# image-generation

Sorts an image request into a task class, picks the model and reference rules, then hands a ready brief to the runner.

- skill · `type=skill` · Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, OpenCode · 703 installs · ★ 27
- Author: PostPlusAI
- License: LicenseRef-Unknown · policy=link-only · description only; the file stays with the author
- Source: https://github.com/PostPlusAI/postplus-skills/tree/HEAD/skills/10-routing/image-generation/SKILL.md
- Updated: 2026-10-22
- HTML: https://affpapa.org/en/nevibecode/skills/postplusai-image-generation

## What it does

This skill is a controller, not a generator. It never submits jobs. It reads the request, works out what kind of image is wanted and which references are binding, then writes the handoff for `image-batch-runner`. Useful when the input is a prompt, a product photo, a URL or a storyboard and you need a decision before spending anything.

Seven task classes are covered: `text_to_image`, `image_edit`, `reference_image`, `product_image`, `banner_thumbnail`, `storyboard_image` and `batch_variant`. Each one has its own input and handoff rules. Edits need a bound source image and an endpoint that can edit. Persona, product and brand identity count as binding references unless the user marks them inspiration-only. Benchmark clips and mood boards go the other way, as inspiration only. Excluded references stay out of the runner request.

Routing sends non-image work elsewhere: media understanding, reference decoding, video. The skill stops when user intent or source evidence is missing and a guess would change the result. Paid tasks draw on PostPlus credits after the price and balance are checked, and estimate-only requests do not run. Insufficient credits end the run.

## Install

### Claude Code (native platform)

1. **Skills CLI (Vercel)**
```bash
npx skills add PostPlusAI/postplus-skills --skill image-generation -a claude-code
```

2. **Manually: put the files in place**
- File: `~/.claude/skills/image-generation/SKILL.md` — Copy the whole skill folder; for one project use .claude/skills/image-generation/

### Codex

1. **Skills CLI (Vercel)**
```bash
npx skills add PostPlusAI/postplus-skills --skill image-generation -a codex
```

2. **Manually: put the files in place**
- File: `.agents/skills/image-generation/SKILL.md` — For all projects use ~/.agents/skills/

### Cursor

1. **Skills CLI (Vercel)**
```bash
npx skills add PostPlusAI/postplus-skills --skill image-generation -a cursor
```

2. **Manually: put the files in place**
- File: `.cursor/skills/image-generation/SKILL.md` — Cursor also reads .agents/skills/ and .claude/skills/

### GitHub Copilot

1. **GitHub CLI**
```bash
gh skill install PostPlusAI/postplus-skills image-generation
```

2. **Manually: put the files in place**
- File: `.github/skills/image-generation/SKILL.md`

### Gemini CLI

1. **Skills CLI (Vercel)**
```bash
npx skills add PostPlusAI/postplus-skills --skill image-generation -a gemini-cli
```

2. **Platform CLI**
```bash
gemini skills install https://github.com/PostPlusAI/postplus-skills --path skills/10-routing/image-generation
```

### Windsurf (Devin Desktop)

**Manually: put the files in place**
- File: `.devin/skills/image-generation/SKILL.md` — The legacy .windsurf/skills/ path still works

### OpenCode

**Skills CLI (Vercel)**
```bash
npx skills add PostPlusAI/postplus-skills --skill image-generation -a opencode
```

### Claude.ai

**Claude.ai**
- Zip the folder and upload it in Settings → Capabilities → Skills

Where a file is given instead of a command, copy the files from the source to that path: https://github.com/PostPlusAI/postplus-skills/tree/HEAD/skills/10-routing/image-generation/SKILL.md

## When to use it
- classify an image request before any job is submitted
- bind a source image to edit and preserve rules
- separate binding references from inspiration-only ones
- prepare storyboard panels ahead of execution
- build a runner handoff with no guessed intent

## Example prompts
- I need a banner image, classify the request and hand it to `image-batch-runner`
- here is the product photo and the change: keep identity, invent nothing
- turn this panel plan into storyboard panels ready to run

## Similar
- [qwencloud-image-generation](https://affpapa.org/en/nevibecode/skills/qwencloud-image-generation.md) — skill · 1600 installs
- [ai-image-generation](https://affpapa.org/en/nevibecode/skills/prime-skills-ai-image-generation.md) — skill · 383000 installs
- [stable-diffusion-image-generation](https://affpapa.org/en/nevibecode/skills/stable-diffusion-image-generation.md) — skill · 1000 installs
- [gpt-image-2](https://affpapa.org/en/nevibecode/skills/gpt-image-2.md) — skill · 84300 installs
- [physical-ai-defect-image-generation](https://affpapa.org/en/nevibecode/skills/physical-ai-defect-image-generation.md) — skill · 2000 installs
- [p-image](https://affpapa.org/en/nevibecode/skills/p-image.md) — skill · 12400 installs

## Other versions with the same name
- [image-generation · bytedance](https://affpapa.org/en/nevibecode/skills/bytedance-image-generation.md) — 2900 installs
- [image-generation · claude-office-skills](https://affpapa.org/en/nevibecode/skills/image-generation.md) — 5600 installs

From the same set: [postplusai/postplus-skills](https://affpapa.org/en/nevibecode/by/postplusai/postplus-skills.md) — 6 cards

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md