[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6PEZ64AC0PHTXP69SVZXN0V":3,"skill-same:01M6PEZ64AC0PHTXP69SVZXN0V":79},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":34,"publishedAt":54,"linkOnly":55,"markdownContent":56,"markdownBody":57,"frontMatter":58,"refName":37,"commitSha":59,"skillDirectory":60,"forksCount":61,"repositoryHtmlUrl":62,"repositoryHomepageUrl":6,"ownerHtmlUrl":63,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":64,"install":65,"resources":78},"01M6PEZ64AC0PHTXP69SVZXN0V","Vertex AI Media Master",null,"Automatic activation for ALL Google Vertex AI multimodal operations - video processing, audio generation, image creation, and marketing campaigns.\n\n**TRIGGER PHRASES:**\n- \"vertex ai\", \"gemini multimodal\", \"process video\", \"generate audio\", \"create images\", \"marketing campaign\"\n- \"imagen\", \"video understanding\", \"multimodal\", \"content generation\", \"media assets\"\n\n**AUTO-INVOKES FOR:**\n- Video processing and understanding (up to 6 hours)\n- Audio generation and transcription\n- Image generation with Imagen 4\n- Marketing campaign automation\n- Social media content creation\n- Ad creative generation\n- Multimodal content workflows","sandraschi\u002Fdocumentation-mcp","sandraschi","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F34750307?v=4","01M6C42H9WE5EC9CK3N5RGZP8S","Sandra Schipal","01M6PE1X2FZP8KR5GANPPFTHA8",2,"MIT","https:\u002F\u002Fgithub.com\u002Fsandraschi\u002Fdocumentation-mcp\u002Fblob\u002Fmaster\u002Fdocs\u002Fnot-mcp-related\u002Fclaude-skills\u002Ftemp\u002Fcode-plugins\u002Fplugins\u002Fproductivity\u002F003-jeremy-vertex-ai-media-master\u002Fskills\u002Fvertex-media-master\u002FSKILL.md",[18,23,26,29],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000019","营销推广",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",{"categoryNo":30,"categoryName":31,"taxonomyType":32,"taxonomyTypeDesc":33},"01JBSEEDCAT000000000000035","市场营销","PROFESSION","适用职业",[35,36,5,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53],"vertex ai","Media","master","processing","image","creation","content creation","social","images","campaign","up","auto","video processing","ad creative","Audio","Video","generate","create","workflows","2026-11-10 10:12:30",false,"---\nname: Vertex AI Media Master\ndescription: |\n  Automatic activation for ALL Google Vertex AI multimodal operations - video processing, audio generation, image creation, and marketing campaigns.\n\n  **TRIGGER PHRASES:**\n  - \"vertex ai\", \"gemini multimodal\", \"process video\", \"generate audio\", \"create images\", \"marketing campaign\"\n  - \"imagen\", \"video understanding\", \"multimodal\", \"content generation\", \"media assets\"\n\n  **AUTO-INVOKES FOR:**\n  - Video processing and understanding (up to 6 hours)\n  - Audio generation and transcription\n  - Image generation with Imagen 4\n  - Marketing campaign automation\n  - Social media content creation\n  - Ad creative generation\n  - Multimodal content workflows\n---\n\n# Vertex AI Media Master - Comprehensive Multimodal AI Operations\n\nThis Agent Skill provides comprehensive mastery of Google Vertex AI multimodal capabilities for video, audio, image, and text processing with focus on marketing applications.