Skip to content
Back to skills

Ztx3 Design Intelligence

ASecurity

Design Intelligence Engine — select, implement, audit and test design intelligence for production Codex frontend work, with responsive and accessibility checks.

  • 14 stars
  • 0 votes
  • 0 copies
  • 0 views
  • Added November 7, 2026
designgofrontend

Works with

  • cli
  • mcp

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned November 7, 2026

npx -y skills add Realjustawall/Perfect-AI --skill ztx3-design-intelligence --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Ztx3 Design Intelligence?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Ztx3 Design Intelligence
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/realjustawall-ztx3-design-intelligence/badge)](https://www.skillsdirectory.com/skills/realjustawall-ztx3-design-intelligence)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: ztx3-design-intelligence
description: "Design Intelligence Engine — select, implement, audit and test design intelligence for production Codex frontend work, with responsive and accessibility checks."
---

# Design Intelligence Engine

Establish constraints and information hierarchy before choosing a visual language. Score design candidates for user task fit, accessibility, novelty, content, brand fidelity and implementation budget. Return a traceable decision record: problem, audience, approved mood, disallowed clichés, palette, typography, layout, motion owner, and skill shortlist. Use deterministic recommendations first, creative divergence second. Never infer fake user studies.

## Workflow

1. Record explicit project requirements, business goal, content and accepted test budget.
2. Read `references/HANDBOOK.md` and pick precise technique Skill files, not the entire catalog.
3. Implement smallest meaningful working baseline, then add incremental enhancements.
4. Measure or inspect result with real devices and produce fallback.
5. Report verified/untested results. No MCP, no destructive overwrites.

## Core obligations

Capture a normalized DesignBrief JSON; enumerate 3 alternatives; score with written justification; emit a decision record and selected Skill names.

Run design router on at least 3 dissimilar briefs and check no identical automatic palettes/engines are forced.

## References

- `references/HANDBOOK.md` — full architecture and 12 deep techniques.
- Refer to `ztx3-<technique>` Skill for focused implementation and acceptance.

Files in this skill

  • SKILL.md1.5 KB
  • references/HANDBOOK.md7.3 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.