@unityclaw/skills 1.1.1 → 1.1.3

package/unityclaw-image-compress/SKILL.md

@@ -1,274 +0,0 @@
----
-name: unityclaw-image-compress
-description: Compress images with quality control to reduce file size
-version: 1.1.1
-metadata:
-  openclaw:
-    requires:
-      env:
-        - UNITYCLAW_API_KEY
-      bins:
-        - node
-        - npm
-    primaryEnv: UNITYCLAW_API_KEY
-    emoji: "🗜️"
-    homepage: https://unityclaw.com
-    install:
-      - kind: node
-        package: "@unityclaw/sdk"
-        bins: []
----
-
-# UnityClaw Image Compress
-
-Compress images to reduce file size while maintaining visual quality.
-
-## Installation
-
-```bash
-npm install @unityclaw/sdk
-```
-
-## Configuration
-
-Set your API key using one of these methods:
-
-```bash
-# Method 1: Use SDK CLI (recommended - persists across sessions)
-npx @unityclaw/sdk config set apiKey your-api-key
-
-# Method 2: Environment variable
-export UNITYCLAW_API_KEY=your-api-key
-```
-
-## Response Structure
-
-> **IMPORTANT:** The result has a nested structure. Use `result.success` to check overall success, and access data via `result.response.data`.
-
-```typescript
-interface UnityClawResult {
-  success: boolean;        // ✅ Use this to check if SDK call succeeded
-  taskId: string;          // Task identifier
-  taskFolder: string;      // Path to task folder with logs
-  duration: number;        // Request duration in ms
-  response: {              // API response object
-    code: number;          // 0 = success
-    data: Array<{          // ✅ Result data here
-      name: string;
-      contentType: string;
-      content: string;     // URL to compressed image
-    }> | null;
-  };
-  logs: Array<{ timestamp; level; message }>;
-  attachments: any[];
-}
-```
-
-## Quick Start
-
-```typescript
-import { UnityClawClient } from '@unityclaw/sdk';
-
-const client = new UnityClawClient();
-
-const result = await client.image.compress({
-  attachment: [
-    { tmp_url: 'https://example.com/large-image.jpg', name: 'image.jpg' }
-  ],
-  quality: 80
-});
-
-// ✅ Correct: Check result.success, access data via result.response.data
-if (result.success && result.response?.data) {
-  console.log('Compressed images:', result.response.data);
-}
-```
-
-## API Reference
-
-### compress()
-
-Compress one or more images with customizable quality.
-
-```typescript
-await client.image.compress({
-  attachment: AttachmentFieldItem[],
-  quality?: number
-}): Promise<APIResponse<AttachmentResult[]>>
-```
-
-## Parameters
-
-| Parameter | Type | Required | Description |
-|-----------|------|----------|-------------|
-| `attachment` | `AttachmentFieldItem[]` | Yes | Array of images to compress |
-| `quality` | `number` | No | Compression quality (0-100, default: 80) |
-
-### AttachmentFieldItem
-
-```typescript
-interface AttachmentFieldItem {
-  tmp_url: string;    // URL of the image to compress
-  name?: string;      // File name
-  type?: string;      // MIME type (e.g., 'image/jpeg')
-}
-```
-
-## Examples
-
-### Single Image Compression
-
-```typescript
-const client = new UnityClawClient();
-
-const result = await client.image.compress({
-  attachment: [
-    { tmp_url: 'https://example.com/photo.jpg', name: 'photo.jpg', type: 'image/jpeg' }
-  ],
-  quality: 75
-});
-
-if (result.success && result.response?.data) {
-  const compressedImage = result.response.data[0];
-  console.log('Compressed URL:', compressedImage.content);
-}
-```
-
-### Batch Compression
-
-```typescript
-const images = [
-  { tmp_url: 'https://example.com/img1.jpg', name: 'img1.jpg' },
-  { tmp_url: 'https://example.com/img2.png', name: 'img2.png' },
-  { tmp_url: 'https://example.com/img3.webp', name: 'img3.webp' }
-];
-
-const result = await client.image.compress({
