메뉴
Detect whether a UI looks AI-generated. Use during design review to run the fingerprint test: identifies the default-theme, gradient, and layout tells that make interfaces read as AI slop, and how to fix each one.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
| name | ai-slop-detection |
| description | Detect whether a UI looks AI-generated. Use during design review to run the fingerprint test: identifies the default-theme, gradient, and layout tells that make interfaces read as AI slop, and how to fix each one. |
The fingerprint test: if you showed your interface to someone and said "AI made this," would they believe you immediately? If yes, the design has failed.
A distinctive interface makes someone ask "how was this made?" — not "which AI made this."
These are the patterns of 2024-2025 AI-generated frontends. Flag ANY of these during review.
Open your UI. Run through this checklist:
AI SLOP AUDIT — [project name]
Color:
[ ] Using cyan/purple/neon gradients?
[ ] Gradient text on headings?
[ ] Pure black or pure white background?
[ ] Dark mode with glowing accents?
Layout:
[ ] Hero metric "dashboard starter kit"?
[ ] Identical card grids?
[ ] Everything centered?
[ ] Cards nested inside cards?
Visuals:
[ ] Glassmorphism / glass cards?
[ ] Generic rounded rectangles with shadows?
[ ] Decorative sparklines?
Typography:
[ ] Inter/Roboto/Arial as only font?
[ ] Random monospace for "dev vibes"?
[ ] Muddy size hierarchy?
Motion:
[ ] Bounce/elastic easing?
[ ] Every button looks the same?
Score: [N] / 15 tells detected
For each tell you find, the fix is usually the opposite:
| AI Slop | Fix |
|---|---|
| Gradient text | Solid color, one accent |
| Everything centered | Left-align body, asymmetric layout |
| Glassmorphism | Solid backgrounds, subtle borders |
| Identical card grid | Vary card sizes, break the grid |
| Inter everywhere | Pick one distinctive typeface |
| Bounce easing | Ease-out or custom cubic-bezier |
| All buttons primary | One primary, rest ghost/text |
| Pure black bg | Tinted dark (#0a0a0f, #0d0f0e) |
AI-generated UIs aren't bad because AI made them. They're bad because they're generic. They look like every other AI output because the models converge on the same "safe" patterns from training data.
The fix isn't "don't use AI for UI." The fix is: generate with AI, then apply taste. Remove the tells. Add the one distinctive choice that makes it yours. One unusual color. One unexpected layout break. One typeface nobody else is using.
Generic is the enemy. Distinctive is the goal.
From AGT Skill Pack — free skills from Agent Dev Thailand
Turn a content creator's AI stack into a factory that sounds like THEM. One voice spine (CONTENT.md) governs every format — FB/blog posts, TikTok carousels, YouTube Shorts, covers — so the output stops smelling like AI and comes out consistent every run. Use when a creator (not a dev) wants to set up Claude Code / an AI agent for content production across channels, or fix output that reads generic, breaks Thai fonts, or looks different every gen. Triggers: "setup AI for content", "brandbook for AI", "AI writes generic", "content creator claude md", "carousel/shorts pipeline", "cover generator".
Keep an AI character's face and voice identical across every clip. Lock the identity ONCE (train a face, lock a voice), then reuse it — never re-generate the face. Use when a recurring AI character drifts between clips, looks like a different person each render, or the brand face is never consistent.
Split AI content into two layers — AI generates raw material (backgrounds, characters, clips), code assembles the deliverable (text, layout, render). Use when AI-generated carousels/cards come out inconsistent, Thai fonts break, or every re-gen is a gamble.
Pump the brakes — clarify before acting. Use when a request is exploratory, mid-decision, or underspecified and the AI is about to edit, commit, hand off, deploy, or run a workflow on a partial picture. Fires on /hold-up or "just talk", "don't action this", "let's think first" — or auto-fires when the AI catches discuss-mode cues right as it was about to take a non-trivial action.
Game-theory review loop for AI drafts: tit-for-tat trust tracking across review rounds. Review depth adapts to the author's track record of addressing feedback, so clean drafts earn lighter reviews and ignored flags trigger deep audits. Use for recurring content or code review loops.
Personal commitments tracker with escalating confrontation. Use when the user wants accountability on recurring commitments, training, habits, or deadlines they keep deferring. Reviews the track record and escalates tone based on the avoidance pattern, not the excuses.