Skills
96,770 packaged capabilities and playbooks for agents. Install any of them with one command.
Other
Turn a token name into a vetted, sized buy order. Two things here are exclusive to this skill: resolving a NAME or symbol to the one right contract among its copycats, and sizing an order — amount, slippage, gas, position. No sibling does either. USE THIS SKILL WHEN a buy is being prepared, which shows up as a NAME or symbol, or an AMOUNT, or both — including the plainest possible ask with no mention of checking: 我想买 200u 的 PENGU, 帮我买 500 刀的 BONK, 买 1 个 SOL 的 WIF, 帮我买点 dogwifhat, 想梭 100u 的 XX, PENGU 现在能买吗, PENGU 能不能买, 能不能冲, 值不值得进, 确认是正主不是仿盘再买, buy me $500 of PENGU — and including a bare contract address once an amount arrives with it. DO NOT USE THIS SKILL for a bare contract address with no name to resolve and no amount to size (「这个地址能不能买」, 打个分, 尽调, 有没有貔貅, rug check, is this token safe): that one belongs to gmgn-contract-dd, which is the skill that returns the 0-100 safety verdict. This skill never computes a second verdict of its own — it CALLS gmgn-contract-dd and defers to it — so there is nothing to gain by taking that ask, and the user gets an order card they never asked for. Come back here the moment they name an amount. A buy question about a LAUNCHER rather than about a token — 「这个 dev 的新盘能不能买」, 「他下一个盘值不值得冲」, "should I buy his next launch", "will this dev rug at open" — is gmgn-dev-score: it scores the creator's own record, and there is no token name to resolve or amount to size yet. Come back here once they name the coin. Naming a token with no buy intent at all is gmgn-market search. gmgn-swap is where this skill ENDS, not a rival for it: gmgn-swap signs and submits, and this skill never touches a private key and never places an order, so a plain buy request starts HERE and reaches gmgn-swap only after the user confirms the order card. Note that gmgn-swap cannot start from a name either — its --output-token is a contract address and the only names it resolves are the currencies SOL/BNB/ETH/USDC — so 帮我买点 dogwifhat has to come here regardless of who is asked. Go straight to gmgn-swap only when the user says the pre-buy check is unwanted (skip the checks, 直接买, 不用尽调, 我很急), or for what this skill does not do at all: selling, percentage sells, limit orders, stop loss, take profit, trailing orders, multi-wallet batch trading, order status, gas-price lookups. The split is by what the ask still needs done, not by who executes: a name needs resolving and an amount needs sizing, so both start here; a bare address needs only a verdict, so it is gmgn-contract-dd's; a signed transaction is always gmgn-swap's.
Look up the "individual officially announced land price" (KRW/㎡) published annually by South Korea’s Ministry of Land, Infrastructure and Transport. This government-announced unit price for land by parcel is the legal basis for calculating property tax, comprehensive real estate tax, capital gains tax, and other taxes. **It is not a market price or actual transaction price.** Use when the user asks for an officially announced land price, individual officially announced land price, officially announced land unit price, land unit price for tax calculations, or “What is the officially announced land price of this plot?” Do NOT use for market prices, actual transaction prices, sale prices, asking prices, or apartment prices (those need a different data source).
Use this skill when the user wants to 'login/log in/sign in', 'authenticate', 'authorize', 'connect OKX account', 'set up credentials', 'first time setup', 'configure okx', '登录', '授权', '认证', '连接账户', '首次配置'. Also when any OKX CLI command fails with an auth error: 'Run okx auth login first', 'Session expired', 'not authenticated', 'requires_auth', '401 Unauthorized', 'token expired/not found', 'StorageNotFoundError', '会话过期', '未认证', '需要登录'. Also when the user asks about login status or the login was interrupted. Also when the user wants to install/update/check/remove the okx-auth binary — 'install/update/remove auth', 'download okx-auth', '安装/更新/卸载认证', 'auth binary status', 'Failed to spawn okx-auth'. Also use before using okx-cex-trade/portfolio/earn/bot for the first time. Do NOT use for market data queries (use okx-cex-market).
Query Ondo tokenized US stock data on Binance Web3. Covers: supported stock token list, RWA metadata (company info, attestation reports), market and per-asset trading status (with corporate action codes for earnings, dividends, splits), real-time on-chain data (token price, holders, circulating supply, market cap), US stock fundamentals (P/E, dividend yield, 52-week range), and token K-line/candlestick charts. Use this skill when users ask about: - Tokenized stock price, holders, or on-chain data for specific tickers - Whether a stock token is tradable, paused, or halted - Ondo RWA token list or which US stocks are available on-chain - Corporate actions affecting a token (dividends, stock splits, earnings halt) - Stock token K-line or candlestick chart data - Comparing on-chain token price vs US stock price NOT for general crypto tokens (BTC, ETH, SOL, etc.) — use query-token-info for those.
