skills/vendix-ai-engine/SKILL.md
High-level AI Engine integration guide for Vendix: choosing the right AI subsystem, creating AI-powered features, and consuming AI Applications. Trigger: When creating AI-powered features, integrating AI Engine into domains, configuring AI providers/apps, or styling AI interaction elements.
npx skillsauth add rzyfront/vendix vendix-ai-engineInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
| Need | Skill |
| --- | --- |
| Core providers, run(), logging, rate limits, costs | vendix-ai-platform-core |
| Chat conversations/widget | vendix-ai-chat |
| SSE/token streaming | vendix-ai-streaming |
| Embeddings, semantic search, RAG | vendix-ai-embeddings-rag |
| ReAct agent and tools | vendix-ai-agent-tools |
| BullMQ async AI jobs | vendix-ai-queue |
| MCP external client gateway | vendix-mcp-server |
| Subscription feature/quota gate | vendix-subscription-gate |
For domain features, prefer AIEngineService.run(appKey, variables, extraMessages?) over hardcoded complete() prompts.
const response = await this.aiEngine.run('product_description_creator', {
name: dto.name,
context: JSON.stringify(productData),
});
if (!response.success) {
throw new VendixHttpException(ErrorCodes.AI_REQUEST_001);
}
run() uses the configured AI Application: prompt template, system prompt, provider config, temperature, max tokens, retry config, rate limit, subscription gate/quota, response sanitization, logging, and cost tracking.
apps/backend/src/domains/store/products/products.service.ts.apps/backend/src/domains/store/orders/purchase-orders/invoice-scanner.service.ts.apps/backend/src/domains/store/ai-chat/ai-chat.service.ts.Applications live in ai_engine_applications and are managed by super-admin backend/controllers.
Current caveats:
metadata, but the current frontend app modal does not expose metadata JSON.metadata.agent_enabled and metadata.rag_enabled drive chat routing, but may need backend/API tooling to set if frontend does not expose it.ai_feature_category exists in schema and drives subscription gate/quota, but current app DTO/frontend do not expose it.isGenerating, aiUsesLeft, and aiLimitReached.sparkles and loader-2.--color-primary-rgb, --color-secondary-rgb) over hardcoded colors.vendix-ai-platform-corevendix-ai-chatvendix-ai-streamingvendix-ai-embeddings-ragvendix-ai-agent-toolsvendix-ai-queuevendix-mcp-serverdevelopment
Mobile app development rules for Vendix Expo/React Native project. Trigger: When editing, creating, or modifying any file under apps/mobile, or when developing mobile-specific features.
development
Feature gating by store subscription state: global store write guard, AI feature gate, Redis feature resolution, quota consumption, frontend paywall interceptor, banner, and subscription UI states. Trigger: When adding feature gates, paywalls, subscription-based access control, protecting store write operations, AI feature gates, or rollout flags.
testing
SaaS subscription billing for Vendix stores: plan pricing, invoices, Wompi platform payments, manual payments, partner commissions, payouts, proration, and dunning. Trigger: When creating SaaS invoices, working with partner rev-share, margin/surcharge pricing, invoice sequence allocation, partner payout batches, subscription payments, manual payments, or dunning flows.
development
Periodic quota counters with Redis, UTC period keys, Lua-based idempotent AI quota consumption, request-id deduplication, and post-success consumption. Trigger: When building quota counters, enforcing monthly/daily feature caps, or reusing AI quota patterns for uploads, emails, exports, or rate-limited features.