-  attachment: images,
-  quality: 80
-});
-
-if (result.success && result.response?.data) {
-  result.response.data.forEach((img, i) => {
-    console.log(`Image ${i + 1}: ${img.content}`);
-  });
-}
-```
-
-### High Quality Compression
-
-```typescript
-// Preserve more detail (larger file size)
-const result = await client.image.compress({
-  attachment: [{ tmp_url: 'https://...', name: 'photo.jpg' }],
-  quality: 90
-});
-```
-
-### Aggressive Compression
-
-```typescript
-// Smaller file size (more quality loss)
-const result = await client.image.compress({
-  attachment: [{ tmp_url: 'https://...', name: 'photo.jpg' }],
-  quality: 50
-});
-```
-
-### With Generated Images
-
-```typescript
-// Generate then compress
-const generated = await client.image.gemini({
-  prompt: 'A beautiful landscape'
-});
-
-if (generated.success && generated.response?.data) {
-  const compressed = await client.image.compress({
-    attachment: generated.response.data.map(img => ({
-      tmp_url: img.content,
-      name: img.name
-    })),
-    quality: 75
-  });
-
-  console.log('Compressed generated images:', compressed.response?.data);
-}
-```
-
-## Response Format
-
-```typescript
-interface AttachmentResult {
-  name: string;
-  contentType: 'attachment/url';
-  content: string;  // URL to compressed image
-}
-```
-
-## Error Handling
-
-```typescript
-const result = await client.image.compress({
-  attachment: [{ tmp_url: 'invalid-url', name: 'test.jpg' }],
-  quality: 80
-});
-
-if (!result.success) {
-  console.error('Request failed');
-  console.log('Check logs:', result.logs);
-  return;
-}
-
-if (result.response?.code !== 0) {
-  console.error('API error:', result.response);
-  return;
-}
-
-// Success
-console.log('Success:', result.response.data);
-```
-
-## Quality Guidelines
-
-| Quality | Use Case | File Size Reduction |
-|---------|----------|---------------------|
-| 90-100 | Print, professional photography | Minimal |
-| 75-89 | Web display, social media | Moderate |
-| 50-74 | Thumbnails, previews | Significant |
-| 0-49 | Aggressive optimization | Maximum |
-
-## Supported Formats
-
-- JPEG/JPG
-- PNG
-- WebP
-- GIF (static)
-
-## Task Folders
-
-Each execution creates a task folder with logs and downloaded attachments:
-
-```typescript
-const result = await client.image.compress({
-  attachment: [{ tmp_url: 'https://...', name: 'image.jpg' }],
-  quality: 80
-});
-
-console.log('Task ID:', result.taskId);
-console.log('Task Folder:', result.taskFolder);
-console.log('Local Attachments:', result.attachments);
-```
-
-## Related Skills
-
-- [unityclaw-image-generation](../unityclaw-image-generation/SKILL.md) - Generate images before compression
-
-<!-- SDK_VERSION_RULE_START -->
-## SDK Version Check Rule
-
-- Before invoking this skill, check local `@unityclaw/sdk` version.
-- Required minimum SDK version: `1.1.1`
-- If local SDK version is lower than this skill version, stop and prompt user to upgrade SDK first.
-- Suggested command: `npm i @unityclaw/sdk@latest`
-<!-- SDK_VERSION_RULE_END -->

package/unityclaw-image-generation/SKILL.md

@@ -1,313 +0,0 @@
----
-name: unityclaw-image-generation
-description: Generate high-quality images using Gemini or JiMeng (Doubao) models
-version: 1.1.1
-metadata:
-  openclaw:
-    requires:
-      env:
-        - UNITYCLAW_API_KEY
-      bins:
-        - node
-        - npm
-    primaryEnv: UNITYCLAW_API_KEY
-    emoji: "🎨"
-    homepage: https://unityclaw.com
-    install:
-      - kind: node
-        package: "@unityclaw/sdk"
-        bins: []
----
-
-# UnityClaw Image Generation
-
-Generate high-quality images using Gemini or JiMeng (Doubao) AI models.
-This skill keeps JiMeng as one unified entry (no separate v3 skill).
