unslop-ui
Cut AI tells from interface and chart copy
Safety scan
A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.
Check it deeper on your machine
It has changed since its scan on 19 Nov 2026.
As a Claude Code plugin, install it and then ask Claude Code:
/plugin marketplace add keithmackay/mackayi/plugin install scanskillsafety@mackayiDo a deep scan of https://github.com/felipebasurto/unslop-ui with scanskillsafety
Or from a terminal, clone it and run it:
git clone https://github.com/keithmackay/scanskillsafety-skill ~/.claude/skills/scanskillsafetynode ~/.claude/skills/scanskillsafety/cli.cjs --deep 'https://github.com/felipebasurto/unslop-ui'
It checks the exact commit: every file, its packages against OSV (api.osv.dev), how it compares with this page's scan (findsafeskills.com receives the repository's address), and, if you agree, Claude reading every file with your own Claude subscription. It never runs the code.
Badge for your README
Markdown
[](/listings/felipebasurto--unslop-ui)HTML
<a href="/listings/felipebasurto--unslop-ui"><img src="/api/listings/felipebasurto--unslop-ui/badge.svg" alt="findsafeskills safety rating" /></a>Install
Install instructions from the README
As written by the repo's author. findsafeskills has not verified these steps.
Install it:
npx skills add felipebasurto/unslop-ui -g
Then run it on a file, a folder or a component:
/unslop-ui src/pages/landing.tsx /unslop-ui src/pages/dashboard.tsx --surface
With no argument it works on the files changed in the conversation. Codex uses `$unslop-ui`, and the Claude Code plugin uses `/unslop-ui:unslop-ui`.
The skill never triggers on its own, because cutting copy is a decision you should make. You have to call it.
What was scanned
The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.
.claude-plugin/marketplace.json · Manifest · 14 lines
- {
- "name": "unslop-ui",
- "description": "Cut AI tells from interface and chart copy",
- "owner": {
- "name": "Felipe Basurto"
- },
- "plugins": [
- {
- "name": "unslop-ui",
- "source": "./plugins/unslop-ui",
- "description": "Cut AI tells from interface and chart copy: eyebrow labels, 01/02/03 numbering, captions that explain what is visible, decorative badges, icons and status dots. With --surface it also fixes gradients, off-scale spacing, heavy weights and decorative motion."
- }
- ]
- }
README.md · README · 315 lines
- <p align="center">
- <img src="assets/banner.png" width="100%" alt="unslop-ui: a Share Workspace sheet before and after /unslop-ui">
- </p>
- <p align="center">An agent skill that strips the AI look out of interface and chart copy, and optionally its visual surface.</p>
- <p align="center">
- <a href="https://github.com/felipebasurto/unslop-ui/actions/workflows/test.yml"><img src="https://github.com/felipebasurto/unslop-ui/actions/workflows/test.yml/badge.svg" alt="Tests"></a>
- <a href="LICENSE"><img src="https://img.shields.io/badge/license-MIT-blue" alt="MIT license"></a>
- <a href="https://agentskills.io"><img src="https://img.shields.io/badge/format-Agent%20Skills-555" alt="Agent Skills format"></a>
- </p>
- Agents decorate everything they build: a tiny uppercase label over every heading, `01 //` before each feature, a subtitle that repeats the title, a caption explaining the button you are looking at, a green "LIVE" dot wired to nothing. `unslop-ui` finds those patterns, removes them, and tells you what it cut and what it left for you to decide.
- - **Subtractive.** It deletes first and writes little. It never adds a number, a speed or a feature the code doesn't show.
- - **Safe by default.** Without `--surface` it touches only visible text and decoration, never logic, data, colors or layout. It keeps `aria-label`, `alt`, visible form labels and anything tied to real state.
- - **Reports, not just edits.** Every run ends with a table of counts, the strings it rewrote, what it kept on purpose and the tasks it left for you.
- ## Quick start
- Install it:
- ```bash
- npx skills add felipebasurto/unslop-ui -g
- ```
- Then run it on a file, a folder or a component:
- ```
- /unslop-ui src/pages/landing.tsx
- /unslop-ui src/pages/dashboard.tsx --surface
- ```
- With no argument it works on the files changed in the conversation. Codex uses `$unslop-ui`, and the Claude Code plugin uses `/unslop-ui:unslop-ui`.
