Deslop Ui logo

Deslop Ui

Organization
KyaniteLabs
deslop-ui

Anti-slop UI review for generated or generic frontend work. Use after LLM UI output, or for requests to remove AI tells: purple gradients, pill CTAs, default type, centered heroes, three-card grids, glassmorphism, and template sameness.

Overview

PublisherKyaniteLabs
Repositorytastecheck
Skill namedeslop-ui
Stars
10
Forks
7
Bundled files
5
LicenseMIT
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by KyaniteLabs on GitHub. Read the source before you install it.

Installation

Install the Deslop Ui AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/KyaniteLabs/tastecheck/tree/main/skills/deslop-ui
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/KyaniteLabs/tastecheck.git /tmp/tastecheck
mkdir -p .claude/skills
cp -r /tmp/tastecheck/skills/deslop-ui .claude/skills/deslop-ui
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Deslop Ui in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Deslop Ui on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Deslop Ui is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Deslop UI

Slop is predictable, uncommitted design, not merely ugly design. Audit surface, structure, and voice against the brief; repair with a specific, verifiable choice.

Repair order and evidence contract

  1. Establish brief, preserved signals, and artifact; separate surface, structural, and verbal findings.
  2. Cite selector, section, phrase, screenshot, or browser observation; assign P0–P3.
  3. Choose a brief-bound direction, prescribe repairs, and reinspect the same views.

n/a requires an absent subject. Stop before changing a coherent brief-supported brand choice; ask for direction when brief or acceptance criteria are absent.

Diagnose cause, then tell

Make two passes: intent (job, audience, hierarchy, retained signals, signature) and behavior (first view, transitions, narrow view; trace code to selector/token or screenshot geometry). Test whether a neutral replacement changes meaning or performance. Preserve a documented functional pill, gradient, table, or system font; repair implementation, not role.

Rank P0 meaning/interaction/accessibility/fact, P1 direction/hierarchy, P2 repeated default, then P3 polish. Every P0–P2 packet names subject, observation+brief, mechanism, preserved signal, concrete replacement+owner, and after-state observation (including narrow view). Make one causal structural repair when the skeleton is generic.

Fast audit and self-check

Render before acting; grep is only a lead. Check these detector/decision pairs:

PlaneDetectorRequired repair decision
surfaceunsupported purple/white gradient, default neutral tokens, equal-weight palettedominant field, purposeful accent, semantic tokens, contrast
type/shapeunexamined default type, timid hierarchy, pill CTA, universal radius/shadowtype stance and role-based scale/radius/elevation
structurecentered hero → one CTA → equal cards, uniform section rhythmreplacement topology, lead/supporting evidence, narrow reading order
decoration/functiondefault glass/blobs/emoji/gradient text, static forms, placeholder copybrief-supported atmosphere or none; route behavior/copy to the owning skill

Every finding needs subject, P0–P3, observed evidence, preserved signal, replacement, and after-state proof. Verify surface, structural stack/rhythm, and verbal claims (hand factual prose to humanize-copy). A named direction states aesthetic, dominant field/accent job, type stance, and signature move. Re-run original views.

Reference files

  • references/anti-patterns.md — full detector catalog and fixes.
  • references/structural-tells.md — structural audit and dated attractors.
  • references/design-direction.md — positive direction method.
  • references/decision-records.md — novel-case ADR rules.

How to deliver

Deliver prioritized repairs and named direction; state what changed, why, what survives, and after-state proof. Respect existing tokens; pair with web-typography, color-system, and micro-motion as needed.

Contract (generated)

Canonical detail: contract.json.

  • Route: A rendered or coded interface feels generic and needs a structural, visual, and verbal anti-slop audit. (+1 in contract.json); avoid: The task is a greenfield aesthetic interview before a page exists. (+1 in contract.json)
  • Exclude: Do not replace a coherent brand system merely because it is not your preference. (+2 in contract.json)
  • Stop / handoff: Stop before changing a coherent branded choice that is supported by the brief. (+2 in contract.json); receives [design-system-interview, improve-existing-website, art-direction, responsive-layout] -> sends [web-typography, color-system, humanize-copy, tastecheck-pass, a11y-pass, empty-states, form-ux, micro-motion]
  • Output: prioritized anti-slop repair specification and committed direction
  • Evidence: table_with_evidence with status, reason, remediation, evidence, provenance.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Deslop Ui AI skill do?

Anti-slop UI review for generated or generic frontend work. Use after LLM UI output, or for requests to remove AI tells: purple gradients, pill CTAs, default type, centered heroes, three-card grids, glassmorphism, and template sameness.

Why use Deslop Ui on TypingMind?

Because you install it once and use it with any model. Deslop Ui is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Deslop Ui in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/KyaniteLabs/tastecheck/tree/main/skills/deslop-ui. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Deslop Ui?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Deslop Ui?

As many as you like. As long as a model supports skills, you can use Deslop Ui with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Deslop Ui AI skill free?

Yes. It is published on GitHub by KyaniteLabs under the MIT license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