agentleFS
ne11nnne11nn/cantos-plugin/skills/ui-refactor/SKILL.md

ui-refactor

Skill1 starsChanged 5 months agoMITView on GitHub

Tactical user interface design guide for fixing layouts, selecting colors/fonts, and creating professional UIs. Use when the user asks to "make this look better," needs help with CSS/styling decisions, wants to create a design system, or needs to fix a cluttered interface.

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈4

    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:

    Feature First: Do not start by designing a "shell" (nav bars, sidebars).

    line 12
  2. Distinctive:

    Define Systems: Do not use arbitrary values.

    line 14
  3. Distinctive:

    Limit Choices: If you can't decide between two options, you have too many choices.

    line 29
  4. Distinctive:

    Complexity: Do not design for edge cases first.

    line 33

≈ “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

UI Refactoring and Design

This skill applies tactical, logical rules to user interface design. It prioritizes clarity, hierarchy, and systems over "artistic talent."

Core Workflow

  1. Feature First: Do not start by designing a "shell" (nav bars, sidebars). Start with the specific functionality (e.g., the search form, the contact card).
  2. Low Fidelity: Ignore color, shadows, and fonts initially. Design in grayscale using a thick marker or basic wireframes to solve layout and spacing first.
  3. Define Systems: Do not use arbitrary values. establishing restrictive systems for spacing, type, and color immediately.
  4. Refine: Apply specific tactics for hierarchy, depth, and polish.

Domain-Specific Tactics

Consult these references for specific implementation rules:

  • Making elements stand out/fit in: See hierarchy.md (Size, weight, contrast, semantics).
  • Whitespace and alignment: See layout-spacing.md (Grids, spacing scales, density).
  • Text and fonts: See typography.md (Type scales, line-height, fonts).
  • Colors and palettes: See color.md (HSL, saturation, accessible contrast).
  • Images, shadows, and polish: See depth-and-polish.md (Light sources, assets, finishing touches).

Quick Heuristics

  • Limit Choices: If you can't decide between two options, you have too many choices. constrain your inputs (colors, font sizes, spacing) to a pre-defined scale.
  • Personality:
    • Serious/Elegant: Serif fonts, sharp corners, gold/blue colors, formal language.
    • Playful/Friendly: Rounded sans-serifs, large border-radius, pink/orange, casual language.
  • Complexity: Do not design for edge cases first. Design the "happy path" (simple version), then iterate for complexity.

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.