- Home
- Skills
- Frontend & Web Apps
- Slop Design — AI UI & Frontend Contract
Works with the AI Agents you already use
Slop Design — AI UI & Frontend Contract
Reference contract of 245 AI slop patterns and engineering rules for bespoke, high-end UI generation.
$19
Slop Design — AI UI & Frontend Contract
Example session with this skill installed
Load slop-design and generate a modern dashboard analytics screen. Enforce the construction contract, OKLCH color tokens, and run the pre-emit delivery gate before emitting code.
- Read your context and instructions
- Compiled the slop design
Summary
Constructed a bespoke dashboard analytics view following the slop-design construction contract. Avoided generic card-grid tropes, applied custom OKLCH semantic tokens, physics-tuned motion easings, and verified all 38 rules at the Pre-Emit Delivery Gate.
Pre-Emit Gate Verification
| Stage | Check | Result | Design Choice |
|---|---|---|---|
| Archetype | X5 / L10 Avoided | PASS | Asymmetric layout with prominent chart anchor (no 50/50 split) |
| Color | C7–C10 OKLCH Rules | PASS | Tinted dark slate neutrals (no pure #000000 or zero-chroma grey) |
| Motion | M9–M14 Physics Tokens | PASS | Explicit opacity, transform only; no blanket transition: all |
| Source | E1–E58 Code Contract | PASS | Clean React state, AbortController in effects, strictly typed |
| Gate Status | Delivery Gate | PASSED | Ready for production emit |
Connects securely to your tools. The creator never sees your data.
About this skill
Design and build high-fidelity UI that avoids the predictable tropes of AI-generated templates. This skill provides a reference catalog of 245 design and engineering anti-patterns across 18 categories, ranging from visual layout and typography to React state management and security hygiene. It serves as a comprehensive knowledge base for AI agents to consult before and during the frontend development process.
What it does
- Anti-pattern detection provides a documented catalog of 245 visual, typographic, and engineering defects to avoid.
- Workflow enforcement outlines a 5-stage construction process from initial brief to a blocking pre-emit gate.
- Luxury domain specialized includes a specific H-series contract for ultra-luxury hospitality and editorial web design.
- Source-code auditing targets engineering slop in React, Next.js, and TypeScript, including state leaks and fetch races.
- Token standardization provides specific rules for OKLCH color palettes, motion budgets, and modular type scales.
How it works
- Initialize the project context by creating the
.slop-trackerdirectory structure for design briefs and logs. - Consult Reference by loading the pattern catalog to identify forbidden tropes like "AI capsule badges" or "derived state."
- Execute Workflow following the stages in
design-spec.md, starting with a purpose-driven brief before writing code. - Pass Gate by running the Stage 5 checklist to block delivery if craftsmanship or security requirements are not met.
Frameworks & tools
This skill is optimized for React, Next.js, TypeScript, and Tailwind CSS. It includes specialized grep signatures for code auditing and a Python-based WCAG contrast checker.
Why this beats prompting it yourself
Generic prompts often result in "SaaS-default" layouts and boilerplate code. This skill provides specific, stable IDs for hundreds of niche defects that simple instructions miss, ensuring the output feels bespoke and technically sound.
Use cases
- Generating React components that don't look like Bootstrap or v0 defaults.
- Building editorial-grade websites for luxury hospitality or high-end brands.
- Reviewing AI-generated PRs for "Engineering Slop" like uncleaned effects or
anytypes. - Hardening frontend code against layout shifts and accessibility failures.
Known limitations
This is a reference skill only. It does not perform automated code refactoring or scan files autonomously without the companion slop-audit skill.
Reference only. Does not auto-fix code. Requires manual execution of the Stage 5 gate. Optimized for React/Next.js/Tailwind stacks.
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
Pure knowledge base and design specification. No network calls, no telemetry, and no external code execution. I guarentee you , you will love this skill