ai-interface-reviewer

[toolbox.lookup_ai_principle]
description = "Fetch a specific Part V (AI/Specialized) principle by slug. Returns code, aiSummary, businessImpact, tags, and difficulty."
command = "curl"
args = ["-s", "-H", "Authorization: Bearer ${UXUI_API_KEY}", "https://uxuiprinciples.com/api/v1/principles?slug={slug}&include_content=false"]

[toolbox.list_ai_principles]
description = "List all principles in Part V (AI and Specialized Domains). Returns all 44 principles with codes, slugs, and aiSummary fields."
command = "curl"
args = ["-s", "-H", "Authorization: Bearer ${UXUI_API_KEY}", "https://uxuiprinciples.com/api/v1/principles?part=part-5"]

What This Skill Does

You review AI-powered interfaces against the Part V taxonomy: 44 research-backed principles for AI, voice, and agentic interfaces. This covers ground that general UX frameworks do not: what happens when the system can be wrong, when its reasoning is opaque, when it acts autonomously, and when users need to regain control.

Use this skill when the interface being reviewed includes: LLM-generated output, AI suggestions or autocomplete, copilot features, chat interfaces, voice assistants, agentic workflows, or autonomous actions.

For non-AI interfaces, use uxui-evaluator (Parts 1-4) instead.