-
-## Installation
-
-```bash
-npm install @unityclaw/sdk
-```
-
-## Configuration
-
-Set your API key using one of these methods:
-
-```bash
-# Method 1: Use SDK CLI (recommended - persists across sessions)
-npx @unityclaw/sdk config set apiKey your-api-key
-
-# Method 2: Environment variable
-export UNITYCLAW_API_KEY=your-api-key
-```
-
-## Response Structure
-
-> **IMPORTANT:** The result has a nested structure. Use `result.success` to check overall success, and access image data via `result.response.data`.
-
-```typescript
-interface ImageGenerationResult {
-  success: boolean;        // ✅ Use this to check if SDK call succeeded
-  taskId: string;          // Task identifier (e.g., "b7b613d1")
-  taskFolder: string;      // Path to task folder with logs
-  duration: number;        // Request duration in ms
-  response: {              // API response object
-    code: number;          // 0 = success
-    data: Array<{          // ✅ Generated images here
-      name: string;        // File name
-      contentType: string; // "attachment/url"
-      content: string;     // Image URL
-    }> | null;
-  };
-  logs: Array<{            // Execution logs
-    timestamp: string;
-    level: string;
-    message: string;
-  }>;
-  attachments: any[];      // Downloaded attachments
-}
-```
-
-## Quick Start
-
-```typescript
-import { UnityClawClient } from '@unityclaw/sdk';
-
-const client = new UnityClawClient();
-
-// Generate image with Gemini
-const result = await client.image.gemini({
-  prompt: 'A beautiful sunset over mountains',
-  aspect_ratio: { value: '16:9', label: '16:9' }
-});
-
-// ✅ Correct: Check result.success, access data via result.response.data
-if (result.success && result.response?.data) {
-  console.log('Generated images:', result.response.data);
-} else {
-  console.error('Error:', result.response);
-}
-```
-
-You can pass local files directly and SDK will auto-upload them:
-
-```typescript
-attachment: [{ path: './files/reference.jpg' }]
-```
-
-## Available APIs
-
-### Gemini Image Generation
-
-```typescript
-// Basic usage
-const result = await client.image.gemini({
-  prompt: 'A beautiful sunset over mountains'
-});
-
-// With all options
-const result = await client.image.gemini({
-  prompt: 'A futuristic city at night',
-  attachment: [{ tmp_url: 'https://...', name: 'reference.jpg' }],
-  model: { value: 'gemini-2.0-flash-exp', label: 'Gemini 2.0 Flash' },
-  aspect_ratio: { value: '16:9', label: '16:9' },
-  size: { value: '2K', label: '2K' }
-});
-
-// Gemini V2
-const result = await client.image.geminiV2({
-  prompt: 'An abstract digital art piece',
-  aspect_ratio: { value: '1:1', label: '1:1' }
-});
-```
-
-### JiMeng Image Generation
-
-> **IMPORTANT:** JiMeng uses different parameters than Gemini. Pay attention to the `size` and `model_selector` values.
-
-```typescript
-// Basic usage (defaults to Seedream 5.0 Lite model)
-const result = await client.image.jimeng({
-  prompt: '一只可爱的猫咪在花园里玩耍',
-  size: { value: '2048x2048', label: '2K 1:1' }
-});
-
-// With Seedream 5.0 Lite (supports web_search, 2K and 3K resolutions)
-const result = await client.image.jimeng({
-  prompt: 'A serene Japanese garden in autumn',
-  attachment: [{ tmp_url: 'https://...', name: 'style.jpg' }],
-  size: { value: '2048x2048', label: '2K 1:1' },
-  model_selector: { value: 'doubao-seedream-5-0-260128', label: 'Seedream 5.0 Lite' },
-  web_search: { value: 'true', label: 'Enable' },
-  image_count: { value: 4, label: '4 images' }
-});
-
-// With Seedream 4.5 (supports 4K resolution, no web_search)
-const result = await client.image.jimeng({
-  prompt: 'A mystical forest with glowing mushrooms',
-  size: { value: '4096x4096', label: '4K 1:1' },
-  model_selector: { value: 'doubao-seedream-4-5-251128', label: 'Seedream 4.5' }
-});
-
-```
-
-#### JiMeng Size Options
-
-| Resolution | 5.0 Lite | 4.5 | Size Values |
-|------------|----------|-----|-------------|
-| 2K | ✅ | ✅ | `2048x2048`, `1728x2304`, `2304x1728`, `2848x1600`, `1600x2848`, `2496x1664`, `1664x2496`, `3136x1344` |
-| 3K | ✅ | ❌ | `3072x3072`, `2592x3456`, `3456x2592`, `4096x2304`, `2304x4096`, `3744x2496`, `2496x3744`, `4704x2016` |
-| 4K | ❌ | ✅ | `4096x4096`, `3520x4704`, `4704x3520`, `5504x3040`, `3040x5504`, `4992x3328`, `3328x4992`, `6240x2656` |
-
-> **Note:** `web_search` only works with Seedream 5.0 Lite model.
