[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6FNPFN6H4VFH53C61WCD9DX":3,"skill-same:01M6FNPFN6H4VFH53C61WCD9DX":98},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":15,"categories":16,"keywords":22,"publishedAt":43,"linkOnly":44,"markdownContent":45,"markdownBody":46,"frontMatter":47,"refName":49,"commitSha":50,"skillDirectory":51,"forksCount":52,"repositoryHtmlUrl":53,"repositoryHomepageUrl":6,"ownerHtmlUrl":54,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":55,"install":56,"resources":69},"01M6FNPFN6H4VFH53C61WCD9DX","video-ad-analyzer",null,"Extract and analyze content from video ads using Gemini Vision AI. Supports frame extraction, OCR text detection, audio transcription, and AI-powered scene analysis. Use when analyzing video creative content, extracting text overlays, or generating scene-by-scene descriptions.","kbarbel640-del\u002Fskills","kbarbel640-del","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F255315490?v=4","01M6CJPPQGCCESXMG3K7BBGQ5J","01M6CJPPX2PB2BCZERFVM2C2B3",1,"MIT","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffortytwode\u002Fmeta-video-ad-analyzer\u002FSKILL.md",[17],{"categoryNo":18,"categoryName":19,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000016","图像与多媒体","SCENARIO","使用场景",[23,24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42],"video ad analyzer","analyzer","ad","Video","text","extracting","transcription","vision ai","vision","creative","use","gemini","analyze","ads","Audio","analysis","ocr","detection","analyzing","content","2026-11-10 10:12:30",false,"---\nname: video-ad-analyzer\nversion: 1.0.0\ndescription: Extract and analyze content from video ads using Gemini Vision AI. Supports frame extraction, OCR text detection, audio transcription, and AI-powered scene analysis. Use when analyzing video creative content, extracting text overlays, or generating scene-by-scene descriptions.\n---\n\n# Video Ad Analyzer\n\nAI-powered video content extraction using Google Gemini Vision.\n\n## What This Skill Does\n\n- **Frame Extraction**: Smart sampling with scene change detection\n- **OCR Text Detection**: Extract text overlays using EasyOCR\n- **Audio Transcription**: Convert speech to text with Google Cloud Speech\n- **AI Scene Analysis**: Describe each scene using Gemini Vision\n- **Native Video Analysis**: Direct video understanding for longer content\n- **Thumbnail Generation**: Auto-generate thumbnails from first frame\n\n## Setup\n\n### 1. Environment Variables\n\n```bash\n# Required for Gemini Vision\nGOOGLE_APPLICATION_CREDENTIALS=\u002Fpath\u002Fto\u002Fservice-account.json\n\n# Required for audio transcription\n# (same service account needs Speech-to-Text API enabled)\n```\n\n### 2. Dependencies\n\n```bash\npip install opencv-python pillow easyocr ffmpeg-python google-cloud-speech vertexai google-api-python-client\n```\n\nAlso requires `ffmpeg` and `ffprobe` installed on system.\n\n## Usage\n\n### Basic Video Analysis\n\n```python\nfrom scripts.video_extractor import VideoExtractor\nfrom scripts.models import ExtractedVideoContent\nimport vertexai\nfrom vertexai.generative_models import GenerativeModel\n\n# Initialize Vertex AI\nvertexai.init(project=\"your-project-id\", location=\"us-central1\")\ngemini_model = GenerativeModel(\"gemini-1.5-flash\")\n\n# Create extractor\nextractor = VideoExtractor(gemini_model=gemini_model)\n\n# Analyze video\nresult = extractor.extract_content(\"\u002Fpath\u002Fto\u002Fvideo.mp4\")\n\nprint(f\"Duration: {result.duration}s\")\nprint(f\"Scenes: {len(result.scene_timeline)}\")\nprint(f\"Text overlays: {len(result.text_timeline)}\")\nprint(f\"Transcript: {result.transcript[:200]}...\")\n```\n\n### Extract Only Frames\n\n```python\nframes, timestamps, text_timeline, scene_timeline, thumbnail = extractor.extract_smart_frames(\n    \"\u002Fpath\u002Fto\u002Fvideo.mp4\",\n    scene_interval=2,    # Check for scene changes every 2s\n    text_interval=0.5    # Check for text every 0.5s\n)\n```\n\n### Analyze Images\n\n```python\n# Works with images too\nresult = extractor.extract_content(\"\u002Fpath\u002Fto\u002Fimage.jpg\")\nprint(result.scene_timeline[0]['description'])\n```\n\n## Output Structure\n\n```python\nExtractedVideoContent(\n    video_path=\"\u002Fpath\u002Fto\u002Fvideo.mp4\",\n    duration=30.5,\n    transcript=\"Here's what we found...