Skills
96,981 packaged capabilities and playbooks for agents. Install any of them with one command.
Other
Use this skill when viewing or transferring NFTs on the TON blockchain. It lists collectibles, checks NFT details, and sends NFTs to other addresses. Also use when the user mentions collectibles, digital assets, NFT collections, or wants to send an NFT to someone on TON.
Guide a seller through getting ungated in a restricted Amazon category or brand. Identifies what is gated, what documents Amazon wants, how to source a compliant invoice, and how to submit an approval request that passes the first time. Use when a user asks about ungating, restricted categories, getting approved to sell a category or brand, gated products, or an approval request that was denied. Trigger phrases: "ungating", "restricted category", "get approved to sell", "gated", "category approval", "brand approval", "invoice for ungating". Works with zero tools.
Responds to an Amazon IP complaint correctly. The fastest path is a polite retraction request to the rights owner, not a generic appeal. Saves 7-21 days of lost sales by skipping the wrong-template trap. Use when a user gets an IP complaint, listing suppression, or trademark/copyright/patent/counterfeit notice. Trigger phrases: \"IP complaint Amazon\"、\"listing taken down trademark\"、\"rights owner retraction\"、\"[email protected]\". Works with zero tools.
Diagnose why an Amazon product gets returned and build a plan to cut the return rate. Clusters returns into five named root causes, quantifies the dollar bleed per return including the Returns Processing Fee where it applies, and fixes each cause at the listing, the product, or the packaging. Use when a user asks about reducing returns, a high return rate, why customers return a product, return reasons, the Returns Processing Fee, or refunds eating profit. Trigger phrases: "reduce returns", "return rate", "why are customers returning", "return reasons", "too many refunds", "cut returns", "Returns Processing Fee", "returns eating margin". Works with zero tools. The user pastes return reasons and reviews.
Plan Amazon wholesale sourcing: finding suppliers and brands to resell, opening wholesale accounts, negotiating terms and minimum order quantities, and checking that a wholesale deal is actually profitable and not gated. Use when a user asks about wholesale sourcing, finding suppliers, reselling brands, opening wholesale accounts, negotiating with distributors, or evaluating a wholesale product. Trigger phrases: "wholesale", "wholesale sourcing", "find suppliers", "resell brands", "distributor", "wholesale account", "MOQ negotiation". Works with zero tools.
Join the Degenerate Claw perpetuals trading competition for ACP agents. Use this skill when asked to trade perps on Hyperliquid, join the leaderboard, post trading signals, or interact with the Degenerate Claw platform. Registration is a join_leaderboard ACP job via dgclaw.sh; trading itself (deposit, perp orders, withdrawals, status) uses the ACP CLI's built-in `acp trade` command, which trades directly on Hyperliquid. Forum and leaderboard run through dgclaw.sh. Forums are open to the public. Requires the acp-cli to be set up first.
Use this skill whenever the user wants Gate Exchange asset allocation optimization for spot holdings (list eligible assets, load config, evaluate/preview, place orders, query history). Trigger phrases include "asset allocation optimization", "allocation configuration", "portfolio allocation", "rebalance spot to stablecoin", "Top 5 market cap allocation", "optimize holdings to BTC", "preview allocation optimization", "allocation optimization order list".
Use for any credits work in Stigg — defining a credit currency (also called "credit type"), the full lifecycle (create / update / archive / list / inspect associations), granting recurring / prepaid / promotional credits, configuring consumption mappings or custom formulas per plan, auto-recharge, ledger inspection, overdraft, billing integration for paid credits, or driving credit-based monetization end-to-end. Triggers include "monetize with credits", "AI tokens", "API credits", "compute units", "credit grants", "credit pool", "credit balance low", "auto-recharge", "credit ledger", "consumption mapping", "custom credit formula", "seat-based credits", "OpenAI-style pricing", "create credit currency", "credit type", "tokens consumed", "deduct credits", "prepaid credits". Skip for static catalog modeling of non-credit features (stigg-pricing-modeling), runtime gating of non-credit features (stigg-entitlements), or subscription lifecycle (stigg-subscriptions).