-
-## Troubleshooting (`/api/jimeng/image`)
-
-If you see backend errors like `{"code":1254500}`, check these first:
-
-- Do not use `jimeng/image/v3` size values (for example `1152x896`) on `/api/jimeng/image`.
-- For `/api/jimeng/image`, use 2K/3K/4K size values such as:
-  `2048x2048`, `3072x3072`, `4096x4096`.
-- Model and size must match:
-  - `doubao-seedream-5-0-260128` does **not** support 4K.
-  - `doubao-seedream-4-5-251128` does **not** support 3K.
-- `web_search=true` only works with `doubao-seedream-5-0-260128`.
-
-## Parameter Types
-
-### GeminiImageParams
-
-| Parameter | Type | Required | Description |
-|-----------|------|----------|-------------|
-| `prompt` | `string \| TextFieldItem[]` | Yes | Text description of the image |
-| `attachment` | `AttachmentFieldItem[]` | No | Reference images for style transfer |
-| `model` | `LabelFieldItem` | No | Model selection (default: gemini-2.0-flash-exp) |
-| `aspect_ratio` | `LabelFieldItem` | No | Aspect ratio: `'1:1'`, `'9:16'`, `'16:9'` |
-| `size` | `LabelFieldItem` | No | Resolution: `'1K'`, `'2K'`, `'4K'` |
-
-### JiMengImageParams
-
-| Parameter | Type | Required | Description |
-|-----------|------|----------|-------------|
-| `prompt` | `string \| TextFieldItem[]` | Yes | Text description (supports Chinese) |
-| `attachment` | `AttachmentFieldItem[]` | No | Reference images for style transfer |
-| `size` | `LabelFieldItem` | Yes | Size: `'2048x2048'` (2K), `'3072x3072'` (3K), `'4096x4096'` (4K) and more |
-| `model_selector` | `LabelFieldItem` | No | Model: `'doubao-seedream-5-0-260128'` (5.0 Lite) or `'doubao-seedream-4-5-251128'` (4.5) |
-| `web_search` | `LabelFieldItem` | No | Enable web search (5.0 Lite only): `'true'` or `'false'` |
-| `image_count` | `LabelFieldItem \| number` | No | Number of images to generate (0-5) |
-| `model` | `string` | No | Direct model override |
-
-## Examples
-
-### Text-to-Image
-
-```typescript
-const client = new UnityClawClient();
-
-const result = await client.image.gemini({
-  prompt: 'A cyberpunk cityscape with neon lights reflecting on wet streets',
-  aspect_ratio: { value: '16:9', label: '16:9' },
-  size: { value: '2K', label: '2K' }
-});
-
-if (result.success && result.response?.data) {
-  result.response.data.forEach((img, i) => {
-    console.log(`Image ${i + 1}: ${img.content}`);
-  });
-}
-```
-
-### Image-to-Image (Style Transfer)
-
-```typescript
-const result = await client.image.gemini({
-  prompt: 'Transform this photo into a watercolor painting style',
-  attachment: [
-    { tmp_url: 'https://example.com/photo.jpg', name: 'photo.jpg' }
-  ],
-  aspect_ratio: { value: '1:1', label: '1:1' }
-});
-
-if (result.success) {
-  console.log('Style transfer complete:', result.response.data);
-}
-```
-
-### Batch Generation
-
-```typescript
-const prompts = [
-  'A serene mountain lake at dawn',
-  'A bustling Tokyo street at night',
-  'An underwater coral reef scene'
-];
-
-const results = await Promise.all(
-  prompts.map(prompt => client.image.gemini({ prompt }))
-);
-
-results.forEach((result, i) => {
-  if (result.success) {
-    console.log(`Prompt ${i + 1}: Success`);
-  }
-});
-```
-
-## Error Handling
-
-> **IMPORTANT:** Always check `result.success` first, then access data via `result.response.data`.
