Frontend-Focused Multi-Model Workflow

SkillAI & models

Advanced: Frontend-focused multi-model workflow (Research → Ideation → Plan → Execute → Optimize → Review), Gemini-led.

Available today. Use it from your connected AI after setup.

Connect ahel once, and every AI you use reads what you have installed.

Then ask your AI: use the Frontend-Focused Multi-Model Workflow skill

What this skill tells your AI

The instructions your AI receives, as published by luohaothu/everything-codex in skills/multi-frontend/SKILL.md and read by ahel’s review.

Advanced skill — Frontend-focused development with Gemini-led multi-model collaboration.

Usage

/multi-frontend <UI task description>

Applicability

Component design, responsive layout, UI animations, style optimization, accessibility.

Phases

Phase 1: Research

Understand requirements, retrieve existing components, styles, design system.

Phase 2: Ideation (Gemini-Led)

  • Call Gemini for UI feasibility analysis
  • Output: recommended solutions (at least 2), UX evaluation
  • Wait for user selection

Phase 3: Planning (Gemini-Led)

  • Call Gemini for frontend architecture
  • Output: component structure, UI flow, styling approach
  • Save plan, wait for user approval

Phase 4: Implementation

Follow approved plan, maintain design system, ensure responsiveness and accessibility.

Phase 5: Optimization (Gemini-Led)

  • Call Gemini for frontend review
  • Focus: accessibility, responsiveness, performance, design consistency
  • Execute optimization after user confirmation

Phase 6: Quality Review

Check completion, verify responsiveness, report issues.

Key Rules

  1. Gemini frontend opinions are authoritative
  2. Other model backend opinions are for reference only
  3. External models have zero filesystem write access
  4. All code writes handled by the orchestrator

Signals

GitHub stars
24
Forks
5
Last commit
Aug 2026
Advanced
Catalog kind
skill
Gateway key
multi-frontend
Source
github.com/luohaothu/everything-codex