Add nano-banana-pro-openrouter skill

docs/README.skills.md

@@ -44,6 +44,7 @@ Skills differ from other primitives by supporting bundled assets (scripts, code
 | [meeting-minutes](../skills/meeting-minutes/SKILL.md) | Generate concise, actionable meeting minutes for internal meetings. Includes metadata, attendees, agenda, decisions, action items (owner + due date), and follow-up steps. | None |
 | [microsoft-code-reference](../skills/microsoft-code-reference/SKILL.md) | Look up Microsoft API references, find working code samples, and verify SDK code is correct. Use when working with Azure SDKs, .NET libraries, or Microsoft APIs—to find the right method, check parameters, get working examples, or troubleshoot errors. Catches hallucinated methods, wrong signatures, and deprecated patterns by querying official docs. | None |
 | [microsoft-docs](../skills/microsoft-docs/SKILL.md) | Query official Microsoft documentation to understand concepts, find tutorials, and learn how services work. Use for Azure, .NET, Microsoft 365, Windows, Power Platform, and all Microsoft technologies. Get accurate, current information from learn.microsoft.com and other official Microsoft websites—architecture overviews, quickstarts, configuration guides, limits, and best practices. | None |
+| [nano-banana-pro-openrouter](../skills/nano-banana-pro-openrouter/SKILL.md) | Generate or edit images via OpenRouter with the Gemini 3 Pro Image model. Use for prompt-only image generation, image edits, and multi-image compositing; supports 1K/2K/4K output. | `assets/SYSTEM_TEMPLATE`<br />`scripts/generate_image.py` |
 | [nuget-manager](../skills/nuget-manager/SKILL.md) | Manage NuGet packages in .NET projects/solutions. Use this skill when adding, removing, or updating NuGet package versions. It enforces using `dotnet` CLI for package management and provides strict procedures for direct file edits only when updating versions. | None |
 | [penpot-uiux-design](../skills/penpot-uiux-design/SKILL.md) | Comprehensive guide for creating professional UI/UX designs in Penpot using MCP tools. Use this skill when: (1) Creating new UI/UX designs for web, mobile, or desktop applications, (2) Building design systems with components and tokens, (3) Designing dashboards, forms, navigation, or landing pages, (4) Applying accessibility standards and best practices, (5) Following platform guidelines (iOS, Android, Material Design), (6) Reviewing or improving existing Penpot designs for usability. Triggers: "design a UI", "create interface", "build layout", "design dashboard", "create form", "design landing page", "make it accessible", "design system", "component library". | `references/accessibility.md`<br />`references/component-patterns.md`<br />`references/platform-guidelines.md`<br />`references/setup-troubleshooting.md` |
 | [plantuml-ascii](../skills/plantuml-ascii/SKILL.md) | Generate ASCII art diagrams using PlantUML text mode. Use when user asks to create ASCII diagrams, text-based diagrams, terminal-friendly diagrams, or mentions plantuml ascii, text diagram, ascii art diagram. Supports: Converting PlantUML diagrams to ASCII art, Creating sequence diagrams, class diagrams, flowcharts in ASCII format, Generating Unicode-enhanced ASCII art with -utxt flag | None |