Employer-side hiring for tech-event-organizing roles - producer/manager/coordinator, and the community-manager-shaped end of the field. Calibrates the scorecard to operating context (in-house, agency, non-profit/community, or a standing conference business), builds the loop from the general event-planner sequence plus CMX's five-competency set and paid mini-audit work sample, flags the "one hire owns sponsorship, content and production" consolidation pattern seen in postings, sources candidates from general event-industry boards since no tech-specific one exists, and gates compensation on named sources (PCMA, BLS, Glassdoor) rather than a blended figure. Use when the user asks how to hire an event producer or manager, write a posting, design a loop, or hire an event community manager. Do NOT use for candidate prep (samber/dev-event-organizer-skills@dev-event-career) or team org design (samber/dev-event-organizer-skills@event-team-structure).
Build the budget and P&L for a technical event - every cost line split into fixed and per-head, the revenue mix against the funding model, a Good/Better/Best scope-tier ladder so break-even has three answers instead of one, a contingency sized as a stacked floor, pad and downgrade ladder whose cuts also price lost sponsor reach, a cross-edition reserve policy, annual funding decoupled from single events, and outflows scheduled against the dates sponsor and ticket money actually lands. Use whenever asked to build an event budget, model conference or hackathon costs, find break-even, size a contingency reserve, set a reserve or surplus policy across editions, fund a recurring meetup series annually, plan event cash flow, or decide what to cut when revenue falls short. Consumes prices and real vendor quotes, never sets them. Do NOT use to set ticket or sponsor prices - use samber/dev-event-organizer-skills@event-ticket-pricing or samber/dev-event-organizer-skills@event-sponsor-pricing.
Comprehensive US stock analysis including fundamental analysis (financial metrics, business quality, valuation), technical analysis (indicators, chart patterns, support/resistance), stock comparisons, and investment report generation. Use when user requests analysis of US stock tickers (e.g., "analyze AAPL", "compare TSLA vs NVDA", "give me a report on Microsoft"), evaluation of financial metrics, technical chart analysis, or investment recommendations for American stocks.
Structure what a hackathon actually awards — cash versus non-cash medium, including no monetary prize at all, total pool size inside the event budget's prizes line, how that pool splits across places and sponsor tracks, and who may legally receive a payout. Use whenever the user mentions hackathon prize amounts, cash versus hardware or credits, splitting a prize pool across tracks, prize eligibility for minors, sponsor employees or cross-border winners, or how winners actually get paid — even if they never say "prize". Names the contest-law, tax and cross-border exposure categories and routes them to counsel or a fiscal host, never stating a threshold or a form name. Do NOT use to rank the projects — use samber/dev-event-organizer-skills@hackathon-judging instead.
Design a technical event's call for papers — the published call, not the selection behind it. Covers the CFP open/close timeline worked back from the event date, submission form fields, which session formats the call offers, the anonymization posture (named, opt-in, or mandatory blind review), review criteria published in the call itself, stated speaker benefits, per-person submission caps, first-time-speaker support, and the CFP tooling capabilities to look for. Use whenever asked to open or write a CFP, set a CFP deadline, design a talk submission form, decide on blind review, or state speaker perks in a call for proposals. Do NOT use to review or score submissions — use samber/dev-event-organizer-skills@event-talk-selection.
Design the mentor programme for one hackathon edition - coverage depth sized against the challenge tracks rather than a headcount, recruitment through community and sponsor channels, expertise tagging matched to the brief's tracks and any sponsor API, the request mechanic a stuck team uses to reach a mentor, the mentor briefing including the help-versus-build boundary, and rotation by expertise across shifts. Use whenever the user mentions how many mentors a hackathon needs, recruiting or briefing mentors, how a stuck team reaches help during the hacking window, or what a mentor may touch in a team's repository - even if they never say "mentoring". Do NOT use for generic shift and roster mechanics - use samber/dev-event-organizer-skills@event-volunteers instead.