\",\n    text_timeline=[\n        {\"at\": 0.0, \"text\": [\"Download Now\"]},\n        {\"at\": 5.5, \"text\": [\"50% Off Today\"]}\n    ],\n    scene_timeline=[\n        {\"timestamp\": 0.0, \"description\": \"Woman using phone app...\"},\n        {\"timestamp\": 2.0, \"description\": \"Product showcase with features...\"}\n    ],\n    thumbnail_url=\"\u002Fstatic\u002Fthumbnails\u002Fvideo_thumb.jpg\",\n    extraction_complete=True\n)\n```\n\n## Key Features\n\n| Feature | Description |\n|---------|-------------|\n| Scene Detection | Histogram-based change detection (threshold=65) |\n| OCR Confidence | Tiered thresholds (0.5 high, 0.3 low) |\n| AI Proofreading | Gemini cleans up OCR errors |\n| Source Reconciliation | Merges OCR + Vision text intelligently |\n| Native Video | Direct Gemini analysis for \u003C20MB files |\n\n## Prompts\n\nCustomize AI behavior by editing prompts in the `prompts\u002F` folder:\n\n- `scene_analysis.md` - Frame analysis prompts\n- `scene_reconciliation.md` - Scene enrichment prompts\n\n## Common Questions This Answers\n\n- \"What text appears in this video ad?\"\n- \"Describe each scene in this creative\"\n- \"What does the narrator say?\"\n- \"Extract the call-to-action from this ad\"\n","# Video Ad Analyzer\n\nAI-powered video content extraction using Google Gemini Vision.\n\n## What This Skill Does\n\n- **Frame Extraction**: Smart sampling with scene change detection\n- **OCR Text Detection**: Extract text overlays using EasyOCR\n- **Audio Transcription**: Convert speech to text with Google Cloud Speech\n- **AI Scene Analysis**: Describe each scene using Gemini Vision\n- **Native Video Analysis**: Direct video understanding for longer content\n- **Thumbnail Generation**: Auto-generate thumbnails from first frame\n\n## Setup\n\n### 1. Environment Variables\n\n```bash\n# Required for Gemini Vision\nGOOGLE_APPLICATION_CREDENTIALS=\u002Fpath\u002Fto\u002Fservice-account.json\n\n# Required for audio transcription\n# (same service account needs Speech-to-Text API enabled)\n```\n\n### 2. Dependencies\n\n```bash\npip install opencv-python pillow easyocr ffmpeg-python google-cloud-speech vertexai google-api-python-client\n```\n\nAlso requires `ffmpeg` and `ffprobe` installed on system.\n\n## Usage\n\n### Basic Video Analysis\n\n```python\nfrom scripts.video_extractor import VideoExtractor\nfrom scripts.models import ExtractedVideoContent\nimport vertexai\nfrom vertexai.generative_models import GenerativeModel\n\n# Initialize Vertex AI\nvertexai.init(project=\"your-project-id\", location=\"us-central1\")\ngemini_model = GenerativeModel(\"gemini-1.5-flash\")\n\n# Create extractor\nextractor = VideoExtractor(gemini_model=gemini_model)\n\n# Analyze video\nresult = extractor.extract_content(\"\u002Fpath\u002Fto\u002Fvideo.mp4\")\n\nprint(f\"Duration: {result.duration}s\")\nprint(f\"Scenes: {len(result.scene_timeline)}\")\nprint(f\"Text overlays: {len(result.text_timeline)}\")\nprint(f\"Transcript: {result.transcript[:200]}...\")\n```\n\n### Extract Only Frames\n\n```python\nframes, timestamps, text_timeline, scene_timeline, thumbnail = extractor.extract_smart_frames(\n    \"\u002Fpath\u002Fto\u002Fvideo.mp4\",\n    scene_interval=2,    # Check for scene changes every 2s\n    text_interval=0.5    # Check for text every 0.5s\n)\n```\n\n### Analyze Images\n\n```python\n# Works with images too\nresult = extractor.extract_content(\"\u002Fpath\u002Fto\u002Fimage.jpg\")\nprint(result.scene_timeline[0]['description'])\n```\n\n## Output Structure\n\n```python\nExtractedVideoContent(\n    video_path=\"\u002Fpath\u002Fto\u002Fvideo.mp4\",\n    duration=30.5,\n    transcript=\"Here's what we found...\",\n    text_timeline=[\n        {\"at\": 0.0, \"text\": [\"Download Now\"]},\n        {\"at\": 5.5, \"text\": [\"50% Off Today\"]}\n    ],\n    scene_timeline=[\n        {\"timestamp\": 0.0, \"description\": \"Woman using phone app...