orcaqubits/acp-product-feed
dist/codex/acp-agentic-commerce/skills/acp-product-feed/SKILL.md
Build product feed generation and submission for ACP. Use when implementing product catalog export, feed formatting (CSV/JSON/XML/TSV), feed validation, and push-based catalog sync to the agent platform.
$ install --global
skillsauthnpx skillsauth add orcaqubits/agentic-commerce-claude-plugins acp-product-feedInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: May 9, 2026, 6:50 AM173.9s1 file scanned
SKILL.md
- name:
- acp-product-feed
- description:
- >
ACP Product Feed
Before writing code
Fetch live docs: Fetch https://developers.openai.com/commerce/product-feeds/spec for the exact feed field specifications, supported formats, required vs optional fields, and submission endpoint.
Also web-search site:developers.openai.com commerce feed for any updates to feed requirements.
Conceptual Architecture
What Product Feeds Do
ACP uses a push model for product discovery. Merchants generate structured product data files and push them to the agent platform's ingestion endpoint. The agent (ChatGPT) indexes this data to surface products in conversational shopping.
Feed Formats
Four supported formats:
- CSV — Comma-separated, with header row
- JSON — Array of product objects
- XML — Structured product elements
- TSV — Tab-separated, with header row
Feed Fields (~40+ fields across 15 categories)
Key field categories include:
- Identification — Product ID, title, brand, SKU, GTIN/UPC/EAN
- Pricing — Price, sale price, currency, price effective dates
- Media — Image URLs, additional images, product page URL
- Fulfillment — Availability, shipping info, condition, fulfillment type
- Attributes — Category, description, color, size, material, gender, age group, custom attributes
- Eligibility —
is_eligible_search(controls ChatGPT search visibility),is_eligible_checkout(controls ChatGPT checkout visibility) — both are critical required fields - Seller Info —
seller_name,seller_url,target_countries,store_country— required fields identifying the merchant and market
Refresh Frequency
Feeds can be refreshed up to every 15 minutes. Merchants should refresh more frequently for volatile data (pricing, stock) and less frequently for static data (descriptions, images).
Key Concepts
- Product variants — Size/color/material variants are separate feed entries linked by a group ID
- Availability signals —
in_stock,out_of_stock,pre_order,backorder,unknown - Price formatting — Check feed spec for exact format (may differ from checkout's integer minor units)
- Image requirements — Minimum resolution, accepted formats, primary vs additional images
- Category taxonomy — Standard category paths for product classification
Use Cases
- E-commerce catalog export
- Shopify/WooCommerce product sync
- Multi-channel product distribution
- Inventory-aware feed generation (suppress out-of-stock)
- Scheduled feed refresh pipelines
Best Practices
- Validate feed against the spec schema before submission
- Include GTIN/UPC when available for better product matching
- Use high-quality primary images (min resolution per spec)
- Set appropriate refresh intervals based on data volatility
- Handle feed generation errors gracefully — partial feeds are better than no feeds
- Log submission responses for debugging
Fetch the feed spec for exact field names, types, constraints, validation rules, and the submission endpoint URL before implementing.
Related Skills
orcaqubits/spree-headless-storefront
development
VerifiedTrustedCommunity
Build with Spree's headless Next.js storefront — the official `spree/storefront` repo (Next.js 16 App Router with Server Actions and Turbopack, React 19 Server Components, Tailwind CSS 4, TypeScript 5, `@spree/sdk`, Sentry), server-only auth (httpOnly JWT cookies + publishable key), MeiliSearch faceted catalog, one-page checkout with Apple/Google Pay/Klarna/Affirm/SEPA, multi-region market routing, GA4 + JSON-LD SEO, and Vercel/Docker deployment. Use when forking or customizing the storefront, or evaluating headless adoption.
27SKILL.mdUpdated May 14, 2026
orcaqubits/spree-extensions
tools
VerifiedTrustedCommunity
Build Spree extensions as Rails engines — gem scaffolding, `bin/rails g spree:extension`, mounting routes/migrations/assets, the modern `prepend` decorator pattern (`*_decorator.rb` with `self.prepended(base)`), generators (`spree:model_decorator`, `spree:controller_decorator`), the four customization surfaces in preference order (Events > Webhooks > Dependencies > Decorators), Spree::Dependencies for swapping service objects, gem release/versioning, and the deprecated Deface engine. Use when building a reusable Spree extension or adding non-trivial customization to an app.
27SKILL.mdUpdated May 14, 2026
orcaqubits/spree-events-webhooks
development
VerifiedTrustedCommunity
Build with Spree's event bus and Webhooks 2.0 — `Spree::Events` publication, `Spree::Subscriber` DSL with `subscribes_to` and `on`, wildcard matching, lifecycle events (`{model}.created/.updated/.deleted` via `publishes_lifecycle_events`), the canonical event catalog (order.*, payment.*, shipment.*, product.*), Webhooks 2.0 endpoints, HMAC-SHA256 signing (`X-Spree-Webhook-Signature`), exponential-backoff retries, and Sidekiq job orchestration. Use when wiring event-driven business logic, building webhook consumers, or replacing ActiveSupport callback chains.
27SKILL.mdUpdated May 14, 2026
orcaqubits/spree-dev-patterns
tools
VerifiedTrustedCommunity
Cross-cutting Spree development patterns — the customization preference hierarchy (Events > Webhooks > Dependencies > Decorators), `Spree::Dependencies` service-object swapping, the `_decorator.rb` + `prepend` + `self.prepended` idiom, idempotent subscribers and webhook receivers, multi-store scoping discipline, prefixed IDs, calculator polymorphism (shipping/promotion/tax share the base), service-object composition with `dry-monads` or simple results, why to avoid `class_eval` reopening and Deface, and Spree-on-Rails idioms (Hotwire/Turbo Stimulus, ActiveStorage, Action Cable, Sidekiq). Use when designing the architecture of a Spree extension or solving cross-cutting concerns.
27SKILL.mdUpdated May 14, 2026