- The skill never triggers on its own, because cutting copy is a decision you should make. You have to call it.
- ## For agents
- If a user sent you this repo and said "use this", do the following.
- 1. **Install the skill**, unless `unslop-ui` is already in your skills folder:
- ```bash
- npx skills add felipebasurto/unslop-ui -g
- ```
- Drop `-g` to install into the current project instead of your user folder. Requirements: Python 3.9 or newer, no packages.
- 2. **Pick the target.** Use the file, folder or component the user named. If they named none, use the files changed in this conversation. If there are none, ask.
- 3. **Run the skill.** In Claude Code, Cursor and any agent with slash commands or skill invocation, call `unslop-ui` with the target. Add `--surface` only if the user asked for visual cleanup (gradients, spacing, heavy weights, motion).
- 4. **If you can't invoke skills**, open [`skills/unslop-ui/SKILL.md`](skills/unslop-ui/SKILL.md) and follow it by hand:
- - Treat the target as `$ARGUMENTS`.
- - Run `python3 scripts/load_unslop.py` from the skill's folder and apply the rules it prints. In Claude Code that line runs automatically. Elsewhere it doesn't.
- - Follow the procedure: count, read, verdict, edit, count again, review, report.
- 5. **End with the report** the skill defines: the counts table, then **Rewritten**, **Kept on purpose** and **Tasks**. The user needs the Rewritten list, because it is the only text you wrote.
- Do not run it on a screen with nothing to cut. The verdict step exists so that a clean screen comes back untouched.
- ## What it removes
- 
- | Id | Pattern | Example |
- |---|---|---|
- | U1 | Eyebrow labels | `INTRODUCING LEDGER` above the H1, or a `● POLAR EXPEDITIONS` pill |
- | U2 | Decorative numbering | `01 //`, `02 //` on features with no real order |
- | U3 | Subtitle reflex | "Analytics" with "Understand your data better" under it, or a blurb under every menu item |
- | U4 | Botsplaining | "Click the button above to get started" |
- | U5 | Leaked design notes | "(updates in real time)", "This card shows..." |
- | U6 | Status strings | `Live · v2.4 · Synced · Updated just now` |
- | U7 | Labeling everything | Label, placeholder and helper text that all say "email" |
- | U8 | Staccato slogans | "Finance. Simplified. Finally." |
- | U9 | Badges without state | `NEW`, `AI`, `Beta` added for flavor |
- | U10 | Status dots | `animate-pulse` dot next to static data |
- | U11 | Decorative emojis and icons | `🚀 Get started`, an icon in a tinted square beside every menu item |
- | U12 | Chart titles that name the chart | "Line chart of weekly active users" |
- | U13 | Reading instructions | "Each point represents one week. Hover for details." |
- | U14 | Saying it twice | A value on every point plus axis plus gridlines; `▲ 12% up` plus "Revenue grew 12%..." |
- | U15 | Chart scaffolding | Frame box around the plot, dark or dense gridlines, thick axes, shadows, 3D |
- | U16 | Legend instead of a label | A legend box when each line could carry its name at its end |
- Everything that remains goes through the writing rules of [`/pstack:unslop`](https://github.com/cursor/plugins/tree/main/pstack) (em dashes, AI vocabulary, rule of three). If pstack is installed, `unslop-ui` reads its rules on every run and follows their updates. If not, it uses the condensed copy in [`references/unslop-fallback.md`](skills/unslop-ui/references/unslop-fallback.md). Either way it loads only the rules that apply to interface text.
