- Home
- Skills
- Frontend & Web Apps
- inspo: design research that ends in a built page
More screenshots
Works with the AI Agents you already use
inspo: design research that ends in a built page
Gathers ~50 real references per page section from your industry, lets you vote on a local board, then builds the page.
$9.99
inspo: design research that ends in a built page
Example session with this skill installed
/inspo a subscription for Mexican specialty coffee, roasted weekly. I love bluebottlecoffee.com, it must not feel corporate.
- Read your context and instructions
- Compiled the inspo
Here's what I understood: a
website (a marketing site with a store front) for a monthly subscription to Mexican specialty coffee, roasted every week and shipped fresh. It's for people who already drink good coffee and want it fresh without thinking about it. The visitor should
pick a plan and subscribe. It should feel crafted and warm, like Blue Bottle, and never corporate.
Before I research, three quick questions:
- Do you already have a logo or brand colors I should keep?
- Three words for how it should feel? (My guess: warm, crafted, honest.)
- Copy in Spanish (es-MX), English, or both?
Proposed sections, in page order
| # | Section | Why this page needs it |
|---|---|---|
| 1 | navbar | Plans and "Subscribe" always one tap away |
| 2 | hero | The promise: roasted this week, at your door next week |
| 3 | catalog | The origins (Chiapas, Oaxaca, Veracruz) and roast profiles |
| 4 | process | Farm → roast → door: the reason to pay for freshness |
| 5 | pricing | 2–3 plans by bag size and frequency, the main conversion |
| 6 | about | The roaster and the producers behind each bag |
| 7 | testimonials | Proof from people who already subscribe |
| 8 | faq (optional) | Pausing, skipping and shipping zones |
| 9 | footer | Contact, socials and newsletter |
What happens next
- I'll gather
about 50 references per section (around 450 in total), mostly from coffee and food & drink sites, with live sites cut into the matching section so you compare heroes with heroes. Want more or fewer?
- In the meantime I'll render your landing in
5 style directions with real coffee photos. My first picks:
Editorial Serif,
Organic Soft,
Dark Luxury,
Neo-Brutalist (the surprise), plus a custom "Oaxacan clay" direction made for this brand.
- The
Lab will have live components to vote on: a 3D coffee bag that rotates with the scroll, Editorial Text Reveal, and a Sticky Stack Scroll for the farm → roast → door story.
- When the board is ready, you vote 👍 / 👎 / ★ section by section and press
Send. Then I write a plan for each section from your favorites, export the PDF report, and build the page.
Tell me what to add or remove from the list and I'll start.
Connects securely to your tools. The creator never sees your data.
About this skill
Tell your agent what you're making. inspo gathers about 50 references for every section of your page, renders your own product in several visual styles with real photos, opens a local board where you vote on all of it, and then builds the page. It works for websites, web systems (SaaS, dashboards, admin panels) and mobile apps.
Why it's different
- References from your industry. A restaurant gets food sites. About 40 of every 50 references come from your industry, and the other 10 come from anywhere, for ideas you wouldn't have looked for.
- Real sites, cut into sections. It visits award-winning sites (Awwwards, Siteinspire, Sites of the Day), closes the cookie banners, finds the hero, the catalog or the footer, and screenshots just that part. You compare footers with footers.
- You vote instead of describing. 👍, 👎 or ★ on every reference, style and component, plus why (layout, type, color, motion). The agent reads your votes and looks at the images you liked.
- It ends in a page. The agent builds the page from your votes, and you keep commenting section by section until it's right: v1, v2, v3, all on the same board.
How it works
- The idea. The agent reflects back what it understood and asks only what's missing: audience, the feeling, sites you love, brand assets. If there's a repo or a running app, it looks at it first.
- Sections or screens. It recommends a list for your kind of project (19 website sections, 22 app screens), one line of why each, and you adjust it.
- Research. A background harvest of ~50 references per section from galleries (Dribbble, footer.design, navbar.gallery, Collect UI, SaaS Interface…) and live sites. The agent reviews every section on numbered contact sheets and removes anything that doesn't belong.
- Styles and components. 4–6 style directions rendered with your copy and CC-licensed photos (16 presets: Swiss Minimal, Editorial Serif, Neo-Brutalist, Tech Noir…), plus 18 live 3D and motion components (WebGL shaders, a dot globe, particle galaxies, magnetic buttons, sticky stacks…).
- Votes → plan → brief → PDF. You vote and press Send. The agent analyzes your favorites, publishes a plan per section that you can edit and approve, writes the brief with CSS tokens (
DESIGN.md) and exports a studio-style PDF report. - The page. A responsive HTML page (or a clickable prototype for apps), published to the board in desktop, tablet and mobile. Click anything to pin a comment, attach a reference, and choose tweak, replace, add above or add below. The agent applies each one and publishes the next version.
What's in the package
SKILL.md: the full workflow plus setup for Claude Code, Cursor, VS Code Copilot, Windsurf, Claude Desktop, Codex CLI and Gemini CLI.- A local MCP server (Node.js) with 21 tools, the voting board, the PDF report, 16 style presets and 18 live components.
- Two playbooks: research recipes per niche, and how to port components to React / R3F / GSAP.
Requirements
- An agent that supports MCP servers.
- Node.js 20+ and Google Chrome (or Playwright's Chromium).
- Internet access while researching. Mobbin is optional and needs your own account.
What it accesses, and why
Everything runs on your machine. On first start it runs npm install for its three dependencies (the MCP SDK, Playwright and zod). While researching, it drives your local Chrome to read public design galleries and live sites at human pace, and fetches CC-licensed photos from Openverse. The board is served on localhost. Sessions, screenshots and votes are saved in .inspo/ inside your project. It sends nothing to any server of its own, needs no API keys, and only reads the INSPO_DIR, INSPO_PORT and INSPO_HOME settings.
Good to know
References are for inspiration: the skill takes principles, never pixels, and never clones a site. Open source under the MIT license.
Needs an agent that supports MCP servers, Node.js 20+ and Google Chrome (or Playwright's Chromium), and runs locally (not in browser-only chat apps). A full harvest takes several minutes (about 6 minutes for 250 references). Design galleries change their markup now and then, so a source can return nothing until it's updated; the harvest uses many sources, so it keeps working. Mobbin needs your own account. Builds are standalone HTML; porting to your React/Next stack is done by your agent afterwards.
How to use
- 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
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 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 1 month ago
Requires
Permissions
Allowed Hosts
File Scopes
Terminal/shell: the launcher (bin/inspo-mcp.sh) runs `npm install --omit=dev` once, for @modelcontextprotocol/sdk, playwright and zod, then starts the local MCP server with Node. Browser + network: Playwright drives the user's local Chrome to read public design galleries (the domains listed above) and live sites at human pace, fetches CC-licensed photos from api.openverse.org, and loads Google Fonts and three.js/GSAP from jsDelivr in the rendered previews. Read/write files: screenshots, votes, DESIGN.md, the PDF report and the built pages are saved in .inspo/ (and the page in inspo-build/) inside the user's project. Environment variables: only INSPO_DIR, INSPO_PORT and INSPO_HOME (folder, board port, browser profile). No API keys, no telemetry, nothing is sent to a server of its own; the board is served on localhost.