@swarmclawai/swarmclaw 1.2.1 → 1.2.3

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

@@ -0,0 +1,235 @@
+#!/usr/bin/env python3
+# /// script
+# requires-python = ">=3.10"
+# dependencies = [
+#     "google-genai>=1.0.0",
+#     "pillow>=10.0.0",
+# ]
+# ///
+"""
+Generate images using Google's Nano Banana Pro (Gemini 3 Pro Image) API.
+
+Usage:
+    uv run generate_image.py --prompt "your image description" --filename "output.png" [--resolution 1K|2K|4K] [--api-key KEY]
+
+Multi-image editing (up to 14 images):
+    uv run generate_image.py --prompt "combine these images" --filename "output.png" -i img1.png -i img2.png -i img3.png
+"""
+
+import argparse
+import os
+import sys
+from pathlib import Path
+
+SUPPORTED_ASPECT_RATIOS = [
+    "1:1",
+    "2:3",
+    "3:2",
+    "3:4",
+    "4:3",
+    "4:5",
+    "5:4",
+    "9:16",
+    "16:9",
+    "21:9",
+]
+
+
+def get_api_key(provided_key: str | None) -> str | None:
+    """Get API key from argument first, then environment."""
+    if provided_key:
+        return provided_key
+    return os.environ.get("GEMINI_API_KEY")
+
+
+def auto_detect_resolution(max_input_dim: int) -> str:
+    """Infer output resolution from the largest input image dimension."""
+    if max_input_dim >= 3000:
+        return "4K"
+    if max_input_dim >= 1500:
+        return "2K"
+    return "1K"
+
+
+def choose_output_resolution(
+    requested_resolution: str | None,
+    max_input_dim: int,
+    has_input_images: bool,
+) -> tuple[str, bool]:
+    """Choose final resolution and whether it was auto-detected.
+
+    Auto-detection is only applied when the user did not pass --resolution.
+    """
+    if requested_resolution is not None:
+        return requested_resolution, False
+
+    if has_input_images and max_input_dim > 0:
+        return auto_detect_resolution(max_input_dim), True
+
+    return "1K", False
+
+
+def main():
+    parser = argparse.ArgumentParser(
+        description="Generate images using Nano Banana Pro (Gemini 3 Pro Image)"
+    )
+    parser.add_argument(
+        "--prompt", "-p",
+        required=True,
+        help="Image description/prompt"
+    )
+    parser.add_argument(
+        "--filename", "-f",
+        required=True,
+        help="Output filename (e.g., sunset-mountains.png)"
+    )
+    parser.add_argument(
+        "--input-image", "-i",
+        action="append",
+        dest="input_images",
+        metavar="IMAGE",
+        help="Input image path(s) for editing/composition. Can be specified multiple times (up to 14 images)."
+    )
+    parser.add_argument(
+        "--resolution", "-r",
+        choices=["1K", "2K", "4K"],
+        default=None,
+        help="Output resolution: 1K, 2K, or 4K. If omitted with input images, auto-detect from largest image dimension."