Run the technical and audience-facing delivery of a fully-remote technical event once the format decision has already chosen virtual - the platform that replaces the venue, remote-speaker connectivity and local backup recordings, live chat and Q&A moderation staffing, and the failure drills an event with no physical room needs. Use whenever the user mentions a virtual event platform, an online or remote-only conference or meetup, preparing remote speakers, staffing chat and Q&A moderation, or what happens when the stream dies - even if they never say "virtual". Do NOT use when a physical room exists - the room's signal path is samber/dev-event-organizer-skills@event-production and two audiences at once is samber/dev-event-organizer-skills@hybrid-event-design.
Decide whether to take a technical audience into an organization the organizer does not control, and on what terms - when a host's own premises, operation and staff are the programme rather than a room rented and filled by the organizer. Sets the host-dependency posture (host speaker hosted in-house, one host site host-led or to a negotiated agenda, a multi-host circuit) and the access posture, meaning what the host lets attendees see and repeat afterwards. Use whenever asked to design a learning expedition, company tour, field trip, site-visit programme or executive immersion. Do NOT use for catering - use samber/dev-event-organizer-skills@event-hospitality - or multi-venue logistics - use samber/dev-event-organizer-skills@event-production. States no legal threshold or instrument.
Receive named guests who are neither speaking nor sponsoring but whose presence creates escort, protocol, security or discretion obligations the general attendee flow cannot absorb — public officials, dignitaries, major funders, executives with no booth duty. Covers the qualification test (obligation, never status), the identification roster, escort depth, and a visibility posture that meets the obligation without building a status tier attendees can read. Use whenever the user mentions receiving a minister, mayor, funder or visiting executive, VIP badges or reserved seating, escorting a dignitary, or coordinating with a guest's own security detail — even if they never say "VIP". Do NOT use for speakers — use samber/dev-event-organizer-skills@event-speaker-experience instead.
Design and audit the lived culture of a technical event - the register (hacker, corporate, design, business) and its consistent expression across venue, catering, swag, dress code, stage production, MC and hosting tone, opening and closing ceremonies, and the values a code of conduct puts in the room. Use whenever asked to define an event's vibe or cultural identity, design a signature tradition or ritual, script an opening or closing, brief an MC or organizer-hosts, choose a swag posture, or audit an event whose stated values and on-site experience contradict each other. Embodiment only. Do NOT use for what the event stands for - use samber/dev-event-organizer-skills@event-positioning - or CoC policy and enforcement - use samber/dev-event-organizer-skills@event-code-of-conduct.
Write a technical event's code of conduct and build the enforcement pipeline behind it - what the policy has to say, who and which spaces it binds (attendees, speakers, volunteers, sponsor and booth staff, satellite events), the reporting channels including an anonymous path, response-team composition and rehearsal, the on-site incident runbook and its response clock, the sanctions ladder, which rungs carry an appeal, and the transparency report. Use whenever asked to write or review an event or conference code of conduct, set up incident reporting, staff or train a CoC response team, decide a sanction for an attendee, or handle an on-site incident. Do NOT use for accessibility provisions - use samber/dev-event-organizer-skills@event-accessibility-inclusion. Not legal advice.
Design the standing organizing team of a recurring technical event—the structure that persists between editions. Covers legal-entity posture (none, fiscal sponsorship, own non-profit), decision-rights shape (board-plus-organizers split, domain-lead federation, consensus committee), the role taxonomy, succession and bus-factor planning, burnout guardrails, organizer conflict of interest, a voluntary peer network of independent local communities, and the volunteer-to-paid-staff hiring gate. Use whenever the user mentions structuring or governing an organizing team, forming an association or non-profit for an event, splitting decision rights, organizer succession or rotation, organizer burnout, finding co-organizers, organizers doing business through the event, several independent meetups cooperating as a network, or hiring the first paid staff—even if they never say “team structure.” Do NOT use for day-of staffing—use samber/dev-event-organizer-skills@event-volunteers instead.
Design what a volunteer gets when they are not standing at a post, and how one edition closes with them - off-duty time they can actually use, the volunteer-specific hospitality top-up on the event's general standard, recognition not tied to a shift, a public thank-you, and the past-volunteer list next edition's recruitment starts from. Use whenever the user mentions looking after volunteers beyond their shift, whether volunteers get to see a talk, a volunteer lounge or volunteer meal, thanking volunteers after the event, or bringing the same volunteers back next edition - even if they never say "volunteer experience". Do NOT use for recruitment, roles, shifts or briefing - use samber/dev-event-organizer-skills@event-volunteers instead.
