
An agent skill (Claude Code, Codex, Cursor, Copilot, Gemini CLI...) that makes your app or site stop
An agent skill (Claude Code, Codex, Cursor, Copilot, Gemini CLI...) that makes your app or site stop looking AI-generated: 64 numbered design fixes, scripts that score your UI from 0 to 100 (example: 26 → 100), and a before/after you approve.
·
An agent skill that makes your app stop looking AI-generated.
It reviews your UI, shows you the before/after, and applies 65 numbered design fixes one at a time.
Works with Claude Code · Codex · Cursor · Copilot · Gemini CLI · Windsurf · OpenCode and more.
Quick start · Use it · The 65 fixes · Web · How it works · FAQ
Real screenshots of Refil, same screen and city, before and after running the skill.
What you get
Claude Code, as a plugin (updates with /plugin update):
/plugin marketplace add marcosnovo/unslop-design
/plugin install unslop-design@unslopAny other agent (Codex, Cursor, Copilot, Gemini CLI, Windsurf, OpenCode…), with the skills CLI:
npx skills add marcosnovo/unslop-design -gPick one route per agent: installing the same skill twice makes it show up twice. Other routes (one command for every agent, one project only, chat apps, manual clone) are in More ways to install.
Check it works. In a project, paste a screenshot and write unslop this screen. You should get five numbered fixes, each with its reason, and a before/after to approve before any code changes.
AI-built UIs all drift to the same look: gradient backgrounds, an accent color on everything, "Hey Alex! 👋" as the title, emoji as icons, badges shouting in saturated pink, three numbers the same size, spacing picked by eye. Each of those has a concrete fix. This skill gives your agent the list, the reasons, and a way to apply them one at a time without you losing control of the design.
Two Refil screens going through the checklist, each step labeled with the area it touches. Every fix is applied and looked at on its own, so you can see which one helped.
![]() | ![]() |
| Map · spacing → color → price → surface | Profile · title → color → savings → alerts |
The app is in Spanish. Full-quality MP4s: map · profile.
Claude Code from a terminal: claude plugin marketplace add marcosnovo/unslop-design && claude plugin install unslop-design@unslop.
Update with claude plugin marketplace update unslop && claude plugin update unslop-design@unslop. Plugin skills are namespaced, so the command is
/unslop-design:unslop-design; asking in plain words works the same.
Every agent on your machine, one command:
curl -fsSL https://raw.githubusercontent.com/marcosnovo/unslop-design/main/install.sh | bashIt clones the skill once into ~/.agents/skills/unslop-design and links it
into every agent it finds, so one git pull updates them all. Nothing is
overwritten: an existing folder with the same name is left alone.
--dry-run shows what it would do, --copy copies instead of linking, and
--uninstall removes only what it installed.
(Read the script before piping it into a shell.)
Or one agent by hand. Clone into its skills folder:
| Agent | Global folder | Call it |
|---|---|---|
| Claude Code | ~/.claude/skills/ | /unslop-design |
| Codex · Cline · Zed | ~/.agents/skills/ | $unslop-design (Codex) |
| Cursor | ~/.cursor/skills/ | ask for it by name |
| GitHub Copilot | ~/.copilot/skills/ | ask for it by name |
| Gemini CLI | ~/.gemini/skills/ | ask for it by name |
| Antigravity | ~/.gemini/antigravity/skills/ | ask for it by name |
| Windsurf | ~/.codeium/windsurf/skills/ | ask for it by name |
| OpenCode | ~/.config/opencode/skills/ | ask for it by name |
| Amp | ~/.config/agents/skills/ | ask for it by name |
| Kiro | ~/.kiro/skills/ | ask for it by name |
| Goose · Roo Code · Junie | ~/.config/goose/skills/ · ~/.roo/skills/ · ~/.junie/skills/ | ask for it by name |
git clone https://github.com/marcosnovo/unslop-design ~/.claude/skills/unslop-designEvery agent also picks it up on its own when the request matches (design review, screenshots, "less AI"), so calling it by name is optional.
