Loading...
Loading...
Found 808 Skills
Run MTHDS methods and interpret results. Use when user says "run this pipeline", "execute the workflow", "execute the method", "test this .mthds file", "try it out", "see the output", "dry run", or wants to execute any MTHDS method bundle and see its output.
Edit existing MTHDS bundles (.mthds files). Use when user says "change this pipe", "update the prompt", "rename this concept", "add a step", "remove this pipe", "modify the workflow", "modify the method", "refactor this pipeline", or wants any modification to an existing .mthds file. Supports automatic mode for clear changes and interactive mode for complex modifications.
Design websites with Miles AI. Use when building websites, generating site layouts, creating web content, or when the user mentions Miles. Manages the full design conversation from brief through design direction selection to final build.
Apply when implementing search functionality, faceted navigation, or autocomplete in a headless VTEX storefront. Covers product_search, autocomplete_suggestions, facets, banners, correction_search, and top_searches endpoints, plus analytics event collection. Use for any custom frontend that integrates VTEX Intelligent Search API for product discovery and search result rendering.
Apply when implementing asynchronous payment methods (Boleto, Pix, bank redirects) or working with callback URLs in payment connector code. Covers undefined status response, callbackUrl notification, X-VTEX-signature validation, sync vs async handling, and the 7-day retry window. Use for any payment flow where authorization does not complete synchronously.
BANK OF AI account query and recharge skill. Use for requests like 'recharge 1 usdt', '给 BANK OF AI 充值 1 USDT', or to query BANK OF AI balance/orders. Recharge uses the remote MCP endpoint https://recharge.bankofai.io/mcp with the single `recharge` tool.
Apply when building backend service apps under node/ in a VTEX IO project or configuring service.json routes. Covers the Service class, middleware functions, ctx.clients pattern, JanusClient, ExternalClient, MasterDataClient, and IOClients registration. Use for implementing backend APIs, event handlers, or integrations that must use @vtex/api clients instead of raw HTTP libraries.
Apply when working with MasterData v2 entities, schemas, or MasterDataClient in VTEX IO apps. Covers data entities, JSON Schema definitions, CRUD operations, the masterdata builder, triggers, search and scroll operations, and schema lifecycle management. Use for storing, querying, and managing custom data in VTEX IO apps while avoiding the 60-schema limit through proper schema versioning.
Automatically detect GPU vendor, find appropriate PyTorch container image, launch with correct mounts, and validate GPU functionality. Supports NVIDIA, Ascend, Metax, Iluvatar, and AMD/ROCm. Use when user says "setup container", "start pytorch container", or invokes /gpu-container-setup.
List taxonomy labels in One Horizon (goals, companies, products, releases, components). Use when asked "show taxonomy", "find label IDs", or "tag this initiative". Requires One Horizon MCP.
Find teams, members, and resolve IDs in One Horizon. Use when asked "what teams am I on", "who is on this team", or when you need teamId/userId before running other tools. Requires One Horizon MCP.
Douyin Traffic Distribution Dashboard. Activated when users ask questions such as 'Where is Douyin traffic?', 'Which categories are growing?', 'Traffic dashboard', 'What content types get the most traffic?'. Even if users do not explicitly mention 'Douyin', this skill should be activated when the topic involves platform traffic distribution, content track selection, or traffic trend analysis.