Install any skill in seconds. Free to start, no credit card required.
Get Started Free →surgepix/surgepix-generate-logo
Generate a brand logo (PNG, transparent by default) via SurgePix API and return a download URL.
Passed 2 of 8 test cases with the skill, and 1 of 8 without it.
and 1 more in the full report
3 fixed3 passed either way17 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 3 test cases the skill fixed. Same model, same prompt, with and without the skill.
The command executed with --nowait true and returned {"ok":true,"taskId":"sp_task_abc123"}. What information should be communicated back to the user?
| Checked | Without skill | With skill |
|---|---|---|
| Communicates the task ID sp_task_abc123 to the user. | Passed | Passed |
| Directs the user to query task completion using surgepix-query-task. | Missed | Passed |
The instructions your model reads when the skill loads.
Generate one brand logo image from a brand/product name, optional design notes and reference images. Default output is transparent background.
Match the user's conversation language for --prompt design notes — unless the user explicitly requests another language.
| User writes in | Write --prompt in |
|---|---|
| English | English |
| 中文 | 中文 |
| 日本語 | 日本語 |
SURGEPIX_API_KEY and SURGEPIX_BASE_URL configured (see Step 0)| Action | Description |
|---|---|
| Generate logo | Create one logo PNG from brand name (+ optional prompt/size/reference) |
| Upload references | Local reference paths are uploaded automatically |
| Check task status | With --nowait true, resolve via surgepix-query-task |
| Download result | Return the download URL from task result |
The script always submits asynchronously to the API (
noWait=true). CLI--nowaitcontrols local behavior:
--nowait false(default) — poll untilsucceeded/failedand returndownload--nowait true— returntaskIdimmediately; use surgepix-query-task later
test cases passed, vs 1 / 8 without
More skills from the same source and nearby in the registry, with their headline benchmark lift.