\n\n## Core Capabilities\n\n### ? Video Processing (Gemini 2.0\u002F2.5)\n- **Video Understanding**: Process videos up to 6 hours at low resolution or 2 hours at default resolution\n- **2M Context Window**: Gemini 2.5 Pro handles massive video content\n- **Audio Track Processing**: Automatic audio transcription from video\n- **Multi-video Analysis**: Process multiple videos in single request\n- **Video Summarization**: Extract key moments, scenes, and insights\n- **Marketing Use Cases**:\n  - Analyze competitor video ads\n  - Extract highlights from long-form content\n  - Generate video summaries for social media\n  - Transcribe and caption video content\n  - Identify brand mentions and product placements\n\n### ? Audio Generation & Processing\n- **Lyria Model (2025)**: Native audio and music generation\n- **Speech-to-Text**: Transcribe audio with speaker diarization\n- **Text-to-Speech**: Generate natural voiceovers\n- **Music Composition**: Background music for campaigns\n- **Audio Enhancement**: Noise reduction and quality improvement\n- **Marketing Use Cases**:\n  - Generate podcast scripts and voiceovers\n  - Create audio ads and radio spots\n  - Produce background music for video campaigns\n  - Transcribe customer interviews\n  - Generate multilingual voiceovers\n\n### ?️ Image Generation (Imagen 4 & Gemini 2.5 Flash Image)\n- **Imagen 4**: Highest quality text-to-image generation\n- **Gemini 2.5 Flash Image**: Interleaved image generation with text\n- **Style Transfer**: Apply brand styles to generated images\n- **Product Visualization**: Generate product mockups\n- **Campaign Assets**: Create ad creatives and social media graphics\n- **Marketing Use Cases**:\n  - Generate personalized ad images (Adios solution)\n  - Create social media graphics at scale\n  - Produce product lifestyle images\n  - Generate A\u002FB test variations\n  - Create branded campaign visuals\n\n### ? Marketing Campaign Automation\n- **ViGenAiR**: Convert long-form video ads to short formats automatically\n- **Adios**: Generate personalized ad images tailored to audience context\n- **Campaign Asset Generation**: Photos, soundtracks, voiceovers from prompts\n- **Content Pipeline**: Email copy, blog posts, social media, PMax assets\n- **Catalog Enrichment**: Multi-agent workflow for product onboarding\n- **Marketing Use Cases**:\n  - Automated campaign asset production\n  - Personalized content at scale\n  - Multi-channel content distribution\n  - Product catalog enhancement\n  - Visual merchandising automation\n\n### ? Technical Implementation\n\n**API Integration:**\n```python\nfrom google.cloud import aiplatform\nfrom vertexai.preview.generative_models import GenerativeModel\n\n# Initialize Vertex AI\naiplatform.init(project=\"your-project\", location=\"us-central1\")\n\n# Gemini 2.5 Pro for video\nmodel = GenerativeModel(\"gemini-2.5-pro\")\n\n# Process video with audio\nresponse = model.generate_content([\n    \"Analyze this video and extract key marketing insights\",\n    video_file,  # Up to 6 hours\n])\n\n# Imagen 4 for image generation\nfrom vertexai.preview.vision_models import ImageGenerationModel\nimagen = ImageGenerationModel.from_pretrained(\"imagen-4\")\nimages = imagen.generate_images(\n    prompt=\"Professional product photo, studio lighting, white background\",\n    number_of_images=4\n)\n```\n\n**Gemini 2.5 Flash Image (Interleaved Generation):**\n```python\n# Generate images within text responses\nmodel = GenerativeModel(\"gemini-2.5-flash-image\")\nresponse = model.generate_content([\n    \"Create a 5-step recipe with images for each step\"\n])\n# Returns text + images interleaved\n```\n\n**Audio Generation (Lyria):**\n```python\nfrom vertexai.preview.audio_models import AudioGenerationModel\nlyria = AudioGenerationModel.from_pretrained(\"lyria\")\naudio = lyria.generate_audio(\n    prompt=\"Upbeat background music for product launch video, 30 seconds\",\n    duration=30\n)\n```\n\n### ? Marketing Workflow Automation\n\n**1. Multi-Channel Campaign Creation:**\n```python\n# Single prompt generates all assets\ncampaign = model.generate_content([\n    \"\"\"Create a product launch campaign for [product]:\n    - Hero image (1920x1080)\n    - 3 social media graphics (1080x1080)\n    - 30-second video script\n    - Background music description\n    - Email marketing copy\n    - Instagram caption\"\"\"\n])\n```\n\n**2. Video Repurposing Pipeline:**\n```python\n# Long-form to short-form conversion (ViGenAiR approach)\nlong_video = \"gs:\u002F\u002Fbucket\u002Foriginal-ad-60s.mp4\"\nresponse = model.generate_content([\n    f\"Extract 3 engaging 15-second clips from this video for TikTok\u002FReels\",\n    long_video\n])\n# Auto-generates format-specific versions\n```\n\n**3. Personalized Ad Generation:**\n```python\n# Context-aware image generation (Adios approach)\nfor audience in audiences:\n    ad_image = imagen.generate_images(\n        prompt=f\"Product ad for {product}, targeting {audience.demographics}, {audience.style_preference}\",\n        aspect_ratio=\"16:9\"\n    )\n```\n\n### ? Best Practices for Jeremy\n\n**1. Project Setup:**\n```bash\n# Set environment variables\nexport GOOGLE_CLOUD_PROJECT=\"your-project-id\"\nexport GOOGLE_APPLICATION_CREDENTIALS=\"path\u002Fto\u002Fservice-account.json\"\n\n# Install SDK\npip install google-cloud-aiplatform[vision,audio] google-generativeai\n```\n\n**2. Rate Limits & Quotas:**\n- Gemini 2.5 Pro: 2M tokens\u002Fmin (video processing)\n- Imagen 4: 100 images\u002Fmin\n- Monitor usage in Cloud Console\n\n**3. Cost Optimization:**\n- Use Gemini 2.5 Flash for faster, cheaper operations\n- Batch image generation requests\n- Cache video embeddings for repeated analysis\n- Use low-resolution video setting when appropriate\n\n**4. Security & Compliance:**\n- Keep API keys in Secret Manager, never in code\n- Use service accounts with minimal permissions\n- Enable VPC Service Controls for data residency\n- Log all API calls for audit trails\n\n### ? Advanced Marketing Use Cases\n\n**1. Campaign Performance Analysis:**\n```python\n# Analyze competitor campaigns\ncompetitor_videos = [\"gs:\u002F\u002Fbucket\u002Fcompetitor1.mp4\", \"gs:\u002F\u002Fbucket\u002Fcompetitor2.mp4\"]\nanalysis = model.generate_content([\n    \"Compare these competitor videos: themes, messaging, CTAs, production quality\",\n    *competitor_videos\n])\n```\n\n**2. Content Localization:**\n```python\n# Generate multilingual campaigns\nfor lang in [\"en\", \"es\", \"fr\", \"de\", \"ja\"]:\n    localized_content = model.generate_content([\n        f\"Translate and culturally adapt this campaign for {lang} market:\",\n        campaign_brief,\n        hero_image\n    ])\n```\n\n**3. A\u002FB Test Generation:**\n```python\n# Generate variations automatically\nvariations = []\nfor style in [\"minimalist\", \"bold\", \"luxury\", \"playful\"]:\n    variation = imagen.generate_images(\n        prompt=f\"Product ad, {style} style, {brand_guidelines}\",\n        number_of_images=1\n    )\n    variations.append(variation)\n```\n\n### ? Reference Documentation\n\n**Official Documentation:**\n- Vertex AI Multimodal: https:\u002F\u002Fcloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Fmultimodal\u002Foverview\n- Gemini 2.5 Pro: https:\u002F\u002Fcloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Fmodels\n- Imagen 4: https:\u002F\u002Fcloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Fimage\u002Foverview\n- Video Understanding: https:\u002F\u002Fcloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Fmultimodal\u002Fvideo-understanding\n\n**Marketing Solutions:**\n- GenAI for Marketing: https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fgenai-for-marketing\n- ViGenAiR (video repurposing)\n- Adios (personalized ad