Dados e Análise

Optimize Magento 2 performance — full page cache (Varnish), Redis, indexer tuning, JavaScript/CSS optimization, database optimization, and profiling. Use when diagnosing slow pages, optimizing load times, or configuring caching.

Use the BigCommerce GraphQL Storefront API — queries, mutations, authentication tokens, customer impersonation, cart operations, and schema exploration. Use when building storefront features that need client-side data fetching.

Manage Salesforce Commerce customers — B2C (customer objects, customer groups, segmentation, SLAS authentication, wishlists) and B2B (Account/Contact, buyer groups, buyer permissions, self-registration). Both platforms share Data Cloud for unified customer profiles and consent management.

Use Shopify GraphQL APIs — Admin API for server-side CRUD, Storefront API for client-side queries, versioning, cost-based rate limiting, bulk operations, pagination. Use when integrating with Shopify data.

Work with WooCommerce product attributes, custom meta fields, taxonomies, custom product tabs, and variation data. Use when adding custom data to products, orders, or customers.

Scan a target codebase for data model definitions (SQL schemas, ORM models, TypeScript interfaces, Pydantic models) and propose data_concept, data_aggregate, and data_entity registry entries. Presents findings for review before writing files.

Generate detailed cost reports with charts and breakdowns. Shows daily/weekly/monthly spend, per-tool costs, per-branch costs, and trends. Use when user says 'cost report', 'spending report', 'usage report', 'show costs', 'branch costs', or '/cost-report'.

Esta skill é um auditor de segurança para bancos de dados multi-backend. Ela audita Supabase, Firebase, MongoDB (auto-hospedado e Atlas), PostgreSQL auto-hospedado e MySQL auto-hospedado em busca de configurações incorretas de RLS/regras, credenciais expostas, bypasses de autenticação e vulnerabilidades como MongoBleed (CVE-2025-14847) e pgBouncer CVE-2025-12819.

Implement A2A messages and parts — TextPart, FilePart, DataPart, message roles, metadata, and content negotiation. Use when building message construction, parsing, or content type handling in A2A agents.

Deploy Medusa v2 to production — build process, server vs worker mode, environment variables, hosting options, Redis caching, database configuration, and production checklist. Use when deploying Medusa applications.

Implement the UCP Buyer Consent extension — GDPR/CCPA consent collection, consent fields in checkout sessions, and privacy-compliant consent management. Use when adding consent flows, privacy compliance, or data processing agreements to UCP checkout.

Ingest site content into NLWeb's vector store using `db_load.py` — supports RSS/Atom feeds, Schema.org JSON-LD, sitemap-driven URL lists, and CSV. Covers chunking, embedding computation, site partitioning, batch sizing, delete-and-reload, and per-backend write_endpoint targeting. Use when bootstrapping a site's index, refreshing content, or migrating between retrieval backends.