0xkobold 0.0.1

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

@@ -0,0 +1,184 @@
+#!/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
+
+
+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 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="1K",
+        help="Output resolution: 1K (default), 2K, or 4K"
+    )
+    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 = []
+    output_resolution = args.resolution
+    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)
+
+        max_input_dim = 0
+        for img_path in args.input_images:
+            try:
+                img = PILImage.open(img_path)
+                input_images.append(img)
+                print(f"Loaded input image: {img_path}")
+
+                # Track largest dimension for auto-resolution
+                width, height = img.size
+                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)
+
+        # Auto-detect resolution from largest input if not explicitly set
+        if args.resolution == "1K" and max_input_dim > 0:  # Default value
+            if max_input_dim >= 3000:
+                output_resolution = "4K"
+            elif max_input_dim >= 1500:
+                output_resolution = "2K"
+            else:
+                output_resolution = "1K"
+            print(f"Auto-detected resolution: {output_resolution} (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:
+        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_size=output_resolution
+                )
+            )
+        )
+
+        # 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}")
+            # Kobold parses MEDIA tokens and will attach the file on supported providers.
+            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 +1,38 @@
+---
+name: nano-pdf
+description: Edit PDFs with natural-language instructions using the nano-pdf CLI.
+homepage: https://pypi.org/project/nano-pdf/
+metadata:
+  {
+    "kobold":
+      {
+        "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"
+```
+
+Notes:
+
+- Page numbers are 0-based or 1-based depending on the tool’s version/config; if the result looks off by one, retry with the other.
+- Always sanity-check the output PDF before sending it out.

