Skills
97,222 packaged capabilities and playbooks for agents. Install any of them with one command.
Development
Apply when designing or implementing how a VTEX IO backend app integrates with VTEX services or external APIs through @vtex/api and @vtex/clients. Covers choosing the correct client type, registering clients in IOClients, configuring InstanceOptions, and consuming integrations through ctx.clients. Use for custom client design, VTEX Core Commerce integrations, or reviewing backend code that should use VTEX IO client patterns instead of raw HTTP libraries.
Apply when deciding whether and how VTEX IO apps should use Master Data v2 for custom data. Covers entity boundaries, schema lifecycle, indexing strategy, and when Master Data is the right storage mechanism versus another data approach. Use for reviews, wishlists, forms, or other custom data modeling decisions in VTEX IO apps.
Use when playing, mixing or debugging sound in Unreal Engine — one-shot SFX, looping ambience, music, dialogue or procedural audio. Also use when the user mentions 'UAudioComponent', 'PlaySoundAtLocation', 'SpawnSoundAttached', 'SoundCue', 'MetaSound', 'UMetaSoundSource', 'SetFloatParameter', 'sound attenuation', 'spatialization', 'occlusion', 'sound concurrency', 'submix', 'audio bus', 'sound mix', 'SetSubmixOutputVolume', 'reverb', 'Quartz', 'audio modulation' or 'subtitles'. For VFX timing, see ue-niagara-effects; for anim-notify sounds, see ue-animation-system; for component lifetime and attachment, see ue-actor-component-architecture.
React and Next.js performance optimization guidelines from Vercel Engineering. This skill should be used when writing, reviewing, or refactoring React/Next.js code to ensure optimal performance patterns. Triggers on tasks involving React components, Next.js pages, data fetching, bundle optimization, or performance improvements.
Apply when connecting React components to Store Framework blocks and render-runtime behavior in VTEX IO. Covers interfaces.json, block registration, block composition, and how storefront components become configurable theme blocks. Use for block mapping, theme integration, or reviewing whether a React component is correctly exposed to Store Framework.
Guide for building Apple-platform applications with Apollo iOS, the strongly typed GraphQL client for Swift. Use this skill when: (1) adding Apollo iOS to a Swift Package Manager or Xcode project, (2) configuring `apollo-codegen-config.json` and running code generation, (3) configuring an `ApolloClient` with auth, interceptors, and caching, (4) writing queries, mutations, or subscriptions from SwiftUI views, (5) writing tests against generated operation mocks.
Runs an autonomous review-and-fix improvement loop over any code target — a skill, plugin, module, or directory — using a reviewer the user names: any installed skill or agent. Keeps a cross-round findings ledger, escalates when fixes stop converging, and guards scope mechanically. Use when asked to 'improve this code until review passes', 'run an improvement loop with <reviewer>', or to iterate review-and-fix with a specific reviewer. For skills prefer the skill-improver entry; for a branch prefer pr-improver.
Improve Elasticsearch search relevance for content and catalog indices: pin or promote results with query rules (correct rule type, criteria and rule-query wiring) and tune organic ranking with multi_match, field boosts and analysis grounded in the index mapping. Use when search results rank poorly, a specific document must appear first for a query, or the user asks to tune full-text matching — not for ES|QL analytics, index ingest or cluster health
Use this skill when creating Sprites or Images in Phaser 4. Covers factory methods, texture/frame selection, position, scale, rotation, tint, flip, alpha, origin, depth, and the component mixin system. Triggers on: Sprite, Image, this.add.sprite, this.add.image, texture, setTint, setAlpha.
Use when adding metadata to commits without changing history, tracking review status, test results, code quality annotations, or supplementing commit messages post-hoc — provides git notes commands and patterns for attaching non-invasive metadata to Git objects.
Finish an open PR by batching review feedback, applying valid fixes, running verification, pushing once per batch, and monitoring CI with bounded waits. Use when the user asks to update code until PR review comments are handled, review-all has no valid blocking findings, and required checks pass.
Batteries-included agent component for React/Next.js from ui.inference.sh. One component with runtime, tools, streaming, approvals, and widgets built in. Capabilities: drop-in agent, human-in-the-loop, client-side tools, form filling. Use for: building AI chat interfaces, agentic UIs, SaaS copilots, assistants. Triggers: agent component, agent ui, chat agent, shadcn agent, react agent, agentic ui, ai assistant ui, copilot ui, inference ui, human in the loop
Apply when choosing which VTEX IO authentication token should back a request from a backend app. Covers `ctx.authToken`, `ctx.storeUserAuthToken`, `ctx.adminUserAuthToken`, `authMethod`, and how requester context should determine the identity used by VTEX clients. Use for deciding which identity talks to VTEX endpoints in storefront-backed requests, Admin actions, or app-level integrations that should avoid hardcoded VTEX credentials
WeChat Pay product coupon integration solution covering coupon type selection and the full lifecycle of issuance, redemption, lookup, refund, and callbacks. Provides five capabilities: selection guidance, sample code, business quick reference, quality assessment, and troubleshooting. Use when the user mentions “product coupon,” “issue coupon,” “redeem,” “create product coupon,” “product coupon code,” “product coupon callback,” “refund product coupon,” or asks to “integrate product coupons,” “generate coupon issuance code,” or “troubleshoot product coupon issues.”
