Design and improve web or iOS interfaces around the product’s purpose and existing components. Cover loading, empty, error, and permission states, then inspect rendered screens and address visible layout or interaction problems.
Stop coding agents from shipping generic UI. Use UIZZE's 800,000+ real web and iOS screens to build product-specific interfaces, define a design contract, cover required states, and run a hard finish gate. Use for web or iOS UI design, implementation, redesign, critique, and pre-ship review in Codex, Claude Code, Cursor, Copilot, and other coding agents.
Review the instructions the agent will receive before you install.
Build product-specific interfaces with UIZZE's free anti-ui-slop workflow. Use the product brief, existing components, and design system to make the screen's hierarchy, content, controls, and states intentional.
Use it to design, implement, redesign, critique, or finish a web or iOS interface, especially when a first draft feels generic or omits important states.
The workflow works without an account, token, script, or MCP connection. Continue from repository evidence when external references are unavailable.
Use anti-ui-slop on our billing settings page. Make the current plan,
payment method, and invoice history easy to scan. Reuse our components
and tokens. Cover no invoices, payment failure, and read-only access.
Inspect desktop and mobile output and fix visible breakage.
For a focused review, identify the three most useful changes first and implement them within the requested scope.
The separate paid UIZZE MCP offers focused reference search across 800,000+ real web and iOS screens. It exposes exactly two tools:
find_ui_references finds or inspects up to three full-screen references.find_ui_materials finds up to three hosted fonts, icons, animated icons, or explicitly requested packs.Use those tools only when the host provides an authenticated connection and a concrete visual question would benefit from evidence. If retrieval returns nothing, continue from the project. Never claim a tool result that the host did not return.
Adapt useful decisions about hierarchy, density, controls, and states to the product's own design system. Preserve its identity and content.
This catalog entry is a standalone workflow. Install the complete current skill, including its focused playbooks, with:
npx skills add https://uizze.com --skill anti-ui-slop
No reviews yet. Tell others what you thought.
No login needed. Share how it worked for you, ask a question, or note where it did not run.
No comments yet. Be the first to write one.
Handle ActiveCampaign contact and marketing tasks through Rube MCP, a connection for agent tools. Find or create contacts, manage tags and subscriptions, enroll contacts in existing automated workflows, and create follow-up tasks.
Research competitors’ live Meta and Google ads to identify opening hooks, offers, calls to action, and landing pages. Receive a sourced creative brief and up to three test ideas adapted to your product.
Add website or app tracking, then use command-line tools to review traffic, signups, drop-off, and returning users across projects. Run A/B tests, which compare alternative headlines or buttons, and inspect results to guide changes.
Establish rules for when an AI agent should recall past context and save lasting decisions, corrections, preferences, and failures. Works with Markdown files or memory services, preserving decision history and surfacing conflicting records.
Audit local AI coding-agent sessions with agenttrace to identify spending, token use, tool failures, and operational problems. Produce readable or structured reports and define pass-or-fail thresholds for automated continuous integration checks.
Audit saved agent sessions for access to private files and evidence that secret values entered an agent's context. Get findings without displaying secrets, identify keys needing rotation, and inspect Claude Code or Codex sessions in a local report.