Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Site from References: Brief to Website in 8 Steps

    1

    The reason is simple — the AI improvises from images and a vague request.

    $9.99

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Site from References: Brief to Website in 8 Steps

    Site from References: Brief to Website in 8 Steps

    Example session with this skill installed

    I want a landing page for my pilates studio in Austin,

    Balance Studio. The goal is booking a free trial class through WhatsApp. I like the look of https://reference-one.example and https://reference-two.example, and I saved 2 screenshots in etapas/00_briefing/prints/.

    • Read your context and instructions
    • Compiled the site from references

    Summary

    All 8 steps are done for

    Balance Studio. Steps 1, 5, 6 and 7 were approved by you and logged in etapas/aprovacoes.md. The site lives in site/, validated against the build plan, with a Dockerfile ready.

    Progress

    #StepFileStatus
    1Briefetapas/00_briefing/briefing.md✅ approved
    2Code extraction (2 sites)etapas/01_extracao/codigo/*/resumo.mddone
    3Screenshot extraction (2)etapas/01_extracao/prints/resumo.mddone
    4Previewetapas/02_previa/previa_site.mddone
    5Site imageetapas/03_mockup/mockup_home-desktop.svg✅ approved (v2)
    6Wireframes (1 page × desktop/mobile)etapas/04_wireframes/✅ approved
    7Design systemetapas/05_design_system/✅ approved
    8Build & validationsite/, etapas/06_construcao/done

    Design system (excerpt of generated tokens)

    TokenValueSource
    --color-primary#2F5D50your decision in the brief
    --color-bg#FAF7F2measured on reference 1
    --color-secondary#D98E5Festimated from screenshot 2
    --font-headingFraunces 600measured on reference 2
    --font-bodyInter 400measured on reference 1
    --space-2496px between sections (--space-16 on mobile)measured on reference 1

    WCAG contrast: body text on background 9.8:1 (AAA); primary button 5.1:1 (AA).

    :root {
      --color-primary: #2F5D50;
      --color-bg: #FAF7F2;
      --color-secondary: #D98E5F;
      --font-heading: "Fraunces", serif;
      --font-body: "Inter", sans-serif;
      --radius-full: 999px;
      --space-24: 96px;
    }
    

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Stop getting generic websites from AI

    Ask an AI agent to "make a site like this one" and you usually get the same thing: a template-looking layout, guessed colors, random typography, and hours of rework. The reason is simple — the AI improvises from images and a vague request.

    Site from References replaces improvisation with a process. It is a bundle of 10 skills that walks your agent through 8 steps, from understanding the business to a validated, deploy-ready site. Each step writes a structured text file that the next one reads, and the steps that shape the result only move forward with your approval.

    The 8 steps

    #StepWhat you getApproval
    1Interview & briefQuestions in rounds, each with a recommended answer → briefing.md✅
    2Design from codeColors, fonts, spacing, radii, shadows and breakpoints measured in a real browser (computed styles)
    3Design from screenshotsPalette with area and contrast (script) + typography and shape analysis, marked as estimated
    4Site previewPages, sections, content and visual direction in Markdown
    5Site imagePrompt + full-color SVG mockup✅
    6WireframesSVG for every page, desktop and mobile, with a review page✅
    7Design systemdesign_system.md + visual HTML version + tokens.css + Tailwind tokens, with WCAG contrast checks✅
    8Build & validateBuild plan, section-by-section code (tokens only), Docker/deploy and a validation report

    Why it works

    • Measured, not guessed. Step 2 opens your references in a real browser and reads computed styles — including what JavaScript renders.
    • Explicit trust order. Your decision > value measured in code > value estimated from a screenshot > mockup proposal. No silent conflicts.
    • One visual source of truth. design_system.md rules; code uses tokens only. Changing a color? Change it in the design system and regenerate tokens with a script.
    • Approvals at the right moments. Fixing a brief takes minutes; fixing a finished site takes hours.
    • Resumable. Progress lives in etapas/aprovacoes.md. Stop today, continue tomorrow — the orchestrator figures out which step you're on.
    • Ethical by default. References inform structure and style only. Their text, images, logos and code never reach your site — your brief's content or clearly marked placeholders do.
    • Secure. Ships with auditar-skill, which scans any third-party skill for prompt injection, data exfiltration, credential access, obfuscated code and destructive commands before installing it.