package/skills/notion/SKILL.md

@@ -0,0 +1,172 @@
+---
+name: notion
+description: Notion API for creating and managing pages, databases, and blocks.
+homepage: https://developers.notion.com
+metadata:
+  {
+    "kobold":
+      { "emoji": "📝", "requires": { "env": ["NOTION_API_KEY"] }, "primaryEnv": "NOTION_API_KEY" },
+  }
+---
+
+# notion
+
+Use the Notion API to create/read/update pages, data sources (databases), and blocks.
+
+## Setup
+
+1. Create an integration at https://notion.so/my-integrations
+2. Copy the API key (starts with `ntn_` or `secret_`)
+3. Store it:
+
+```bash
+mkdir -p ~/.config/notion
+echo "ntn_your_key_here" > ~/.config/notion/api_key
+```
+
+4. Share target pages/databases with your integration (click "..." → "Connect to" → your integration name)
+
+## API Basics
+
+All requests need:
+
+```bash
+NOTION_KEY=$(cat ~/.config/notion/api_key)
+curl -X GET "https://api.notion.com/v1/..." \
+  -H "Authorization: Bearer $NOTION_KEY" \
+  -H "Notion-Version: 2025-09-03" \
+  -H "Content-Type: application/json"
+```
+
+> **Note:** The `Notion-Version` header is required. This skill uses `2025-09-03` (latest). In this version, databases are called "data sources" in the API.
+
+## Common Operations
+
+**Search for pages and data sources:**
+
+```bash
+curl -X POST "https://api.notion.com/v1/search" \
+  -H "Authorization: Bearer $NOTION_KEY" \
+  -H "Notion-Version: 2025-09-03" \
+  -H "Content-Type: application/json" \
+  -d '{"query": "page title"}'
+```
+
+**Get page:**
+
+```bash
+curl "https://api.notion.com/v1/pages/{page_id}" \
+  -H "Authorization: Bearer $NOTION_KEY" \
+  -H "Notion-Version: 2025-09-03"
+```
+
+**Get page content (blocks):**
+
+```bash
+curl "https://api.notion.com/v1/blocks/{page_id}/children" \
+  -H "Authorization: Bearer $NOTION_KEY" \
+  -H "Notion-Version: 2025-09-03"
+```
+
+**Create page in a data source:**
+
+```bash
+curl -X POST "https://api.notion.com/v1/pages" \
+  -H "Authorization: Bearer $NOTION_KEY" \
+  -H "Notion-Version: 2025-09-03" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "parent": {"database_id": "xxx"},
+    "properties": {
+      "Name": {"title": [{"text": {"content": "New Item"}}]},
+      "Status": {"select": {"name": "Todo"}}
+    }
+  }'
+```
+
+**Query a data source (database):**
+
+```bash
+curl -X POST "https://api.notion.com/v1/data_sources/{data_source_id}/query" \
+  -H "Authorization: Bearer $NOTION_KEY" \
+  -H "Notion-Version: 2025-09-03" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "filter": {"property": "Status", "select": {"equals": "Active"}},
+    "sorts": [{"property": "Date", "direction": "descending"}]
+  }'
+```
+
+**Create a data source (database):**
+
+```bash
+curl -X POST "https://api.notion.com/v1/data_sources" \
+  -H "Authorization: Bearer $NOTION_KEY" \
+  -H "Notion-Version: 2025-09-03" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "parent": {"page_id": "xxx"},
+    "title": [{"text": {"content": "My Database"}}],
+    "properties": {
+      "Name": {"title": {}},
+      "Status": {"select": {"options": [{"name": "Todo"}, {"name": "Done"}]}},
+      "Date": {"date": {}}
+    }
+  }'
+```
+
+**Update page properties:**
+
+```bash
+curl -X PATCH "https://api.notion.com/v1/pages/{page_id}" \
+  -H "Authorization: Bearer $NOTION_KEY" \
+  -H "Notion-Version: 2025-09-03" \
+  -H "Content-Type: application/json" \
+  -d '{"properties": {"Status": {"select": {"name": "Done"}}}}'
+```
+
+**Add blocks to page:**
+
+```bash
+curl -X PATCH "https://api.notion.com/v1/blocks/{page_id}/children" \
+  -H "Authorization: Bearer $NOTION_KEY" \
+  -H "Notion-Version: 2025-09-03" \
+  -H "Content-Type: application/json" \
+  -d '{
+    "children": [
+      {"object": "block", "type": "paragraph", "paragraph": {"rich_text": [{"text": {"content": "Hello"}}]}}
+    ]
+  }'
+```
+
+## Property Types
+
+Common property formats for database items:
+
+- **Title:** `{"title": [{"text": {"content": "..."}}]}`
+- **Rich text:** `{"rich_text": [{"text": {"content": "..."}}]}`
+- **Select:** `{"select": {"name": "Option"}}`
+- **Multi-select:** `{"multi_select": [{"name": "A"}, {"name": "B"}]}`
+- **Date:** `{"date": {"start": "2024-01-15", "end": "2024-01-16"}}`
+- **Checkbox:** `{"checkbox": true}`
+- **Number:** `{"number": 42}`
+- **URL:** `{"url": "https://..."}`
+- **Email:** `{"email": "a@b.com"}`
+- **Relation:** `{"relation": [{"id": "page_id"}]}`
+
+## Key Differences in 2025-09-03
+
+- **Databases → Data Sources:** Use `/data_sources/` endpoints for queries and retrieval
+- **Two IDs:** Each database now has both a `database_id` and a `data_source_id`
+  - Use `database_id` when creating pages (`parent: {"database_id": "..."}`)
+  - Use `data_source_id` when querying (`POST /v1/data_sources/{id}/query`)
+- **Search results:** Databases return as `"object": "data_source"` with their `data_source_id`
+- **Parent in responses:** Pages show `parent.data_source_id` alongside `parent.database_id`
+- **Finding the data_source_id:** Search for the database, or call `GET /v1/data_sources/{data_source_id}`
+
+## Notes
+
+- Page/database IDs are UUIDs (with or without dashes)
+- The API cannot set database view filters — that's UI-only
+- Rate limit: ~3 requests/second average
+- Use `is_inline: true` when creating data sources to embed them in pages

