@unityclaw/skills 1.0.0

package/unityclaw-media-analysis/SKILL.md

@@ -0,0 +1,315 @@
+---
+name: unityclaw-media-analysis
+description: Analyze video and audio content to extract subtitles, summaries, and insights
+version: 1.0.0
+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 Media Analysis
+
+Analyze video and audio content to extract subtitles, summaries, and insights from various sources.
+
+## Installation
+
+```bash
+npm install @unityclaw/sdk
+```
+
+## Configuration
+
+Set your API key as environment variable:
+
+```bash
+export UNITYCLAW_API_KEY=your-api-key
+```
+
+## Quick Start
+
+```typescript
+import { UnityClawClient } from '@unityclaw/sdk';
+
+const client = new UnityClawClient();
+
+// Analyze from URL
+const result = await client.media.analyze({
+  url: [{ link: 'https://youtube.com/watch?v=...' }]
+});
+
+if (result.code === 0) {
+  console.log('Summary:', result.data?.summary);
+  console.log('Subtitle:', result.data?.subtitle);
+}
+```
+
+## Available APIs
+
+### analyze()
+
+Analyze media from URL or uploaded file.
+
+```typescript
+await client.media.analyze({
+  url: Array<{ tmp_url?: string; link?: string; text?: string; type?: string }>
+}): Promise<APIResponse<MediaAnalysisResult>>
+```
+
+### analyzeVideo()
+
+Analyze a video file directly.
+
+```typescript
+await client.media.analyzeVideo({
+  file: { tmp_url: string; type?: string; name?: string; size?: number };
+  prompt?: string;
+}): Promise<APIResponse<MediaAnalysisResult>>
+```
+
+### analyzeSocialVideo()
+
+Analyze social media videos (TikTok, YouTube, etc.).
+
+```typescript
+await client.media.analyzeSocialVideo({
+  url: string;
+}): Promise<APIResponse<MediaAnalysisResult>>
+```
+
+## Parameters
+
+### MediaAnalysisParams
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `url` | `Array` | Yes | Array of media sources |
+
+### URL Item Properties
+
+| Property | Type | Description |
+|----------|------|-------------|
+| `tmp_url` | `string` | Uploaded file URL |
+| `link` | `string` | External URL (YouTube, TikTok, etc.) |
+| `text` | `string` | Text description |
+| `type` | `string` | MIME type or 'url' |
+
+### VideoAnalysisParams
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `file` | `object` | Yes | Video file info |
+| `prompt` | `string` | No | Custom analysis prompt |
+
+## Response Format
+
+```typescript
+interface MediaAnalysisResult {
+  summary: string;   // Content summary
+  subtitle: string;  // Extracted subtitles/transcript
+}
+```
+
+## Examples
+
+### YouTube Video Analysis
+
+```typescript
+const client = new UnityClawClient();
+
+const result = await client.media.analyze({
+  url: [{ link: 'https://www.youtube.com/watch?v=dQw4w9WgXcQ' }]
+});
+
+if (result.code === 0 && result.data) {
+  console.log('Summary:', result.data.summary);
+  console.log('Transcript:', result.data.subtitle);
+}
+```
+
+### TikTok Video Analysis
+
+```typescript
+const result = await client.media.analyzeSocialVideo({
+  url: 'https://www.tiktok.com/@user/video/123456789'
+});
+
+if (result.code === 0 && result.data) {
+  console.log('Content:', result.data.summary);
+}
+```
+
+### Uploaded Video Analysis
+
+```typescript
+const result = await client.media.analyzeVideo({
+  file: {
+    tmp_url: 'https://example.com/uploaded-video.mp4',
+    type: 'video/mp4',
+    name: 'meeting-recording.mp4'
+  }
+});
+
+if (result.code === 0 && result.data) {
+  console.log('Meeting summary:', result.data.summary);
+}
+```
+
+### Custom Analysis Prompt
+
+```typescript
+const result = await client.media.analyzeVideo({
+  file: {
+    tmp_url: 'https://example.com/tutorial.mp4',
+    name: 'tutorial.mp4'
+  },
+  prompt: 'Extract all code snippets and programming concepts mentioned in this tutorial'
+});
+
+if (result.code === 0 && result.data) {
+  console.log('Analysis:', result.data.summary);
+}
+```
+
+### Multiple Videos Analysis
+
+```typescript
+const videos = [
+  { link: 'https://youtube.com/watch?v=video1' },
+  { link: 'https://youtube.com/watch?v=video2' },
+  { link: 'https://youtube.com/watch?v=video3' }
+];
+
+const results = await Promise.all(