- ### Surface rules (opt-in)
- Add `--surface` and the skill also fixes four visual tells, each with a concrete replacement value from [`references/tokens.md`](skills/unslop-ui/references/tokens.md):
- | Id | Pattern | Fix |
- |---|---|---|
- | U17 | Hue-to-hue gradients, gradient text, colored glows, blurred blobs | Solid neutral surface, hairline border, shadow no stronger than `0 1px 2px rgb(0 0 0 / 0.05)` |
- | U18 | Off-scale spacing: `mt-[13px]`, `gap: 7px` | Nearest step of 4, 8, 12, 16, 20, 24, 32, 40, 48, 64 |
- | U19 | `font-extrabold`, `font-black`, weights 800 and 900 | 500 or 600 |
- | U20 | `transition-all`, `hover:scale-*` on cards, `animate-bounce` | Named properties at 150ms ease-out |
- Without the flag these four never run. They replace a value with a better value. They don't change the palette, the type family or the layout. For that, see [Pairs well with](#pairs-well-with). If the project already has tokens (a Tailwind theme, CSS variables), the skill fixes toward those instead.
- ## How it behaves
- Every run ends with a verdict: **heavy** (work through every rule), **light** (fix only what was found) or **none** (edit nothing, say so). A screen with nothing to cut is left alone.
- - It keeps `aria-label`, `alt`, screen-reader text, and a visible label tied to every form field.
- - Anything that reflects real state (a badge rendered from a prop, a real step order) stays, and the report says why.
- - Text that comes from a translation file, props or a CMS is fixed at its source or reported, not hard-coded into the component.
- - When a slogan has to become a sentence, the new text uses only what the page already says. Claims the code can't verify, such as "Trusted by 10,000+ teams" or a testimonial, are left in place and listed as tasks for you.
- - When it deletes an element, it also deletes the empty wrapper, margin and unused import left behind.
- ### The report
- This one is from the run that produced `examples/after`, shortened:
- | Rule | Before | After | Kept |
- |---|---|---|---|
- | U1 eyebrow | 5 | 0 | |
- | U4 botsplaining | 5 | 0 | |
- | U11 emoji | 6 | 0 | |
- | unslop 13 em dash | 3 | 0 | |
- **Rewritten**
- ```
- "Finance. Simplified. Finally." → "Manage your team's money" (U8, from the cut hero line "manage their money")
- "▲ 12% up" → "▲ 12% vs last month" (U14, the period came from the cut description)
- "📈 Line chart of weekly active users" → "Weekly active users" (U12)
- ```
- **Kept on purpose**
- - `aria-label="Subscribe to newsletter"`: guardrail.
- - The email label: it stays visible. I added `for="email"` and `id="email"` so it is tied to the input.
- **Tasks**
- - [ ] `Dashboard.tsx:15` "12%" is hard-coded, not bound to data. Bind it to a prop or confirm it is a placeholder.
- - [ ] `landing.html` The hero now has no supporting line. If you want one, add a fact you can verify (price, free tier, integrations).
- "Rewritten" lists every string the skill wrote, old and new, because that is the part you have to check. Deletions are in the diff. "Kept" is how many hits it left on purpose, so the count doesn't have to reach 0: the skill is told never to delete something legitimate to get there.
- ## Examples
- The files in [`examples/before`](examples/before) were written to be full of tells. [`examples/after`](examples/after) is the unedited output of one `/unslop-ui` run in a fresh Claude Code session. The drawings show those files rendered with sample data, and each tell carries the id of the rule that removed it.
- ### A sheet, step by step
- [](assets/video/unslop-ui-steps.mp4)
- Five changes to one sheet, one at a time. [Watch the MP4](assets/video/unslop-ui-steps.mp4). The before and after live in [`examples/share-workspace`](examples/share-workspace).
- ### A dashboard
- 
- <details>
- <summary>See the code change</summary>
- ```diff
- - <div>
- - <p className="... uppercase tracking-[0.2em] ...">Overview</p>
- <h1 className="text-2xl font-semibold">Dashboard</h1>
- - <p className="text-muted-foreground">A real-time overview of your key business metrics, all in one place.</p>
- - </div>
- - <CardTitle>💰 Total revenue</CardTitle>
- + <CardTitle>Total revenue</CardTitle>
- - <span className="text-green-600">▲ 12% up</span>
- - <CardDescription>Revenue grew 12% compared to last month, showing strong momentum.</CardDescription>
- + <span className="text-green-600">▲ 12% vs last month</span>
- - <span ...><span className="size-2 rounded-full bg-emerald-500 animate-ping" />Live</span>
- - <CardDescription>This card shows the number of users active right now (updates in real time).</CardDescription>
- - <span className="text-xs">Last 30 days · All plans · Excl. trials</span>
- + <span className="text-xs">Last 30 days</span>
- ```
- Full files: [before](examples/before/Dashboard.tsx), [after](examples/after/Dashboard.tsx).