.agents/skills/unslop-design inside the
repo (Claude Code: .claude/skills/, Windsurf: .windsurf/skills/,
Kiro: .kiro/skills/) and commit it, so your team and cloud sessions get
it too.unslop-design.zip
from the latest release
and upload it as a skill (Claude: Settings → Capabilities → Skills).
Chat apps can review screenshots and draw the before/after; the parts
that touch a codebase need a coding agent.
examples/dashboard-before.html → examples/dashboard-after.html, rendered at 1280 px.
For a site or web app the agent also measures instead of eyeballing:
python3 scripts/slop-scan.py src/ # gradients, glows, emoji, raw colors, starter-kit defaults, rows of stat cards… with file:line and fix #
node scripts/web-audit.mjs http://localhost:3000 # the rendered page at 390/768/1280 pxOn the example above, web-audit.mjs goes from 19 spacing values (15 off
the scale), 5 weights, 6 radii, 6 shadows, a page that scrolls sideways
on a phone and 11 links with no focus style, to 6 spacing values, all on the scale, 2
weights, 1 shadow, no sideways scroll and a focus ring on everything.
slop-scan.py finds 88 hits in the before and none in the after, and
unslop-score.py goes from 25 to 100 on the code alone. Details
in web.md.
Type /unslop-design (or $unslop-design in Codex), or just ask in plain
words. It triggers on its own
when you send screenshots or a screen recording and ask for design feedback.
/unslop-design here's a screen recording of the onboarding, make it look less AIReview the design of the settings and profile screens and give me a proposalAudit our tokens: spacing, type scale, contrast in dark modeWith one screenshot or one screen the agent runs quick mode: no subagents, the five fixes that change the screen most (each with its number), the before/after, and on your yes it applies them and reports the score. Several screens, a recording or "full review" switch to the full process with parallel reviewers.
python3 scripts/unslop-score.py src/ # the code alone
python3 scripts/unslop-score.py src/ --audit unslop-audit/report.json # plus the rendered page (web-audit.mjs)$ python3 scripts/unslop-score.py examples/dashboard-before.html
unslop score: 25/100 — slop (1 source file)
Where the points went (fix the top rows first):
- 12 [#32] Colored glows (4)
- 10 [#33] Emoji in the UI (19)
- 8 [#53] Focus outline removed (1)
…
Badge: [](https://github.com/marcosnovo/unslop-design)Each kind of slop costs points per hit up to a cap, so the number says how
many kinds are left, not how big the codebase is. Paste the badge in your
README, and put "score 25 → 100" at the top of the PR. It's a smoke alarm,
not a judge: a 95 can still have a flat hierarchy. --min 80 makes it exit
1 below 80 if you want it in a pre-commit hook.
Screen recordings need ffmpeg (brew install ffmpeg) so the agent can
pull frames from them.
Every fix has a number so reviewers can cite it ("#20 badge is too loud") and you can accept or reject them one by one. A few of them:
| # | Fix | Instead of |
|---|---|---|
| 1 | Non-linear spacing scale, neighbors ≥ 25% apart | padding(13), padding(15), padding(18) |
| 11 | Hierarchy with weight and color before size | three numbers fighting at the same size |
| 12 | "12 left in stock" | "Stock: 12" |
| 15 | Number and unit on one baseline | $ and /gal vertically centered |
| 16 | Only numbers that exist | "vs. last month" with one month of data |
| 19 | One accent, for one gesture | brand color on cards, icons and titles |
| 20 | Quiet badges: dark text on a light tint | white on saturated pink |
| 22 | A shade of the same hue on colored panels | gray or 60% white text |
| 26 | The title says what the screen is | "Hey Alex! 👋" |
| 31 | Space, then background, then shadow, border last | a border around everything |
| 32 | Shadows mean height | shadows as decoration |
| 33 | One icon set, one stroke | emoji as icons, icons in colored circles |
| 39 | Charts: today saturated, values on the bars | gridlines and axes nobody reads |
| 41 | The primary button names where it goes | "Let's Go! 🚀" |
| 43 | One left and one right rail for everything | blocks starting at 12, 16 and 20 pt |
