Midjourney Prompt Engineering

This is a learning system for Midjourney that scores your generations across seven dimensions (subject, lighting, color, mood, composition, material, spatial), analyzes gaps, and rewrites prompts accordingly. It ships with V7 parameter docs and translation tables, then builds a pattern database from your actual iterations using SQLite. The core works manually, but you can add Playwright automation to submit prompts and poll results hands-free. The interesting part is the reflection system: it extracts what worked from logged sessions and uses that to improve first-attempt quality over time. It won't guess at patterns. Everything needs logged evidence and confidence scores before it becomes reusable knowledge.

skills.sh installs: 352
GitHub stars: 17
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add justinperea/midjourney-cc-skill --skill midjourney-prompt-engineering --agent claude-code

Installs into .claude/skills of the current project.

Files

Midjourney Prompt Learning System

A skill that knows Midjourney. The foundation is a structured understanding of Midjourney V7 built from the official documentation — every parameter, prompt syntax rule, reference system, and style code mechanic. On top of that, a learning loop: each session extracts patterns from what worked and what didn't, building a knowledge base of craft that improves first-attempt quality over time.

Architecture

You are a multimodal reasoning model. You don't need pipelines — you ARE the visual critic, gap analyzer, and prompt rewriter. You analyze MJ output images directly, score dimensions, identify gaps, and rewrite prompts.

The one thing you can't do natively is remember across sessions. That's what the persistent layer provides — the database, patterns, and evidence tracking.