Skip to content
Agents tracked: 502 Releases (7d): 613 Agent status: 4 with issuesSince last limit reset: Claude 7d · Codex 5d For AI agents: Markdown Updated Nov 18, 2026

unslop: turn AI-looking screens into designed ones

heydamir/unslop

A design playbook for your AI assistant that cleans up screens that look AI-made. It first lists what looks generic (purple gradients, glows, emoji labels, shouty copy, uneven spacing), proposes a direction taken from your product and waits for your answer. Then it fixes the screen layer by layer, like a designer marking up a page.

Pack description by its author: “A design playbook for your AI assistant that cleans up screens that look AI-made. It first lists what looks generic (purple gradients, glows, emoji labels, shouty copy, uneven spacing), proposes a direction taken from your product and waits for your answer. Then it fixes the screen layer by layer, like a designer marking up a page.”

Design and frontendKnowledge and rules for your assistantGives your assistant new abilities with scripts

GitHub

Checked against the pack's files at commit 97daa3e, on Nov 13, 2026. Tap a verdict to see its source.How we checkedReport an error

The pack has changed since AgentGid checked it on Nov 13, 2026. Some details may be out of date.

Knowledge and rules for your assistantGives your assistant new abilities with scripts

Good for you if

  • Your dashboard, app screen or landing page was made with AI and looks like every other AI-made page
  • You want to polish or clean up a screen without changing what the product does
  • You only have a link to a live site and want a redesigned copy to hand to whoever owns it
  • You want a short square video of your screen fixing itself, to post

Probably not for you if

  • Your screen is already designed: it will say so and suggest two or three small tweaks at most
  • You want a new product, new features or new sections: it keeps your features, content and section order

What changes, in one chat

/unslop this dashboard
Without the skillexamples/dashboard.html (190 lines): Inter, violet to blue gradients, gradient text, a 'Welcome back, Damir! 👋' greeting and a 'New ✨' badge.
With the skillThe author's finished version is an image, references/refs/unslop-dashboard-after.webp: quiet graphite chrome, two rendered payment cards and a revenue chart drawn as soft coloured curves over a grey comparison.

Real answers from the author's run. More examples

What you'll notice

  • A list of what looks AI-made on your screen, one line each, with where it lives
  • A five-line direction (product, character, world, moments, signature) and a pause for your answer before any edit
  • Nine passes in a fixed order: spacing, colour, icons, copy, type, layout, details, visuals, motion
  • Questions about claims like 'Trusted by 10,000+ teams': kept only if you confirm they are real

What you need

  • Claude Code, Codex, Google Antigravity
  • Free, CC-BY-4.0 license
  • Copy one folder into your assistant's skills folder
  • Saving a live site or making the story video needs Node.js with Playwright and its Chromium browser; the video also needs ffmpeg. Generated hero pictures need an image service you connect (fal, Replicate, OpenAI images or Higgsfield), which can cost money.
Words on this page
Skill
A set of written instructions your AI assistant follows. Installing one is like giving it a playbook.
MCP
A standard way to connect an AI assistant to outside tools and data.
Repositoryheydamir/unslop
GitHub stars16,214
Skills1 · 1 with scripts
CategoryDesign and frontend
LicenseCC-BY-4.0
Last updatedNov 15, 2026 · card checked Nov 13, 2026 at commit 97daa3e
Install countsheydamir/unslop on skills.sh, Vercel's skills directory, which shows installs and security audits per skill

heydamir/unslop popularity over time

Most starred skill packs

heydamir/unslop: GitHub starstotal over time 16,214
heydamir/unslop: new stars per weekGitHub 4,000

What unslop does

Before writing anything, the assistant takes the first option that fully works:

  1. Look: open the screen and take a screenshot; with only a link it saves the live page with a bundled script; with only a screenshot it rebuilds it as one HTML file
  2. Audit: go through its list of signs (surfaces and colour, type, icons, spacing, copy, components, heroes, visuals, motion) and note each one found
  3. Decide how much: heavy slop gets the full process, light slop gets polish only, no slop gets a few suggestions
  4. Direction: five short lines from what the product does, shown to you before any edit
  5. Nine passes in order: spacing, colour, icons, copy, type, layout, details, visuals, motion
  6. Check against its checklist, render again (at most three renders) and report what changed per pass
  7. Optional story video: a square clip of about 10 seconds where the screen morphs step by step with red redlines

Never cut, per the skill: ['The product name, a real logo, features, content and section order', 'No invented features, claims or data', 'No swapping one trend for another (glass, grain, noise, neon, bento grids)'].

From the pack's SKILL.md files, summarised by AgentGid.