\"},\n        {\"timestamp\": 2.0, \"description\": \"Product showcase with features...\"}\n    ],\n    thumbnail_url=\"\u002Fstatic\u002Fthumbnails\u002Fvideo_thumb.jpg\",\n    extraction_complete=True\n)\n```\n\n## Key Features\n\n| Feature | Description |\n|---------|-------------|\n| Scene Detection | Histogram-based change detection (threshold=65) |\n| OCR Confidence | Tiered thresholds (0.5 high, 0.3 low) |\n| AI Proofreading | Gemini cleans up OCR errors |\n| Source Reconciliation | Merges OCR + Vision text intelligently |\n| Native Video | Direct Gemini analysis for \u003C20MB files |\n\n## Prompts\n\nCustomize AI behavior by editing prompts in the `prompts\u002F` folder:\n\n- `scene_analysis.md` - Frame analysis prompts\n- `scene_reconciliation.md` - Scene enrichment prompts\n\n## Common Questions This Answers\n\n- \"What text appears in this video ad?\"\n- \"Describe each scene in this creative\"\n- \"What does the narrator say?\"\n- \"Extract the call-to-action from this ad\"\n",{"name":5,"version":48,"description":7},"1.0.0","main","e7e336ac628c3e3bd771aff1aaa469c93778f94a","skills\u002Ffortytwode\u002Fmeta-video-ad-analyzer",0,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del","2026-08-23 22:39:37",{"source":8,"skillName":5,"commands":57,"prompt":67,"zipAvailable":68},[58,61,64],{"tool":59,"command":60},"npx","npx skills add kbarbel640-del\u002Fskills --skill video-ad-analyzer",{"tool":62,"command":63},"bunx","bunx skills add kbarbel640-del\u002Fskills --skill video-ad-analyzer",{"tool":65,"command":66},"pnpm","pnpm dlx skills add kbarbel640-del\u002Fskills --skill video-ad-analyzer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffortytwode\u002Fmeta-video-ad-analyzer\u002FSKILL.md",true,[70,76,80,84,90,94],{"path":71,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":74,"sourceHtmlUrl":75},"_meta.json","REFERENCE","参考文档",300,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffortytwode\u002Fmeta-video-ad-analyzer\u002F_meta.json",{"path":77,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":78,"sourceHtmlUrl":79},"prompts\u002Fscene_analysis.md",3391,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffortytwode\u002Fmeta-video-ad-analyzer\u002Fprompts\u002Fscene_analysis.md",{"path":81,"resourceType":72,"resourceTypeDesc":73,"sizeBytes":82,"sourceHtmlUrl":83},"prompts\u002Fscene_reconciliation.md",3671,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffortytwode\u002Fmeta-video-ad-analyzer\u002Fprompts\u002Fscene_reconciliation.md",{"path":85,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":88,"sourceHtmlUrl":89},"scripts\u002Fmodels.py","SCRIPT","脚本",548,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffortytwode\u002Fmeta-video-ad-analyzer\u002Fscripts\u002Fmodels.py",{"path":91,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":92,"sourceHtmlUrl":93},"scripts\u002Fprompt_manager.py",4986,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffortytwode\u002Fmeta-video-ad-analyzer\u002Fscripts\u002Fprompt_manager.py",{"path":95,"resourceType":86,"resourceTypeDesc":87,"sizeBytes":96,"sourceHtmlUrl":97},"scripts\u002Fvideo_extractor.py",28663,"https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Ffortytwode\u002Fmeta-video-ad-analyzer\u002Fscripts\u002Fvideo_extractor.py",[99,128,153,174,180,200],{"skillNo":100,"name":101,"nameZh":6,"description":102,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":103,"categories":104,"keywords":110,"publishedAt":43},"01M6G8J55967D6281ACMKAKTEQ","crowd-prompting","A marketplace where AI agents improve prompts, system instructions, tool descriptions, and other text-based content with domain expertise from real-world operations — and earn tokens for valuable contributions.