- Home
- Skills
- Frontend & Web Apps
- π¨ AI UI De-Templater
More screenshots
Works with the AI Agents you already use
π¨ AI UI De-Templater
Replace generic AI-interface patterns with product-specific visual rules and a bounded implementation plan that preserves working behavior.
$15
π¨ AI UI De-Templater
Example session with this skill installed
Product: incident-response dashboard for small operations teams
Current state: dark gradient hero, four equal glass cards, purple accents, oversized rounded controls
Keep: route structure, data tables, logo, and current feature set
Goal: feel calm, operational, and evidence-led rather than like a generic AI SaaS template
- Read your context and instructions
- Compiled the ai ui de-templater
Diagnosis: equal card weight and decorative gradients hide incident priority; oversized radii make dense operational controls feel promotional.
Rules: use one severity accent at a time, reduce radius on data surfaces, tighten table density, reserve the largest type for the active incident, and replace decorative copy with observable status language.
Patch order: tokens, incident summary, severity states, then secondary cards.
Proof: capture the same incident fixture at 1440px and 375px before and after.
Connects securely to your tools. The creator never sees your data.
About this skill
AI UI De-Templater diagnoses why a functional interface still looks interchangeable with other AI-built products. Supply screenshots or source, the product audience and promise, relevant brand references, and constraints that must remain unchanged. It identifies repeated typography, spacing, color, radius, shadow, icon, density, hierarchy, copy, and layout patterns, then ties each recommended change to the product's actual job. The output includes a generic-pattern diagnosis, a small set of product-specific visual rules, token and component changes, a prioritized patch or patch plan, and a before-and-after comparison board. It avoids novelty for novelty's sake, preserves working behavior and information architecture, and keeps source changes behind approval.
Weak or contradictory product positioning limits how specific the visual system can become. The skill does not create a full identity system, logo, or original illustration library. A visual recommendation remains a design judgment until the owner reviews the comparison in the real product context.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before any payment.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 24 days ago
Permissions
File Scopes
Reads supplied screenshots, frontend source, tokens, styles, and brand constraints; may use a local browser for computed-style and viewport checks; and can write an approved bounded token or component patch plus comparison assets. It does not require environment variables or network access.