Skills
98,639 packaged capabilities and playbooks for agents. Install any of them with one command.
All
Facebook's library for efficient similarity search and clustering of dense vectors. Supports billions of vectors, GPU acceleration, and various index types (Flat, IVF, HNSW). Use for fast k-NN search, large-scale vector retrieval, or when you need pure similarity search without metadata. Best for high-performance applications.
Use when the user asks to “mine my search terms”, “find new keywords from converting queries”, “build a negative-keyword list”, or “cut wasted paid spend”; harvests converting queries into new keywords/ad groups, builds a standing negative-keyword list and an n-gram waste report from the search-terms export, and delivers a maintenance diff (add / negate / move). Not for account structure — use campaign-architect; not for budget split — use budget-optimizer; not for computing the final RQS — use ad-account-auditor. 付费广告搜索词挖掘/否定关键词/浪费词清单
Official skill for twitterapi.io—query Twitter/X data (tweets, profiles, followers, advanced search, trends, spaces, communities, lists) and perform authenticated actions (post, reply, like, retweet, follow, DM) via the twitterapi.io REST API using a single `x-api-key` header—no OAuth. Use when the user needs to scrape, analyze, monitor, or automate X/Twitter without going through the official developer portal
Rewrite and humanize Simplified Chinese while preserving facts, meaning, evidence strength, register, and authorial voice. Use for requests such as `/qu-ai-wei`, “remove the AI flavor,” “make it sound human,” “humanize Chinese,” “make it more natural,” “rewrite this Chinese passage,” “polish it to sound natural,” or “it’s too stiff,” including structural rewrites of paragraphs, articles, and long-form texts. Do not use for translation, writing new Chinese, typo-only correction, Traditional Chinese, or changing a real person’s voice without authorization.
End-to-end recipe for integrating Sumsub ID Connect — the OIDC-based “Verify with Sumsub ID” flow that lets a user share previously-verified identity claims with your app. TRIGGER when the user asks to “integrate Sumsub ID Connect”, “add Verify-with-Sumsub-ID button”, “reuse Sumsub KYC via OIDC”, “exchange the Sumsub authorization code”, “mint a Sumsub ID share token”, or asks how to wire up `@sumsub/id-connect`, the OIDC `code → access_token` exchange (`/api/snsId/oauth/token`), the share-token / partner-consent flow, or the share-link redirect. Covers preconditions checklist, automated preflight, frontend button (library button + raw redirect alternative), backend code-for-token exchange, share-token minting, partner-consent shareLink flow, and applicant materialisation through `/resources/api/reusableIdentity/reuse`. SKIP for the standalone WebSDK / KYC widget (use `sumsub-integrate-websdk`), or for plain Reusable-KYC-via-API where the donor and recipient are both your own tenants without a user-mediated OIDC step.
When the user wants to run app install ads, user acquisition (UA), or promote mobile apps. Also use when the user mentions “app ads,” “app install ads,” “UA,” “user acquisition,” “Google App Campaigns,” “Apple Search Ads,” “ASA,” “UAC,” “App Store ads,” “Play Store ads,” “CPI,” or “app promotion.” For store listings, use distribution-channels.
Remove backgrounds from images with BiRefNet via inference.sh CLI. Model: BiRefNet (high accuracy background removal). Use for: product photos, portraits, e-commerce, transparent PNGs, photo editing. Triggers: remove background, background removal, remove bg, transparent background, cut out image, background remover, rembg, product photo editing, cutout, transparent png, bg removal, photo cutout
Generate images with Google Gemini 3.1 Flash Image Preview (Nano Banana 2) via inference.sh CLI. Capabilities: text-to-image, image editing, multi-image input (up to 14 images), Google Search grounding. Triggers: nano banana 2, nanobanana 2, gemini 3.1 flash image, gemini 3 1 flash image preview, google image generation
Port an existing Remotion (React) composition to HyperFrames HTML. Use ONLY when the user explicitly asks to port/convert/migrate/translate a Remotion source. Do NOT use: (a) authoring a new HyperFrames composition; (b) Remotion mentioned in passing; (c) Remotion code shared as reference only; (d) "same video as my Remotion one" without an explicit migrate request — treat as fresh build. In doubt → `/general-video`. One-way, Remotion-only: no reverse export (HyperFrames→Remotion or any framework), no non-Remotion source (After Effects, Framer Motion, plain React/CSS) → out of scope, re-create via `/general-video`. Flags unsupported patterns (useState, useEffect, async calculateMetadata, third-party React libs, `@remotion/lambda`) and recommends runtime interop over lossy translation. Unsure whether to port vs. build fresh, or only a passing Remotion mention? → /hyperframes.