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzzadrian\u002Fcrowd-prompting\u002FSKILL.md",[105],{"categoryNo":106,"categoryName":107,"taxonomyType":108,"taxonomyTypeDesc":109},"01JBSEEDCAT000000000000036","内容创作者","PROFESSION","适用职业",[111,112,113,114,115,116,117,118,119,120,27,121,122,123,124,125,126,42,127],"crowd prompting","prompting","api","with","tokens","domain","world","prompts","operations","instructions","tool","system","improve","productivity","marketplace","https","ai agents",{"skillNo":129,"name":130,"nameZh":6,"description":131,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":132,"categories":133,"keywords":137,"publishedAt":43},"01M6G8J0PKPAYVET6BWE8W4C26","dilemm-ai","Compete in DilemmAI, the prisoner's dilemma AI arena at dilemm.ai. Use when an OpenClaw agent wants to create an account, design and submit strategy prompts for their bot, enter matchmaking, analyze historical matches and leaderboards, and iterate on bot strategy. Requires headless browser automation (no API available yet).","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzyori\u002Fdilemm-ai\u002FSKILL.md",[134],{"categoryNo":135,"categoryName":136,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000023","Skill与智能体开发",[138,113,139,35,140,141,142,143,144,145,146,147,148,149,150,151,152,118,33],"dilemm ai","arena","browser","openclaw agent","create","automation","browser automation","bot","openclaw","design","strategy","headless","compete","submit","matchmaking",{"skillNo":154,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":157,"categories":158,"keywords":162,"publishedAt":43},"01M6G8HWAF3K9SW7NP3Z83CPJ6","arxiv-paper-reviews","Interact with arXiv Crawler API to fetch papers, read reviews, and submit comments. Use when working with arXiv papers, fetching paper lists by date\u002Fcategory\u002Finterest, viewing paper details with comments, or submitting paper reviews via API at http:\u002F\u002F150.158.152.82:8000.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Fweak-accept\u002FSKILL.md",[159],{"categoryNo":160,"categoryName":161,"taxonomyType":20,"taxonomyTypeDesc":21},"01JBSEEDCAT000000000000021","资料检索与研究",[163,164,165,166,167,168,169,114,170,151,33,171,113,172,173],"arxiv paper reviews","reviews","arxiv","paper","crawler","papers","comments","fetch","read","http","via",{"skillNo":175,"name":155,"nameZh":6,"description":156,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":176,"categories":177,"keywords":179,"publishedAt":43},"01M6G8HQJ7N7WMY6YV7D7SSJ16","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzxrys\u002Farxiv-paper-reviews\u002FSKILL.md",[178],{"categoryNo":160,"categoryName":161,"taxonomyType":20,"taxonomyTypeDesc":21},[166,165,164,163,173,168,169,114,167,151,33,170,171,113,172],{"skillNo":181,"name":182,"nameZh":6,"description":183,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":184,"categories":185,"keywords":186,"publishedAt":43},"01M6G8HM95Y64JNVFC2HN4E2BG","git-summary","Get a quick summary of the current Git repository including status, recent commits, branches, and contributors.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fzweack\u002Fgit-summary\u002FSKILL.md",[],[187,188,189,190,191,192,193,194,195,196,197,198,199],"git","summary","git summary","commits","repository","win32","status","linux","contributors","true","quick","get","branches",{"skillNo":201,"name":202,"nameZh":6,"description":203,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":6,"repositoryNo":12,"starsCount":13,"licenseSpdxId":14,"licenseFileUrl":6,"sourceHtmlUrl":204,"categories":205,"keywords":210,"publishedAt":43},"01M6G8HGEGF05CNEJCGVYFSC4R","agent-constitution","Interact with AgentConstitution governance contracts on Base Sepolia. Check compliance, read rules, log actions, query governance state.","https:\u002F\u002Fgithub.com\u002Fkbarbel640-del\u002Fskills\u002Fblob\u002Fmain\u002Fskills\u002Fztsalexey\u002Fagent-constitution\u002FSKILL.md",[206,207],{"categoryNo":135,"categoryName":136,"taxonomyType":20,"taxonomyTypeDesc":21},{"categoryNo":208,"categoryName":209,"taxonomyType":108,"taxonomyTypeDesc":109},"01JBSEEDCAT000000000000037","律师与法务",[211,212,213,214,114,215,216,49,217,171,218,219,220,221,222,126,223,224,225],"agent constitution","constitution","contracts","tree","query","base","log","check","Rules","projects","compliance","actions","state","governance","github"]