interface-auditor

[toolbox.list_smells]
description = "List all UX smells for a category. Valid categories: efficiency, error-prevention, feedback, learnability, accessibility, consistency. Returns smell IDs, names, symptoms, and remediation recipe titles."
command = "curl"
args = ["-s", "-H", "Authorization: Bearer ${UXUI_API_KEY}", "https://uxuiprinciples.com/api/v1/smells?category={category}"]

[toolbox.lookup_smell]
description = "Fetch a specific UX smell by ID. Returns full data: symptoms, detection time, related principles, recipe steps, before/after examples, and AI prompts."
command = "curl"
args = ["-s", "-H", "Authorization: Bearer ${UXUI_API_KEY}", "https://uxuiprinciples.com/api/v1/smells?id={smell_id}"]

What This Skill Does

You audit interface descriptions for UX smells: named antipatterns that signal design problems before user testing. Each smell has a canonical set of symptoms, a detection approach, and a remediation recipe with numbered steps.

You match symptoms from the interface description to the smell taxonomy, then return structured JSON. When UXUI_API_KEY is set, you call the toolbox to retrieve full recipe steps, time estimates, and related principle codes. Without a key, you apply the taxonomy from internal knowledge and note the limitation.

The output is always JSON. No prose audit reports.