Add Sumsub Device Intelligence (the Fisherman JS module) to your own web pages where there is NO Sumsub verification widget — login, signup, password reset, 2FA, checkout, or any high-value action you want fraud-screened. TRIGGER when the user asks to "add device intelligence to login / signup", "fingerprint the device on a custom page", "use Fisherman standalone / self-hosted", "ongoing monitoring of platform events", "pre-KYC device check", "detect multi-accounting at signup", or "send a financial transaction with the captured device". Covers the whole loop — behavior access token, @sumsub/fisherman init + fingerprint, confirming the event (platform event / financial transaction / create-applicant), reading results, sandbox, go-live. SKIP when the page already embeds the Sumsub WebSDK — Device Intelligence rides along inside it, use `sumsub-integrate-dint-websdk`.
Understand video content locally using ffmpeg frame extraction and Whisper transcription. No API keys needed. Use when: (1) Understanding what a video contains, (2) Transcribing video audio locally, (3) Extracting key frames for visual analysis, (4) Getting video content without API keys
Appwrite Dart SDK skill. Use when building Flutter apps (mobile, web, desktop) or server-side Dart applications with Appwrite. Covers client-side auth (email, OAuth), database queries, file uploads with native file handling, real-time subscriptions, and server-side admin via API keys for user management, database administration, storage, and functions.
Use when the user asks to "build audience segments from my customer list", "make value-based / lookalike seed lists", "set up exclusion / suppression segments", or "map audiences to funnel stages across platforms"; turns the user's OWN customer/CRM/GA4 export into seed audiences, value-based lookalike SEED lists, exclusion/suppression segments, and a cross-platform funnel-stage targeting map, informing the ROAS A (Audience) dimension. Not for building account structure or match types — use campaign-architect; not for organic SERP intent — use keyword-research. Paid-ad audience segmentation / seed audiences / exclusion audiences / lookalike seed audiences
Use when the user asks to "plan my paid account structure", "pick Search vs PMax", "lay out ad groups / asset groups", or "audit paid-vs-organic cannibalization"; designs campaign-type selection, ad-group/asset-group layout, targeting + match types, negative/exclusion hygiene, and a paid↔organic overlap audit, and scores the ROAS A (Audience) dimension + structure. Not for computing the final RQS — use ad-account-auditor; not for budget split — use budget-optimizer; not for organic site architecture — use site-structure-optimizer. Paid-ad account structure / campaign planning / negative keywords
Creates complete AEM components with dialog, HTL template, Sling Model, unit tests, and clientlibs. Supports extending Core Components and project components. When a Figma design URL is provided, fetches the design via Figma MCP (get_design_context) and translates it into pixel-perfect HTL, CSS, and JS. Follows Adobe Experience League best practices for AEM Cloud Service and 6.5. Use this skill whenever the user mentions creating, building, generating, or scaffolding an AEM component, or mentions component types like teaser, card, hero, banner, accordion, tabs, carousel, list, navigation, breadcrumb, or any custom AEM component. Also trigger when the user wants to extend a Core Component, create a component dialog, add a Sling Model, or convert a Figma design into an AEM component
Benchmarks LLM inference and drives GPU kernel optimization with Magpie. Use when the user wants to benchmark vLLM, SGLang, or Atom; capture torch traces; post-process inference traces with TraceLens into prefill/decode and roofline reports; identify top bottleneck kernels or map profiler names to source; analyze or compare HIP, CUDA, PyTorch, or Triton kernels; validate and rank optimized variants; run local, container, or Ray workloads; or mentions Magpie, TraceLens, gap analysis, TTFT, TPOT, kernel evaluation, or AMD GPU optimization.
This skill should be used when the user asks to "migrate from OpenAI Apps SDK", "convert OpenAI App to MCP", "port from window.openai", "migrate from skybridge", "convert openai/outputTemplate", or needs guidance on converting OpenAI Apps SDK applications to MCP Apps SDK. Provides step-by-step migration guidance with API mapping tables.
