midjourney-image
Plan, prompt, iterate, edit, migrate, and quality-check still-image work made with Midjourney's documented website and Discord interfaces. Use for Midjourney model and parameter selection, image/style/Omni references, Draft or Conversational workflows, typography-aware production, privacy and rights review, or troubleshooting a Midjourney image pipeline; do not use it to invent or automate an unsupported Midjourney API.
Profile →npx skills add calesthio/generative-media-skills --skill midjourney-image --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Plans, prompts, iterates, edits, migrates, and quality-checks still-image work produced with Midjourney's consumer interfaces, and supports model/parameter selection, image/style/Omni references, Draft or Conversational workflows, typography-aware production, privacy/rights review, and troubleshooting a Midjourney image pipeline. It does not enable automation of unsupported Midjourney APIs.
How it works
- Uses only Midjourney consumer surfaces (midjourney.com UI and the Midjourney Bot in Discord) for image generation; explicitly forbids browser automation, unofficial clients, scraping, or API-like automation.
- Offloads briefing, prompts, parameter matrix, reference manifest, consent record, and QA checklist offline.
- Requires an authorized account holder to manually submit approved jobs via the official website or Discord UI.
- After generation, users return outputs and, if useful, job ID, seed, final prompt, version, and parameter record.
- Performs selection, comparison, rights review, compositing, typography, metadata, and QA in authorized local tools.
- Enforces separation between the consumer interface and any automation, and requires actual provider-issued agreements for rare automation exceptions.
When to use it
Use when planning and supervising still-image projects with Midjourney through official surfaces, including selecting models/parameters, referencing styles, drafting prompts, and performing QA and rights reviews before moving assets into production. It is explicitly scoped away from automation of Midjourney APIs or non-supported automation.
What it can touch
- Tools allowed: claude-code, codex, copilot, cursor.
- Workflow touches include offline briefing materials, consent records, QA checklists, and local touchpoints for rights reviews and typography.
Caveats
- License: MIT.
- It prohibits automation that interacts with Midjourney services beyond the official UI/Discord interfaces.
- It cautions against interpreting Draft availability inconsistencies across documentation and recommends verifying live site guidance.
- It covers still-image work; moving from stills to video is described as a handoff to a video workflow, not part of this image-focused skill.
# Midjourney image production ## Operating boundary Use this skill to prepare and supervise image work in Midjourney's documented consumer surfaces: - the Imagine bar, Create/Organize pages, Editor, Personalize page, and Moodboards page on `midjourney.com`; - the Midjourney Bot and documented slash commands in Discord. Do **not** translate those buttons, slash commands, parameters, job IDs, or ima
What does the midjourney-image skill do?
Plan, prompt, iterate, edit, migrate, and quality-check still-image work made with Midjourney's documented website and Discord interfaces. Use for Midjourney model and parameter selection, image/style/Omni references, Draft or Conversational workflows, typography-aware production, privacy and rights review, or troubleshooting a Midjourney image pipeline; do not use it to invent or automate an unsupported Midjourney API.
How do I install it?
Run `npx skills add calesthio/generative-media-skills --skill midjourney-image --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From calesthio/generative-media-skills, a repository with 112 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.