Molecular cloning, in both directions. DESIGN — Gibson Assembly (overlap design for seamless multi-fragment joining) and Golden Gate Assembly (Type IIS / BsaI / BbsI / Esp3I / BsmBI / SapI design with unique 4-bp fusion overhangs). ANALYSIS — work out what an existing reaction produces: given input plasmid sequences and an enzyme, digest them, join the fragments by their overhangs, and identify features of the product (expressed ORF, gRNA spacer and its target gene). Use when you need to plan how to join DNA fragments into a construct, design assembly overlaps/overhangs, decide between cloning methods, or determine the product of a stated Gibson/Golden Gate reaction. Covers the domestication (internal-site removal), overhang-uniqueness, and overlap-Tm rules. For PCR primers to generate the fragments, see tooluniverse-primer-design.
Find the real protein target(s) of a peptide from its sequence — peptide target deorphanization / off-target identification, for ANY target class (GPCR, ion channel, protease, cytokine/growth-factor receptor, enzyme, integrin), not only GPCRs. Use when a peptide has a phenotype but does not bind its hypothesized target, when a peptide binds a target in one species or assay but not another, or to screen candidate targets for an orphan peptide. A target-class router steers a multi-route keyless pipeline (PROSITE/ELM motif, BLAST homology, HGNC/InterPro/GPCRdb/GtoPdb target-family enumeration, OpenTargets phenotype anchor, EnsemblCompara/Alliance cross-species reconciliation) plus optional NVIDIA-NIM co-folding (Boltz2, AlphaFold2-Multimer, OpenFold3) for structural confirmation.
Analyze Taiwan-listed stocks using fundamental analysis including EPS, P/E ratio, dividend yield, and financial statement review. Use this skill when the user needs to evaluate a Taiwan stock, compare TWSE/TPEx-listed companies, assess valuation, or review earnings — even if they say 'should I buy this stock', 'analyze 台積電', 'is this stock overvalued', or 'compare these two Taiwan companies'.
Screen and filter A-share stocks based on fundamental metrics, technical indicators, capital flow, and custom criteria. Support multiple screening strategies including value investing, growth investing, momentum trading, and dividend hunting. Use when user wants to find stocks meeting specific criteria like "低PE高ROE股票", "北向资金加仓股", "突破年线的股票".
Gate CandyDrop activity operations guide. Use this skill whenever users want to browse CandyDrop activities, view activity rules, register for activities, check task completion progress, or query participation and airdrop records. Trigger phrases include: candydrop, candydrop activities, activity list, register for candydrop, task progress, participation records, airdrop records.
Draft, analyse, score, and improve IELTS Academic or General Training Writing Task 2 essays (250-word minimum). Use this skill when the user shares a Task 2 prompt, wants a model essay, needs band-score feedback on their own essay, or asks about essay structure, argument development, thesis writing, or common Task 2 mistakes. Covers all Task 2 types: opinion/agree-disagree, discuss-both-views, advantages-disadvantages, problem-solution, two-part questions. Also use when the user asks about Task 2 vocabulary, paraphrasing, or how to avoid common errors. Task 2 carries more weight than Task 1 in the overall Writing band score.
Advise startup founders on choosing the best jurisdiction and legal entity for their business. Triggers when users ask about where to incorporate, which state/country to register a company, choosing between Delaware vs other states, offshore vs US incorporation, entity types (C-Corp, LLC, PBC), or jurisdiction selection for specific industries (crypto, AI, SaaS, GameDev, solopreneurs). Also triggers for questions about startup formation, company registration, or corporate structure decisions.
Send transactional emails and SMS via SMTP2GO API. Covers authentication, /email/send and /email/mime endpoints, template management, attachments (base64/URL), webhooks for delivery events, statistics, and suppressions. Use when sending emails from Cloudflare Workers, building notifications, tracking delivery status, handling bounces. Prevents auth errors, attachment encoding issues.
Place bets on Polymarket prediction markets using the Polygon Agent CLI (CLOB V2). Browse markets, check prices, buy YES/NO positions, sell positions, manage orders. Collateral is pUSD (auto-wrapped from USDC.e). All commands are JSON output. Dry-run by default — always add --broadcast to execute.
IMPLEMENTATION skill — use when the user is **building** a Stigg product catalog (model is already chosen). Covers features (boolean / metered / configuration), plans (free / paid / custom), add-ons, products, charges (flat / per-unit / pay-as-you-go / in-advance commitment / minimum spend / credits), overages, coupons, custom credit currencies, price localization. Triggers include "create a plan", "add an add-on", "define a feature", "model my pricing in Stigg", "set up usage-based pricing", "configure overages", "publish a plan", "publish a draft", "edit a published plan", "add a charge", "create a coupon", "set up price localization", or any Stigg catalog mutation. MCP-first — catalog work runs through the Stigg MCP, not by hand-writing REST. Skip when the user is still **picking** the model — that's stigg-pricing-expert. Skip for runtime entitlement checks (stigg-entitlements) and subscription lifecycle (stigg-subscriptions).
