agentleFS
igovetigovet/cortex-orch-acp/skills/design-ui-ux-pro-max/SKILL.md

design-ui-ux-pro-max

Skill1 starsChanged 59 days agoMITView on GitHub

Design-system foundations for product UI. Choose or check a palette, type pairing, spacing scale and UX rules from bundled reference tables, with a pre-delivery checklist. Use when a visual system must be chosen or reviewed for a product interface, not for backend or logic-only work.

The file

We split this skill into the rules it gives an agent

7 rules. About 0 are common, 5 are distinctive, and 2 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.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Use this skill to establish or check the foundations of a product interface: palette, type pairing, spacing, component conventions and UX …

    line 8
  2. Distinctive:

    Read them through Cortex read_skill using the corresponding registered id: design-colors, design-typography, design-ux-guidelines, …

    line 33
  3. Distinctive:

    Read only needed tables; do not assume the whole set is loaded in context.

    line 35
  4. Very specific:

    Use them as starting points, then adapt to the brief and to any DESIGN.md direction.

    line 45
  5. Very specific:

    Choose a type pairing: Use typography.csv rows whose mood and best-for fields match the product.

    line 48
  6. Distinctive:

    Do not mix flat and skeuomorphic styles in one product, and do not use emoji as functional icons.

    line 68
  7. Distinctive:

    Keep one icon family with consistent stroke weight and sizing.

    line 70

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 UX Pro Max (Cortex adaptation)

Use this skill to establish or check the foundations of a product interface: palette, type pairing, spacing, component conventions and UX rules. Skip it for pure backend logic, data design, infrastructure, or other work that does not change how something looks, feels or is operated.

Adapted for Cortex from the MIT-licensed ui-ux-pro-max skill (see LICENSE and CORTEX-SOURCE.md). The upstream search scripts are not bundled. Read the reference files directly; they are the only data this skill uses.

Reference files

  • references/colors.csv: product-type palettes. Columns include Product Type, Primary, On Primary, Secondary, Accent, Background, Foreground, Card, Muted, Muted Foreground, Border, Destructive, Ring and Notes.
  • references/typography.csv: font pairings with heading and body families, mood keywords, best-for uses and notes. Google Fonts URLs and CSS snippets in the data are references only; this skill does not fetch them.
  • references/ux-guidelines.csv: UX rules with Category, Issue, Platform, Do, Don't, example code and Severity.
  • references/pro-rules.md: app-specific pre-delivery checklist (icons, touch feedback, light and dark contrast, safe areas, accessibility) for native and mobile app UI.

These files live in the installed Cortex package, not the target project. Read them through Cortex read_skill using the corresponding registered id: design-colors, design-typography, design-ux-guidelines, design-pro-rules. Read only needed tables; do not assume the whole set is loaded in context.

Procedure

  1. Define the product. Take product type, audience, platform and the one primary user goal from the brief or docs/PRODUCT.md when present. If a material fact is missing, use your advertised ask_question route before choosing the system. Label only non-material implementation assumptions; never invent product functions.
  2. Choose a palette. Find the closest product-type rows in colors.csv. Use them as starting points, then adapt to the brief and to any DESIGN.md direction. Keep semantic roles: text on background at 4.5:1 or better for body text, a visible focus ring, a clearly distinct destructive color.
  3. Choose a type pairing. Use typography.csv rows whose mood and best-for fields match the product. Check that the chosen families are already available to the project or approved for it before adding any dependency.
  4. Apply UX rules. Work through ux-guidelines.csv for the product's categories, highest severity first. Cite the rule numbers (No) you applied.
  5. Run the checklist. For native or mobile app UI, apply pro-rules.md before delivery.
  6. Return the system as tokens. List color roles with hex values, the type scale, the spacing scale, radius and elevation rules, and the state styles (default, hover, focus, active, disabled, error). Record the decisions in the project design documentation only through a role that is allowed to write.

Rules

  • Apply the banned AI-tell patterns (read_skill id design-banned-patterns): never add a one-sided accent stripe or decorative leading dot/meta-chip; only a spec-required semantic status indicator is allowed, and a dot cannot be its only signal.
  • Table rows are starting points, not mandates. The brief and the project's design direction win.
  • Contrast, focus visibility, touch target size and reduced-motion support are not optional.
  • Do not mix flat and skeuomorphic styles in one product, and do not use emoji as functional icons.
  • Keep one icon family with consistent stroke weight and sizing.

No self-scoring as evidence

A system that matches the tables is not proof that the interface is good. Show the applied rule numbers and the rendered result. Rendered review is handled by design-visual-qa; quality claims rest on opened screenshots, concrete findings and re-checks.

Output

Report the product definition and assumptions, the palette and type choices with the rows they came from, the rule numbers applied, the token list, and the open decisions that need the owner.

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.