Claude Skills by OrcaQubits

Build Medusa v2 workflows — steps with createStep, compensation/rollback, parallel execution, hooks for extending built-in workflows, and when conditions. Use when orchestrating multi-step operations.

Write modern TypeScript for Medusa v2 — DML type inference, service generics, container typing, strict mode constraints, utility types, and module interface patterns. Use when writing TypeScript in Medusa projects.

Implement and consume the NLWeb /ask REST endpoint — request shape (GET/POST, query-string and v0.55 structured body), SSE streaming response, modes (list/summarize/generate), in-stream "message_type" headers, error envelopes, and client-side parsing. Use when building an NLWeb server route, calling /ask from a custom agent, or debugging /ask responses.

Configure NLWeb authentication and multi-tenant deployments — OAuth providers (GitHub, Google, Microsoft, Facebook), session storage, the `sites:` allowlist in `config_nlweb.yaml`, conversation persistence per authenticated user, and per-tenant data isolation. Use when adding login to an NLWeb instance, hosting multiple customers on one deployment, or persisting conversation history.

Integrate NLWeb with ChatGPT's Apps SDK — the Node.js MCP server in `openai-apps-sdk-integration/`, the `nlweb-list` tool, the React widget at `ui://widget/nlweb-list.html`, and the port-8100 AppSDK adapter that translates NLWeb's message list to OpenAI Apps SDK envelopes. Use when publishing an NLWeb site as a ChatGPT app or wiring NLWeb results into an Apps SDK widget.

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.

Deploy NLWeb to production — Azure App Service (`deploy_azure_webapp.sh` + AI Search + Azure OpenAI), Snowflake Container Services, Cloudflare Worker + AutoRAG, Docker, and self-hosted. Covers env-var conventions, `mode: production` lockdown, scaling, TLS, OAuth, and CI for data reloads. Use when going from local dev to a hosted, internet-facing NLWeb instance.

NLWeb development patterns — the mixed-mode programming philosophy, FastTrack vs Analysis parallel paths, config file precedence and the `mode: development` override trap, in-stream NLWS headers vs HTTP headers, embedding/ingest determinism, debugging the LLM-call chain, neural scorer selection (NLWebScorer ModernBERT+GAM), and the A2A / AgentFinder / DataFinder / ModelRouter subsystems. Use when designing the internal architecture of an NLWeb deployment or solving cross-cutting concerns.

Configure NLWeb LLM and embedding providers — OpenAI, Azure OpenAI (default), Anthropic, Google Gemini, DeepSeek on Azure, Llama on Azure, HuggingFace, Inception Labs, Snowflake Cortex, Ollama, Pi Labs. Covers `config_llm.yaml` high/low tier model selection, the ModelRouter cost/quality routing logic, `config_embedding.yaml`, and adding a custom provider. Use when picking models, tuning cost, or wiring a new LLM backend.

Expose NLWeb as an MCP (Model Context Protocol) server — JSON-RPC 2.0 endpoint at /mcp, the `ask` / `list_sites` / `who` tools, MCP protocol version 2024-11-05, and integration with ChatGPT, Claude, Gemini, and other agent clients. Use when wiring NLWeb to an AI agent via MCP or building an MCP client that consumes an NLWeb site.

Customize NLWeb's LLM prompts and per-Schema.org-type behavior via `prompts.xml` and `site_types.xml` — covers the `<promptString>` template format, `<returnStruc>` JSON schemas, prompt inheritance, decontextualization/ranking/generate templates, per-site overrides, and pitfalls of editing prompts in place. Use when tuning answer quality, supporting a new domain, or localizing prompts.

Choose and configure NLWeb retrieval backends — Qdrant (local + remote), Azure AI Search, Elasticsearch, OpenSearch (with/without k-NN), Postgres pgvector, Milvus, Snowflake Cortex Search, Cloudflare AutoRAG, Shopify MCP, and Bing Web Search. Covers `config_retrieval.yaml`, the single `write_endpoint` rule, parallel read-fanout with URL dedup, and per-backend setup pages. Use when picking a retrieval store, migrating between backends, or debugging "results are empty."

