Generate or edit images from a prompt through ChatGPT in Chrome or the OpenAI Images API. Use for logos, icons, hero art, mockups, transparent assets or prompt edits.
Collected from public GitHub. Every version is saved exactly as it was and never changes. Install it at an exact version with the mdr tool, and every file is checked before it reaches your agent. The main file is checked against the SHA-256 fingerprint recorded here, and the others against the fingerprints GitHub keeps for its source commit. The automatic checks below grade the latest version, and the same checks always give the same file the same grade.
What the file says
Generate images from text prompts (and edit existing ones) by one of two routes: ChatGPT's own UI, driven through Claude in Chrome, or the OpenAI Images API. Both leave behind the same run folder, so the route is an implementation detail the user shouldn't have to think about. The bundled scripts are stdlib-only Python — no SDK, no `pip install`.
## Pick the route
**Try the browser first.** It runs on the user's ChatGPT subscription: no API key to hunt down, nothing billed per image. Same underlying model.
**Skip it and go straight to the API when** any of these are true:
- The browser tools aren't in this session (see below) — don't stall the task trying to get them.
- The image needs a **transparent background**, an **exact pixel size**, or a **masked edit**. The UI can't do any of the three.
- The user wants **several variations at once**, or a run that's meant to be scripted and repeated.
- The user said to use the API, or mentioned their key.
Say which route produced the image when you report back — the user's mental model of cost depends on it.
| | ChatGPT UI | Images API |
|---|---|---|
| Cost | included in their plan | ~$0.006 (low) – $0.21 (high) per image |
…
The line at the top of this page pins the label git:20261020.ce5808a, which is what most people want. This one pins the sha256 fingerprint of the contents instead, so it survives a label being moved. Either way the exact version is written to mdr.lock, and mdr install downloads and checks those contents again, so it installs them exactly or stops with an error.
GET https://markdownregistry.com/api/v1/artifacts/art_573un5dz5f52zftq
GET https://markdownregistry.com/api/v1/resolve?ref=imagile-dev/claude-plugins/image-generation
GET https://markdownregistry.com/api/v1/blob/7f5040d3a611d0fb85e4ba2419a0e04a8ab15a1aaf65d4e3a420a655b2ee626c
Your AI assistant does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
imagile-dev/claude-plugins · plugins/imagile/skills/accessibility/SKILL.md · Audit a site or app for WCAG 2.2 AA with axe-core across widths, color schemes and themes, then guide fixes. Use for…
imagile-dev/claude-plugins · plugins/imagile/skills/architecture/SKILL.md · Design or review a system with Imagile's opinions on .NET, Blazor, TypeScript, Astro and Azure. Use for structure…
imagile-dev/claude-plugins · plugins/imagile/skills/background-removal/SKILL.md · Remove image backgrounds offline with Python and rembg, for one file or a folder. Use for cutouts, transparent PNGs or…
imagile-dev/claude-plugins · plugins/imagile/skills/code-review/SKILL.md · Review a diff or PR with a clear Approve or Request Changes and short Major, Minor and Nit findings. Use when asked to…
imagile-dev/claude-plugins · plugins/imagile/skills/commit/SKILL.md · Write a Conventional Commit for the staged changes and commit them. Use when asked to commit, or to write a commit…
imagile-dev/claude-plugins · plugins/imagile/skills/plan/SKILL.md · Scope engineering work as a GitHub issue and a vertical-slice plan. Use for "plan X", "scope Y", "break this down", or…
imagile-dev/claude-plugins · plugins/imagile/skills/principles/SKILL.md · Write, sharpen and audit a principle-first CLAUDE.md so agents decide without asking. Use to set up CLAUDE.md, turn a…
imagile-dev/claude-plugins · plugins/imagile/skills/revisit/SKILL.md · Review the decisions agents logged in AGENT_DECISIONS.md in one batch, then keep, promote to a principle, or reverse…
imagile-dev/claude-plugins · plugins/imagile/skills/ship/SKILL.md · Take a branch to a merged PR. Rebase, run parallel reviewer agents, fix every finding, log principle gaps, open the PR…
imagile-dev/claude-plugins · plugins/imagile/skills/web-optimize/SKILL.md · Convert images to AVIF and WebP with responsive srcset widths, and judge if it is worth it. Use to optimize, compress…
bytedance/deer-flow · skills/public/image-generation/SKILL.md · Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes…
devin-axis/ipollowork · .agents/skills/image-generation/SKILL.md · Generate image assets through iPolloWork's image service, whether Image Studio is open or closed.
letta-ai/letta-code · src/skills/builtin/image-generation/SKILL.md · Generate images from text prompts (and optionally edit/remix input images). Use when the user asks to create, generate…
shinpr/mcp-image · skills/image-generation/SKILL.md · Optimizes image generation prompts using Subject-Context-Style structure. Use this skill when generating images…
hyperfx-ai/marketing-skills · skills/image-generation/SKILL.md · Generate images through the Hyper MCP with the unified `images_generate` tool — text-to-image, image-to-image, and…
guinacio/claude-image-gen · skills/image-generation/SKILL.md · Generates professional AI images using Google Gemini. ALWAYS invoke this skill when building websites, landing pages…
postplusai/postplus-skills · skills/10-routing/image-generation/SKILL.md · Plan image creation or edits from prompts, products, or references. Resolve task type, model, and reference rules…