skills/ship-faster/skills/stripe/SKILL.md
Billing and payment operations for Stripe: customers, products, prices, invoices, payment links, subscriptions, refunds, disputes, balance. Triggers: create customer, create product, create invoice, generate payment link, query transactions, process refunds, manage subscriptions, view disputes, check balance. Money operations require confirmation. MCP is optional — works with Dashboard/CLI too.
npx skillsauth add enuno/claude-command-and-control stripeInstall 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.
Execute billing and payment operations on Stripe: customers, products, invoices, payment links, subscriptions, refunds, and disputes.
MCP is optional. This skill works with MCP (auto), Stripe CLI, or Dashboard. See BACKENDS.md for execution options.
| Operation Type | Rule | |----------------|------| | Read (list, get, search) | Execute directly | | Create (customer, product, price, invoice) | Check for duplicates first | | Money (refund, subscription cancel/update, dispute) | Display details → Await confirmation → Execute | | Mode | Test mode by default. Live requires explicit "live mode" + double confirmation |
Before executing these operations:
| Action | Risk |
|--------|------|
| create_refund | Money leaves account |
| cancel_subscription | Revenue loss |
| update_subscription | Contract change |
| update_dispute | Legal implications |
Example confirmation prompt:
About to execute refund:
- PaymentIntent: pi_xxx
- Amount: $50.00 (full amount)
- Reason: requested_by_customer
Reply "confirm" to proceed, or "cancel" to abort.
1. Search/list to check if customer exists (by email)
2. If not exists, create_customer(name, email, metadata)
3. Return cus_xxx + key info
1. List products to check if already exists
2. create_product(name, description)
3. create_price(product=prod_xxx, unit_amount=cents, currency)
4. Return prod_xxx + price_xxx
1. Confirm customer ID (list_customers if unknown)
2. create_invoice(customer=cus_xxx, collection_method, days_until_due)
3. create_invoice_item(invoice=inv_xxx, price=price_xxx, quantity)
4. finalize_invoice(invoice=inv_xxx)
5. Return inv_xxx + hosted_invoice_url
1. Confirm price ID (list_prices if unknown)
2. create_payment_link(line_items=[{price, quantity}])
3. Return payment link URL
1. list_payment_intents to find target payment
2. Display pi_xxx + amount + customer info
3. Request user confirmation
4. create_refund(payment_intent=pi_xxx, amount?, reason)
5. Return re_xxx + status
1. list_subscriptions(customer=cus_xxx) to find target
2. Display sub_xxx + status + next billing date
3. Ask: cancel immediately or at period end?
4. After confirmation, cancel_subscription(subscription=sub_xxx)
5. Return cancellation result
These operations are NOT available via standard tools:
For these, use Dashboard or API directly.
When integrating into multi-step workflows:
runs/<workflow>/active/<run_id>/
├── proposal.md # Requirements / objective
├── context.json # Known IDs (customer, invoice, etc.)
├── tasks.md # Checklist + approval gate
├── evidence/stripe-actions.md # Operations to execute (money ops written here first)
├── evidence/receipt.md # Results + object IDs
└── logs/events.jsonl # Optional tool call summary (no sensitive data)
| Situation | Action | |-----------|--------| | Object doesn't exist | Search to find correct ID | | Parameter error | Check documentation for correct format | | Insufficient permissions | Check API key scope | | Network error | Retry or check connection |
tools
MemPalace local-first AI memory system. Use when setting up persistent memory for Claude Code sessions, mining project files or conversation transcripts, querying past context, configuring MCP tools, managing the knowledge graph, or troubleshooting palace operations.
tools
LangSmith Python SDK — trace, evaluate, and monitor LLM applications. Covers @traceable decorator, trace context manager, Client API, evaluate() / aevaluate(), comparative evaluation, custom evaluators, dataset management, prompt caching, ASGI middleware, and pytest plugin.
development
LangGraph (Python) — build stateful, controllable agent graphs with checkpointing, streaming, persistence, interrupts, fault tolerance, and durable execution. Covers both Graph API (StateGraph) and Functional API (@entrypoint/@task).
development
LangGraph Graph API (Python) — build explicit DAG agent workflows with StateGraph, typed state, nodes, edges, Command routing, Send fan-out, checkpointers, interrupts, and streaming. Use when you need explicit control flow and graph topology.