Stripe App Setup logo

Stripe App Setup

OrganizationPopular
vellum-ai
stripe-app-setup

Create and configure a Stripe restricted API key so the assistant can manage payments, subscriptions, and customers under its own scoped identity

Overview

Publishervellum-ai
Repositoryvellum-assistant
Skill namestripe-app-setup
Stars
1.4K
Forks
208
Bundled files
3
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 3 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by vellum-ai on GitHub. Read the source before you install it.

Installation

Install the Stripe App Setup AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/vellum-ai/vellum-assistant/tree/main/skills/stripe-app-setup
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/vellum-ai/vellum-assistant.git /tmp/vellum-assistant
mkdir -p .claude/skills
cp -r /tmp/vellum-assistant/skills/stripe-app-setup .claude/skills/stripe-app-setup
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Stripe App Setup in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Stripe App Setup on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Stripe App Setup is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Overview

Set up a Stripe restricted API key so the assistant can interact with a Stripe account — querying customers, managing subscriptions, processing refunds, reading invoices, and monitoring payments as a scoped entity.

Restricted API keys (RAKs) limit access to only the specific Stripe resources the assistant needs, reducing the blast radius if a key is ever compromised. RAKs are drop-in replacements for secret keys — they work identically with every Stripe API.

Total manual effort: ~2 interactions — create the restricted key in the Dashboard and hand it over via secure prompt.

Prerequisites

  • User must have admin or developer access to the Stripe account
  • User must be logged into the Stripe Dashboard in their browser

Setup Flow

Step 0: Check Existing Configuration

Before starting, check whether Stripe is already configured by running the check script:

bash
bun skills/stripe-app-setup/scripts/check-config.ts

The script outputs JSON: { "configured": boolean, "details": string }.

  • If configured is true — Stripe is already set up. Offer to verify the connection or reconfigure.
  • If configured is false — continue to Step 1.

Step 1: Create the Restricted API Key

Direct the user to create a new restricted key:

Open https://dashboard.stripe.com/apikeys and click + Create restricted key.

When Stripe asks "How will you use this API key?", select Providing this key to another website and enter the assistant's name.

Guide them through the permissions. A good default for managing payments, customers, and subscriptions:

ResourceAccess Level
CustomersRead & Write
ChargesRead & Write
InvoicesRead & Write
Payment IntentsRead & Write
SubscriptionsRead & Write
ProductsRead
PricesRead
BalanceRead
DisputesRead
PayoutsRead

Adjust permissions up or down based on the user's needs. The principle of least privilege applies — only request what the assistant will actually use. For read-only monitoring, set everything to Read.

Click Create key when done.

Important: The restricted key is revealed only once after creation. The user must copy it immediately.

Step 2: Collect the API Key

After the user copies their restricted key, run the store script to securely collect and store it:

bash
bun skills/stripe-app-setup/scripts/store-key.ts

The script opens a secure credential prompt in the user's app, stores the key in the encrypted vault with the correct injection templates for api.stripe.com, and exits. If it exits 0, the key is stored. Exit code 130 means the user cancelled the prompt — nothing was stored; that's a valid choice, not an error, so ask whether they'd like to try again rather than treating it as a failure. Any other non-zero exit is a real failure.

Step 3: Verify

After storing the key, verify the connection:

bash
curl -s https://api.stripe.com/v1/balance

Run with network_mode: "proxied" and the stripe credential. A successful response returns the account's balance object with available and pending arrays.

If the response returns a 401, the key is invalid or revoked. If 403, the key doesn't have the required permissions for the endpoint.

Step 4: Report Success

Summarize with the completed checklist:

"Setup complete! ✅ Restricted API key configured ✅ Connection verified — balance accessible

Key type: Restricted API key (rk_...) Permissions: {list the configured permission levels} Key management: https://dashboard.stripe.com/apikeys"

API Usage

After setup, use bash with curl to call the Stripe API. The credential proxy injects the Authorization: Bearer header automatically when using network_mode: "proxied" with the stripe credential.

Common API Calls

List customers:

bash
curl -s https://api.stripe.com/v1/customers?limit=10

Create a customer:

bash
curl -s https://api.stripe.com/v1/customers \
  -d "email=customer@example.com" \
  -d "name=Jane Doe"

List recent payments:

bash
curl -s https://api.stripe.com/v1/payment_intents?limit=10

List subscriptions:

bash
curl -s https://api.stripe.com/v1/subscriptions?limit=10

Retrieve an invoice:

bash
curl -s https://api.stripe.com/v1/invoices/{invoice_id}

Issue a refund:

bash
curl -s https://api.stripe.com/v1/refunds \
  -d "payment_intent={pi_id}"

All calls use network_mode: "proxied" with the stripe credential.

Pagination

Stripe uses cursor-based pagination. Use starting_after with the last object's ID to page forward:

bash
curl -s "https://api.stripe.com/v1/customers?limit=100&starting_after=cus_lastId"

Sandbox vs Live

Stripe has separate sandbox and live modes with separate API keys. Keys starting with rk_test_ are sandbox keys; rk_live_ are live keys. The assistant uses whichever key the user provides.

Credential Reference

All credentials are stored under service: stripe:

FieldDescriptionWhen Set
api_keyRestricted API key (rk_live_ or rk_test_)Step 2

Troubleshooting

401 Unauthorized

The API key is invalid or has been revoked. Create a new restricted key in the Dashboard and re-run Step 2.

403 Forbidden / "Insufficient permissions"

The restricted key doesn't have the required permission for the API endpoint being called. Edit the key's permissions in the Dashboard at https://dashboard.stripe.com/apikeys (click the overflow menu → Edit key).

"No such customer" / "No such subscription"

Sandbox and live mode are separate environments. A sandbox key can't access live mode objects and vice versa. Confirm the key mode matches the data being queried.

Important Notes

  • Restricted API keys do not expire automatically. They remain valid until revoked in the Dashboard.
  • Live mode restricted keys can only be revealed once — the user must copy immediately after creation.
  • Always confirm with the user before performing write operations (creating charges, issuing refunds, modifying subscriptions).
  • Stripe rate limits API calls — standard limit is 100 read operations/second and 100 write operations/second per key.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Stripe App Setup AI skill do?

Create and configure a Stripe restricted API key so the assistant can manage payments, subscriptions, and customers under its own scoped identity

Why use Stripe App Setup on TypingMind?

Because you install it once and use it with any model. Stripe App Setup is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Stripe App Setup in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/vellum-ai/vellum-assistant/tree/main/skills/stripe-app-setup. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Stripe App Setup?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Stripe App Setup?

As many as you like. As long as a model supports skills, you can use Stripe App Setup with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Stripe App Setup AI skill free?

Yes. It is published on GitHub by vellum-ai under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