- </details>
- ### A chart
- 
- <details>
- <summary>See the code change</summary>
- ```diff
- plugins: {
- - title: { display: true, text: "📈 Line chart of weekly active users" },
- - subtitle: { display: true, text: "Each point represents one week — hover over a point to see the exact value." },
- - legend: { display: true, position: "bottom" },
- - datalabels: { display: true },
- + title: { display: true, text: "Weekly active users" },
- + legend: { display: false },
- + datalabels: {
- + display: (ctx) => ctx.dataIndex === ctx.dataset.data.length - 1,
- + formatter: (value, ctx) => `${ctx.dataset.label} ${value}`,
- + align: "right",
- + },
- },
- scales: {
- - x: { grid: { color: "#9ca3af", lineWidth: 2 }, border: { display: true, width: 2, color: "#111827" } },
- - y: { grid: { color: "#9ca3af", lineWidth: 2 }, border: { display: true, width: 2, color: "#111827" }, ticks: { stepSize: 25 } },
- + x: { grid: { color: "#e5e7eb", lineWidth: 1 }, border: { display: true, width: 1, color: "#e5e7eb" } },
- + y: { grid: { color: "#e5e7eb", lineWidth: 1 }, border: { display: true, width: 1, color: "#e5e7eb" }, ticks: { stepSize: 25 } },
- },
- ```
- Full files: [before](examples/before/chart.js), [after](examples/after/chart.js).
- </details>
- ### A landing page
- The page from the annotated drawing above, rendered in a browser. Full files: [before](examples/before/landing.html), [after](examples/after/landing.html).
- 
- ### By the numbers
- 
- The counter only sees the patterns a regex can find. The run also removes the ones that need reading, such as subtitles, botsplaining and slogans, and its report counts those separately.
- ## Install
- With the [skills CLI](https://github.com/vercel-labs/skills), for Claude Code, Cursor, Codex and other agents:
- ```bash
- npx skills add felipebasurto/unslop-ui -g
- ```
- As a Claude Code plugin:
- ```bash
- claude plugin marketplace add felipebasurto/unslop-ui
- claude plugin install unslop-ui@unslop-ui
- ```
- The plugin lives in [`plugins/unslop-ui`](plugins/unslop-ui). It is instructions only, with no scripts or shell commands, so it can pass the Claude plugin directory's checks. It counts tells with the Grep patterns in [`finding-tells.md`](plugins/unslop-ui/skills/unslop-ui/references/finding-tells.md) instead of `count_tells.py`. The rules in both builds are the same, and a test keeps them in step.
- By hand:
- ```bash
- git clone https://github.com/felipebasurto/unslop-ui
- cp -R unslop-ui/skills/unslop-ui ~/.claude/skills/
- ```
- Optional: install [pstack](https://github.com/cursor/plugins/tree/main/pstack) so `unslop-ui` reads the live unslop rules instead of the bundled copy.
- ### Compatibility
- | Agent | Invoke with | Notes |
- |---|---|---|
- | Claude Code | `/unslop-ui` (plugin: `/unslop-ui:unslop-ui`) | Full support: loads unslop rules automatically, takes arguments. The plugin build counts with Grep, not the script |
- | Cursor | `/unslop-ui` | Works. Run `scripts/load_unslop.py` yourself if the unslop rules don't appear |
- | Codex | `$unslop-ui` | Works, explicit invocation only (`agents/openai.yaml`) |
- | Any other agent | "Follow `skills/unslop-ui/SKILL.md` on `<target>`" | See [For agents](#for-agents) |
- ## The counter
- `scripts/count_tells.py` is a regex counter for the patterns that can be found mechanically: U1, U2, U6, U9, U10, U11 (emojis and icon tiles), em dashes, and the common code forms of U12, U13, U15 and U16 (a title that names the chart type, "hover over", shadows, thick axis borders and gridlines, legends turned on). With `--surface` it also counts U17 to U20. The skill runs it before and after editing. You can run it on its own, and `--max` makes it fail a CI job:
- ```bash
- python3 skills/unslop-ui/scripts/count_tells.py src/
- python3 skills/unslop-ui/scripts/count_tells.py --surface src/
- python3 skills/unslop-ui/scripts/count_tells.py --max 0 src/ # exit 1 above 0
- ```
- It reads HTML, JSX, TSX, JS, TS, Vue, Svelte, Astro, Markdown and MDX, plus CSS, SCSS and Less for the styling rules, JSON for translation files, and Python for matplotlib and Plotly charts. It prints JSON with a count and up to five `file:line` locations per rule.