Build quick IRR/MOIC sensitivity tables for PE deal evaluation. Models returns across entry multiple, leverage, exit multiple, growth, and hold period scenarios. Use when sizing up a deal, stress-testing assumptions, or preparing IC returns exhibits. Triggers on "returns analysis", "IRR sensitivity", "MOIC table", "what's the return at", "model the returns", or "back of the envelope"
Add Sumsub Device Intelligence (the Fisherman module) to a web project that already verifies users with the Sumsub WebSDK. TRIGGER when the user asks to “add device intelligence”, “enable device capture / fingerprinting in the WebSDK”, “turn on Fisherman”, “detect device fraud / multi-accounting in the verification flow”, or asks how device risk labels get onto an applicant verified through the WebSDK. Covers the whole loop — enabling Capture device data on the level, the automatic in-SDK Fisherman lifecycle, the advanced self-rendered wiring, reading device signals (Devices tab, Device Check, risk labels, webhooks), sandbox testing, go-live checklist. SKIP for device intelligence on pages with NO WebSDK widget (login / signup / checkout) — use `sumsub-integrate-dint-standalone`; SKIP for the base WebSDK embed itself — use `sumsub-integrate-websdk`.
Use when the user asks to “find trending topics”, “what trends should my brand jump on”, or “time a campaign around a cultural moment”; produces a ranked trend report with brand-fit scores, format calls (rising/peak/declining), a cultural calendar, and go/skip recommendations. Not for finding the creators to run those trends — use influencer-discovery; not for building the brand posting calendar from a go verdict — use social-calendar-builder. 热点趋势洞察/借势营销
Use when the user asks to "write ad copy", "generate RSA headlines", or "build ad creative at volume"; produces ad units — RSA headlines/descriptions, hooks, and an angle matrix — message-matched to the destination landing page. Not for scoring an ad account — use ad-account-auditor; not for the post-click page — use landing-optimizer; not for organic articles — use content-writer. Ad creative / ad copy / RSA headlines
Use when the user asks to "write influencer outreach", "follow up with a creator", "pitch a journalist, hunter, or launch partner", or "negotiate partnership terms"; produces personalized pitches, multi-touch follow-up sequences, negotiation scripts with objection handling, and a status pipeline tracker — the shared outreach mechanics engine for creator, media/analyst, launch-partner, and social-selling / advocate-recruitment targets. Not for finalizing signed agreements — use contract-helper; not for media-list tiering, embargo terms, or press-release structure — use press-media-relations. Influencer outreach / partnership negotiation scripts
Create diverse synthetic test inputs for LLM pipeline evaluation using dimension-based tuple generation. Use when bootstrapping an eval dataset, when real user data is sparse, or when stress-testing specific failure hypotheses. Do not use when you already have 100+ representative real traces (use stratified sampling instead), or when the task is collecting production logs.
Apply when handling credit card data, implementing secureProxyUrl flows, or working with payment security and proxy code. Covers PCI DSS compliance, Secure Proxy card tokenization, sensitive data handling rules, X-PROVIDER-Forward-To header usage, custom token creation, and the constraint that Secure Proxy applies only to card authorization (not post-auth operations like cancel, capture, or refund). Use for any payment connector that processes credit, debit, or co-branded card payments to prevent data breaches and PCI violations.
When the user faces brand impersonation, fake websites, phishing sites, or trademark infringement. Also use when the user mentions “fake site,” “impersonation,” “phishing site,” “trademark infringement,” “domain squatting,” or “brand abuse.” For monitoring, use brand-monitoring.
Generate enriched lead lists using Exa Agent. Finds companies matching an ICP, enriches with signals/news/scores, and outputs CSV. Use when generating leads, building prospect lists, finding companies to sell to, doing outbound research, or ICP-based company discovery. Triggers on "leads", "lead gen", "prospect list", "find companies", "ICP", "outbound list".
Formats and executes dbt CLI commands, selects the correct dbt executable, and structures command parameters. Use when running models, tests, builds, compiles, or show queries via dbt CLI. Use when unsure which dbt executable to use or how to format command parameters.