Source, vet and contract the suppliers a venue does not include — caterers, AV and production suppliers, security firms, insurance brokers, swag and print. Covers the venue-exclusivity check that precedes any evaluation, one identical brief per category, sourcing posture and quote-comparison depth, contract red flags and the certificate-of-insurance ask, ordering lead times, delivery buffers, and day-of coordination. Use whenever the user mentions finding a caterer, comparing supplier quotes, briefing an AV or security supplier, ordering swag or T-shirts, or reading a vendor contract before signing — even if they never say "vendor". Refuses to invent supplier prices. Do NOT use to write the AV technical spec — use samber/dev-event-organizer-skills@event-production instead.
Design the general-attendee on-site journey for a technical event - check-in desk and badge pickup, the badge's privacy and scanning posture, wayfinding and signage, the quiet room and other facilities, meal and dietary mechanics, the help path, first-time-attendee orientation, and a walkthrough audit of the finished design. Use whenever asked how to run conference check-in, whether to put a QR code on a badge, where the quiet room goes, how to sign a venue so people find rooms, how to hand out dietary-restricted meals, what a help desk should cover, or how a first-timer finds their feet. Starts at the door. Do NOT use for registration or no-show mechanics - use samber/dev-event-organizer-skills@event-no-show-management; speakers, sponsors and volunteers have their own journey skills.
Design the rubric and the scoring process for judging projects built during a hackathon - evaluation criteria and their weights, the scoring scale, judge coverage and the allocation arithmetic that fits the judging window, cross-judge score normalization, tie-breaking, sponsor and judge conflict-of-interest handling, judge recruitment and briefing, and results announcement including a contested result. Use whenever the user mentions a hackathon judging rubric, criteria weights, how many judges a team count needs, briefing a jury, a sponsor judging its own challenge track, or tie-break and dispute rules - even if they never say "judging". Do NOT use for prize amounts and payout law - use samber/dev-event-organizer-skills@hackathon-cash-prize instead.
Decide which accessibility and inclusion provisions a technical event commits to—the physical, sensory, dietary, economic and digital-access set, at what depth, sized for whom, funded from where—plus the public declaration of it and the data-handling posture for accommodation requests. Use whenever asked what accessibility a conference should offer, whether to caption talks, whether to run a quiet room, childcare or travel grants, whether to staff an identifiable inclusion team, how to write an accessibility page, or how to answer an accommodation request, even if the user never says “accessibility.” Decides the bar, not delivery. Do NOT use for the code of conduct—use samber/dev-event-organizer-skills@event-code-of-conduct. Not legal advice; access duties vary by jurisdiction.
Check “Is this business actually problem-free?” with just one business registration number — cross-reference free public data on the business registration status from the National Tax Service, National Pension Service-registered workplaces, national tax delinquencies, Financial Services Commission corporate summaries, Public Procurement Service disqualifications, and local government licensing and operating status, presenting only the facts in a due diligence report (no scores, grades, or risk judgments).
Use local administrative licensing data (LOCALDATA) to look up the operating, temporarily closed, or permanently closed status, license date (time in business), closure date, business type, and address of local businesses (208 licensed categories, including restaurants, cafes, lodging, pharmacies, beauty salons, and academies). Search by business name + city/county/district. No authentication key required.
Search the National Tax Service's published list of high-value, habitual tax delinquents via the public search on nts.go.kr. Match corporate and individual lists by business or corporate name and list published delinquency details (total amount owed, tax type, delinquency summary, etc.). No authentication key required. In 돌쇠, follow-up actions are also performed through the official interface.
Interprets Culture Index (CI) surveys, behavioral profiles, and personality assessment data. Supports individual profile interpretation, team composition analysis (gas/brake/glue), burnout detection, profile comparison, hiring profiles, manager coaching, interview transcript analysis for trait prediction, candidate debrief, onboarding planning, and conflict mediation. Accepts extracted JSON or PDF input via an OpenCV extraction script. Use when the user shares a Culture Index PDF or JSON profile, asks what someone's CI traits mean, compares Culture Index profiles across a team or against a hiring profile, or asks about burnout risk from Survey-versus-Job gaps.
Helps users send funds to another Stripe business, transfer money to a Stripe Profile handle or network ID, or ask whether an agent can pay a Stripe business. Use Stripe Directory to find or verify a recipient when the user doesn't provide an exact Stripe Profile handle or network ID
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.
