Skip to content
Agentmart
Submit a tool

frontend-mockup

Implement frontend screens from a mockup image and use the local visual-check loop to compare the result against the reference.

Skill by SofianeBel

IndexedMIT
Write a review

Chalk Labs

Need help deploying frontend-mockup?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/sofianebel-frontend-mockup

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Implement frontend screens from a mockup image and use the local visual-check loop to compare the result against the reference.

Use cases: frontend

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/frontend-mockup

What's inside

Skill name
frontend-mockup
Description
Implement frontend screens from a mockup image and use the local visual-check loop to compare the result against the reference.
License
MIT
Instructions
47 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Frontend Mockup

Use this skill when implementing a frontend UI from a mockup image or static design reference.

## Workflow

1. Inspect the mockup before coding. Identify layout grid, spacing, typography, colors, shadows, border radii, icons, image assets, and responsive assumptions.
2. Build the UI in small passes: structure first, then spacing, then typography/colors, then polish details.
3. Keep visual references in `.visual-references/`; never copy them into the frontend app.
4. Run the app locally with the project command from `visual.config.json`.
5. Run `npm run visual:check`.
6. Read `artifacts/visual-report.json` and inspect `artifacts/diff.png`.
7. Fix anti-cheat, asset, DOM, interaction, responsive, and accessibility failures before tuning pixels.
8. Repeat until the final score and visual score meet their configured targets.

## Forbidden Shortcuts

Never:

- embed the full mockup as an image
- use the mockup as a CSS background
- convert the mockup to base64
- draw the mockup on canvas
- place invisible clickable zones over an image
- copy reference screenshots into `public`, `src`, or app assets
- use one full-page SVG/image as the UI

Always:

- use semantic HTML
- use real text
- use real buttons and links
- use CSS layout
- use reusable components
- use only explicitly allowed assets
- keep the UI interactive and accessible

## Implementation Rules

- Match the reference viewport exactly before judging visual fidelity.
- Disable or stabilize animations, timers, randomized content, and loading states during capture.
- Prefer real CSS/layout fixes over moving elements only to satisfy one screenshot.
- Treat anti-cheat failure as a hard failure: final score must be `0`.
- Treat generated reports as objective signals, not perfect diagnosis. Use the diff image to decide what changed.
- Keep the final answer tied to evidence: final score, visual score, gate failures, report path, and whether the check passed.

From SofianeBel/codex-frontend-plugin, MIT.

Signals

Stars
0
Forks
0
Open issues
0
Last commit (this folder)
Jun 4, 2026 (4 months ago)
Last release
Jun 4, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from SofianeBel

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped
50+
launches shipped
media placements
500+
media placements
founders on every account
2
founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get frontend-mockup running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Goes to the Chalk Labs founders, not the newsletter. Privacy

Need help deploying frontend-mockup?

CallGet help
Cite this page

frontend-mockup skill. Agent Mart. https://agentmart.dev/skills/sofianebel-frontend-mockup (last updated 2026-10-24)