+    )
+    parser.add_argument(
+        "--aspect-ratio", "-a",
+        choices=SUPPORTED_ASPECT_RATIOS,
+        default=None,
+        help=f"Output aspect ratio (default: model decides). Options: {', '.join(SUPPORTED_ASPECT_RATIOS)}"
+    )
+    parser.add_argument(
+        "--api-key", "-k",
+        help="Gemini API key (overrides GEMINI_API_KEY env var)"
+    )
+
+    args = parser.parse_args()
+
+    # Get API key
+    api_key = get_api_key(args.api_key)
+    if not api_key:
+        print("Error: No API key provided.", file=sys.stderr)
+        print("Please either:", file=sys.stderr)
+        print("  1. Provide --api-key argument", file=sys.stderr)
+        print("  2. Set GEMINI_API_KEY environment variable", file=sys.stderr)
+        sys.exit(1)
+
+    # Import here after checking API key to avoid slow import on error
+    from google import genai
+    from google.genai import types
+    from PIL import Image as PILImage
+
+    # Initialise client
+    client = genai.Client(api_key=api_key)
+
+    # Set up output path
+    output_path = Path(args.filename)
+    output_path.parent.mkdir(parents=True, exist_ok=True)
+
+    # Load input images if provided (up to 14 supported by Nano Banana Pro)
+    input_images = []
+    max_input_dim = 0
+    if args.input_images:
+        if len(args.input_images) > 14:
+            print(f"Error: Too many input images ({len(args.input_images)}). Maximum is 14.", file=sys.stderr)
+            sys.exit(1)
+
+        for img_path in args.input_images:
+            try:
+                with PILImage.open(img_path) as img:
+                    copied = img.copy()
+                    width, height = copied.size
+                input_images.append(copied)
+                print(f"Loaded input image: {img_path}")
+
+                # Track largest dimension for auto-resolution
+                max_input_dim = max(max_input_dim, width, height)
+            except Exception as e:
+                print(f"Error loading input image '{img_path}': {e}", file=sys.stderr)
+                sys.exit(1)
+
+    output_resolution, auto_detected = choose_output_resolution(
+        requested_resolution=args.resolution,
+        max_input_dim=max_input_dim,
+        has_input_images=bool(input_images),
+    )
+    if auto_detected:
+        print(
+            f"Auto-detected resolution: {output_resolution} "
+            f"(from max input dimension {max_input_dim})"
+        )
+
+    # Build contents (images first if editing, prompt only if generating)
+    if input_images:
+        contents = [*input_images, args.prompt]
+        img_count = len(input_images)
+        print(f"Processing {img_count} image{'s' if img_count > 1 else ''} with resolution {output_resolution}...")
+    else:
+        contents = args.prompt
+        print(f"Generating image with resolution {output_resolution}...")
+
+    try:
+        # Build image config with optional aspect ratio
+        image_cfg_kwargs = {"image_size": output_resolution}
+        if args.aspect_ratio:
+            image_cfg_kwargs["aspect_ratio"] = args.aspect_ratio
+
+        response = client.models.generate_content(
+            model="gemini-3-pro-image-preview",
+            contents=contents,
+            config=types.GenerateContentConfig(
+                response_modalities=["TEXT", "IMAGE"],
+                image_config=types.ImageConfig(**image_cfg_kwargs)
+            )
+        )
+
+        # Process response and convert to PNG
+        image_saved = False
+        for part in response.parts:
+            if part.text is not None:
+                print(f"Model response: {part.text}")
+            elif part.inline_data is not None:
+                # Convert inline data to PIL Image and save as PNG
+                from io import BytesIO
+
+                # inline_data.data is already bytes, not base64
+                image_data = part.inline_data.data
+                if isinstance(image_data, str):
+                    # If it's a string, it might be base64
+                    import base64
+                    image_data = base64.b64decode(image_data)
+
+                image = PILImage.open(BytesIO(image_data))
+
+                # Ensure RGB mode for PNG (convert RGBA to RGB with white background if needed)
+                if image.mode == 'RGBA':
+                    rgb_image = PILImage.new('RGB', image.size, (255, 255, 255))
+                    rgb_image.paste(image, mask=image.split()[3])
+                    rgb_image.save(str(output_path), 'PNG')
+                elif image.mode == 'RGB':
+                    image.save(str(output_path), 'PNG')
+                else:
+                    image.convert('RGB').save(str(output_path), 'PNG')
+                image_saved = True
+
+        if image_saved:
+            full_path = output_path.resolve()
+            print(f"\nImage saved: {full_path}")
+            # OpenClaw parses MEDIA: tokens and will attach the file on
+            # supported chat providers. Emit the canonical MEDIA:<path> form.
+            print(f"MEDIA:{full_path}")
+        else:
+            print("Error: No image was generated in the response.", file=sys.stderr)
+            sys.exit(1)
+
+    except Exception as e:
+        print(f"Error generating image: {e}", file=sys.stderr)
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

package/skills/nano-pdf/SKILL.md

@@ -0,0 +1,53 @@
+---
+name: nano-pdf
+description: Edit or create PDFs with natural-language instructions using the nano-pdf CLI. Use when asked to make a PDF, edit a PDF, add pages, change text in a PDF, or convert content to PDF format.
