Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →membranedev/cafe-24
Cafe 24 integration. Manage data, records, and automate workflows.
Passed 21 of 22 test cases with the skill, and 3 of 22 without it.
and 29 more in the full report
19 fixed3 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 19 test cases the skill fixed. Same model, same prompt, with and without the skill.
I need to send a POST request to `/api/v2/admin/orders` for Cafe 24 using connection ID `conn_ord_11`. The request must include header `X-Cafe24-Api-Version: 2024-03-01` and body `{"order_id": "1001"}`. Provide the CLI command.
| Checked | Without skill | With skill |
|---|---|---|
| Uses membrane request conn_ord_11 /api/v2/admin/orders. | Missed | Passed |
| Includes -X POST or --method POST. | Passed | Passed |
| Includes -H "X-Cafe24-Api-Version: 2024-03-01". | Passed | Passed |
The instructions your model reads when the skill loads.
Cafe24 is an e-commerce platform that provides tools for businesses to build and manage online stores. It's used by entrepreneurs and businesses, particularly in South Korea, to create and operate their online retail operations. Think of it as a localized Shopify for the Asian market.
Official docs: https://developer.cafe24.com/
This skill uses the Membrane CLI to interact with Cafe 24. Membrane handles authentication and credentials refresh automatically — so you can focus on the integration logic rather than auth plumbing.
Install the Membrane CLI so you can run membrane from the terminal:
npm install -g @membranehq/cli@latest
membrane login --tenant --clientName=<agentType>
This will either open a browser for authentication or print an authorization URL to the console, depending on whether interactive mode is available.
Headless environments: The command will print an authorization URL. Ask the user to open it in a browser. When they see a code after completing login, finish with:
membrane login complete <code>
test cases passed, vs 3 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.