ui-ux-excellence

L1 Improvement

• Recast the UX skill in Prompt Architect style with clear triggers, heuristics, and confidence ceilings.
• Added structure-first guardrails and validation steps aligned to Skill Forge.
• Clarified outputs (audit + prioritized fixes) with memory tagging.

---

LIBRARY-FIRST PROTOCOL (MANDATORY)

Before writing ANY code, you MUST check:

Step 1: Library Catalog

• Location: .claude/library/catalog.json
• If match >70%: REUSE or ADAPT

Step 2: Patterns Guide

• Location: .claude/docs/inventories/LIBRARY-PATTERNS-GUIDE.md
• If pattern exists: FOLLOW documented approach

Step 3: Existing Projects

• Location: D:\Projects\*
• If found: EXTRACT and adapt

Decision Matrix

Match	Action
Library >90%	REUSE directly
Library 70-90%	ADAPT minimally
Pattern exists	FOLLOW pattern
In project	EXTRACT
No match	BUILD (add to library after)

---

STANDARD OPERATING PROCEDURE

Purpose

Evaluate and improve product UI/UX using heuristic reviews, user flows, accessibility checks, and prioritized fix plans.

Trigger Conditions

• Positive: UX/UI audit, usability review, accessibility check, design critique, or journey optimization.
• Negative: branding-only requests (route to design specialists) or backend-only tasks.

Guardrails

• Maintain structure-first docs (SKILL, README, examples/tests/references).
• Apply explicit heuristics: clarity, consistency, affordance, feedback, accessibility, performance.
• Confidence ceilings required; cite evidence (screens, flows, metrics).
• Memory tagging for audits and recommendations.

Execution Phases

1. Intent & Context – Identify product area, target users, platforms, and success metrics.
2. Heuristic Review – Assess clarity, consistency, affordance, feedback, and accessibility; capture screenshots/notes.
3. Journey Analysis – Map critical flows; note friction points, latency, and error states.
4. Prioritized Plan – Rank issues by severity/impact/effort; propose design/UX changes.
5. Validation – Prototype or simulate fixes when possible; ensure accessibility (WCAG) and responsiveness.
6. Delivery – Provide findings, recommended changes, and confidence ceiling with memory keys.

Output Format

• Audit summary, user flows assessed, key issues with evidence, and prioritized fixes.
• Accessibility/performance notes and suggested metrics to track.
• Confidence: X.XX (ceiling: TYPE Y.YY); memory namespace recorded.

Validation Checklist

• Scope and personas defined; platforms noted.
• Heuristics applied with evidence; accessibility checked.
• Prioritized backlog includes impact/effort/owner.
• Confidence ceiling declared; memory tagged.

Integration

• Memory MCP: skills/tooling/ui-ux-excellence/{project}/{timestamp} for audits and artifacts.
• Hooks: follow Skill Forge latency bounds; integrate with screenshot tooling when available.

Confidence: 0.70 (ceiling: inference 0.70) – SOP aligned to Prompt Architect clarity and Skill Forge guardrails.