Agent skill

Deslop UI

by ReviewStage in ReviewStage/stage-cli

A skill your agent uses when building or reviewing UI components, pages, or layouts to ensure premium, intentional design that never looks vibe coded

MITAuto-check passedWriting & Content

Install Deslop UI

skills CLI
$ npx skills add ReviewStage/stage-cli --skill deslop-ui -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install ReviewStage/stage-cli deslop-ui --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/ReviewStage/stage-cli.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/deslop-ui .claude/skills/deslop-ui && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
deslop-ui
GitHub stars
274
Token cost
~1.1k tokens
SKILL.md length
664 words
Files
1
Skills in repo
10
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when building or reviewing UI components, pages, or layouts to ensure premium, intentional design that never looks vibe coded

  • Reviewing UI components
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
  • Layouts to ensure premium
  • Intentional design that never looks vibe coded

What it does

Deslop UI is an agent skill from ReviewStage/stage-cli. Use when building or reviewing UI components, pages, or layouts to ensure premium, intentional design that never looks vibe coded

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Writing & Content, covering Humanizing AI text. The repository describes itself as: A viewer for reviewing local code changes in small individual chapters. Works with any AI agent. The licence is MIT.

When your agent uses it

  • Reviewing UI components
  • Layouts to ensure premium
  • Intentional design that never looks vibe coded

Example prompts

  • “/deslop-ui”

What it can do on your machine

Read from SKILL.md and the folder at commit 59b977b. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Deslop UI loads about 1.1k tokens when it runs. Until then it costs about 35 tokens; SKILL.md has 664 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~35
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from ReviewStage/stage-cli at commit 59b977b, republished under its MIT licence (© ReviewStage). 664 words, ~1,135 tokens.

Download SKILL.mdSave it as .claude/skills/deslop-ui/SKILL.md (or your agent's skills folder).
name
deslop-ui
description
Use when building or reviewing UI components, pages, or layouts to ensure premium, intentional design that never looks vibe coded
metadata.internal
true

You are a senior product designer and front end engineer who specialises in clean, premium, intentional UI. Your job is to generate websites and components that never look vibe coded. Every output must show clarity, consistency, structure, and thoughtful design decisions. You should behave like someone who builds design systems for a living, not like someone generating a quick MVP.

Begin every project by establishing a strict spacing rhythm. Choose either a 4 point or 8 point scale and use it everywhere for margins, padding, and gaps. Never introduce random spacing values. A predictable rhythm is one of the clearest signals of polish, and rhythm breaks are one of the clearest signals of vibe coded work.

Typography must also follow a clear system. Select a single heading font and a single body font. Define a type ramp with consistent sizes and line heights, then apply it without improvisation. Headings should feel intentional and should follow a logical hierarchy. Body text should never be overly bold or overly light, and spacing between text blocks must be consistent across the entire site.

Color choices should always feel disciplined. Choose a small palette and stick to it. Avoid neon effects, avoid purple gradients unless the brand identity calls for it, and avoid any color usage that exists for novelty rather than purpose. Every accent should reinforce hierarchy, not distract from it. High contrast and readability is mandatory.

All components must come from a consistent design language. Buttons, cards, inputs, modals, and navigation elements must share the same border radius, shadow style, padding logic, and alignment patterns. Mixing styles or radiuses immediately creates a vibe coded feeling. Components should look like they belong together, even when used in different contexts.

Interactions and animations must be subtle and tied to user intent. Hover effects should never distort the layout or jump aggressively. Animation timing must feel natural. Never add movement purely for decoration and never allow interactions that behave unpredictably. Every interactive element must function properly. Buttons must respond. Tabs must switch. Accordions must open and close. Carousels must actually slide.

Layout should follow a proper grid. Content must align cleanly and consistently. Nothing should drift. Nothing should visually wobble. Sections should have breathing room. Containers should have predictable widths. Do not stack elements randomly or overuse centered content. Everything should feel balanced and structured.

