agentleFS
Pesty-MarketingPesty-Marketing/agent-skills/desktop-mockup/SKILL.md

desktop-mockup

Skill0 starsChanged 25 days agoMITView on GitHub

Create presentation-ready website screenshots inside a desktop Chrome browser mockup. Use for desktop mockups, browser-framed screenshots, and Chrome window images from a URL or existing screenshot.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create a real website screenshot inside a light Chrome window with tab, address bar, rounded corners, and shadow.

    line 8
  2. Distinctive:

    Use local headless Chromium, a 1440 × 900 content viewport, 2× capture/export, and transparent PNG output.

    line 12
  3. Distinctive:

    Use ScreenshotAPI when the user chooses scale, batch/hosted capture, or explicitly requests it.

    line 14
  4. Distinctive:

    Read command options for viewport dimensions, a requested page section, an existing PNG, background color, or a 4K slide export.

    line 32
  5. Distinctive:

    Keep website pixels intact through deterministic HTML/CSS framing.

    line 36

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Desktop Mockup

Create a real website screenshot inside a light Chrome window with tab, address bar, rounded corners, and shadow. Deliver the framed image; a raw screenshot alone is incomplete.

Defaults

Use local headless Chromium, a 1440 × 900 content viewport, 2× capture/export, and transparent PNG output. Use the requested URL's hostname in the frame, and the page title in the tab. Save in the task's output directory or a new folder under ~/Documents/website-mockups/.

Use ScreenshotAPI when the user chooses scale, batch/hosted capture, or explicitly requests it. Read hosted capture for that branch. Creating a paid plan or subscription requires a separate request.

Create

  1. Resolve the target URL from the user or current artifact. Ask only if no target is available.
  2. Find this skill's installation directory. For first use, follow setup: Node.js 20+, npm ci, then npm run setup. Each skill contains its own renderer and assets; it works independently of the other mockup skill. Existing bundled Playwright packages are optional.
  3. From this skill folder run:

    npm run capture -- --url https://example.com/ --out ./output

    Substitute the actual URL and output directory. Run node scripts/capture.cjs --help for supported options. The browser runs in the background without a visible window.

  4. Inspect capture.png and mockup.png. Verify the real page, loaded fonts/images, correct address/title, complete frame, preserved proportions, and unobstructed content. Read back dimensions and transparency. A blocked or incomplete page is a failed capture, not a successful mockup.
  5. Return the mockup inline and link the PNG. Link slide.png when requested. Retain the source capture, self-contained HTML, and metadata beside it.

Customize

Read command options for viewport dimensions, a requested page section, an existing PNG, background color, or a 4K slide export. Inspect the current DOM before using --hide to suppress an obstructive popup or chat widget only within the capture session. Preserve meaningful page content.

The helper captures one viewport. For a full-page request, choose a section, separate captures, or an explicitly tall frame; preserve readable proportions. Existing images must match the intended viewport aspect ratio, which the helper checks.

Keep website pixels intact through deterministic HTML/CSS framing. The Chrome controls are illustrative. Personalized content and tracking numbers may vary between sessions. Use consistent capture preparation for comparisons.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.