image-generator

Generate compliant visuals from creative briefs with quality gates.

Updated Nov 29, 2025
One-click install
npx skills add https://github.com/92Bilal26/physical-ai-textbook --skill image-generator-92bilal26
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: image-generator
Source: https://github.com/92Bilal26/physical-ai-textbook/tree/main/.claude/skills/image-generator
Command: npx skills add https://github.com/92Bilal26/physical-ai-textbook --skill image-generator-92bilal26

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Visual generation often settles for generic aesthetics when prompts focus on technical specs. This skill provides a multi-turn reasoning partnership with Gemini to craft professional visuals that meet high standards and teaching goals.

Core Features & Use Cases

  • Reasoning over prediction: Activate reasoning with narrative briefs (Story/Intent/Metaphor) rather than technical specs.
  • Multi-turn partnership: Teach Gemini your standards through principle-based feedback across iterations.
  • Quality gates: Explicit pass/fail criteria ensure clarity, spelling, layout, color, typography, and teaching effectiveness.
  • Autonomous batch mode: Generate multiple visuals without back-and-forth permission prompts.

Quick Start

Provide a creative brief to Gemini, including The Story, Emotional Intent, Visual Metaphor, Subject / Composition / Action / Location / Style / Camera / Lighting, Color Semantics, Typography Hierarchy, and Pedagogical Reasoning; then trigger the browser-based generation workflow and deploy the result into your lesson.

Frequently Asked Questions about image-generator

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate professional-quality visuals from creative briefs using AI?▼

Professional-quality visual generation applies multi-turn reasoning with Gemini to transform narrative briefs—including story, intent, metaphor, composition, color semantics, and pedagogical goals—into compliant visuals. This skill automates batch browser-based generation with 5-gate quality checks (spelling, layout, color, typography, teaching effectiveness) and iterative feedback loops to meet high standards without generic output.

Can I automate batch image generation with quality gates and feedback loops?▼

Yes. Batch image generation with autonomous workflows and gate-based quality checks enables multi-turn brief-to-visual cycles without back-and-forth prompts. The skill applies principle-based feedback across iterations, enforces pass/fail criteria for clarity and teaching effectiveness, and integrates results into lesson deployment pipelines.

What's the best way to structure creative briefs for AI image generation?▼

Structure briefs with narrative reasoning layers—The Story, Emotional Intent, Visual Metaphor—paired with technical specification layers: Subject/Composition/Action/Location/Style/Camera/Lighting, Color Semantics, Typography Hierarchy, and Pedagogical Reasoning. This framework activates reasoning over prediction and teaches Gemini your standards through principle-based iteration.

How do I check if generated visuals meet teaching and design standards?▼

Quality gates enforce explicit pass/fail criteria across five dimensions: spelling accuracy, layout coherence, color semantics alignment, typography hierarchy clarity, and teaching effectiveness. Automated gate-based checks validate each visual and trigger per-visual iteration feedback without manual review overhead.

Does this approach work for scaling visual generation across multiple lessons?▼

Yes. The skill supports autonomous batch workflows with token-conservation prompts and embedded uniqueness checks, enabling multi-visual generation at scale. Results integrate directly into asset pipelines and lesson deployment, reducing manual iteration cycles while maintaining compliance with design and pedagogical standards.

What limitations should I know before using browser-based batch image generation?▼

Batch generation depends on Gemini's reasoning capabilities and Playwright's browser automation scope. Complex briefs require well-structured narrative and technical specification layers; incomplete briefs may produce generic output. Gate-based quality checks validate compliance but cannot guarantee creative novelty beyond embedded uniqueness constraints.