image-generator

Generate educational images with Gemini-driven multi-turn feedback and quality gates.

9|2|Updated Nov 28, 2025
One-click install
npx skills add https://github.com/mjunaidca/robolearn --skill image-generator-mjunaidca
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: image-generator
Source: https://github.com/mjunaidca/robolearn/tree/main/.claude/skills/engineering/image-generator
Command: npx skills add https://github.com/mjunaidca/robolearn --skill image-generator-mjunaidca

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Visual generation often leans on generic aesthetics; this skill guides Gemini to produce distinctive, pedagogy-focused visuals via professional briefs.

Core Features & Use Cases

  • Structured creative briefs to activate reasoning over prediction
  • Multi-turn feedback loop to refine visuals
  • Professional quality gates for visuals (spelling, layout, color, typography)

Quick Start

Provide a visual brief and generate one educational image; verify against the 5-gate quality standard.

Frequently Asked Questions about image-generator

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

FAQPage Schema
How do I generate educational images with professional quality standards?

Educational image generation requires structured briefs and quality gates. This Skill uses Gemini-driven reasoning to apply six professional standards—spelling, layout, color, typography, teaching effectiveness, and uniqueness—across batch and single-image workflows, replacing premature acceptance of initial renders.

Can I refine generated visuals through multi-turn feedback?

Yes. This Skill enables multi-turn feedback loops where Gemini applies principle-based reasoning to iteratively improve visuals. Each cycle validates against the six-gate quality framework, ensuring pedagogical alignment and professional output.

What makes structured creative briefs better than generic prompts for image generation?

Structured briefs activate Gemini's reasoning over prediction, guiding distinctive, pedagogy-focused visuals instead of generic aesthetics. This Skill builds briefs that encode teaching intent, enabling quality gates to evaluate both visual and educational effectiveness.

Does this work for batch processing educational visuals?

Yes. The Skill supports autonomous batch processing with asset-workflow integration, applying consistent quality gates and Gemini-driven reasoning across multiple images, ideal for coursework, learning materials, or curriculum development at scale.

What are the quality dimensions evaluated for educational images?

Six gates assess spelling, layout, color harmony, typography, teaching effectiveness, and uniqueness. This framework ensures visuals meet both professional design standards and pedagogical requirements, preventing low-quality renders from proceeding downstream.