-
-```typescript
-const result = await client.image.gemini({ prompt: 'test' });
-
-if (!result.success) {
-  console.error('Request failed');
-  console.log('Check logs:', result.logs);
-  return;
-}
-
-// Check API response code
-if (result.response?.code !== 0) {
-  console.error('API error:', result.response);
-  return;
-}
-
-// Success - access result.response.data
-console.log('Success:', result.response.data);
-console.log('Task ID:', result.taskId);
-```
-
-## Task Folders
-
-Each execution creates a task folder with detailed logs:
-
-```typescript
-const result = await client.image.gemini({ prompt: 'test' });
-
-console.log('Task ID:', result.taskId);        // e.g., "609600db"
-console.log('Task Folder:', result.taskFolder); // e.g., "~/Documents/tasks/20260312_202723_609600db/"
-
-// Task folder structure:
-// ├── attachments/     - Generated images
-// │   └── xxx.png
-// └── logs/
-//     ├── execution.log
-//     ├── request.json   - API request payload
-//     ├── response.json  - Raw API response
-//     └── summary.json   - Task summary with success status
-```
-
-## Related Skills
-
-- [unityclaw-image-compress](../unityclaw-image-compress/SKILL.md) - Compress generated images
-- [unityclaw-video-generation-kling](../unityclaw-video-generation-kling/SKILL.md) - Generate videos
-
-<!-- SDK_VERSION_RULE_START -->
-## SDK Version Check Rule
-
-- Before invoking this skill, check local `@unityclaw/sdk` version.
-- Required minimum SDK version: `1.1.1`
-- If local SDK version is lower than this skill version, stop and prompt user to upgrade SDK first.
-- Suggested command: `npm i @unityclaw/sdk@latest`
-<!-- SDK_VERSION_RULE_END -->

package/unityclaw-video-frame-extract/SKILL.md

@@ -1,50 +0,0 @@
----
-name: unityclaw-video-frame-extract
-description: Extract first/last/specified-time frame from video attachments
-version: 1.1.1
-metadata:
-  openclaw:
-    requires:
-      env:
-        - UNITYCLAW_API_KEY
-      bins:
-        - node
-        - npm
-    primaryEnv: UNITYCLAW_API_KEY
-    emoji: "🖼️"
-    homepage: https://unityclaw.com
-    install:
-      - kind: node
-        package: "@unityclaw/sdk"
-        bins: []
----
-
-# UnityClaw Video Frame Extract
-
-Extract one frame from video at first frame, last frame, or specific `mm:ss`.
-
-```typescript
-import { UnityClawClient } from '@unityclaw/sdk';
-
-const client = new UnityClawClient();
-const result = await client.media.extractFrame({
-  attachment: [{ path: './files/demo.mp4' }],
-  frame_option: 'first',
-});
-
-if (result.success && result.response?.data?.[0]) {
-  console.log(result.response.data[0].content);
-}
-```
-
-- API: `/api/video/frame`
-- field-feishu: `video/frame`
-
-<!-- SDK_VERSION_RULE_START -->
-## SDK Version Check Rule
-
-- Before invoking this skill, check local `@unityclaw/sdk` version.
-- Required minimum SDK version: `1.1.1`
-- If local SDK version is lower than this skill version, stop and prompt user to upgrade SDK first.
-- Suggested command: `npm i @unityclaw/sdk@latest`
-<!-- SDK_VERSION_RULE_END -->