| 44 | One gap between sections, no filler copy | "✨ Share your best moments" |
| 47 | A signature taken from the domain, as a small family | a new font plus a glow |
| 50 | Counts as muted tabular numbers | 12 in a hot-pink pill, 210 👤 |
| 52 | A delta names its baseline | "+12%!!" |
| 55 | Ink headline on a neutral canvas | gradient text over a purple glow |
System · 1 spacing scale · 2 type scale and two weights · 3 palette with shades defined up front · 4 grays with one temperature · 5 named elevation and radii · 6 a chosen personality
Spacing · 7 start with too much space · 8 more space around a group than within · 9 uniform card padding · 10 you don't have to fill the screen
Hierarchy · 11 data first · 12 labels as a last resort · 13 small section titles · 14 balance weight and contrast · 15 parts of a number · 16 only numbers that exist · 17 each number once per screen · 18 what's next, concretely
Color · 19 one accent · 20 quiet badges · 21 dark ink on brand fills · 22 no gray on color · 23 neutral global tint · 24 color never alone
Typography · 25 sentence case · 26 title, not a greeting · 27 line height and length · 28 align for readability · 29 letter-spacing with intent
Decoration and depth · 30 remove ornaments · 31 fewer borders · 32 shadows mean height · 33 one icon style · 34 decoration with conditions
Images and charts · 35 good images or none · 36 text over images · 37 user content in fixed frames · 38 screenshots at their size · 39 charts without noise
Layout · 40 one card per idea · 41 action pyramid · 42 components don't scale proportionally
Chrome and signature · 43 rails · 44 one section gap, no filler · 45 section headers are quiet labels · 46 floating chrome in the system material, content solid · 47 a signature is a family · 48 real content in every mock
Web and dashboards · 49 one icon slot · 50 counts are text, not pills · 51 one category, one color · 52 a delta names its baseline · 53 interactive states drawn · 54 shortcuts as keys · 55 no gradient text, no page glow · 56 a data voice · 57 works at 390, 768 and 1280 px
Beyond clean · 58 objects before boxes · 59 when the content is a canvas, chrome floats · 65 a skeleton from the job, not from the template
Craft floor · 60 structure carries information or goes · 61 real typography characters · 62 system surfaces wear the theme · 63 motion is named, short and optional · 64 nothing invented, nothing inflated
Full text with the reason behind each one: checklist.md.
Small job? It scales down: a single screen gets the checklist and a before/after without the whole team.
| File | What it covers |
|---|---|
SKILL.md | Principles, quick mode and the full flow (what the agent reads first) |
checklist.md | The 65 fixes, each with what to do and why |
spec-card.md | The card each reviewer fills: named values, ticked as they land |
process.md | Inventory, reviewers, proposal, devs, verification, PR |
platforms.md | SwiftUI, Compose, web, widgets, watch and car notes |
web.md | Web playbook: finding tokens per stack, dashboards, landing pages, web PR checks |
scripts/slop-scan.py | Finds slop patterns in source with file, line and fix number |
scripts/web-audit.mjs | Measures a rendered page: overflow, value census, contrast, focus |
scripts/unslop-score.py | Both as one score from 0 to 100, with the breakdown and a badge |
examples/ | One dashboard before and after, to try the scripts on |
.claude-plugin/ | Claude Code plugin and marketplace manifests |
install.sh | Installs or updates the skill for every agent it finds |
scripts/validate.py | Checks SKILL.md against the Agent Skills spec |
scripts/test.py | Regression tests: every case in tests/cases gives exactly the hits tests/expected.json lists |
agents/openai.yaml | Codex UI metadata (name, description, default prompt) |
references.md | Six real before/afters, one reference app and a chapter map of Refactoring UI |
No. The process stops at the before/after page and waits for your yes. After that it works on branches and opens a PR; merging is up to your repo's rules.