Creates reusable Convex components with defineComponent, a clean client wrapper, their own schema, and an npm publish setup. Use when extracting a feature into a package, building something for the Convex component directory, or when a component's functions are not showing up in the parent app.
Framer Motion performance optimization guidelines. Use this skill when writing, reviewing, or refactoring React animations with Framer Motion to ensure optimal performance patterns. Triggers on tasks involving motion components, animations, gestures, layout transitions, scroll-linked effects, and SVG animations
Expert Django Celery guidance for asynchronous task processing. Use when designing background tasks, configuring Celery workers, handling task retries and errors, optimizing Celery performance, implementing periodic tasks with Celery Beat, or setting up production monitoring for Celery. Do not use for general Django questions unrelated to Celery, non-Celery task systems (Django Q, Huey, RQ), ML/data pipeline orchestration (Airflow, Prefect), or frontend and API-only concerns. Follows Vinta's Django Celery best practices
Guides the agent through creating a new Capacitor app from scratch. Covers project scaffolding with the Capacitor CLI, configuring the app (appId, appName, webDir), adding native platforms (iOS, Android), and syncing. Includes decision points for Ionic Framework integration, live updates, and CI/CD setup. Do not use for upgrading existing Capacitor apps, migrating from other frameworks, or plugin installation.
Use ElevenLabs Realtime models (`eleven_realtime_v1_mini`, `eleven_realtime_v1_max`), the low-latency models built for voice conversation. Use when the user wants to create an ElevenAgents agent on a Realtime model or switch an existing agent's Voice mode to Realtime, set `conversation_config.realtime_model`, choose between Realtime Mini and Max, or debug a Realtime agent that won't publish or transfer. Also use when migrating a voice app built on OpenAI's Realtime API and SDK (`@openai/agents-realtime`, `gpt-realtime`) to the OpenAI-compatible ElevenLabs Realtime API, including the `client_secrets` mint, the WebSocket transport, and audio after leaving WebRTC (closes with 4001/4003, no audio). Not for choosing an agent's LLM or TTS model in Custom mode, Scribe realtime speech-to-text, or migrating Chat Completions or Responses API text calls.
Deploys, queries, and debugs AWS Marketplace usage-based (PAYG) metering — the pipeline (ResolveCustomer, BatchMeterUsage, EventBridge via SAM) and querying/debugging metering records, statuses, failures, discrepancies. Covers Concurrent Agreements (CustomerAWSAccountId + LicenseArn), multi-product, CloudTrail Event History (90 days; never CloudTrail Lake), Seller Reports (Billed Revenue/Usage columns + CSV/SDDS parsing), existing-stack detection, metering region for BatchMeterUsage/MeterUsage (DisabledApiException), metered AMI/Container + IAM roles, where registration data lives (customer-profile table), legacy ProductCode + CustomerIdentifier, DuplicateRecord/CustomerNotSubscribed, bad LicenseArn. Also SCOPES adjacent asks — flat-rate/SaaS-Subscription "do I still meter", CCP included-units + overage, contract term/annual renewal, forecasting future bills/usage — with the right answer or a one-line redirect. Use for any BatchMeterUsage/ResolveCustomer or SaaS usage-billing question.
Automated coordination, formatting, and learning from Claude Code operations using intelligent hooks with MCP integration. Includes pre$post task hooks, session management, Git integration, memory coordination, and neural pattern training for enhanced development workflows.
Apply when defining or changing the contract of a VTEX IO app through manifest.json, builder declarations, dependencies, peerDependencies, billingOptions, and app identity. Covers how the app declares capabilities and integration boundaries. Use for scaffolding apps, splitting responsibilities across apps, or fixing contract-level link and publish issues.
Use when writing or debugging State Tree logic in Unreal Engine C++ — tasks, conditions, evaluators, considerations, schemas, transitions, events or Mass behaviours. Also use when the user mentions 'StateTree', 'state tree', 'FStateTreeTaskBase', 'FStateTreeExecutionContext', 'GetInstanceDataType', 'FInstanceDataType', 'UStateTreeComponent', 'UStateTreeAIComponent', 'FStateTreeReference', 'SendStateTreeEvent', 'EStateTreeRunStatus', 'StateTree schema', 'utility selection', 'scheduled tick', 'FinishTask', or 'Mass StateTree'. For behaviour trees, perception and navigation, see ue-ai-navigation; for Mass processors and fragments, see ue-mass-entity; for USTRUCT basics, see ue-cpp-foundations.
Apply when deciding where and how a VTEX IO app should store and read data. Covers when to use app settings, configuration apps, Master Data, VBase, VTEX core APIs, or external stores, and how to avoid duplicating sources of truth or abusing configuration stores for operational data. Use for new data flows, caching decisions, refactors, or reviewing suspicious storage and access patterns in VTEX IO apps.
Apply when designing or implementing the runtime structure of a VTEX IO backend app under node/. Covers the Service entrypoint, typed context and state, service.json runtime configuration, and how routes, events, and GraphQL handlers are registered and executed. Use for structuring backend apps, defining runtime boundaries, or fixing execution-model issues in VTEX IO services.
Expert knowledge in Flutter Riverpod state management (2025 best practices). Use when working with Riverpod, Flutter state management, AsyncNotifier, provider types, code generation with riverpod_generator, state synchronization, or when the user mentions data fetching, mutations, reactive state, performance optimization, or testing in Flutter apps. Covers AsyncNotifierProvider patterns, repository architecture, autoDispose, family providers, and common anti-patterns to avoid.
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.