image-gen
Image generation, editing, and review via OpenRouter API. Five models from budget to premium. Style presets for series consistency, JSON structured prompts, reference image anchoring, system message support, prompt upsampling. Vision-based quality review loop. Zero dependencies beyond Python stdlib. Use when: generate, create, draw, design, illustrate, edit, or modify images.
npx skills add majiayu000/claude-skill-registry --skill image-gen-buildoak-fieldwork-skills --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
Image generation, editing, and review via OpenRouter API. Five models from budget to premium. Style presets for series consistency, JSON structured prompts, reference image anchoring, system message support, prompt upsampling. Vision-based quality review loop. Zero dependencies beyond Python stdlib. Use when: generate, create, draw, design, illustrate, edit, or modify images.
How it works
The skill provides three scripts: ./scripts/generate.py, ./scripts/edit.py, ./scripts/review.py. It includes presets in ./presets/*.json and outputs to ./data/. Setup requires exporting OPENROUTER_API_KEY_IMAGES. It supports multiple models (e.g., flux.2-pro, nanobanana-pro, gpt-5-image, and others) with a CLI that accepts --prompt, --model, --preset, --style-ref (up to 8), and --system-prompt. For editing, use --mode openrouter or --mode openai with appropriate flags like --input-image, --prompt, and optional --mask. The generation workflow includes: selecting a preset, enhancing the prompt, generating via python ./scripts/generate.py, optional review via python ./scripts/review.py, and delivering the file paths.
Key commands shown in the tool usage:
python ./scripts/generate.py \ --prompt "A red fox in snow" \ --output-dir ./data/python ./scripts/edit.py \ --mode openrouter \ --input-image ./data/input.png \ --prompt "Change the background to a sunset beach" \ --model nanobanana-propython ./scripts/review.py \ --image /path/to/output.png \ --original-prompt "A red fox in snow" \ --auto
When to use it
Triggers include generation, creation, drawing, design, illustration, sketch, render, or edits like background changes or text additions. It also supports style transfers and inpainting with masks. system messages are injected for GPT-5/NanoBanana models; Flux models ignore system messages.
What it can touch
Tools referenced: python3 (stdlib only, no pip deps). Scripts: ./scripts/generate.py, ./scripts/edit.py, ./scripts/review.py. Presets: ./presets/*.json. Output: ./data/.
Caveats
Requires environment variable OPENROUTER_API_KEY_IMAGES. Flux prompt upsampling is default unless --no-prompt-upsampling is used. Some features (system messages) are not supported by Flux models. Cost estimates are provided by the script output in cost_estimate.
# image-gen Image generation and editing via OpenRouter. Five models, three scripts, style presets, one JSON contract. **Scripts:** `./scripts/generate.py`, `./scripts/edit.py`, `./scripts/review.py` **Presets:** `./presets/*.json` **Output dir:** `./data/` ## Setup ```bash export OPENROUTER_API_KEY_IMAGES='your-api-key-here' ``` - **Claude Code:** copy this skill folder into `.claude/skills/image-gen/` - **Codex CLI:** append this SKILL.md content to your project's root `AGENTS.md` For the full installation walkthrough (prerequisites, API keys, verification, troubleshooting), see [references/installation-guide.md](references/installation-guide.md). ### Credential management Three tiers for managing the `OPENROUTER_API_KEY_IMAGES` environment variable: 1. **Vault skill (recommended):** If you have a vault or secret-management skill, store the key there and export it before running scripts. Example: `export OPENROUTER_API_KEY_IMAGES=$(vault get OPENROUTER_API_KEY_IMAGES)` 2. **Custom secret manager:** Use your team's preferred secret manager (1Password CLI, AWS Secrets Manager, etc.) 3. **Plain export:** `export OPENROUTER_API_KEY_IMAGES='your-api-key-here'` in your shell profile Op
- Setup
- Credential management
- Model Selection
- Quick Reference
- Style Presets
- How Presets Work
- Available Presets
- Preset Schema
- Priority Order (CLI > Preset > Hardcoded)
- Creating a New Preset
- Style References
- System Messages
- Prompt Upsampling
- Prompt Engineering
export OPENROUTER_API_KEY_IMAGES='your-api-key-here' Generate with default model (flux.2-pro) python ./scripts/generate.py \ Generate with style preset Generate with style reference image Generate with multiple style refs Generate with system message (GPT-5 / NanoBanana only) Generate with prompt upsampling disabled Generate with options (model, aspect ratio, size) Generate with text (GPT-5 Image)
What does the image-gen skill do?
Image generation, editing, and review via OpenRouter API. Five models from budget to premium. Style presets for series consistency, JSON structured prompts, reference image anchoring, system message support, prompt upsampling. Vision-based quality review loop. Zero dependencies beyond Python stdlib. Use when: generate, create, draw, design, illustrate, edit, or modify images.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill image-gen-buildoak-fieldwork-skills --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 majiayu000/claude-skill-registry, a repository with 534 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.