Nothing in the rules: all of them read the same SKILL.md (the open
Agent Skills format); Codex also reads
agents/openai.yaml for its UI. The parallel reviewers use subagents where
your tool has them, and run one after another where it doesn't. The
before/after is a published artifact in Claude Code and a local HTML file
elsewhere. The full process (parallel reviewers, worktrees, PR) works best
in agents with subagents and git: Claude Code, Codex, Cursor, Copilot.
No. The checklist is platform-agnostic and platforms.md has notes for
SwiftUI, Jetpack Compose and the web, plus widgets, watch and car surfaces.
Good. The skill uses your tokens and components, and when one of its rules clashes with a written decision of yours, yours wins and the proposal says so.
It builds on it (and you should buy the book). The skill turns those ideas into numbered, checkable fixes, adds what came up in real redesigns of AI-built apps (invented numbers, greeting titles, emoji icons, carousels hiding content), and is stricter where the book allows decoration that AI-generated UIs overuse.
The full process spawns several agents (reviewers, a jury, devs, auditors), so it uses noticeably more tokens than a normal chat. For one screen, ask for the checklist review only.
Found a pattern of AI slop the checklist misses? Open an issue with a before/after screenshot and the fix. See CONTRIBUTING.md.
Paste this prompt into your agent. It reads this page and does the setup for you.
Read https://aiagentslisting.com/mcp/unslop-design to learn what the "Unslop Design" MCP server does and how to install it. Add it to my coding agent's MCP configuration as documented on that page, then confirm the server connects and list the tools it exposes.Agents can also browse this directory over MCP at https://aiagentslisting.com/api/mcp
npx skills add marcosnovo/unslop-design -gThis server runs locally, so we can't read its tool list over the web yet.
We could not run this server: it ships no npx package for our sandbox and no public endpoint. The four checks that need a live server are left out, and the grade tops out at B until one exists.
Maintain this server? Claiming proves you own the listing and earns the last 4 points.
Claim this listingPaste this line near the top of your repository's README. The badge always renders the current score.
[](https://aiagentslisting.com/mcp/unslop-design)Nothing comparable is listed yet.
v1.9.0Release notesv1.8.9v1.8.9 — project decisions vs floors, quick-mode report, reading checksRelease notesv1.8.8v1.8.8 — regression suite for the scriptsRelease notesv1.8.7v1.8.7 — implementation-stage gaps: stale spec cards, token ownership, dangling tokensRelease notesv1.8.6v1.8.6 — full-flow process gaps, glow and type-scale fixesRelease notesv1.8.5v1.8.5 — icon contrast, checked critic findings, tab bar over a canvasRelease notesv1.8.4v1.8.4 — draw the interaction, and four scanner fixes from a landing pageRelease notesv1.8.3v1.8.3 — native copy rules and the iOS secondary-gray noteRelease notesv1.8.2v1.8.2 — fixes found by running the skill on a new screenRelease notesv1.8.1v1.8.1 — slop-scan: starter-kit defaults and rows of stat cardsRelease notesv1.8.0v1.8.0 — concept first, three directions, a second critic, device rendersRelease notesv1.7.0v1.7.0 — better judgment: critique passes, plan score, craft floorRelease notesv1.6.1v1.6.1 — Claude Code pluginRelease notesv1.6.0v1.6.0 — quick mode and a 0-100 scoreRelease notesv1.5.01.5.0 — Beyond cleanRelease notesv1.4.01.4.0 — WebRelease notesv1.3.0unslop-design 1.3.0 — spec card and 6 new fixesRelease notesv1.2.0unslop-design 1.2.0 — every agentRelease notesv1.1.0unslop-design 1.1.0 — Codex supportRelease notesv1.0.0unslop-design 1.0.0Release notesConnect to the AI Agents Listing MCP server at https://aiagentslisting.com/api/mcp using the HTTP transport and complete the sign-in when it asks. Then call the submit_review tool for the listing "unslop-design" with a rating from 1 to 5 and a short note on what worked and what did not.No reviews yet
Be the first to share your experience with this tool.
One email a week. New agents, MCP servers and skills, and what is actually getting traction.