agentleFS
ForgeyClapForgeyClap/Forge-Core/.claude/skills/forge-ecommerce/SKILL.md

forge-ecommerce

Skill2 starsChanged 6 days agoMITView on GitHub

Playbook for web shops: checkout, Shopify, WooCommerce, Etsy (gebruik bij een webwinkel).

  • Reads credentials

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use for: stores and digital products: catalog, cart, inventory correctness, orders and store connectors.

    line 11

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Forge playbook — E-commerce / store / digital products

When to use

  • Use for: stores and digital products: catalog, cart, inventory correctness, orders and store connectors.

Storefront UI defers to forge-website; anything that charges a card defers to forge-payments (this playbook never re-implements card handling). This file owns the commerce-specific concerns: catalog, cart, inventory correctness, orders, and connectors. Forge context: a cashflow or digital-goods shop / Etsy-style shops.

Hard rules

  • Real product/listing data with honest empty states.
  • Oversell-safe inventory.
  • Idempotent order creation.
  • Connectors gated until keys + approval.
  • Money = integer minor units + currency
  • Secrets (store API keys, webhook secrets) in env + .env.example placeholders only.

Full text of every rule: references/hard-rules.md.

Team (conditional)

Lead: build-boss (full store) or integration-boss (connector/sync-only). Specialists: payment-integration (checkout/charge — via forge-payments), database-reviewer (inventory + order schema, race-safety), silent-failure-hunter (a dropped inventory sync or swallowed order error looks like a clean sale), typescript-reviewer / python-reviewer. Storefront: forge-website team (a11y, responsive, real content). Optional: codex-reviewer on the checkout/order/inventory paths.

Skills / commands / MCP

forge-website (storefront, product pages, cart UI), forge-payments (checkout + billing), forge-integration / forge-n8n (connector sync, order-notification automations). Store MCP/SDK docs via Context7 for exact connector APIs. Draft-only for any customer outreach (order emails staged, not blasted — shared with forge-integration).

Fan-out & flow

L2 catalog + cart; L3 catalog + cart + checkout + inventory + orders + a connector; L4 multi-channel store with marketplace sync. Parallel: catalog/product pages ∥ cart logic ∥ inventory service ∥ storefront UI (independent once the product + order schema/contract is fixed). Serial: data model (products, SKUs, minor-units prices, inventory) → catalog → cart → checkout (forge-payments) → atomic inventory decrement → order record → fulfillment/notification.

Domain gates

  • Real catalog data or an honest empty state; no fabricated sales/inventory/metrics.
  • Inventory decrement is atomic/reservation-based and proven oversell-safe under a concurrent-buyer test.
  • Order creation is idempotent (unique idempotency key); a double-submit returns one order.
  • Prices/tax/shipping in integer minor units; no float money math; totals reconcile.
  • Cart → checkout → order → payment flow works end-to-end in test mode (an integration test, not just green units).
  • Connectors inactive until keys + owner approval; no live publish/push/spend performed.
  • Customer-facing emails/messages drafted, not auto-sent, without confirmation; idempotency before any order notification (no duplicate "order confirmed" mails on webhook retry).

Ship-readiness (unique)

Evidence checklist before handoff: references/ship-readiness.md.

Safety, approval and honesty

  • Approval / safety: connectors stay disabled until real keys + owner approval; no live publish, store-push, listing update, price change or spend without explicit owner approval.
  • Approval / safety: customer emails drafted, not auto-sent; store API keys and webhook secrets in env.
  • Honest failure: no fabricated sales, inventory or metrics; an empty catalog shows an honest empty state.
  • Shared gates for every playbook (honesty, owner approval, secrets, reviews): .claude/docs/forge-reference/playbook-template.md.

References

  • references/hard-rules.md — full text of every hard rule.
  • references/ship-readiness.md — full ship-readiness evidence checklist.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.