agentleFS
Rafaelrr5Rafaelrr5/agent-cortex/skills/multi-layout-preview/SKILL.md

multi-layout-preview

Skill1 starsChanged 37 days agoMITView on GitHub

Use when creating multi-layout website previews.

The file

We split this skill into the rules it gives an agent

11 rules. About 0 are common, 9 are distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈9

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Create functional prototypes of multiple website layouts to compare designs visually and interactively, ensuring they work in a real …

    line 10
  2. Very specific:

    Write a rendering script (e.g., shoot.py) that:

    line 15
  3. Distinctive:

    After generating layout screenshots, generate a palette sheet:

    line 22
  4. Distinctive:

    Create a blank canvas.

    line 23
  5. Distinctive:

    Verify the output by checking the screenshots and palette sheet for correctness.

    line 26
  6. Distinctive:

    No static mockups: avoid using image editors to create the previews.

    line 29
  7. Distinctive:

    Do not skip the console error check.

    line 34
  8. Distinctive:

    Do not skip the clipping check.

    line 35
  9. Distinctive:

    Do not reuse screenshots from previous runs without verifying the layout and palette are up-to-date.

    line 36
  10. Distinctive:

    Do not forget to update the palette sheet when changing palettes.

    line 37
  11. Very specific:

    Run python scripts/preview.py from this directory.

    line 40

≈ “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

When to Use

Create functional prototypes of multiple website layouts to compare designs visually and interactively, ensuring they work in a real browser without console errors or layout overflow.

Procedure:

  1. Prepare layout directories: each layout in its own folder with an index.html.
  2. Prepare palette preview images: each as P-<palette>.png in a palettes/ directory.
  3. Write a rendering script (e.g., shoot.py) that:
    • Uses Playwright to load each layout in a browser.
    • Waits for layout to stabilize (e.g., 1800ms).
    • Checks for console errors and fails if any.
    • Checks the wordmark (or a specific element) for overflow (scrollWidth > clientWidth) and fails if clipped.
    • Takes a screenshot of the layout (and optionally scrolls to other sections).
    • Saves screenshots to a shots/ directory with a naming convention (e.g., A1-hero.png).
  4. After generating layout screenshots, generate a palette sheet:
    • Create a blank canvas.
    • For each layout and palette, place the palette preview image and label.
    • Save the combined image (e.g., PALETTES.png).
  5. Verify the output by checking the screenshots and palette sheet for correctness. Preferences:
  • Functional prototypes: the layouts must be actual HTML/CSS/JS that run in a browser.
  • No static mockups: avoid using image editors to create the previews; use the actual browser.
  • Error checking: treat any console error as a failure.
  • Clipping check: treat any overflow of the wordmark (or designated element) as a failure.
  • Palette sheet: must show all palette previews with labels for easy comparison. Pitfalls:
  • Do not skip the console error check; JavaScript errors can break the layout unpredictably.
  • Do not skip the clipping check; overflow may not be visible in the screenshot but breaks the design.
  • Do not reuse screenshots from previous runs without verifying the layout and palette are up-to-date.
  • Do not forget to update the palette sheet when changing palettes; it should reflect the current set.

Runnable public anchor

Run python scripts/preview.py from this directory. See verification for scope and negative tests.

Attribution

Prepared by Rafael with AI assistance. Adapted from private procedural notes whose recorded author was Hermes Agent. This is not a claim of sole authorship of those notes. Third-party tools retain their own licenses.

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.

Reviews can't be read right now.

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.