Integrate the Sumsub Mobile SDK (IdensicMobileSDK / SNSMobileSDK) into a native iOS or Android app—even when the user doesn't name the SDK (e.g. “add Sumsub/KYC to my iPhone app”, “add KYC to my Android app”, “show the verification screen”, “launch Sumsub from a view controller / activity”). Detects the platform from the project (iOS Xcode/Swift vs Android Gradle/Kotlin) and follows the matching track. Covers install, permissions, init, token refresh, and presenting / launching the flow. SKIP for web (`sumsub-integrate-websdk`), backend / API-only token signing (`sumsub-api-generic`), theming (`sumsub-theme-msdk`), and React Native / Flutter (not supported—native iOS & Android only)
Tracks physical units and propagates measurement uncertainty in scientific calculations using pint and uncertainties. Use for unit conversion and dimensional checking, GUM uncertainty budgets, Type A and Type B evaluation, coverage factors and expanded uncertainty, Monte Carlo propagation, significant-figure and plus-minus reporting, error propagation through curve fits, CODATA constants, auditing Python code for stripped units or broken uncertainty propagation, and order-of-magnitude plausibility checks using dimensionless groups (Reynolds, Peclet, Damkohler, Knudsen, Biot, Womersley), characteristic scales such as diffusion time or Debye length, and observed magnitude ranges. Trigger on "is this number physically reasonable", "sanity check these units", "what regime is this flow in", or a result that looks off by orders of magnitude.
Use Xquik to fetch X (Twitter) data or act through a connected account. Covers search, profiles, followers, replies, threads, timelines, media downloads, bulk exports, trends, monitors, signed webhooks, draws, posts, likes, follows, DMs, and AI analysis of posts (sentiment, brand mentions, news, market signals, viral score, custom labels). Also use for hashtag or @handle tracking when no other network is named, Xquik MCP setup, pricing, and X API comparisons. Skip data from other social networks, code that stays on the official X API (such as tweepy with an X developer bearer token), official X widget implementation, and content drafting or analysis without an API task. Not affiliated with X Corp.
Use when auditing a paid ad account for incremental contribution, wasted spend, or measurement integrity before scaling; runs a typed 20-item ROAS profile with verified vetoes and a SHIP/FIX/BLOCK/UNDECIDED gate on own exported data. Not for campaign structure design — use campaign-architect; not for creative production — use ad-creative-builder. 付费广告账户审计/ROAS评分
Use when the user asks to "codify our brand voice", "define naming rules for our products and tiers", or "write the tone-of-voice guide with banned phrases"; produces the brand-level voice canon (register, tone spectrum, banned-phrase list, few-shot examples drawn only from the brand's own published material) and the naming tax (product / feature / tier naming rules plus approved and banned terms) that seeds the narrative-registry canon and that every channel's voice adaptation points up to. Not for per-platform voice adaptation — use channel-registry's voice-dossier; not for finished copy or blog posts — use content-writer; not for the message hierarchy itself — use message-system-architect; not for claim adjudication — use offer-claims-registry. 品牌语气/词汇表/命名税/禁用词/品牌语言规范
Prepare for client review meetings with portfolio performance summaries, allocation analysis, talking points, and action items. Pulls account data together into a concise, meeting-ready format. Use before quarterly reviews, annual checkups, or ad hoc client meetings. Triggers on “client review,” “meeting prep for [client],” “quarterly review,” “prep for [client name],” or “client meeting”
Use when the user asks to “draft an influencer contract,” “review these agreement terms,” or “build a partnership template”; produces a full influencer agreement framework (scope, compensation, usage rights, exclusivity, FTC disclosure), a clause-by-clause review with red flags, and a negotiation cheat sheet. Not for outreach negotiation before a deal exists — use outreach-manager. Influencer contracts / partnership agreement term review
Use when the user asks to "write the email", "draft subject lines", or "build email creative"; produces the pre-click unit — subject-line variants + preheader, body copy, one clear CTA, and a plain-text alt — message-matched to the destination page and claims-ledger-aware. Not for pre-scoring or ranking subject-line variants (spam/truncation/render pre-score) — use subject-line-lab; not for scoring the email or computing EQS — use email-quality-auditor; not for the multi-step flow — use email-sequence-designer; not for the A/B test plan — use send-experiment-designer. 邮件文案/主题行/邮件创意
Use when the user asks to "design an A/B test", "set up a creative/landing test", "run an incrementality test", or "is this result statistically and practically material?"; produces a hypothesis, variant matrix, sample-size/duration/power plan, and a documented effect/uncertainty read from own exported results. It applies only a precommitted owner-approved action rule; the statistical helper never chooses a business action. Not for producing variants — use ad-creative-builder; not for reading back one shipped change — use paid-measurement-loop. 广告AB测试设计/实验设计/显著性判定/增效测试
Creates, manages, and queries Arize datasets and examples. Covers dataset CRUD, appending examples, exporting data, and file-based dataset creation using the ax CLI. Use when the user needs test data, evaluation examples, or mentions create dataset, list datasets, export dataset, append examples, dataset version, golden dataset, or test set.
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.