Prepare and structure site content as Schema.org JSON-LD for NLWeb ingestion — covers the supported types (Recipe, Product, Movie, Event, Article, RealEstate, Course, etc.), per-type behavior in NLWeb's tool routing, JSON-LD embedding patterns in HTML, sites.xml registration, and how the `schema_object` flows through ranking back to agent results. Use when authoring or auditing the structured data on a site that will be exposed via NLWeb.

Bootstrap a local NLWeb development environment from scratch — clone the repo, configure .env, install Python deps via `nlweb init-python`, run `nlweb init` for interactive LLM/retrieval selection, load sample Schema.org data, and verify with `nlweb check`. Use when starting a new NLWeb deployment from zero.

Design and implement NLWeb tools — the per-Schema.org-type handlers that turn a query into a specialized response (search, item_details, compare_items, ensemble, recipe_substitution, accompaniment, conversation_search, etc.). Covers `tools.xml`, the ToolSelector router, builtin handlers in `methods/`, writing a custom tool with a `<returnStruc>` contract, and disabling tool selection for raw retrieval. Use when extending NLWeb beyond the default query → results flow.

Write GraphQL queries, mutations, and subscriptions — fragments, code generation, TypedDocumentNode, variables, error handling, and client setup. Use when writing GraphQL code for Saleor.

Build Next.js and React applications for Saleor — App Router, server and client components, GraphQL client integration, MacawUI in Apps, and Tailwind CSS. Use when building Saleor storefronts or Apps with Next.js.

Write Python and Django code for Saleor — Django ORM patterns, signals, Celery tasks, type hints, migrations, management commands, and async views. Use when writing Python/Django in Saleor projects.

Develop Saleor Apps — App manifest, saleor-app-sdk, Next.js template, permissions, token exchange, APL, App Bridge, and lifecycle management. Use when building Saleor App extensions.

Work with Saleor's typed attribute system — attribute types, product types, page types, variant selection attributes, and attribute-based filtering. Use when defining product schemas.

Manage the Saleor catalog — products, variants, product types, categories, collections, media, and warehouse stock. Use when working with Saleor product data.

Configure Saleor channels — multi-currency, multi-region, per-channel pricing, warehouse allocation, and multi-brand setups. Use when managing multi-channel commerce.

Implement the Saleor checkout flow — checkout creation, line items, shipping/billing addresses, delivery methods, payment, and completion. Use when building checkout experiences.

Manage Saleor customers and staff — customer accounts, registration, addresses, staff users, permission groups, and authentication. Use when working with user management.

Extend the Saleor Dashboard — mounting points, App Bridge actions, MacawUI components, iframe extensions, and custom views. Use when building Dashboard extensions.

Deploy Saleor to production — Docker setup, Saleor Cloud, environment variables, Celery workers, S3 media storage, database management, and scaling. Use when deploying Saleor applications.

Work with the Saleor GraphQL API — queries, mutations, subscriptions, cursor pagination, filters, error handling, GraphQL Playground, and code generation. Use when building against the Saleor API.

Manage the Saleor order lifecycle — order creation, fulfillments, returns, refunds, draft orders, and order events. Use when working with Saleor orders.

Implement Saleor payment processing — transaction-based payment flow, payment Apps, sync webhook events, Stripe/Adyen patterns, and refunds. Use when building payment integrations.

Configure Saleor promotions — catalog promotions, order promotions, vouchers, manual discounts, gift cards, and discount stacking. Use when setting up pricing rules.

Secure Saleor applications — JWT authentication, OIDC integration, App tokens, permission model, rate limiting, CORS, and security headers. Use when configuring Saleor security.

Set up a Saleor development environment — saleor-platform Docker Compose, CLI, PostgreSQL/Redis prerequisites, manage.py commands, environment variables, project structure. Use when starting a new Saleor project.