The skill, explained

unslop

Audits an AI-looking screen, agrees a direction with you, then redesigns it pass by pass

You give

  • The screen: the project files, a link to a live site, or a screenshot
  • Your answer to the proposed direction (or say to just do it)
  • Whether claims like customer counts are real
  • Optionally: a connected image service for a hero picture, and whether you want the story video

You get

  • An audit: every sign of slop, one line each, with where it lives
  • A direction: product, character, world, moments, signature
  • The redesigned screen in your own code, or a redesigned HTML copy of a live page
  • A report: the direction, a few lines per pass, any image prompt it wrote
  • Optionally a square MP4 story video of about 10 seconds
Say: “/unslop this dashboard”

Its rules, in pictures

The page it plans

1 Quiet navigation: logo, existing links, one button
2 Headline on calm empty space
3 One primary and at most one secondary action
4 A scene image filling the hero, or an asymmetric split
5 Product view rising from the bottom edge

Fonts it uses

Geistuses
Interuses
IBM Plex Sansuses
Instrument Sansuses
DM Sansuses
Figtreeuses
Space Groteskuses
Bricolage Grotesqueuses
Newsreaderuses
Instrument Serifuses
Frauncesuses
Geist Monouses
IBM Plex Monouses
JetBrains Monouses

How things move: its curve against a plain one

cubic-bezier(0.22, 1, 0.36, 1), 160ms
linear, for comparison

Each visual acts out what it does

In your designThe story it plays
Purple to blue gradient surfacesThe gradient layer fades out and one neutral surface stays
Emoji nav iconsA line icon crossfades in where the emoji was
A 'New ✨' badgeIt collapses and disappears
Uneven spacingRed measurements count to the new value and turn white once fixed

Drawn by AgentGid from the values in the skill's files. This is not output of the skill; sample text is ours.

See it in action

Same task, same model, with and without the skill

Prompt: /unslop this dashboard

Without the skill

examples/dashboard.html (190 lines): Inter, violet to blue gradients, gradient text, a 'Welcome back, Damir! 👋' greeting and a 'New ✨' badge.

Read the whole answer
With the skill

The author's finished version is an image, references/refs/unslop-dashboard-after.webp: quiet graphite chrome, two rendered payment cards and a revenue chart drawn as soft coloured curves over a grey comparison.

Verbatim output from the author's run, published in README.md. AgentGid did not run it.

When to reach for it

You wantUse
A screen made with AI that looks generic/unslop this screen (Claude Code) or $unslop (Codex)
Only a link to a live site/unslop the hero of <url>; needs Playwright
A short video to post/unslop ... and make the story video; needs Playwright and ffmpeg
A screen that is mostly fineRun it anyway: it switches to polish mode or says there is no slop
Try it. Copy the skill, then point your assistant at the repository's examples/dashboard.html and say "/unslop this dashboard". It should first list the signs it found and a five-line direction, and stop to ask you before editing. That pause is how you know the skill is on.

Skills in heydamir/unslop

SkillIn plain wordsChanges files?What it does (author)
unslop
/unslop in Claude Code, $unslop in Codex, or plain language ("unslop this dashboard")
Audits an AI-looking screen, agrees a direction with you, then redesigns it pass by passYes Turns vibecoded, AI-looking UI into a designed interface with its own character. Finds a direction from the product itself, then fixes spacing, color, icons, copy, type, layout, details, visuals and motion in that order, and can generate a real hero visual with an image tool when one is available.… has scripts
npx skills add heydamir/unslop --skill unslop

The author's descriptions come from each skill's SKILL.md; the plain-words column is AgentGid's.

Good to know before you install

  • It switches on by itself: the assistant picks it up when a screen shows the usual AI tells, even if you do not type the command.
  • It stops after the audit and direction and waits for you, unless you said to just do it.
  • Generated pictures can cost money: it shows the prompt, model and size and asks before each generation. Without an image service it leaves an empty slot and writes the prompt into its report.
  • Every story video gets a small credit to the author, as the license asks.
  • It may swap a default font like Inter for another family that fits the direction; a font that is part of a real brand stays.

Before you start

Works in

  • Claude Code: skills folder
  • Codex: skills folder (~/.agents/skills) or $skill-installer
  • Google Antigravity: skills folder

You will need

  • Node.js with Playwright and Chromium: Only for live-site snapshots and story videos
  • ffmpeg: Only for story videos
  • An image generation MCP server (optional: Only for generated hero scenes and objects

Steps only you can do

  1. Confirm or change the proposed direction before edits start (The chat with your assistant)
    Then: The assistant runs the nine passes
  2. Connect an image generation service and approve each paid generation (optional) (Your image service's account, connected as an MCP server)
    Then: The assistant generates the hero scene or object and saves it into the project's assets
  3. Say whether claims like customer counts are real (The chat with your assistant)
    Then: The assistant keeps them quiet and specific, or removes them

Mistakes to avoid

  • Expect it to edit right away
    Answer the audit and direction it shows, or say "just do it" up front
    It stops and waits after the direction
  • Ask for a live-site snapshot or story video without Playwright and ffmpeg
    Install Playwright and its Chromium in the project folder, and ffmpeg for videos
    Both scripts exit with an install message when Playwright is missing
  • Ship the story file as the real result
    Ship the clean result in the project's own stack; the story file is only for the video
    The story file carries step classes and story attributes
  • Treat a violet to blue gradient in the logo as brand
    Tell it explicitly if that gradient is your real brand
    It counts such gradients as slop unless you say otherwise