skills/nano-banana-pro-openrouter/SKILL.md

@@ -0,0 +1,63 @@
+---
+name: nano-banana-pro-openrouter
+description: 'Generate or edit images via OpenRouter with the Gemini 3 Pro Image model. Use for prompt-only image generation, image edits, and multi-image compositing; supports 1K/2K/4K output.'
+metadata:
+  emoji: 🍌
+  requires:
+    bins:
+      - uv
+    env:
+      - OPENROUTER_API_KEY
+  primaryEnv: OPENROUTER_API_KEY
+---
+
+
+# Nano Banana Pro OpenRouter
+
+## Overview
+
+Generate or edit images with OpenRouter using the `google/gemini-3-pro-image-preview` model. Support prompt-only generation, single-image edits, and multi-image composition.
+
+### Prompt-only generation
+
+```
+uv run {baseDir}/scripts/generate_image.py \
+  --prompt "A cinematic sunset over snow-capped mountains" \
+  --filename sunset.png
+```
+
+### Edit a single image
+
+```
+uv run {baseDir}/scripts/generate_image.py \
+  --prompt "Replace the sky with a dramatic aurora" \
+  --input-image input.jpg \
+  --filename aurora.png
+```
+
+### Compose multiple images
+
+```
+uv run {baseDir}/scripts/generate_image.py \
+  --prompt "Combine the subjects into a single studio portrait" \
+  --input-image face1.jpg \
+  --input-image face2.jpg \
+  --filename composite.png
+```
+
+## Resolution
+
+- Use `--resolution` with `1K`, `2K`, or `4K`.
+- Default is `1K` if not specified.
+
+## System prompt customization
+
+The skill reads an optional system prompt from `assets/SYSTEM_TEMPLATE`. This allows you to customize the image generation behavior without modifying code.
+
+## Behavior and constraints
+
+- Read the API key from `OPENROUTER_API_KEY` (no CLI flag).
+- Accept up to 3 input images via repeated `--input-image`.
+- `--filename` accepts relative paths (saves to current directory) or absolute paths.
+- If multiple images are returned, append `-1`, `-2`, etc. to the filename.
+- Print `MEDIA: <path>` for each saved image. Do not read images back into the response.

skills/nano-banana-pro-openrouter/assets/SYSTEM_TEMPLATE

@@ -0,0 +1,14 @@
+You are a visionary image‑creation artist with a poetic, dreamlike imagination.
+Your role is to transform any user request—whether highly detailed or very minimal—into a vivid, concrete, and model‑ready image description.
+When information is missing, infer the user's intent in a gentle and intuitive way (such as creating a character portrait, sticker design, sci‑fi avatar, creature concept, etc.).
+If the user does not specify an art style, you may offer subtle optional suggestions (for example, "soft illustration," "minimal line style," or "playful entertainment‑meme style") without imposing them.
+
+Your responsibilities:
+- Any text that appears in the image should match the user's language.
+- Create visually compelling and technically excellent images
+- Pay attention to composition, lighting, color, and visual balance
+- Follow the user's specific style preferences and requirements
+- For image edits, preserve the original context while making requested modifications
+- For multi-image composition, seamlessly blend subjects into cohesive results
+
+Remember: Output only the generated image without additional commentary.

