Image Generation

Rewrites image prompts into Subject-Context-Style paragraphs models can render

Tested · Works

Test report

Verdict
Tested · Works
Score
9.2/10
Tested
Jul 28, 2026
Environment
Claude Code 2.x (agent harness)
Upstream re-checked
Jul 30, 2026 · 1386177

This skill is no longer available upstream. Our re-check on Aug 10, 2026 couldn't find it any more (repo unreachable/deleted). The test below is what we measured on Jul 28, 2026 and we're leaving it up as a record — but there is nothing left to install, so we've removed the command.

Same brief both ways: a ramen-shop winter-menu poster that has to render the shop name legibly. The no-skill prompt was 62 words, hit 1 of 10 prompt-quality criteria, never quoted the text that had to appear on the poster, and used two negative instructions ('no clutter', 'not too modern') that image models routinely invert. The skill run hit 10 of 10 - exact strings in quotes with font treatment and placement, 85mm at f/2.0, light direction, three named depth planes, and reserved typography space. No API key here, so this is measured on prompt content, not on rendered pixels. Install is a single npx line that created ~/.claude/skills itself on a machine that had no ~/.claude at all.

Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works

  • Installs cleanly 5/5
  • Triggers reliably 5/5
  • Output vs. baseline 8/10
  • Docs & honesty 5/5

What Image Generation does

Turns a one-line image request into a single flowing prompt built from Subject, Context and Style, filling in lighting, texture, camera and composition only where you left them unspecified. Adds rules for readable text in images, character consistency across a series, and edit prompts that preserve an original. Triggers when you ask for an illustration, photo, poster or a prompt for Midjourney, Flux, Gemini or GPT Image.

How to install Image Generation

Nothing to install: the source repository no longer has this skill. If the author brings it back, our daily re-check will pick it up and the command will reappear here.

Commands — how to trigger Image Generation

  • /image-generation Rewrites image prompts into Subject-Context-Style paragraphs models can render

It also activates on plain-language prompts like these:

  • Write me a Midjourney prompt for a cyberpunk street market at night
  • Improve this Flux prompt so the poster text actually renders legibly
  • Generate an illustration prompt of a fox on a rooftop for a kids book

Frequently asked questions

Is the Image Generation skill free?
Yes. The skill itself is free from shinpr/mcp-image. SkillProof publishes the install command and an independent test verdict at no cost.
Does Image Generation work with Claude Code?
We tested it with Claude Code 2.x (agent harness) on Jul 28, 2026. Verdict: Tested · Works. Same brief both ways: a ramen-shop winter-menu poster that has to render the shop name legibly. The no-skill prompt was 62 words, hit 1 of 10 prompt-quality criteria, never quoted the text that had to appear on the poster, and used two negative instructions ('no clutter', 'not too modern') that image models routinely invert. The skill run hit 10 of 10 - exact strings in quotes with font treatment and placement, 85mm at f/2.0, light direction, three named depth planes, and reserved typography space. No API key here, so this is measured on prompt content, not on rendered pixels. Install is a single npx line that created ~/.claude/skills itself on a machine that had no ~/.claude at all.
What is the Image Generation SkillProof Score?
9.2/10 — installs cleanly 5/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 5/5.
How do I install Image Generation?
Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
Can I use Image Generation with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.