+metadata:
+  {
+    "openclaw":
+      {
+        "emoji": "📄",
+        "requires": { "bins": ["nano-pdf"] },
+        "install":
+          [
+            {
+              "id": "uv",
+              "kind": "uv",
+              "package": "nano-pdf",
+              "bins": ["nano-pdf"],
+              "label": "Install nano-pdf (uv)",
+            },
+          ],
+      },
+  }
+---
+
+# nano-pdf
+
+Use `nano-pdf` to apply edits to a specific page in a PDF using a natural-language instruction.
+
+## Quick Start
+
+```bash
+nano-pdf edit deck.pdf 1 "Change the title to 'Q3 Results' and fix the typo in the subtitle"
+```
+
+## Creating a New PDF
+
+```bash
+nano-pdf create output.pdf "Create a one-page summary of quarterly results with a header, bullet points, and a footer"
+```
+
+## Usage in SwarmClaw
+
+When a user asks to create or edit a PDF:
+
+1. Check if `nano-pdf` is installed: `which nano-pdf`
+2. If not installed, install via `uv tool install nano-pdf` or `pip install nano-pdf`
+3. Run the appropriate command
+4. Report the output file path to the user
+
+## Notes
+
+- Page numbers are 0-based or 1-based depending on the tool's version; if the result looks off by one, retry with the other.
+- Always sanity-check the output PDF before reporting success.
+- For multi-page edits, run separate commands per page.

package/skills/openai-image-gen/SKILL.md

@@ -0,0 +1,78 @@
+---
+name: openai-image-gen
+description: Generate images via OpenAI Images API (GPT Image, DALL-E 3, DALL-E 2). Supports batch generation with random prompt sampler and HTML gallery output. Use when asked to generate images with OpenAI and an OPENAI_API_KEY is available.
+metadata:
+  {
+    "openclaw":
+      {
+        "emoji": "🎨",
+        "requires": { "bins": ["python3"], "env": ["OPENAI_API_KEY"] },
+        "primaryEnv": "OPENAI_API_KEY",
+        "install":
+          [
+            {
+              "id": "python-brew",
+              "kind": "brew",
+              "formula": "python",
+              "bins": ["python3"],
+              "label": "Install Python (brew)",
+            },
+          ],
+      },
+  }
+---
+
+# OpenAI Image Gen
+
+Generate images via the OpenAI Images API with an HTML gallery viewer.
+
+## Run
+
+Note: Image generation can take longer than typical timeouts. Set a higher timeout when running via shell (e.g., 300 seconds).
+
+```bash
+python3 {baseDir}/scripts/gen.py
+```
+
+## Useful Flags
+
+```bash
+# GPT image models with various options
+python3 {baseDir}/scripts/gen.py --count 16 --model gpt-image-1
+python3 {baseDir}/scripts/gen.py --prompt "ultra-detailed studio photo of a lobster astronaut" --count 4
+python3 {baseDir}/scripts/gen.py --size 1536x1024 --quality high --out-dir ./out/images
+python3 {baseDir}/scripts/gen.py --model gpt-image-1.5 --background transparent --output-format webp
+
+# DALL-E 3 (note: count is automatically limited to 1)
+python3 {baseDir}/scripts/gen.py --model dall-e-3 --quality hd --size 1792x1024 --style vivid
+python3 {baseDir}/scripts/gen.py --model dall-e-3 --style natural --prompt "serene mountain landscape"
+
+# DALL-E 2
+python3 {baseDir}/scripts/gen.py --model dall-e-2 --size 512x512 --count 4
+```
+
+## Model-Specific Parameters
+
+### Size
+
+- **GPT image models** (`gpt-image-1`, `gpt-image-1-mini`, `gpt-image-1.5`): `1024x1024`, `1536x1024` (landscape), `1024x1536` (portrait), or `auto`. Default: `1024x1024`
+- **dall-e-3**: `1024x1024`, `1792x1024`, or `1024x1792`. Default: `1024x1024`
+- **dall-e-2**: `256x256`, `512x512`, or `1024x1024`. Default: `1024x1024`
+
+### Quality
+
+- **GPT image models**: `auto`, `high`, `medium`, or `low`. Default: `high`
+- **dall-e-3**: `hd` or `standard`. Default: `standard`
