Nobody pays for one screen; that went free when coding agents got good. What remains is a tuned multi-model pipeline refined over months, and a canvas where a change is a click instead of a file re-prompted. Neither is a moat — the prompt below is the honest test of what they are worth to you.
REPLACEMENT BRIEF
design
Can AI replace Sleek?
EDITORIAL ANSWERKINDACurated prompt
One screen is already a yes without this site — 'design me a settings screen, Tailwind, 402x874' into the agent you pay for gets something decent. What Sleek sells is twelve screens that look like one app, and much of that is prompt discipline: fix the design system once, paste it into every call, hand the model the mobile conventions it skips unprompted. Two gaps remain — no canvas, so edits are re-prompts not clicks, and one model call is rougher than a tuned chain — but the Figma handoff is not one of them; their converter is MIT on npm.
Generate one design system, generate each mobile screen as a standalone Tailwind HTML file against it, review them together in phone frames, and export PNGs plus editable Figma layers.
Build the personal version →AT A GLANCE
- price
- $24.99/mo
- listed annual price
- $299.88/yr
- replaceable scope
- Generate one design system, generate each mobile screen as a standalone Tailwind HTML file against it, review them together in phone frames, and export PNGs plus editable Figma layers.
- build time
- weekend
Build promptreviewed prompt · not run
the prompt
Curated promptBuild me a mobile app screen designer to replace Sleek. Requirements:
- A local Next.js app (App Router) calling the Anthropic API (claude-opus-5,
key in .env). Stream it with max_tokens 32000 · a screen plus its thinking
share that budget, and it rejects sampling params and assistant prefills
outright. Screens are files on disk, no database.
- One route handler takes a plain-language description of the app, or a sketch
I drop on the page, and answers with a screen list first: 6 to 10 names, one
line of purpose each. I edit that list, then it builds every screen on it.
- That same first call writes design-system.json (5 hex colors, 2 fonts with a
6-step type scale, radius, spacing unit, icon set) and _nav.html, and nothing
regenerates either afterwards · every later call gets both pasted in verbatim,
which is what stops screen 9 drifting away from screen 1.
- Each screen is public/screens/<name>.html: one standalone file, Tailwind via
CDN, Lucide icons, a 402x874 viewport with 62px top and 34px bottom insets as
CSS variables, 44px minimum tap targets, and that same nav.
- Edits re-send the current file plus my instruction and overwrite it in place,
so untouched parts stay put; every version lands in screens/.history/.
- The page is a gallery: each screen in an iframe inside a phone frame, side by
side, a text box under each for the next edit. `npm run export` runs
Playwright at deviceScaleFactor 3 into exports/ plus a contact sheet.
- A "copy all to Figma" button: @figit/dom-to-figma (MIT), one frame per screen
passing that iframe's contentDocument.body, convert({ frames }), then
clipboard.write with its toClipboardItem(). Cmd+V in Figma lands the whole
set as editable layers. Keep it in a client component and fire it from a real
click, or the write is blocked.
- Out of scope, do not build: a click-to-edit canvas, share links, or hosting.
Runs on my machine, no accounts, no telemetry.
- README: the API key, `npx playwright install chromium`, where files land, and
that remote images need an imageLoader proxying around CORS.Copy or open in an agent
The prompt stays readable first. Choose a launch option when you are ready.
$ open in your agent (prompt prefilled, you press enter) or copy it raw
what AI can build
Generate one design system, generate each mobile screen as a standalone Tailwind HTML file against it, review them together in phone frames, and export PNGs plus editable Figma layers.
The prompt was editor-reviewed; no completed build is recorded.
The honest tradeoff
why people still pay
what you lose
xclicking an element to change it instead of re-prompting the whole file
xa tuned multi-step pipeline · you get one prompt on one model, and you close the gap in your own iteration time
xsketch input · photograph a hand-drawn screen and get it back as a design
xshare links, project history, and team seats
Start with existing software
prior art · use these instead of building, if you'd rather
dom-to-figmaMIT converter turning a DOM tree into editable Figma layers on paste; Sleek's own team ships it and the README says it runs in production there↗Penpotopen-source design tool where a multi-screen mobile file stays editable, if you want layers rather than a folder of PNGs↗OnlookApache-2.0 visual editor for React codebases, the nearest thing to click-to-edit; web-focused, and the hosted product is now waitlisted↗
EVIDENCE LEDGER
What this page can prove
The verdict judges replaceability. The evidence level records what DeepFeather actually checked.
evidence level
Curated promptThe prompt was editor-reviewed; no completed build is recorded.
Starter · monthly
known limits · clicking an element to change it instead of re-prompting the whole file; a tuned multi-step pipeline · you get one prompt on one model, and you close the gap in your own iteration time
BUILD FEEDBACK
Did you try this build?
Report the outcome. Submissions enter a manual evidence queue and never auto-upgrade the verdict.
related verdicts
Want next week’s replacements?
New verdicts + most-wanted, weekly. Free. One-click out.
Share this verdict
questions
Can AI replace Sleek?
Possibly for a narrower core workflow, but this catalog judgment is not a verified build. Expected gaps include: clicking an element to change it instead of re-prompting the whole file, a tuned multi-step pipeline · you get one prompt on one model, and you close the gap in your own iteration time. Validate the prompt against your own acceptance criteria before committing.
How much does Sleek cost?
Sleek is listed at about $24.99/month (Starter, checked 2026-07-30), or $299.88 per year. This is a pricing reference, not evidence of a completed replacement or realized savings.
What do I lose by replacing Sleek?
Honestly: clicking an element to change it instead of re-prompting the whole file; a tuned multi-step pipeline · you get one prompt on one model, and you close the gap in your own iteration time; sketch input · photograph a hand-drawn screen and get it back as a design; share links, project history, and team seats. If any of those are load-bearing for you, keep paying.
Is there an open-source alternative to Sleek?
Yes — dom-to-figma (MIT converter turning a DOM tree into editable Figma layers on paste; Sleek's own team ships it and the README says it runs in production there), Penpot (open-source design tool where a multi-screen mobile file stays editable, if you want layers rather than a folder of PNGs), Onlook (Apache-2.0 visual editor for React codebases, the nearest thing to click-to-edit; web-focused, and the hosted product is now waitlisted). Using prior art is also a valid exit; the prompt is for when you want it exactly your way.