Which one to pick

If you needPick
You have an existing AI-made screen and want it audited and redesigned pass by pass, with an optional before/after videoThis pack
You want design commands like polish, critique and audit across many tasks, not one cleanup workflowpbakaus/impeccable
You want art direction and reference images while building a new interfaceLeonxlnx/taste-skill
You want a lighter anti-AI-slop design rule set for Claude Code, Cursor or CodexNutlope/hallmark

Works well with

  • playwright-test: The snapshot and story scripts drive Chromium through Playwright
  • ffmpeg: story.mjs encodes the MP4 with ffmpeg
  • lucide: Its default icon set when the project has none
  • fal: One of the image services it names for hero scenes and objects

May I use it like this?

UseAnswerCondition
In a commercial app With conditionsCC BY 4.0: credit the author and link back to the repository
Work for clients With conditionsCC BY 4.0: credit the author
Passing the files on With conditionsCC BY 4.0: keep the credit in copies and adaptations
Shipped inside your app With conditionsCC BY 4.0 with attribution

What leaves your machine

  • Requests for the target page and its stylesheets and images → The live site you name, Only when you give a link and the assistant runs snapshot.mjs. Opt out: Give the project files or a screenshot instead
  • The image prompt you approved → The image service you connected (fal, Replicate, OpenAI images, Higgsfield or a design tool), Only in the Visuals pass, after you approve. Opt out: Skip it; the slot stays empty and the prompt goes into the report

Install unslop

Official commands from the repository

git clone https://github.com/heydamir/unslop
mkdir -p ~/.claude/skills && cp -r unslop/skills/unslop ~/.claude/skills/

For a single project, copy it into .claude/skills/ inside that project instead.

Remove: delete the unslop folder from ~/.claude/skills/ (or the project's .claude/skills/)

Or with the open-source skills CLI: npx skills add heydamir/unslop. Skills are instructions your agent follows: read them before installing.

What it installs and runs on your machine

Read in the code at commit 97daa3e, Nov 13, 2026

WhenWhat happens
InstallMarkdown files, reference images and two Node scripts. No hooks, nothing runs at install.
You give only a link to a live siteThe assistant runs snapshot.mjs: a headless Chromium (Playwright, or your installed Chrome) opens the page, scrolls it, downloads its stylesheets and images under 3 MB to inline them, and writes one HTML file plus a .live.png screenshot to the output path (unslop/original.html in the skill's own command).
You ask for the story videoThe assistant runs story.mjs: it serves the story file's folder on a local 127.0.0.1 port, records 60 fps JPEG frames into a .story-frames folder next to the story file, calls ffmpeg to write the MP4, then deletes the frames folder.
Visuals pass with an image service connectedTells your assistant to send an image prompt to that service (fal, Replicate, OpenAI images, Higgsfield or a design tool) after asking you, and save the result into the project's assets.

Quick answers

Can I use it for paid client work?
Yes. It is CC BY 4.0: use, change and share it, including commercially, if you credit the author and link back to the repository.
Does it work without code, from a link?
Yes. It saves the live page as one HTML file and redesigns that copy, which you hand to whoever owns the site. This needs Playwright installed.
Will it change my product or add features?
No. Features, content and section order stay unless you ask; it does not invent features, claims or data.
Does it need an image service?
No. Dashboards and apps rarely need one. Without a service it builds what it can in code and writes prompts for the rest.
Which frameworks does it work with?
Whatever the screen is built with: Next.js, React, Vue, Svelte, Tailwind or plain HTML and CSS.

Checked by AgentGid on Nov 13, 2026 against commit 97daa3e of the pack's own files. agent.md for AI agents · Report a mistake

More design and frontend skill packs

All design and frontend skills

# Skill pack Skills GitHub stars Updated
1
nextlevelbuilder/ui-ux-pro-max-skill Your AI assistant gets a local design library: UI styles, colour palettes, font pairings and UX rules for many product types. Bef…
7 150K 2026-11-14
2
Leonxlnx/taste-skill Your AI coding assistant stops building the average landing page. It picks one of 20 researched design directions, finds real, cr…
1 116K 2026-11-08
3
tt-a1i/archify Your AI assistant turns a description, a Mermaid sketch or your project's code into an interactive diagram saved as one HTML file…
5 96.5K 2026-11-15
4
cathrynlavery/diagram-design Your AI assistant draws clean, editorial diagrams in your brand colours and fonts. You describe the diagram in plain words and ge…
1 67.2K 2026-11-12
5
Nutlope/hallmark Your AI assistant builds web pages that look designed, not machine-made. It asks once for your real material and picks one of fif…
1 55.2K 2026-11-11
6
alchaincyf/huashu-design One large design playbook for your AI assistant, written in Chinese. It makes clickable app prototypes, web pages, slide decks, i…
1 29.5K 2026-11-10