+- **dall-e-2**: `standard` only
+
+### Other Parameters
+
+- **GPT image models** support `--background` (`transparent`, `opaque`, `auto`) and `--output-format` (`png`, `jpeg`, `webp`)
+- **dall-e-3** supports `--style` (`vivid` for hyper-real, `natural` for more natural looking)
+- **dall-e-3** only supports `n=1`; the script automatically limits count to 1
+
+## Output
+
+- Image files (`*.png`, `*.jpeg`, or `*.webp` depending on model and format)
+- `prompts.json` (prompt-to-file mapping)
+- `index.html` (thumbnail gallery — open in browser to review)

package/skills/openai-image-gen/scripts/gen.py

@@ -0,0 +1,328 @@
+#!/usr/bin/env python3
+import argparse
+import base64
+import datetime as dt
+import json
+import os
+import random
+import re
+import sys
+import urllib.error
+import urllib.request
+from collections.abc import Callable
+from html import escape as html_escape
+from pathlib import Path
+
+
+def slugify(text: str) -> str:
+    text = text.lower().strip()
+    text = re.sub(r"[^a-z0-9]+", "-", text)
+    text = re.sub(r"-{2,}", "-", text).strip("-")
+    return text or "image"
+
+
+def default_out_dir() -> Path:
+    now = dt.datetime.now().strftime("%Y-%m-%d-%H-%M-%S")
+    preferred = Path.home() / "Projects" / "tmp"
+    base = preferred if preferred.is_dir() else Path("./tmp")
+    base.mkdir(parents=True, exist_ok=True)
+    return base / f"openai-image-gen-{now}"
+
+
+def pick_prompts(count: int) -> list[str]:
+    subjects = [
+        "a lobster astronaut",
+        "a brutalist lighthouse",
+        "a cozy reading nook",
+        "a cyberpunk noodle shop",
+        "a Vienna street at dusk",
+        "a minimalist product photo",
+        "a surreal underwater library",
+    ]
+    styles = [
+        "ultra-detailed studio photo",
+        "35mm film still",
+        "isometric illustration",
+        "editorial photography",
+        "soft watercolor",
+        "architectural render",
+        "high-contrast monochrome",
+    ]
+    lighting = [
+        "golden hour",
+        "overcast soft light",
+        "neon lighting",
+        "dramatic rim light",
+        "candlelight",
+        "foggy atmosphere",
+    ]
+    prompts: list[str] = []
+    for _ in range(count):
+        prompts.append(
+            f"{random.choice(styles)} of {random.choice(subjects)}, {random.choice(lighting)}"
+        )
+    return prompts
+
+
+def get_model_defaults(model: str) -> tuple[str, str]:
+    """Return (default_size, default_quality) for the given model."""
+    if model == "dall-e-2":
+        # quality will be ignored
+        return ("1024x1024", "standard")
+    elif model == "dall-e-3":
+        return ("1024x1024", "standard")
+    else:
+        # GPT image or future models
+        return ("1024x1024", "high")
+
+
+def normalize_optional_flag(
+    *,
+    model: str,
+    raw_value: str,
+    flag_name: str,
+    supported: Callable[[str], bool],
+    allowed: set[str],
+    allowed_text: str,
+    unsupported_message: str,
+    aliases: dict[str, str] | None = None,
+) -> str:
+    """Normalize a string flag, warn when unsupported, and reject invalid values."""
+    value = raw_value.strip().lower()
+    if not value:
+        return ""
+
+    if not supported(model):
+        print(unsupported_message.format(model=model), file=sys.stderr)
+        return ""
+
+    if aliases:
+        value = aliases.get(value, value)
+
+    if value not in allowed:
+        raise ValueError(
+            f"Invalid --{flag_name} '{raw_value}'. Allowed values: {allowed_text}."
+        )
+    return value
+
+
+def normalize_background(model: str, background: str) -> str:
+    """Validate --background for GPT image models."""
