터를 조회합니다. 인증 불필요. 빗썸 시세·차트·호가·체결 내역·유의 종목·경보제 관련 요청에 사용하세요. 입출금 현황·블록 갱신시각·블록 동기화·입출금 가능 여부는 bithumb-account를 사용하세요.
Generates a Bill of Materials (BOM) from project descriptions for Arduino/ESP32/RP2040 projects. Use when the user needs component lists, parts shopping lists, cost estimates, or asks “what parts do I need”. Outputs formatted BOMs with part numbers, quantities, suppliers (DigiKey, Mouser, Amazon, AliExpress), and compatibility warnings. Run scripts/generate_bom.py for xlsx/csv export.
Simulates a senior high school Chinese language tutor, helping with modern text reading, classical poetry and prose appreciation, classical Chinese translation, essay writing, and other Chinese language questions. Emphasizes language intuition, textual interpretation, and writing skills. Use when students ask Chinese language questions, request passage analysis, ask for explanations of classical poetry, or request essay edits
A structured preliminary analysis tool for Chinese invention and utility model patents. Use this skill when users need to break down or explain claims, compare patent scope, conduct product infringement comparisons, equivalents analysis, validity and invalidation risk analysis, FTO, design-around analysis, patent valuation, or create patent analysis charts. Do not use it to replace formal opinions from patent attorneys or patent agents, merely download/OCR patents, draft patent application documents, or reach definitive conclusions without confirming the jurisdiction and valid claims. Design similarity assessments require a separate specialized method and manual review.
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.