Import, extract, normalize, and validate Vedic/Jyotish chart data from PDFs, screenshots, text, or common astrology software exports; route birth details to vedic-calculator when no chart file exists. Use for 'read my Vedic chart', 'import this JHora chart', 'extract chart data', 'analyze this Jyotish chart', any supplied chart PDF/image; Chinese triggers such as '读盘', '读取星盘', '看盘', and '排盘'; or Japanese triggers such as '出生図を読んで', 'チャートを読み込んで', and 'このホロスコープを検証して'. / 吠陀占星读盘与数据校验引擎。
Open and manage brokerage accounts via the Alpaca Broker API — account creation, KYC/CIP, identity & disclosures, agreements, document upload (incl. W-8BEN), account status lifecycle, and account updates/closure. Use when a developer is building onboarding, KYC, or account-management flows on Alpaca in any language.
Navigate privacy regulations (GDPR, CCPA), review DPAs, and handle data subject requests. Use when reviewing data processing agreements, responding to data subject access or deletion requests, assessing cross-border data transfer requirements, or evaluating privacy compliance.
Trigger this skill when evidence materials in a case need evaluation of authenticity, legality, relevance (the "three attributes" of evidence), and probative force. Typical trigger scenarios include but are not limited to: - After a party or representative submits evidence, it is necessary to determine whether that evidence can be admitted by the court - The opposing party raises objections to one's own evidence, requiring response and analysis - The full body of evidence in a case needs comprehensive assessment to determine whether the facts to be proven hold - It is necessary to determine whether the evidence meets the corresponding standard of proof (such as high probability, beyond reasonable doubt, etc.) - Weak links in the chain of evidence need to be identified and suggestions for strengthening them proposed - Determination of the validity of special forms of evidence such as electronic data, expert opinions, and witness testimony - Identification and argumentation of the exclusion of illegally obtained evidence
Interact with pump.fun bonding curves on Solana: buy tokens, sell tokens, and check prices/bonding progress. Trigger phrases: buy pump.fun token, sell pump.fun token, check pump.fun price, pump.fun bonding curve. Chinese: 购买pump.fun代币, 出售pump.fun代币, 查询pump.fun价格
Use FIRST for any task involving Stigg — this umbrella must load before any other stigg-* skill (stigg-mcp, stigg-credits, stigg-governance, stigg-pricing-modeling, stigg-entitlements, stigg-subscriptions, stigg-widgets, stigg-webhooks, stigg-api, stigg-pricing-expert, stigg-recipes, stigg-sp). It carries routing, the search-first rule, account/key prerequisites, and core vocabulary the pillars depend on. Even when a specific stigg-* skill looks like a perfect match (rendering a paywall, granting credits, debugging a 401, wiring a webhook, building freemium) — load this one alongside it. Trigger on the word "Stigg", any stigg.io URL, `@stigg/*` imports, Stigg API keys (server-/client-/publishable), the Stigg CLI or MCP, or work on plans/features/addons/entitlements/credits/subscriptions/usage/paywalls/customer portal/checkout/webhooks where Stigg is the platform. Skip only when Stigg isn't the platform (pure Stripe, Chargebee, or generic pricing UI).
Use when operating subscriptions in Stigg — provision a customer onto a plan, preview a subscription's pricing, update an active subscription (plan, add-ons, period, quantities, coupons, spend limits), cancel, run free trials and convert them to paid, support multiple subscriptions per customer (workspaces / projects), or migrate an existing subscription to the latest published plan version. Triggers include "provisionSubscription", "preview a subscription", "upgrade", "downgrade", "cancel subscription", "schedule cancellation", "trial expired", "migrate subscription to latest version".
Move cash (JNLC) and securities (JNLS) BETWEEN accounts inside your own Alpaca omnibus via the Broker API — single, batch, and reverse-batch journals, the Idempotency-Key header, journal status lifecycle including corrections, and the firm/sweep-account pattern that powers instant funding and share rewards. Use for internal account-to-account movement in any language. For deposits/withdrawals to EXTERNAL banks, use funding-transfers instead.
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.