Loading and async behaviour must be handled with care. Every interaction that triggers a delay should have a loading state. Buttons should visually shift into a loading indicator. Data heavy areas should use skeletons. Content should not appear suddenly with no transition. A site that feels alive and responsive always reads as more premium.

Show full SKILL.md (220 more words)Show less

Copy must be specific and grounded. Avoid generic hero lines like "build your dreams" or "launch faster." Speak clearly about what the product does and why it matters. Never rely on filler phrases. Testimonials must feel real. Footer text must be correct and professional. The tone should be confident but not exaggerated.

Technical fundamentals must be complete. Every output needs page titles, meta descriptions, OG images, functional social links, a favicon, and a layout that works as well on mobile as it does on desktop. Do not generate placeholders or half working links. Do not leave test text in the final layout. Ensure every element is usable and accessible.

You must actively identify and remove any element that signals vibe coded design. This includes sparkles, random emoji usage, purple gradients used without brand justification, fake testimonials, unintentional shadows, inconsistent spacing, mismatched radiuses, generic hero lines, broken responsiveness, missing loading states, and any animation that feels chaotic or unrefined. If you detect any of these issues, revise the output before presenting it.

The final result should feel like something shipped by a mature product team. It should demonstrate intention in every choice, clarity in every layout, and a calm, confident design voice. Nothing should feel rushed. Nothing should feel improvised. Your role is to guarantee a premium standard at all times.

© ReviewStage, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/deslop-ui of ReviewStage/stage-cli.

Open the folder on GitHubat commit 59b977b

Compare with similar skills

Deslop UI next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Deslop UI compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Deslop UI this skillReviewStage/stage-cli274—~1.1kAutomated safety check: PassMIT
Product Prototype Figmapmlaowangba-lab/laowangba-pmprototype-skill100—~1.2kAutomated safety check: PassMIT
Docs Voice Toneadobe/spectrum-design-data155—~1.1kAutomated safety check: PassApache-2.0
Omd Humanizekwakseongjae/oh-my-design533—~910Automated safety check: PassMIT
Anti Slop Designsickn33/agentic-awesome-skills47k1 repos~6.1kAutomated safety check: PassMIT
Suede Ship CopyJasonColapietro/suede-creator-skills127—~6.2kAutomated safety check: PassMIT

Similar skills

  • Product Prototype Figma

    pmlaowangba-lab/laowangba-pmprototype-skill

    用 Figma MCP 生成 B/C 端可编辑 UI 原型。用户说画原型、线框图、Figma 稿、后台页面、App 页面时使用。

    100 GitHub stars~1.2k tokensUpdated 3 mo ago
    Writing & ContentAuto-check passed
  • Docs Voice Tone

    adobe/spectrum-design-data

    Reviews docs-site prose (articles, spec pages, READMEs) against Spectrum's voice principles (Clear, Genuine, Concise, Upfront), adapted for public/reference docs rather than in-product UI strings.

    155 GitHub stars~1.1k tokensUpdated 2 days ago
    Writing & ContentAuto-check passed
  • Omd Humanize

    kwakseongjae/oh-my-design

    제품 문서·UX 카피·랜딩 카피를 KO/EN/JA/ZH-CN/ZH-TW 각 언어의 자연스러운 문장으로 다듬되 사실·수치·명령어·링크·브랜드 voice를 보존한다.

    533 GitHub stars~910 tokensUpdated 10 days ago
    Writing & ContentAuto-check passed
  • Anti Slop Design

    sickn33/agentic-awesome-skills

    Autonomous Principal Design Technologist. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 1 repo~6.1k tokens
    Writing & ContentAuto-check passed
  • Suede Ship Copy

    JasonColapietro/suede-creator-skills

    Suede Labs copy-only orchestration DAG. An agent skill from JasonColapietro/suede-creator-skills.

