agentleFS
Dragoon0xDragoon0x/10x-interface/skills/interface-craft/SKILL.md

interface-craft

Skill0 starsChanged 2 months agoMITView on GitHub

Refine visual hierarchy, typography, spacing, density, color, material, and optical alignment. Use when an interface looks unresolved, cramped, flat, or busy, or when tightening visual quality before release.

We split this skill into the rules it gives an agent

13 rules. 0 are common, 12 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 9 edited versions we read keep these.

  • 12

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use color for hierarchy, state, emphasis, interaction, category, and brand.

    line 40
  2. Distinctive:

    Check metaphor, optical size, weight, alignment, consistency, accessible naming, and interaction states.

    line 48
  3. Distinctive:

    Check crop, focal point, aspect ratio, loading, fallback, accessibility, and visual weight.

    line 52
  4. Distinctive:

    When something feels wrong, find the cause before prescribing.

    line 56
  5. Distinctive:

    Before adding a detail ask what it communicates.

    line 66
  6. Very specific:

    Use references/craft-review.md to review hierarchy, typography, rhythm, density, color, material, optical alignment, and state consistency.

    line 70
  7. Distinctive:

    Before changing anything, identify the actual user outcome, the existing system, the relevant constraints, and the evidence available.

    line 80
  8. Distinctive:

    Do not begin by choosing a visual treatment.

    line 82
  9. Distinctive:

    Do not review only the happy path.

    line 99
  10. Distinctive:

    Use only scenarios that are relevant to the surface.

    line 116
  11. Distinctive:

    When code exists, verify that the implementation preserves the interface decision.

    line 120
  12. Distinctive:

    If a change improves none of these and only adds decoration, treat it as suspect.

    line 162
  13. Distinctive:

    Do not claim a check that did not occur.

    line 178

“Common” is measured: kept by at least 6 in 10 of the 9 edited versions of this file we could read. “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

Interface Craft

Mission

Make the interface feel deliberate. Craft is not adding detail; it is removing ambiguity from visible decisions until the result feels coherent and appropriate.

Inspect first

Study existing typography, spacing, color, shape, borders, shadows, iconography, imagery, density, and states before changing the visual language.

Hierarchy first

Determine what should be seen first, understood second, acted on, and kept quiet. Use size, weight, contrast, position, spacing, density, grouping, and shape with restraint.

Typography

Evaluate family, weight, size, line height, tracking, measure, wrapping, truncation, baseline, and optical weight together with surrounding whitespace.

A technically correct font size can still be wrong if the composition gives the heading excessive visual mass.

Spacing

Spacing creates relationships. Use larger gaps to separate ideas and smaller gaps to bind related elements. Avoid uniform spacing everywhere.

Optical alignment

Inspect icons, circles, logos, glyph-heavy labels, buttons, pills, and asymmetric imagery. Mathematical alignment is only the starting point.

Density

Dense interfaces can be excellent for frequent expert workflows when hierarchy is strong. Sparse interfaces can be excellent when focus matters. Never equate sparse with premium or dense with clutter.

Color

Use color for hierarchy, state, emphasis, interaction, category, and brand. Check light, dark, disabled, error, success, selected, and focus conditions.

Material

Borders, shadows, tonal surfaces, blur, and overlap all communicate relationships. Avoid stacking multiple elevation signals without purpose.

Icons

Check metaphor, optical size, weight, alignment, consistency, accessible naming, and interaction states.

Imagery

Check crop, focal point, aspect ratio, loading, fallback, accessibility, and visual weight.

Diagnosis

When something feels wrong, find the cause before prescribing.

"Too much whitespace" may actually be weak grouping. "Flat" may actually be weak hierarchy. "Busy" may actually be competing emphasis signals.

Micro-detail audit

Inspect baseline drift, one-off spacing, inconsistent radii, mismatched shadows, weak focus treatment, awkward wrapping, cramped labels, accidental borders, mismatched icon weight, and unfinished empty/loading states.

Restraint

Before adding a detail ask what it communicates. If the answer is only "more polished," consider removing competing detail instead.

Reference artifact

Use references/craft-review.md to review hierarchy, typography, rhythm, density, color, material, optical alignment, and state consistency.

Completion criteria

Hierarchy is immediately legible, relationships are intentional, the visual grammar is coherent, and remaining imperfections are low-impact rather than structural.

Expert Review Protocol

First pass: understand

Before changing anything, identify the actual user outcome, the existing system, the relevant constraints, and the evidence available.

Do not begin by choosing a visual treatment.

Second pass: compare

Ask:

  • What is the simplest credible solution?
  • What is the strongest alternative?
  • What does the current solution cost?
  • What behavior does each option teach the user?
  • Which decision is easiest to reverse?
  • Which failure would be most expensive?

Choose deliberately.

Third pass: stress

Do not review only the happy path.

Apply pressure through:

  • repetition
  • interruption
  • missing content
  • long content
  • slow operations
  • narrow space
  • large text
  • keyboard use
  • touch use
  • focus changes
  • error recovery
  • restoration

Use only scenarios that are relevant to the surface.

Fourth pass: inspect the implementation

When code exists, verify that the implementation preserves the interface decision.

Look for:

  • duplicated sources of truth
  • styling that bypasses the system
  • state that can become stale
  • behavior that differs from adjacent components
  • abstractions that obscure rather than simplify
  • dependencies that are not earning their cost
  • performance work performed without evidence

Fifth pass: critique the result

Ask:

If this were shipped tomorrow, what would users notice that the builder has stopped noticing?

Look for:

  • friction
  • ambiguity
  • inconsistency
  • unnecessary movement
  • weak recovery
  • hidden state
  • visual noise
  • inaccessible behavior
  • fragile edge cases

Sixth pass: distinguish polish from substance

A useful change improves one or more of:

  • understanding
  • speed
  • confidence
  • recovery
  • accessibility
  • consistency
  • maintainability

If a change improves none of these and only adds decoration, treat it as suspect.

Seventh pass: verify

A claim is complete only when an appropriate form of evidence supports it.

Use:

  • direct interaction
  • tests
  • runtime inspection
  • visual comparison
  • accessibility checks
  • performance measurement
  • source inspection

Do not claim a check that did not occur.

Completion standard

Stop when:

  1. the intended outcome is achieved
  2. important states are handled
  3. meaningful failure modes were considered
  4. the interface fits its surrounding system
  5. important claims are verified
  6. remaining imperfections are lower-value than the risk of further change

The goal is not maximal polish.

The goal is a result that is difficult to improve without changing the underlying decision.

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.