Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →affitor/submit-program
Research an affiliate program and create a verified listing for openaffiliate.dev.
Passed 18 of 21 test cases with the skill, and 5 of 21 without it.
and 26 more in the full report
15 fixed4 passed either way2 still failing1 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 15 test cases the skill fixed. Same model, same prompt, with and without the skill.
Could you research the Notion affiliate offer and generate a directory-ready program breakdown? I need structured key details like commission type/rate, cookie lifespan, tags, and verified source references at the top. Follow that with a comprehensive report covering the product value proposition, key highlights for affiliates, pricing tier commission matrix, target creator segments, projected monthly/annual income across traffic tiers, conversion factors, and potential downside risks.
| Checked | Without skill | With skill |
|---|---|---|
| Standardizes the reward type field using the enum cps_recurring. | Missed | Passed |
| Formats traffic projection estimates using conservative assumptions of 2% click-through rate. | Missed | Passed |
| Contains the subsection header ### Honest Limitations listing real program drawbacks. | Missed | Passed |
The instructions your model reads when the skill loads.
Research an affiliate program from official sources and produce a verified, publish-ready listing for openaffiliate.dev. Every number comes from the program's official affiliate page, network page, or pricing page. No guessing.
This skill belongs to Stage S1: Research
{
program_name: string # (required) Name of the affiliate program, e.g., "HeyGen"
affiliate_link: string # (optional) User's affiliate link to include in the listing
niche: string # (optional) Category hint, e.g., "AI video", "email marketing"
}
Confirm the program name with the user. Ask:
If the user says "just list it" or provides enough context, skip questions and proceed.
test cases passed, vs 5 / 21 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.