Binance Onchain Pay enables users to buy cryptocurrency with fiat (e.g., EUR, USD) or send existing crypto from their Binance account directly to any external on-chain wallet address in a single flow—no manual withdrawal needed. Enables partners to integrate crypto buying services: - payment-method-list: Get available payment methods (Card, P2P, Google Pay, Apple Pay, etc.) with limits for a fiat/crypto pair - trading-pairs: List all supported fiat currencies and cryptocurrencies - estimated-quote: Get real-time price quote including exchange rate, fees, and estimated crypto amount - pre-order: Create a buy order and get redirect URL to Binance payment flow - order: Query order status and details (processing, completed, failed, etc.) - crypto-network: Get supported blockchain networks with withdraw fees and limits - p2p/trading-pairs: List P2P-specific trading pairs
紫鸟 staff management: querying, creating, editing, enabling/disabling/deleting staff and transferring positions. Use when the user needs to look up staff information, create a new staff member, edit staff information, enable/disable/delete staff, or adjust a staff member's department.
Produce THE list of tokens that are hot RIGHT NOW and safe enough to look at, across every chain GMGN supports, scored 0-100 and capped at ten names. This is a screening skill: it starts from no address, sweeps all seven chains, gates every candidate on liquidity / real volume / concentration / rug-and-dev risk, scores the survivors on one cross-chain scale, and returns however many clear the score floor — fewer than ten in a weak market, never padded to fill the quota. USE THIS SKILL WHEN the user wants a curated hot list rather than raw rankings: "热榜", "热门代币", "近期热门", "帮我抓一轮热榜", "现在有什么值得关注的热币", "全链热门币", "生成热榜", "有没有新的热门盘", "what is hot right now", "give me the hot list", "which trending tokens are actually worth looking at", "screen the trending list for me". The same questions in any other language route here too - match on meaning, not wording. DO NOT USE THIS SKILL for a raw ranking dump ("show me the top 20 by volume on sol", "1h trending", "hot search list") - that is `gmgn-market trending` / `hot-searches`, which returns the exchange's own ordering untouched; nor for freshly launched bonding-curve tokens ("just launched", "pump.fun new", "新盘") - that is `gmgn-market trenches`; nor for one address the user already has ("is this token safe", "打个分", "尽调") - that is `gmgn-contract-dd`; nor for a chart read ("走势怎么样", "什么形态") - that is `gmgn-kline-pattern`; nor for early-stage hunting below this skill's own floor ("值得埋伏吗", "新币筛选", "早期机会", "discover early-stage opportunities") - that is `gmgn-market trenches`, because the candidate pool here starts at 500k market cap and 100k liquidity and never contains a bonding-curve token; nor for the wallet-side view of the same market ("聪明钱在买什么", "KOL 在买什么", "on-chain alpha", "copy-trade signals") - that is `gmgn-track smartmoney` / `kol`, which answers who is buying rather than what is worth looking at. The split is by who chooses the tokens: if the user names the token, it is not this skill; if the user is asking the skill to choose, it is. When nobody names a token and the wording alone collides with `gmgn-market` - "hot coins", "what's pumping", "trending tokens", "热门币", "什么币在涨" - the deciding test is the shape of the answer being asked for: an untouched ranking of N rows in the exchange's own order is `gmgn-market trending`; a short list that survived risk gates, carries a score and can be acted on is this skill. A bare ambiguous ask with no other signal defaults here, because this skill can point at the raw ranking while the raw ranking cannot screen itself. Nothing has to be supplied to run it - the trigger phrase alone is enough, and no address, chain or amount is ever required. Four things can be narrowed when the user asks for it: which chains are swept, the age ceiling, how many names come back, and the score floor; any value changed that way is named in the report.
Query Binance fiat payment capabilities — supported countries, currencies, payment methods, limits, and crypto prices — via public APIs, plus authenticated order/payment history lookup. Use whenever users ask about buying or selling crypto with fiat, depositing or withdrawing fiat, fiat-crypto exchange rates, payment options in a specific country, or their fiat order history — even if they don't explicitly mention Binance APIs.
Enable or disable the org preference that controls whether a Salesforce org can receive partner offers from the Transactable Marketplace. Use this skill when the user wants to turn partner offer reception on or off for an org. TRIGGER when: user asks to enable or disable partner offers, configure TransactableMarketplaceReceivePartnerOffers, configure enableTransactableMarketplaceReceivePartnerOffers, set up marketplace partner offer reception, toggle the TM partner offers setting, edit a TransactableMarketplacePrivateOffer.settings file, or configure org preferences related to transactable marketplace. DO NOT TRIGGER when: user needs to create or manage the partner offer records themselves, configure marketplace listing settings, or work with SfdcPartnerOffer objects (use platform-metadata-deploy or platform-apex-generate 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.