+    return normalize_optional_flag(
+        model=model,
+        raw_value=background,
+        flag_name="background",
+        supported=lambda candidate: candidate.startswith("gpt-image"),
+        allowed={"transparent", "opaque", "auto"},
+        allowed_text="transparent, opaque, auto",
+        unsupported_message=(
+            "Warning: --background is only supported for gpt-image models; "
+            "ignoring for '{model}'."
+        ),
+    )
+
+
+def normalize_style(model: str, style: str) -> str:
+    """Validate --style for dall-e-3."""
+    return normalize_optional_flag(
+        model=model,
+        raw_value=style,
+        flag_name="style",
+        supported=lambda candidate: candidate == "dall-e-3",
+        allowed={"vivid", "natural"},
+        allowed_text="vivid, natural",
+        unsupported_message=(
+            "Warning: --style is only supported for dall-e-3; ignoring for '{model}'."
+        ),
+    )
+
+
+def normalize_output_format(model: str, output_format: str) -> str:
+    """Normalize output format for GPT image models and validate allowed values."""
+    return normalize_optional_flag(
+        model=model,
+        raw_value=output_format,
+        flag_name="output-format",
+        supported=lambda candidate: candidate.startswith("gpt-image"),
+        allowed={"png", "jpeg", "webp"},
+        allowed_text="png, jpeg, webp",
+        unsupported_message=(
+            "Warning: --output-format is only supported for gpt-image models; "
+            "ignoring for '{model}'."
+        ),
+        aliases={"jpg": "jpeg"},
+    )
+
+
+def request_images(
+    api_key: str,
+    prompt: str,
+    model: str,
+    size: str,
+    quality: str,
+    background: str = "",
+    output_format: str = "",
+    style: str = "",
+) -> dict:
+    url = "https://api.openai.com/v1/images/generations"
+    args = {
+        "model": model,
+        "prompt": prompt,
+        "size": size,
+        "n": 1,
+    }
+
+    # Quality parameter - dall-e-2 doesn't accept this parameter
+    if model != "dall-e-2":
+        args["quality"] = quality
+
+    # Note: response_format no longer supported by OpenAI Images API
+    # dall-e models now return URLs by default
+
+    if model.startswith("gpt-image"):
+        if background:
+            args["background"] = background
+        if output_format:
+            args["output_format"] = output_format
+
+    if model == "dall-e-3" and style:
+        args["style"] = style
+
+    body = json.dumps(args).encode("utf-8")
+    req = urllib.request.Request(
+        url,
+        method="POST",
+        headers={
+            "Authorization": f"Bearer {api_key}",
+            "Content-Type": "application/json",
+        },
+        data=body,
+    )
+    try:
+        with urllib.request.urlopen(req, timeout=300) as resp:
+            return json.loads(resp.read().decode("utf-8"))
+    except urllib.error.HTTPError as e:
+        payload = e.read().decode("utf-8", errors="replace")
+        raise RuntimeError(f"OpenAI Images API failed ({e.code}): {payload}") from e
+
+
+def write_gallery(out_dir: Path, items: list[dict]) -> None:
+    thumbs = "\n".join(
+        [
+            f"""
+<figure>
+  <a href="{html_escape(it["file"], quote=True)}"><img src="{html_escape(it["file"], quote=True)}" loading="lazy" /></a>
+  <figcaption>{html_escape(it["prompt"])}</figcaption>
+</figure>
+""".strip()
+            for it in items
+        ]
+    )
+    html = f"""<!doctype html>
+<meta charset="utf-8" />
+<title>openai-image-gen</title>
+<style>
+  :root {{ color-scheme: dark; }}
+  body {{ margin: 24px; font: 14px/1.4 ui-sans-serif, system-ui; background: #0b0f14; color: #e8edf2; }}
+  h1 {{ font-size: 18px; margin: 0 0 16px; }}
+  .grid {{ display: grid; grid-template-columns: repeat(auto-fill, minmax(240px, 1fr)); gap: 16px; }}
+  figure {{ margin: 0; padding: 12px; border: 1px solid #1e2a36; border-radius: 14px; background: #0f1620; }}
+  img {{ width: 100%; height: auto; border-radius: 10px; display: block; }}
+  figcaption {{ margin-top: 10px; color: #b7c2cc; }}
+  code {{ color: #9cd1ff; }}
+</style>
+<h1>openai-image-gen</h1>
+<p>Output: <code>{html_escape(out_dir.as_posix())}</code></p>
+<div class="grid">
+{thumbs}
+</div>
+"""
+    (out_dir / "index.html").write_text(html, encoding="utf-8")
+
+
+def main() -> int:
+    ap = argparse.ArgumentParser(description="Generate images via OpenAI Images API.")
