agentleFS
Sign inStart free
jhy0285jhy0285/monofield/skills/impeccable-design-polish/SKILL.md

impeccable-design-polish

Skill6 starsChanged 5 months agoApache-2.0View on GitHub

Follow-up design polish skill inspired by Impeccable. Use after a web or HTML artifact exists to audit, critique, polish, animate, harden, and prepare the page for a live/share pass.

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:

    Use this skill as the post-generation pass for an existing design.

    line 38
  2. Distinctive:

    Animate: add restrained, useful motion only where it improves feedback or storytelling.

    line 45
  3. Distinctive:

    Keep the existing content, brand, and scenario unless the user explicitly asks to change them.

    line 52
  4. Distinctive:

    Prefer a few decisive fixes over broad cosmetic churn.

    line 53
  5. Distinctive:

    Remove common AI tells:

    line 54

≈ “Common” is an estimate: at least 1 in 5 of the 308,232 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

Impeccable Design Polish

Use this skill as the post-generation pass for an existing design. It should not restart the project from scratch; it should make the current artifact sharper, more usable, and closer to something a designer would ship.

Follow-Up Modes

  • Audit: identify the highest-impact issues in hierarchy, spacing, color, type, interaction states, responsiveness, and accessibility.
  • Critique: explain what feels generic, overdesigned, underdesigned, or inconsistent.
  • Polish: directly edit the artifact to improve the top issues while preserving the user's intent.
  • Animate: add restrained, useful motion only where it improves feedback or storytelling.
  • Harden: repair mobile overflow, text clipping, contrast problems, missing states, broken links, and fragile layout assumptions.
  • Live: prepare the artifact for presentation or sharing, including final visual QA and clear next actions.

Operating Rules

  1. Inspect the current HTML/page before editing. Do not guess from the prompt alone.
  2. Keep the existing content, brand, and scenario unless the user explicitly asks to change them.
  3. Prefer a few decisive fixes over broad cosmetic churn.
  4. Remove common AI tells:
    • purple-blue glow gradients with no product reason
    • generic 3-card feature rows
    • oversized rounded cards everywhere
    • empty marketing adjectives
    • inconsistent spacing and type scale
    • decorative effects that do not support comprehension
  5. Preserve accessibility: focus states, contrast, semantic controls, readable text, and reduced-motion fallbacks.
  6. Finish with the artifact in a better runnable state, not just a critique list.

Best Pairings

  • Pair with design-taste-frontend or gpt-taste for stronger anti-slop redesign work.
  • Pair with emilkowalski-motion or GSAP skills for motion-specific polish.
  • Pair with image/video skills when the artifact needs real visual assets rather than CSS-only decoration.

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.

Check your setup, free