    What's included

    • 10 skills: orchestrator + one skill per step + security audit
    • 9 Python/JS scripts (computed-style extraction, screenshot palette, WCAG contrast, CSS/Tailwind tokens, HTML design system, wireframe validation)
    • Templates for brief, preview, image prompt, wireframe, design system, build plan and validation report
    • Ready project structure (etapas/, site/, CLAUDE.md) and setup scripts that audit and install the companion skills
    • Stack chosen in the interview (HTML/CSS, Tailwind, Vite or frameworks); default HTML + Tailwind, mobile-first

    Who it's for

    Freelancers and agencies shipping landing pages, developers tired of "looks like a template", and founders who know what they want but can't translate it into design.

    Use cases

    • Competitor Redesign: Replicating the design language of a reference site while using custom business logic.
    • Landing Page Sprint: Moving from a blank slate to a deployed, containerized landing page with a full design system.
    • Safe Plugin Integration: Auditing external AI skills for security vulnerabilities before adding them to your workspace.

    Known limitations

    Design extraction from screenshots provides estimated values rather than exact CSS. Playwright extraction requires a local browser environment to capture computed styles accurately.

    Screenshot extraction uses estimated values. Playwright requires a local browser for computed style capture. Large JS-heavy sites may require manual cookie consent bypass during extraction.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 15 days ago

    Requires

    Python
    Node.js
    create-video
    Git

    Permissions

    Terminal / Shell
    Read Files
    Browser
    Network Access
    Write Files

    Allowed Hosts

    example.com

    Reads and writes stay inside the project: etapas/ holds the brief, extractions, wireframes and design system; site/ holds the generated code. Network is used only to fetch the HTML/CSS of the reference URLs you provide and, during setup, to download companion skills from GitHub — each audited before install. No data is sent to external servers and no API key is needed.

    Listed15 days ago
    Updated10 days ago

    What's inside

    Frequently Asked Questions

    Unlike single-prompt generators, this skill uses a strict 8-step pipeline that creates a design system and wireframes first, preventing style hallucinations and ensuring the final code matches your specific business goals.

    The skill generates production-ready code for modern frameworks including React, Vue, and Vite, with a heavy emphasis on Tailwind CSS for styling and Docker for containerized deployment.

    You will receive the complete automated workflow, including the discovery interview modules, design extraction scripts, SVG wireframing templates, and the security auditing sub-skill.

    While the skill automates the extraction of styles and typography from references, you will need a local environment capable of running Playwright and Python to perform the live web analysis.

    The built-in security sub-skill automatically scans third-party scripts and plugins for malicious commands or prompt injections before they are integrated into your codebase, ensuring a safe production environment.

    Extraction from live URLs using Playwright captures exact computed CSS, whereas screenshot analysis provides high-fidelity visual estimates for colors and layouts when a live URL isn't available.

    Not to run the flow: you answer the interview and approve the steps. Publishing the site is easier with basic Git and hosting knowledge — step 8 already prepares Docker and deployment for the host you picked.

    Yes. Without URLs step 2 is skipped; without screenshots, step 3. The design comes from the brief and the mockup.

    No. References inform structure and style only. Their text, images, logos and code never reach your site.

    The one you pick in the interview (HTML/CSS, Tailwind, Vite, frameworks). Default: HTML + Tailwind, mobile-first.

    Yes. Progress is stored in `etapas/aprovacoes.md` and the orchestrator resumes from the right step in a new session.

    It was built and tested on Claude Code. The `SKILL.md` files follow the open standard, but the flow relies on `CLAUDE.md` and several skills loaded together — other agents may need adjustments.

    They belong to other authors and have their own licenses, so they are not bundled. The included script downloads each one, audits it and installs only the audited commit.

    New in Frontend & Web Apps