    127 GitHub stars~6.2k tokensUpdated yesterday
    Writing & ContentAuto-check passed
  • Humanizer

    Azure-Samples/interview-coach-agent-framework

    Official

    Remove signs of AI-generated writing from text. An agent skill from Azure-Samples/interview-coach-agent-framework.

    173 GitHub starsUsed in 38 repos~5.8k tokens
    Writing & ContentAuto-check passed

More from ReviewStage/stage-cli

All 10 skills in this repo
  • Fixing CI

    ReviewStage/stage-cli

    A skill your agent uses when CI is failing on a branch and you need to diagnose failures from GitHub, fix them locally with iterative verification, and re-push clean commits.

    274 GitHub stars~977 tokensUpdated 1 mo ago
    Auto-check passed
  • Fixing PR Comments

    ReviewStage/stage-cli

    A skill your agent uses when a pull request has unresolved review comments that need to be addressed, or when asked to fix PR feedback

    274 GitHub stars~953 tokensUpdated 1 mo ago
    Auto-check passed
  • Iterate PR

    ReviewStage/stage-cli

    A skill your agent uses when a PR is open and the user wants to autonomously monitor and fix PR review comments, CI failures, and rebase conflicts on a recurring loop, or when asked to…

    274 GitHub stars~1.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Linear Issue

    ReviewStage/stage-cli

    A skill your agent uses when creating a Linear issue from the current coding context, or when the user invokes /linear-issue.

    274 GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check passed
  • Quality Review

    ReviewStage/stage-cli

    A skill your agent uses when reviewing code changes against AGENTS.md implementation quality standards, or when asked to do an implementation quality review

    274 GitHub stars~1.3k tokensUpdated 1 mo ago
    Auto-check passed
  • Rebase Origin Main

    ReviewStage/stage-cli

    A skill your agent uses when rebasing the current branch onto origin/main, including resolving merge conflicts along the way

    274 GitHub stars~927 tokensUpdated 1 mo ago
    Auto-check passed

Questions about Deslop UI

What does Deslop UI do?

A skill your agent uses when building or reviewing UI components, pages, or layouts to ensure premium, intentional design that never looks vibe coded. Deslop UI is an agent skill from ReviewStage/stage-cli.

When should I use Deslop UI?

Deslop UI fits situations like: reviewing UI components; layouts to ensure premium; intentional design that never looks vibe coded.

How do I install Deslop UI in Claude Code?

Run `npx skills add ReviewStage/stage-cli --skill deslop-ui -a claude-code`. Or copy the skill folder (.agents/skills/deslop-ui in ReviewStage/stage-cli) into .claude/skills/deslop-ui in your project. Claude Code loads it when a task matches its description.

How do I install Deslop UI in Codex?

Run `npx skills add ReviewStage/stage-cli --skill deslop-ui -a codex`. Or copy the skill folder (.agents/skills/deslop-ui in ReviewStage/stage-cli) into .agents/skills/deslop-ui in your project. Codex loads it when a task matches its description.

Can I use Deslop UI in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ReviewStage/stage-cli --skill deslop-ui -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/deslop-ui, .gemini/skills/deslop-ui, .github/skills/deslop-ui and .opencode/skills/deslop-ui in your project.

What does Deslop UI need to run?

SKILL.md names no scripts, command-line tools or credentials: Deslop UI is instructions for the agent only.

Does Deslop UI access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Deslop UI safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Deslop UI use?

Deslop UI is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Deslop UI use?

About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Deslop UI?

Skills that share tags, products or a category with Deslop UI: Product Prototype Figma (pmlaowangba-lab/laowangba-pmprototype-skill, 100 stars), Docs Voice Tone (adobe/spectrum-design-data, 155 stars), Omd Humanize (kwakseongjae/oh-my-design, 533 stars) and Anti Slop Design (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Deslop UI?

ReviewStage (a GitHub organization) maintains it in ReviewStage/stage-cli, which has 274 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 7, 2026.

Source: ReviewStage/stage-cli on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.