+    ap.add_argument("--prompt", help="Single prompt. If omitted, random prompts are generated.")
+    ap.add_argument("--count", type=int, default=8, help="How many images to generate.")
+    ap.add_argument("--model", default="gpt-image-1", help="Image model id.")
+    ap.add_argument("--size", default="", help="Image size (e.g. 1024x1024, 1536x1024). Defaults based on model if not specified.")
+    ap.add_argument("--quality", default="", help="Image quality (e.g. high, standard). Defaults based on model if not specified.")
+    ap.add_argument("--background", default="", help="Background transparency (GPT models only): transparent, opaque, or auto.")
+    ap.add_argument("--output-format", default="", help="Output format (GPT models only): png, jpeg, or webp.")
+    ap.add_argument("--style", default="", help="Image style (dall-e-3 only): vivid or natural.")
+    ap.add_argument("--out-dir", default="", help="Output directory (default: ./tmp/openai-image-gen-<ts>).")
+    args = ap.parse_args()
+
+    api_key = (os.environ.get("OPENAI_API_KEY") or "").strip()
+    if not api_key:
+        print("Missing OPENAI_API_KEY", file=sys.stderr)
+        return 2
+
+    # Apply model-specific defaults if not specified
+    default_size, default_quality = get_model_defaults(args.model)
+    size = args.size or default_size
+    quality = args.quality or default_quality
+
+    count = args.count
+    if args.model == "dall-e-3" and count > 1:
+        print(f"Warning: dall-e-3 only supports generating 1 image at a time. Reducing count from {count} to 1.", file=sys.stderr)
+        count = 1
+
+    out_dir = Path(args.out_dir).expanduser() if args.out_dir else default_out_dir()
+    out_dir.mkdir(parents=True, exist_ok=True)
+
+    prompts = [args.prompt] * count if args.prompt else pick_prompts(count)
+
+    try:
+        normalized_background = normalize_background(args.model, args.background)
+        normalized_style = normalize_style(args.model, args.style)
+        normalized_output_format = normalize_output_format(args.model, args.output_format)
+    except ValueError as e:
+        print(str(e), file=sys.stderr)
+        return 2
+
+    # Determine file extension based on output format
+    if args.model.startswith("gpt-image") and normalized_output_format:
+        file_ext = normalized_output_format
+    else:
+        file_ext = "png"
+
+    items: list[dict] = []
+    for idx, prompt in enumerate(prompts, start=1):
+        print(f"[{idx}/{len(prompts)}] {prompt}")
+        res = request_images(
+            api_key,
+            prompt,
+            args.model,
+            size,
+            quality,
+            normalized_background,
+            normalized_output_format,
+            normalized_style,
+        )
+        data = res.get("data", [{}])[0]
+        image_b64 = data.get("b64_json")
+        image_url = data.get("url")
+        if not image_b64 and not image_url:
+            raise RuntimeError(f"Unexpected response: {json.dumps(res)[:400]}")
+
+        filename = f"{idx:03d}-{slugify(prompt)[:40]}.{file_ext}"
+        filepath = out_dir / filename
+        if image_b64:
+            filepath.write_bytes(base64.b64decode(image_b64))
+        else:
+            try:
+                urllib.request.urlretrieve(image_url, filepath)
+            except urllib.error.URLError as e:
+                raise RuntimeError(f"Failed to download image from {image_url}: {e}") from e
+
+        items.append({"prompt": prompt, "file": filename})
+
+    (out_dir / "prompts.json").write_text(json.dumps(items, indent=2), encoding="utf-8")
+    write_gallery(out_dir, items)
+    print(f"\nWrote: {(out_dir / 'index.html').as_posix()}")
+    return 0
+
+
+if __name__ == "__main__":
+    raise SystemExit(main())