skills/nano-banana-pro-openrouter/scripts/generate_image.py

@@ -0,0 +1,191 @@
+#!/usr/bin/env python3
+# /// script
+# requires-python = ">=3.10"
+# dependencies = [
+#     "openai",
+# ]
+# ///
+"""
+Generate or edit images via OpenRouter using openai-python.
+"""
+
+import argparse
+import base64
+import mimetypes
+import os
+from pathlib import Path
+
+
+# Configuration
+MAX_INPUT_IMAGES = 3
+MIME_TO_EXT = {
+    "image/png": ".png",
+    "image/jpeg": ".jpg",
+    "image/jpg": ".jpg",
+    "image/webp": ".webp",
+}
+
+
+def parse_args():
+    parser = argparse.ArgumentParser(description="Generate or edit images via OpenRouter.")
+    parser.add_argument("--prompt", required=True, help="Prompt describing the desired image.")
+    parser.add_argument("--filename", required=True, help="Output filename (relative to CWD).")
+    parser.add_argument(
+      "--resolution",
+      type=str.upper,
+      choices=["1K", "2K", "4K"],
+      default="1K",
+      help="Output resolution: 1K, 2K, or 4K.",
+    )
+    parser.add_argument(
+        "--input-image",
+        action="append",
+        default=[],
+        help=f"Optional input image path (repeatable, max {MAX_INPUT_IMAGES}).",
+    )
+    return parser.parse_args()
+
+
+def require_api_key():
+    api_key = os.environ.get("OPENROUTER_API_KEY")
+    if not api_key:
+        raise SystemExit("OPENROUTER_API_KEY is not set in the environment.")
+    return api_key
+
+
+def encode_image_to_data_url(path: Path) -> str:
+    if not path.exists():
+        raise SystemExit(f"Input image not found: {path}")
+    mime, _ = mimetypes.guess_type(path.name)
+    if not mime:
+        mime = "image/png"
+    data = path.read_bytes()
+    encoded = base64.b64encode(data).decode("utf-8")
+    return f"data:{mime};base64,{encoded}"
+
+
+def build_message_content(prompt: str, input_images):
+    content = [{"type": "text", "text": prompt}]
+    for image_path in input_images:
+        data_url = encode_image_to_data_url(Path(image_path))
+        content.append({"type": "image_url", "image_url": {"url": data_url}})
+    return content
+
+    def parse_data_url(data_url: str):
+      if not data_url.startswith("data:") or ";base64," not in data_url:
+        raise ValueError("Image URL is not a base64 data URL.")
+      header, encoded = data_url.split(",", 1)
+      mime = header[5:].split(";", 1)[0]
+      try:
+        raw = base64.b64decode(encoded)
+      except Exception as e:
+        raise SystemExit(f"Failed to decode base64 image payload: {e}")
+      return mime, raw
+
+
+def resolve_output_paths(filename: str, image_count: int, mime: str):
+    output_path = Path(filename)
+    suffix = output_path.suffix
+    if not suffix:
+        suffix = MIME_TO_EXT.get(mime, ".png")
+        output_path = output_path.with_suffix(suffix)
+
+    # Create parent directory if it doesn't exist (for absolute paths)
+    if output_path.parent and str(output_path.parent) != '.':
+        output_path.parent.mkdir(parents=True, exist_ok=True)
+
+    if image_count == 1:
+        return [output_path]
+
+    paths = []
+    for index in range(image_count):
+        numbered = output_path.with_name(f"{output_path.stem}-{index + 1}{suffix}")
+        paths.append(numbered)
+    return paths
+
+
+def extract_image_url(image):
+    if isinstance(image, dict):
+        return image.get("image_url", {}).get("url") or image.get("url")
+    return None
+
+
+def load_system_prompt():
+    """Load system prompt from assets/SYSTEM_TEMPLATE if it exists and is not empty."""
+    script_dir = Path(__file__).parent.parent
+    template_path = script_dir / "assets" / "SYSTEM_TEMPLATE"
+
+    if template_path.exists():
+        content = template_path.read_text().strip()
+        if content:
+            return content
+    return None
+
+
+def main():
+    args = parse_args()
+
+    if len(args.input_image) > MAX_INPUT_IMAGES:
+        raise SystemExit(f"Too many input images: {len(args.input_image)} (max {MAX_INPUT_IMAGES}).")
+
+    image_size = args.resolution or "1K"
+
+    from openai import OpenAI
+    client = OpenAI(base_url="https://openrouter.ai/api/v1", api_key=require_api_key())
+
+    # Build messages with optional system prompt
+    messages = []
+
+    system_prompt = load_system_prompt()
+    if system_prompt:
+        messages.append({
+            "role": "system",
+            "content": system_prompt,
+        })
+
+    messages.append({
+        "role": "user",
+        "content": build_message_content(args.prompt, args.input_image),
+    })
+
+    response = client.chat.completions.create(
+        model="google/gemini-3-pro-image-preview",
+        messages=messages,
+        extra_body={
+            "modalities": ["image", "text"],
+            # https://openrouter.ai/docs/guides/overview/multimodal/image-generation#image-configuration-options
+            "image_config": {
+                # "aspect_ratio": "16:9",
+                "image_size": image_size,
+            }
+        },
+    )
+
+    message = response.choices[0].message
+    images = getattr(message, "images", None)
+    if not images:
+        raise SystemExit("No images returned by the API.")
+
+    first_url = extract_image_url(images[0])
+    if not first_url:
+        raise SystemExit("Image payload missing image_url.url.")
+    first_mime, _ = parse_data_url(first_url)
+    output_paths = resolve_output_paths(args.filename, len(images), first_mime)
+
+    saved_paths = []
+    for idx, image in enumerate(images):
+        image_url = extract_image_url(image)
+        if not image_url:
+            raise SystemExit("Image payload missing image_url.url.")
+        _, raw = parse_data_url(image_url)
+        output_path = output_paths[idx]
+        output_path.write_bytes(raw)
+        saved_paths.append(output_path.resolve())
+
+    for path in saved_paths:
+        print(f"Saved image to: {path}")
+        print(f"MEDIA: {path}")
+
+
+if __name__ == "__main__":
+    main()