A design cleanup process for interfaces that look generic or automatically generated. It checks spacing, color, icons, wording, typography, layout, details, visuals, and motion, then applies a structured redesign.

Use it to audit and revise an AI-generated or otherwise generic web interface.

It helps remove common visual patterns such as excessive gradients, glowing cards, emoji labels, and exaggerated copy. This makes the interface more deliberate without relying on a single generic style.

unslop — Skill for Claude Code by oyi77/1ai-skills

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add oyi77/1ai-skills --skill unslop

Clone the repo

git clone --depth 1 https://github.com/oyi77/1ai-skills

Made for: Claude Code.

Or install 1ai-skills, the plugin that ships this one along with the rest of its 240 skills, 4 commands.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/oyi77/1ai-skills/unslop/github.svg)](https://agentmods.dev/skills/oyi77/1ai-skills/unslop)

Your own site

<a href="https://agentmods.dev/skills/oyi77/1ai-skills/unslop"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/unslop/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/oyi77/1ai-skills/unslop"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/unslop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,755 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00071	$0.01755
Opus 5.5	$0.00028	$0.00702
Sonnet 5.5	$0.00014	$0.00351
Haiku 4.5	$0.00007	$0.00176

Measured 2d ago against content hash 211b3e3a5983, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

unslop scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

content/unslop/SKILL.md · 114 lines

How it starts

The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Unslop: Eliminating Vibecoded AI UI

Overview

unslop transforms generic, AI-generated ("vibecoded") interfaces into intentional, character-driven designs. AI models consistently default to a recognizable signature: dark backgrounds with purple/indigo neon gradients, glassmorphism cards with glowing borders, emoji-bulleted feature cards, shouty copy ("Unlock Superhuman 10x Productivity!"), and arbitrary spacing.

This skill audits the screen for slop markers, anchors a distinctive visual direction from the product's actual purpose, and applies a disciplined 9-pass redline review in order: Spacing → Color → Icons → Copy → Type → Layout → Details → Visuals → Motion.

Attribution: Created by Damir Sokolovsky (@heydamir), licensed under CC BY 4.0. Source repository: heydamir/unslop. The upstream skill also ships optional Playwright snapshot and story-video tooling (scripts/snapshot.mjs, scripts/story.mjs) which this port intentionally omits — see When NOT to Use.

When to Use

Trigger phrases:

"unslop", "unslopping", "remove ai slop"
"fix vibecoded ui", "clean up ai interface"
"redline ui review", "make this look less like ai"

Use when:

An AI-generated landing page, dashboard, or component looks generic or stereotypically "AI-built".
Reviewing PRs with excessive purple gradients, neon borders, or floating glassmorphic cards.
Replacing generic placeholder illustrations and blobs with actual product screenshots or functional data displays.
Elevating UI craft before investor demos, product launches, or commercial release.

When NOT to Use

Backend logic, data layer, or API endpoint tasks.
When the codebase already follows a strict, hardened design system (use impeccable or hallmark).
When only fixing a functional bug or accessibility defect without restyling.

Anti-Rationalization Table

Rationalization	Reality
"The purple gradient makes it look modern and high-tech."	Purple neon gradients on dark backgrounds are the universal signature of low-effort AI generation. Real products use restrained palettes derived from their domain.
"Users like emojis in section titles."	Emojis as UI icons look juvenile and amateurish. Use monochrome SVG icon sets (Lucide, Radix, Phosphor) sized consistently at 16–20px.
"Adding glows and borders makes cards pop."	Glowing borders create visual noise and destroy visual hierarchy. Rely on subtle 1px borders, background contrast, or pure whitespace for card separation.
"I should rewrite everything in one big pass."	Changing layout, copy, colors, and typography simultaneously causes regressions. Follow the 9 passes in sequence.

Read the full file on GitHub · 114 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2d ago First seen · 114 lines · 71 tokens per session scan A 211b3e3a5983

Subscribe to this mod's changes

unslop is a skill published in the GitHub repository oyi77/1ai-skills (17 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 1,755 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-11-04.

CSS and styling Design and UX Frontend agent ai-agent ai-automation ai-skills anti-slop automation content design-refactor polish ui-design visual-hierarchy

unslop next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
unslopoyi77/1ai-skills	Skill	17	yesterday	MIT	A	71	Claude Code
empty-statesDragoon0x/product-skills	Skill	4	8mo ago	none	A	49	Claude Code
anti-slop-designsickn33/agentic-awesome-skills	Skill	49k	yesterday	MIT	A	34	Claude Code
proto-bot-getting-startedmakecindy/cindy	Skill	9.3k	yesterday	Apache-2.0	A	43	Claude Code, Codex
proto-bot-opsmakecindy/cindy	Skill	9.3k	yesterday	Apache-2.0	A	38	Claude Code, Codex
web-typographywondelai/skills	Skill	2.6k	4d ago	MIT	A	128	Claude Code, Codex
refactoring-uiwondelai/skills	Skill	2.6k	4d ago	MIT	A	132	Claude Code, Codex