images)\n\n**Pricing:**\n- Gemini 2.5 Pro: $3.50\u002F1M input tokens, $10.50\u002F1M output tokens\n- Imagen 4: $0.04\u002Fimage\n- Video processing: Included in Gemini token pricing\n\n## When This Skill Activates\n\nThis skill automatically activates when you mention:\n- Video processing, analysis, or understanding\n- Audio generation, music composition, or voiceovers\n- Image generation, ad creatives, or visual content\n- Marketing campaigns, content automation, or asset production\n- Gemini multimodal capabilities\n- Vertex AI media operations\n- Social media content, email marketing, or PMax campaigns\n\n## Integration with Other Tools\n\n**Google Cloud Services:**\n- Cloud Storage for media asset management\n- BigQuery for campaign analytics\n- Cloud Functions for automation triggers\n- Vertex AI Pipelines for content workflows\n\n**Third-Party Integrations:**\n- Social media APIs (LinkedIn, Twitter, Instagram)\n- Marketing automation platforms (HubSpot, Marketo)\n- CMS integrations (WordPress, Contentful)\n- DAM systems (Bynder, Cloudinary)\n\n## Success Metrics\n\n**Track These KPIs:**\n- Asset generation speed (baseline: 5 images\u002Fmin)\n- Content approval rate (target: >80%)\n- Campaign personalization scale (target: 1000+ variants)\n- Cost per asset (target: \u003C$0.10\u002Fimage)\n- Time saved vs manual production (target: 90% reduction)\n\n---\n\n**This skill makes Jeremy a Vertex AI multimodal expert with instant access to video processing, audio generation, image creation, and marketing automation capabilities.**\n","# Vertex AI Media Master - Comprehensive Multimodal AI Operations\n\nThis Agent Skill provides comprehensive mastery of Google Vertex AI multimodal capabilities for video, audio, image, and text processing with focus on marketing applications.\n\n## Core Capabilities\n\n### ? Video Processing (Gemini 2.0\u002F2.5)\n- **Video Understanding**: Process videos up to 6 hours at low resolution or 2 hours at default resolution\n- **2M Context Window**: Gemini 2.5 Pro handles massive video content\n- **Audio Track Processing**: Automatic audio transcription from video\n- **Multi-video Analysis**: Process multiple videos in single request\n- **Video Summarization**: Extract key moments, scenes, and insights\n- **Marketing Use Cases**:\n  - Analyze competitor video ads\n  - Extract highlights from long-form content\n  - Generate video summaries for social media\n  - Transcribe and caption video content\n  - Identify brand mentions and product placements\n\n### ? Audio Generation & Processing\n- **Lyria Model (2025)**: Native audio and music generation\n- **Speech-to-Text**: Transcribe audio with speaker diarization\n- **Text-to-Speech**: Generate natural voiceovers\n- **Music Composition**: Background music for campaigns\n- **Audio Enhancement**: Noise reduction and quality improvement\n- **Marketing Use Cases**:\n  - Generate podcast scripts and voiceovers\n  - Create audio ads and radio spots\n  - Produce background music for video campaigns\n  - Transcribe customer interviews\n  - Generate multilingual voiceovers\n\n### ?️ Image Generation (Imagen 4 & Gemini 2.5 Flash Image)\n- **Imagen 4**: Highest quality text-to-image generation\n- **Gemini 2.5 Flash Image**: Interleaved image generation with text\n- **Style Transfer**: Apply brand styles to generated images\n- **Product Visualization**: Generate product mockups\n- **Campaign Assets**: Create ad creatives and social media graphics\n- **Marketing Use Cases**:\n  - Generate personalized ad images (Adios solution)\n  - Create social media graphics at scale\n  - Produce product lifestyle images\n  - Generate A\u002FB test variations\n  - Create branded