package/skills/obsidian/SKILL.md

@@ -0,0 +1,81 @@
+---
+name: obsidian
+description: Work with Obsidian vaults (plain Markdown notes) and automate via obsidian-cli.
+homepage: https://help.obsidian.md
+metadata:
+  {
+    "kobold":
+      {
+        "emoji": "💎",
+        "requires": { "bins": ["obsidian-cli"] },
+        "install":
+          [
+            {
+              "id": "brew",
+              "kind": "brew",
+              "formula": "yakitrak/yakitrak/obsidian-cli",
+              "bins": ["obsidian-cli"],
+              "label": "Install obsidian-cli (brew)",
+            },
+          ],
+      },
+  }
+---
+
+# Obsidian
+
+Obsidian vault = a normal folder on disk.
+
+Vault structure (typical)
+
+- Notes: `*.md` (plain text Markdown; edit with any editor)
+- Config: `.obsidian/` (workspace + plugin settings; usually don’t touch from scripts)
+- Canvases: `*.canvas` (JSON)
+- Attachments: whatever folder you chose in Obsidian settings (images/PDFs/etc.)
+
+## Find the active vault(s)
+
+Obsidian desktop tracks vaults here (source of truth):
+
+- `~/Library/Application Support/obsidian/obsidian.json`
+
+`obsidian-cli` resolves vaults from that file; vault name is typically the **folder name** (path suffix).
+
+Fast “what vault is active / where are the notes?”
+
+- If you’ve already set a default: `obsidian-cli print-default --path-only`
+- Otherwise, read `~/Library/Application Support/obsidian/obsidian.json` and use the vault entry with `"open": true`.
+
+Notes
+
+- Multiple vaults common (iCloud vs `~/Documents`, work/personal, etc.). Don’t guess; read config.
+- Avoid writing hardcoded vault paths into scripts; prefer reading the config or using `print-default`.
+
+## obsidian-cli quick start
+
+Pick a default vault (once):
+
+- `obsidian-cli set-default "<vault-folder-name>"`
+- `obsidian-cli print-default` / `obsidian-cli print-default --path-only`
+
+Search
+
+- `obsidian-cli search "query"` (note names)
+- `obsidian-cli search-content "query"` (inside notes; shows snippets + lines)
+
+Create
+
+- `obsidian-cli create "Folder/New note" --content "..." --open`
+- Requires Obsidian URI handler (`obsidian://…`) working (Obsidian installed).
+- Avoid creating notes under “hidden” dot-folders (e.g. `.something/...`) via URI; Obsidian may refuse.
+
+Move/rename (safe refactor)
+
+- `obsidian-cli move "old/path/note" "new/path/note"`
+- Updates `[[wikilinks]]` and common Markdown links across the vault (this is the main win vs `mv`).
+
+Delete
+
+- `obsidian-cli delete "path/note"`
+
+Prefer direct edits when appropriate: open the `.md` file and change it; Obsidian will pick it up.

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

@@ -0,0 +1,89 @@
+---
+name: openai-image-gen
+description: Batch-generate images via OpenAI Images API. Random prompt sampler + `index.html` gallery.
+homepage: https://platform.openai.com/docs/api-reference/images
+metadata:
+  {
+    "kobold":
+      {
+        "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 a handful of “random but structured” prompts and render them via the OpenAI Images API.
+
+## Run
+
+```bash
+python3 {baseDir}/scripts/gen.py
+open ~/Projects/tmp/openai-image-gen-*/index.html  # if ~/Projects/tmp exists; else ./tmp/...
+```
+
+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
+
+Different models support different parameter values. The script automatically selects appropriate defaults based on the model.
+
+### 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
+  - Default: `standard`
+
+### Other Notable Differences
+
+- **dall-e-3** only supports generating 1 image at a time (`n=1`). The script automatically limits count to 1 when using this model.
+- **GPT image models** support additional parameters:
+  - `--background`: `transparent`, `opaque`, or `auto` (default)
+  - `--output-format`: `png` (default), `jpeg`, or `webp`
+  - Note: `stream` and `moderation` are available via API but not yet implemented in this script
+- **dall-e-3** has a `--style` parameter: `vivid` (hyper-real, dramatic) or `natural` (more natural looking)
+
+## Output
+
+- `*.png`, `*.jpeg`, or `*.webp` images (output format depends on model + `--output-format`)
+- `prompts.json` (prompt → file mapping)
+- `index.html` (thumbnail gallery)