- It is a heuristic. It can't see the patterns that need reading (U3 to U5, U7, U8, U14). It skips what usually isn't a tell: comments, loading skeletons, uppercase table headers, a lone "—" in an empty cell, a single "·" between two facts, "New" on a button. It still flags some legitimate cases, such as a badge that is wired to real data.
- ## Development
- ```bash
- python3 -m unittest discover -s tests
- ```
- The tests check that the counter finds every planted pattern in `examples/before`, finds none in `examples/after`, ignores comments and the legitimate look-alikes, and that the loader picks the newest pstack install, keeps only the rules for interfaces, or falls back to the bundled copy.
- The counter can only reward deleting, so the behavior of the skill itself has its own check. [`evals/`](evals) holds small screens and what must be true after a run:
- | Fixture | What it checks |
- |---|---|
- | `clean` | A screen with nothing to cut comes back byte-identical |
- | `real-state` | A badge, a dot and numbering tied to real state or real order survive; the decorative ones go |
- | `i18n` | Copy in a translation file is fixed there, not hard-coded into the component |
- | `form` | Labels stay visible and tied to their inputs; a real constraint and an accessible name stay |
- | `claims` | Slogans go without invented facts or numbers; unverifiable social proof is reported, not deleted |
- | `nav-menu` | Decorative menu icons and per-item blurbs go; the destinations stay |
- ```bash
- python3 evals/run.py # runs `claude -p` on every fixture, then checks
- python3 evals/run.py form claims # only these
- python3 evals/run.py --agent 'codex exec' --prompt '$unslop-ui .' # another agent
- ```
- It copies the fixtures to a temporary folder, runs the agent there, and prints what failed with the path to the edited copies and each run's report. It needs an agent CLI and spends tokens, so it is not part of CI. Run it after changing `SKILL.md`.
- ## Pairs well with
- [tufte-claude-skill](https://github.com/aref-vc/tufte-claude-skill) builds charts from Edward Tufte's principles: chart choice, graphical integrity, small multiples. `unslop-ui` doesn't redesign charts. It borrows the subtractive half of those ideas (one encoding per quantity, faint scaffolding, direct labels over legends) as U14 to U16, so you can build with the Tufte skill and clean up any interface with this one.
- [unslop](https://github.com/heydamir/unslop) by Damir Sokolovsky ([@heydamir](https://x.com/heydamir)) covers the whole screen instead of the copy: it writes a short design direction first, then works through spacing, color, icons, copy, type, layout, details, visuals and motion, with starting tokens for each. If a dashboard needs a redesign and not only a cleanup, run it first, then run `unslop-ui` as the final copy and chart pass. `unslop-ui` stays subtractive on purpose: it won't pick a direction, a palette or a type family for you.
- ## Credits
- The `--surface` rules, the verdict step and the report-as-tasks list were suggested by user feedback after comparing this skill with [unslop](https://github.com/heydamir/unslop) (CC BY 4.0). The values in `references/tokens.md` are written for this skill, using common practice (a 4px grid, 4.5:1 contrast, hairline borders).
- The unslop rules are by [Lauren Tan](https://github.com/poteto), from [pstack](https://github.com/cursor/plugins/tree/main/pstack) (MIT). U14 to U16 follow Edward Tufte's data-ink and chartjunk principles. The other UI patterns come from what designers and developers keep pointing out about AI-built interfaces in 2026.
- ## License
- [MIT](LICENSE)
Ratings and comments
Sign in to rate this skill.
Sign inFree to use. If it’s helped, pass it on.