campaign visuals\n\n### ? Marketing Campaign Automation\n- **ViGenAiR**: Convert long-form video ads to short formats automatically\n- **Adios**: Generate personalized ad images tailored to audience context\n- **Campaign Asset Generation**: Photos, soundtracks, voiceovers from prompts\n- **Content Pipeline**: Email copy, blog posts, social media, PMax assets\n- **Catalog Enrichment**: Multi-agent workflow for product onboarding\n- **Marketing Use Cases**:\n  - Automated campaign asset production\n  - Personalized content at scale\n  - Multi-channel content distribution\n  - Product catalog enhancement\n  - Visual merchandising automation\n\n### ? Technical Implementation\n\n**API Integration:**\n```python\nfrom google.cloud import aiplatform\nfrom vertexai.preview.generative_models import GenerativeModel\n\n# Initialize Vertex AI\naiplatform.init(project=\"your-project\", location=\"us-central1\")\n\n# Gemini 2.5 Pro for video\nmodel = GenerativeModel(\"gemini-2.5-pro\")\n\n# Process video with audio\nresponse = model.generate_content([\n    \"Analyze this video and extract key marketing insights\",\n    video_file,  # Up to 6 hours\n])\n\n# Imagen 4 for image generation\nfrom vertexai.preview.vision_models import ImageGenerationModel\nimagen = ImageGenerationModel.from_pretrained(\"imagen-4\")\nimages = imagen.generate_images(\n    prompt=\"Professional product photo, studio lighting, white background\",\n    number_of_images=4\n)\n```\n\n**Gemini 2.5 Flash Image (Interleaved Generation):**\n```python\n# Generate images within text responses\nmodel = GenerativeModel(\"gemini-2.5-flash-image\")\nresponse = model.generate_content([\n    \"Create a 5-step recipe with images for each step\"\n])\n# Returns text + images interleaved\n```\n\n**Audio Generation (Lyria):**\n```python\nfrom vertexai.preview.audio_models import AudioGenerationModel\nlyria = AudioGenerationModel.from_pretrained(\"lyria\")\naudio = lyria.generate_audio(\n    prompt=\"Upbeat background music for product launch video, 30 seconds\",\n    duration=30\n)\n```\n\n### ? Marketing Workflow Automation\n\n**1. Multi-Channel Campaign Creation:**\n```python\n# Single prompt generates all assets\ncampaign = model.generate_content([\n    \"\"\"Create a product launch campaign for [product]:\n    - Hero image (1920x1080)\n    - 3 social media graphics (1080x1080)\n    - 30-second video script\n    - Background music description\n    - Email marketing copy\n    - Instagram caption\"\"\"\n])\n```\n\n**2. Video Repurposing Pipeline:**\n```python\n# Long-form to short-form conversion (ViGenAiR approach)\nlong_video = \"gs:\u002F\u002Fbucket\u002Foriginal-ad-60s.mp4\"\nresponse = model.generate_content([\n    f\"Extract 3 engaging 15-second clips from this video for TikTok\u002FReels\",\n    long_video\n])\n# Auto-generates format-specific versions\n```\n\n**3. Personalized Ad Generation:**\n```python\n# Context-aware image generation (Adios approach)\nfor audience in audiences:\n    ad_image = imagen.generate_images(\n        prompt=f\"Product ad for {product}, targeting {audience.demographics}, {audience.style_preference}\",\n        aspect_ratio=\"16:9\"\n    )\n```\n\n### ? Best Practices for Jeremy\n\n**1. Project Setup:**\n```bash\n# Set environment variables\nexport GOOGLE_CLOUD_PROJECT=\"your-project-id\"\nexport GOOGLE_APPLICATION_CREDENTIALS=\"path\u002Fto\u002Fservice-account.json\"\n\n# Install SDK\npip install google-cloud-aiplatform[vision,audio] google-generativeai\n```\n\n**2. Rate Limits & Quotas:**\n- Gemini 2.5 Pro: 2M tokens\u002Fmin (video processing)\n- Imagen 4: 100 images\u002Fmin\n- Monitor usage in Cloud Console\n\n**3. Cost Optimization:**\n- Use