+  videos.map(video => client.media.analyze({ url: [video] }))
+);
+
+results.forEach((result, i) => {
+  if (result.code === 0) {
+    console.log(`Video ${i + 1}:`, result.data?.summary);
+  }
+});
+```
+
+### Audio File Analysis
+
+```typescript
+const result = await client.media.analyze({
+  url: [
+    {
+      tmp_url: 'https://example.com/podcast.mp3',
+      type: 'audio/mpeg',
+      name: 'podcast.mp3'
+    }
+  ]
+});
+
+if (result.code === 0 && result.data) {
+  console.log('Podcast summary:', result.data.summary);
+  console.log('Transcript:', result.data.subtitle);
+}
+```
+
+### Meeting Recording Analysis
+
+```typescript
+const result = await client.media.analyzeVideo({
+  file: {
+    tmp_url: 'https://example.com/meeting.mp4',
+    name: 'team-meeting.mp4'
+  },
+  prompt: 'Extract action items, decisions made, and key discussion points'
+});
+
+if (result.code === 0 && result.data) {
+  console.log('Meeting Notes:', result.data.summary);
+}
+```
+
+### Lecture/Educational Content
+
+```typescript
+const result = await client.media.analyze({
+  url: [{ link: 'https://youtube.com/watch?v=lecture-id' }]
+});
+
+if (result.code === 0 && result.data) {
+  console.log('Lecture Summary:', result.data.summary);
+  console.log('Full Transcript:', result.data.subtitle);
+}
+```
+
+## Supported Platforms
+
+| Platform | URL Format |
+|----------|------------|
+| YouTube | `youtube.com/watch?v=*` |
+| TikTok | `tiktok.com/@user/video/*` |
+| Vimeo | `vimeo.com/*` |
+| Twitter/X | `twitter.com/*/status/*` |
+| Direct Video | Any direct video URL |
+
+## Supported Media Types
+
+- Video: MP4, WebM, MOV, AVI
+- Audio: MP3, WAV, M4A, AAC
+- Streaming: YouTube, TikTok, Vimeo
+
+## Error Handling
+
+```typescript
+const result = await client.media.analyze({
+  url: [{ link: 'https://youtube.com/watch?v=invalid' }]
+});
+
+if (result.code !== 0) {
+  console.error('Analysis failed:', result.msg);
+} else {
+  console.log('Success:', result.data);
+}
+```
+
+## Task Folders
+
+Each execution creates a task folder:
+
+```typescript
+const result = await client.media.analyze({
+  url: [{ link: 'https://youtube.com/watch?v=...' }]
+});
+
+console.log('Task ID:', result.taskId);
+console.log('Task Folder:', result.taskFolder);
+```
+
+## Use Cases
+
+1. **Content Summarization**: Get quick summaries of long videos
+2. **Transcription**: Extract subtitles/transcripts from videos
+3. **Meeting Notes**: Summarize meeting recordings
+4. **Content Analysis**: Analyze social media content
+5. **Educational**: Create study notes from lectures
+6. **Research**: Extract information from video sources
+
+## Best Practices
+
+1. **URL Quality**: Use high-quality video sources
+2. **Custom Prompts**: Use specific prompts for targeted analysis
+3. **Audio Quality**: Clear audio produces better transcripts
+4. **Batch Processing**: Process multiple videos in parallel
+
+## Related Skills
+
+- [unityclaw-document-translation](../unityclaw-document-translation/SKILL.md) - Translate transcripts
+- [unityclaw-video-generation-sora](../unityclaw-video-generation-sora/SKILL.md) - Generate videos

package/unityclaw-video-generation-kling/SKILL.md

@@ -0,0 +1,233 @@
+---
+name: unityclaw-video-generation-kling
+description: Generate AI videos using Kling model with multi-version support
+version: 1.0.0
+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 Generation - Kling
+
+Generate AI videos using the Kling model with support for multiple versions and flexible configuration.
+
+## Installation
+
+```bash
+npm install @unityclaw/sdk
+```
+
+## Configuration
+
+Set your API key as environment variable:
+
+```bash
+export UNITYCLAW_API_KEY=your-api-key
+```
+
+## Quick Start
+
+```typescript
+import { UnityClawClient } from '@unityclaw/sdk';
+
+const client = new UnityClawClient();
+
+const result = await client.video.kling({
+  prompt: 'A dog running happily through a sunny park',
+  aspect_ratio: { value: '16:9', label: '16:9' },
+  duration: { value: '5', label: '5s' }
+});
+
+if (result.code === 0) {
+  console.log('Generated video:', result.data);
+}
+```
+
+## API Reference
+
+### kling()
+
+Generate video using Kling AI model.