Configure Saleor shipping — shipping zones, methods (price/weight-based), custom shipping Apps, warehouse-based allocation, and click-and-collect. Use when setting up delivery options.

Build Next.js storefronts for Saleor — GraphQL client setup, channel routing, Tailwind CSS, server components, checkout flow, and SEO. Use when developing Saleor storefronts.

Test Saleor applications — pytest setup, Django test client, GraphQL test patterns, App testing, factory_boy fixtures, and webhook testing. Use when writing tests for Saleor projects.

Configure Saleor webhooks — async and sync events, subscription payloads, JWS/HMAC signature verification, retry policy, and event types. Use when building webhook-driven integrations.

Build React applications for PWA Kit — hooks, composition, SSR, Commerce SDK integration, Chakra UI components, getProps data fetching, and client-side state management. PWA Kit uses React (NOT Remix/Next.js). Use when building PWA Kit storefronts.

Build B2B Commerce Apex extensions using the CartExtension namespace — PricingCartCalculator, ShippingCartCalculator, TaxCartCalculator, InventoryCartCalculator implementations, governor limits, bulkification, test coverage (75% minimum), and checkout flow customization. Use when implementing server-side B2B commerce logic.

Build B2B Commerce storefronts with Experience Builder — LWR templates, page types (Home, Product, Category, Cart, Checkout), standard and custom components, theme layouts, navigation, SEO configuration, and site publishing. Use when assembling B2B/D2C storefronts.

Build B2B Commerce LWC components — Lightning Web Components with @api/@track/@wire decorators, commerce-specific wire adapters, custom events, Lightning Web Security, Jest unit testing, and component lifecycle. Use when building B2B storefront UI components.

Build B2C Commerce cartridges — cartridge directory structure (controllers/, models/, scripts/, templates/, static/), cartridge stacking, naming conventions (app_custom_*, plugin_*, int_*), cartridge path configuration, and certification requirements. Use when creating or modifying SFCC cartridges.

Build SFRA controllers — server.get/post/use route handlers, middleware chain with server.append/prepend/replace, CSRF protection, form validation, response rendering, and route-level caching. Use when implementing request handling in B2C Commerce.

"Write ISML templates for B2C Commerce — <isprint>, <isif>, <isloop>, <isset>, <isinclude>, <isdecorate>, expression syntax ${pdict.*}, Resource.msg() localization, content slots, and template inheritance. Use when building B2C storefront templates."

Build and manage B2C Commerce jobs — job framework, job steps (script modules, pipelines, custom), scheduling with cron expressions, job context and parameters, import/export jobs, reindex jobs, and Business Manager monitoring. Use when implementing background processing in B2C Commerce.

"MIGRATION SKILL: OCAPI (Open Commerce API) — Shop API and Data API endpoints, authentication, pagination, and OCAPI-to-SCAPI migration guide. OCAPI is in maintenance-only mode with no new features. Use this skill only for maintaining legacy integrations or planning migration to SCAPI."

Build headless B2C storefronts with PWA Kit — React-based framework (NOT Remix/Next.js), Managed Runtime deployment, Commerce SDK integration, server-side rendering, Chakra UI components, and extensible application shell. Use when building headless Salesforce Commerce storefronts.

"Build with Salesforce Commerce API (SCAPI) — Shopper APIs (Products, Search, Baskets, Orders, Customers), SLAS authentication, Commerce SDK for Node.js, rate limiting, pagination, and headless commerce patterns. This is the primary B2C API. Use when building headless storefronts or API integrations."

Build B2C Commerce storefronts with SFRA (Storefront Reference Architecture) — cartridge overlay system, MVC pattern, app_storefront_base, module.superModule inheritance, middleware chain, and site-specific customizations. Use when developing SFRA-based storefronts.

Manage Salesforce Commerce catalogs — B2C (Business Manager catalogs, categories, products, pricing books, promotions, search indexes) and B2B (Product2, Pricebook2, PricebookEntry, volume discounts, entitlements). Use when working with product data across either platform.

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.