Gemini 2.5 Flash for faster, cheaper operations\n- Batch image generation requests\n- Cache video embeddings for repeated analysis\n- Use low-resolution video setting when appropriate\n\n**4. Security & Compliance:**\n- Keep API keys in Secret Manager, never in code\n- Use service accounts with minimal permissions\n- Enable VPC Service Controls for data residency\n- Log all API calls for audit trails\n\n### ? Advanced Marketing Use Cases\n\n**1. Campaign Performance Analysis:**\n```python\n# Analyze competitor campaigns\ncompetitor_videos = [\"gs:\u002F\u002Fbucket\u002Fcompetitor1.mp4\", \"gs:\u002F\u002Fbucket\u002Fcompetitor2.mp4\"]\nanalysis = model.generate_content([\n    \"Compare these competitor videos: themes, messaging, CTAs, production quality\",\n    *competitor_videos\n])\n```\n\n**2. Content Localization:**\n```python\n# Generate multilingual campaigns\nfor lang in [\"en\", \"es\", \"fr\", \"de\", \"ja\"]:\n    localized_content = model.generate_content([\n        f\"Translate and culturally adapt this campaign for {lang} market:\",\n        campaign_brief,\n        hero_image\n    ])\n```\n\n**3. A\u002FB Test Generation:**\n```python\n# Generate variations automatically\nvariations = []\nfor style in [\"minimalist\", \"bold\", \"luxury\", \"playful\"]:\n    variation = imagen.generate_images(\n        prompt=f\"Product ad, {style} style, {brand_guidelines}\",\n        number_of_images=1\n    )\n    variations.append(variation)\n```\n\n### ? Reference Documentation\n\n**Official Documentation:**\n- Vertex AI Multimodal: https:\u002F\u002Fcloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Fmultimodal\u002Foverview\n- Gemini 2.5 Pro: https:\u002F\u002Fcloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Fmodels\n- Imagen 4: https:\u002F\u002Fcloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Fimage\u002Foverview\n- Video Understanding: https:\u002F\u002Fcloud.google.com\u002Fvertex-ai\u002Fgenerative-ai\u002Fdocs\u002Fmultimodal\u002Fvideo-understanding\n\n**Marketing Solutions:**\n- GenAI for Marketing: https:\u002F\u002Fgithub.com\u002FGoogleCloudPlatform\u002Fgenai-for-marketing\n- ViGenAiR (video repurposing)\n- Adios (personalized ad images)\n\n**Pricing:**\n- Gemini 2.5 Pro: $3.50\u002F1M input tokens, $10.50\u002F1M output tokens\n- Imagen 4: $0.04\u002Fimage\n- Video processing: Included in Gemini token pricing\n\n## When This Skill Activates\n\nThis skill automatically activates when you mention:\n- Video processing, analysis, or understanding\n- Audio generation, music composition, or voiceovers\n- Image generation, ad creatives, or visual content\n- Marketing campaigns, content automation, or asset production\n- Gemini multimodal capabilities\n- Vertex AI media operations\n- Social media content, email marketing, or PMax campaigns\n\n## Integration with Other Tools\n\n**Google Cloud Services:**\n- Cloud Storage for media asset management\n- BigQuery for campaign analytics\n- Cloud Functions for automation triggers\n- Vertex AI Pipelines for content workflows\n\n**Third-Party Integrations:**\n- Social media APIs (LinkedIn, Twitter, Instagram)\n- Marketing automation platforms (HubSpot, Marketo)\n- CMS integrations (WordPress, Contentful)\n- DAM systems (Bynder, Cloudinary)\n\n## Success Metrics\n\n**Track These KPIs:**\n- Asset generation speed (baseline: 5 images\u002Fmin)\n- Content approval rate (target: >80%)\n- Campaign personalization scale (target: 1000+ variants)\n- Cost per asset (target: \u003C$0.10\u002Fimage)\n- Time saved vs manual production (target: 90% reduction)\n\n---\n\n**This skill makes Jeremy a Vertex AI multimodal expert with instant access to video processing, audio generation, image creation, and marketing automation capabilities.