+
+```typescript
+await client.video.kling({
+  attachment?: AttachmentFieldItem[];
+  prompt?: string | TextFieldItem[];
+  aspect_ratio?: LabelFieldItem | string;
+  duration?: LabelFieldItem | string;
+  model?: LabelFieldItem | string;
+}): Promise<APIResponse<AttachmentResult[]>>
+```
+
+## Parameters
+
+| Parameter | Type | Required | Description |
+|-----------|------|----------|-------------|
+| `prompt` | `string \| TextFieldItem[]` | No* | Text description (*required if no attachment) |
+| `attachment` | `AttachmentFieldItem[]` | No* | Reference image (*required if no prompt) |
+| `aspect_ratio` | `LabelFieldItem \| string` | No | Video aspect ratio |
+| `duration` | `LabelFieldItem \| string` | No | Video duration |
+| `model` | `LabelFieldItem \| string` | No | Kling model version |
+
+## Examples
+
+### Text-to-Video
+
+```typescript
+const client = new UnityClawClient();
+
+const result = await client.video.kling({
+  prompt: 'A cinematic shot of a rocket launching into space with smoke and fire',
+  aspect_ratio: { value: '16:9', label: '16:9' },
+  duration: { value: '5', label: '5s' },
+  model: { value: 'kling-v1', label: 'V1' }
+});
+```
+
+### Image-to-Video
+
+```typescript
+const result = await client.video.kling({
+  attachment: [
+    { tmp_url: 'https://example.com/portrait.jpg', name: 'portrait.jpg' }
+  ],
+  prompt: 'Bring this portrait to life with subtle animation',
+  aspect_ratio: { value: '9:16', label: '9:16' },
+  duration: { value: '5', label: '5s' }
+});
+```
+
+### Different Model Versions
+
+```typescript
+// Using V1 model
+const result = await client.video.kling({
+  prompt: 'A peaceful lake at sunset',
+  model: { value: 'kling-v1', label: 'V1' }
+});
+
+// Using latest model
+const result = await client.video.kling({
+  prompt: 'A futuristic city with flying cars',
+  model: { value: 'kling-v2', label: 'V2' }
+});
+```
+
+### Simple String Parameters
+
+```typescript
+// Use simple strings for quick calls
+const result = await client.video.kling({
+  prompt: 'A cat chasing a butterfly in a meadow',
+  aspect_ratio: '16:9',
+  duration: '5',
+  model: 'kling-v1'
+});
+```
+
+### Portrait for Social Media
+
+```typescript
+const result = await client.video.kling({
+  prompt: 'A fashion model walking through a stylish boutique',
+  aspect_ratio: { value: '9:16', label: '9:16' },
+  duration: { value: '5', label: '5s' }
+});
+```
+
+### Long Duration Video
+
+```typescript
+const result = await client.video.kling({
+  prompt: 'A time-lapse of clouds moving over a mountain range',
+  aspect_ratio: { value: '16:9', label: '16:9' },
+  duration: { value: '10', label: '10s' }
+});
+```
+
+## Aspect Ratio Options
+
+| Value | Use Case |
+|-------|----------|
+| `16:9` | Standard landscape |
+| `9:16` | Portrait (social media) |
+| `1:1` | Square format |
+
+## Duration Options
+
+| Value | Description |
+|-------|-------------|
+| `5` | 5 seconds (default) |
+| `10` | 10 seconds |
+
+## Model Options
+
+| Value | Description |
+|-------|-------------|
+| `kling-v1` | Kling V1 model |
+| `kling-v2` | Kling V2 model (latest) |
+
+## Response Format
+
+```typescript
+interface AttachmentResult {
+  name: string;
+  contentType: 'attachment/url';
+  content: string;  // URL to generated video
+}
+```
+
+## Error Handling
+
+```typescript
+const result = await client.video.kling({
+  prompt: 'A test video',
+  aspect_ratio: '16:9'
+});
+
+if (result.code !== 0) {
+  console.error('Video generation failed:', result.msg);
+} else {
+  console.log('Success:', result.data);
+}
+```
+
+## Task Folders
+
+Each execution creates a task folder:
+
+```typescript
+const result = await client.video.kling({
+  prompt: 'test',
+  aspect_ratio: '16:9'
+});
+
+console.log('Task ID:', result.taskId);
+console.log('Task Folder:', result.taskFolder);
+console.log('Downloaded Videos:', result.attachments);
+```
+
+## Best Practices
+
+1. **Model Selection**: Use V2 for better quality, V1 for faster generation
+2. **Image Quality**: Use high-resolution images for image-to-video
+3. **Prompt Detail**: Include camera movement and style descriptions
+4. **Duration**: Balance between content needs and generation time
+
+## Related Skills
+
+- [unityclaw-video-generation-sora](../unityclaw-video-generation-sora/SKILL.md) - OpenAI Sora
+- [unityclaw-video-generation-veo](../unityclaw-video-generation-veo/SKILL.md) - Google Veo
+- [unityclaw-video-generation-other](../unityclaw-video-generation-other/SKILL.md) - Other video models