**\n",{"name":5,"description":7},"be156301b65e301887f327d08190ed4f17ba08d2","docs\u002Fnot-mcp-related\u002Fclaude-skills\u002Ftemp\u002Fcode-plugins\u002Fplugins\u002Fproductivity\u002F003-jeremy-vertex-ai-media-master\u002Fskills\u002Fvertex-media-master",0,"https:\u002F\u002Fgithub.com\u002Fsandraschi\u002Fdocumentation-mcp","https:\u002F\u002Fgithub.com\u002Fsandraschi","2026-11-11 11:02:01",{"source":8,"skillName":5,"commands":66,"prompt":76,"zipAvailable":77},[67,70,73],{"tool":68,"command":69},"npx","npx skills add sandraschi\u002Fdocumentation-mcp --skill \"Vertex AI Media Master\"",{"tool":71,"command":72},"bunx","bunx skills add sandraschi\u002Fdocumentation-mcp --skill \"Vertex AI Media Master\"",{"tool":74,"command":75},"pnpm","pnpm dlx skills add sandraschi\u002Fdocumentation-mcp --skill \"Vertex AI Media Master\"","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fsandraschi\u002Fdocumentation-mcp\u002Fblob\u002Fmaster\u002Fdocs\u002Fnot-mcp-related\u002Fclaude-skills\u002Ftemp\u002Fcode-plugins\u002Fplugins\u002Fproductivity\u002F003-jeremy-vertex-ai-media-master\u002Fskills\u002Fvertex-media-master\u002FSKILL.md",true,[],[80,103,130,140,165,191],{"skillNo":81,"name":82,"nameZh":6,"description":83,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":84,"categories":85,"keywords":90,"publishedAt":54},"01M6PFAWAHEJJCKKVNXEWNK87W","Docs Research","Use MCP Central Docs server to search, ask, and retrieve documentation (FastMCP, standards, packaging).","https:\u002F\u002Fgithub.com\u002Fsandraschi\u002Fdocumentation-mcp\u002Fblob\u002Fmaster\u002Fsrc\u002Fdocs_mcp\u002Fskills\u002Fdocs-research\u002FSKILL.md",[86,89],{"categoryNo":87,"categoryName":88,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000021","资料检索与研究",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},[91,92,93,94,95,96,97,98,99,100,101,102],"docs research","docs","research","standards","use","packaging","ask","server","search","fastmcp","documentation","MCP",{"skillNo":104,"name":105,"nameZh":6,"description":106,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":54},"01M6PFAN4DAENMY574Q7Q3CB3H","wrappee-drift","Read-only, single-repo audit of a repo's tool coverage against the software it wraps (its current real API\u002Fdocs, not training-data memory) and against comparable\u002Fcompeting wrappers. Trigger when the user says \"wrappee drift\" followed by a repo name, \"capability audit\" followed by a repo name, or asks whether a repo is missing features the wrapped software or a competitor now has. Always scoped to one named repo per invocation -- never trigger this fleet-wide or unprompted; that is explicitly against the SOP. Do NOT trigger for internal fleet-standard compliance (that is drift-scan) or strategic worth\u002Farchive decisions (that is quality-check) -- this is specifically about the gap between the repo's tool list and the wrapped software's\u002Fcompetitors' actual current capabilities.","https:\u002F\u002Fgithub.com\u002Fsandraschi\u002Fdocumentation-mcp\u002Fblob\u002Fmaster\u002Fdocs\u002Fskills\u002Fwrappee-drift\u002FSKILL.md",[],[110,111,112,113,114,115,116,117,118,119,120,121,122,123,124,125,126,127,128,129],"drift","wrappee drift","api","data","audit","capabilities","training","memory","features","repo audit","competitors","fleet","now","software","tool list","only","never","coverage","list","read",{"skillNo":131,"name":132,"nameZh":6,"description":6,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":133,"categories":134,"keywords":139,"publishedAt":54},"01M6PFADA3X031SK3W3T6X0N6H","modules","https:\u002F\u002Fgithub.com\u002Fsandraschi\u002Fdocumentation-mcp\u002Fblob\u002Fmaster\u002Fdocs\u002Fskills\u002Fwindsurf-mcp-standards\u002Fmodules\u002FSKILL.md",[135,138],{"categoryNo":136,"categoryName":137,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000011","运维与部署",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},[132],{"skillNo":141,"name":142,"nameZh":6,"description":143,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":144,"categories":145,"keywords":150,"publishedAt":54},"01M6PFA8YA029N68TW0X31FB1W","mcp-standards","Use when developing MCP servers to access comprehensive standards for scaffolding, packaging, sampling, documentation, testing, error handling, monitoring, and CI\u002FCD workflows.","https:\u002F\u002Fgithub.com\u002Fsandraschi\u002Fdocumentation-mcp\u002Fblob\u002Fmaster\u002Fdocs\u002Fskills\u002Fwindsurf-mcp-standards\u002FSKILL.md",[146,149],{"categoryNo":147,"categoryName":148,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000008","测试与质量",{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},[151,102,94,95,152,153,154,155,156,157,158,159,160,161,162,163,101,53,164,96],"mcp standards","monitoring","sampling","scaffolding","servers","cd","error","for","CI\u002FCD","access","ci","mcp servers","error handling","testing",{"skillNo":166,"name":167,"nameZh":6,"description":168,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":169,"categories":170,"keywords":173,"publishedAt":54},"01M6PFA1XX344WX57B0DJZY94Q","webapp-cua-test","Run the pre-Tauri CUA click-through test (real browser, dev stack, OCR \"Connected\" wait, sidebar nav walk) for a fleet MCP server repo under D:\\Dev\\repos. Trigger when the user says \"cua webapp test\" or \"webapp clickthrough\" followed by a repo name, asks for an e2e click-through of a webapp, or asks whether a webapp boots and connects in a real browser. Not for the installed NSIS app (that is the nsis-build skill \u002F cua-nsis-test) and not for DOM assertions (Playwright), and not for hunting fake data or dead buttons (fakefind).","https:\u002F\u002Fgithub.com\u002Fsandraschi\u002Fdocumentation-mcp\u002Fblob\u002Fmaster\u002Fdocs\u002Fskills\u002Fwebapp-cua-test\u002FSKILL.md",[171,172],{"categoryNo":147,"categoryName":148,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},[174,175,176,177,178,102,179,180,181,158,182,183,184,185,186,187,188,189,98,190],"webapp","test","webapp cua test","playwright","mcp server","dev","dom","assertions","trigger","click","app","tauri","repo","stack","e2e","ocr","browser",{"skillNo":192,"name":193,"nameZh":6,"description":194,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":195,"categories":196,"keywords":198,"publishedAt":54},"01M6PF9WYF6NWJR7WVN38TT0WH","ship","Final release gate for a fleet MCP server repo under D:\\Dev\\repos -- run all quality gates, build the release artifact, verify it, commit, push, and cut a GitHub release. Trigger this whenever the user says \"ship it\", \"ship\" followed by a repo name, \"release\" followed by a repo name, or asks to finalize and publish work that's already been done in a repo. This is the terminal step after assfix\u002Fnsis-build, not a substitute for them -- if the repo hasn't been assessed recently, say so before shipping rather than shipping blind.","https:\u002F\u002Fgithub.com\u002Fsandraschi\u002Fdocumentation-mcp\u002Fblob\u002Fmaster\u002Fdocs\u002Fskills\u002Fship\u002FSKILL.md",[197],{"categoryNo":27,"categoryName":28,"taxonomyType":21,"taxonomyTypeDesc":22},[193,186,158,182,199,200,201,202,203,204,205,98,206,179,207,208,209,178,210,102],"gates","ship it","artifact","done","say","work","publish","push","shipping","quality gates","commit","github"]