{
  "schemaVersion": "1.0",
  "item": {
    "slug": "meta-video-ad-deconstructor",
    "name": "Meta Video Ad Deconstructor",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/fortytwode/meta-video-ad-deconstructor",
    "canonicalUrl": "https://clawhub.ai/fortytwode/meta-video-ad-deconstructor",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/meta-video-ad-deconstructor",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=meta-video-ad-deconstructor",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "prompts/marketing_analysis.md",
      "scripts/models.py",
      "scripts/deconstructor.py",
      "scripts/prompt_manager.py"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/meta-video-ad-deconstructor"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/meta-video-ad-deconstructor",
    "agentPageUrl": "https://openagent3.xyz/skills/meta-video-ad-deconstructor/agent",
    "manifestUrl": "https://openagent3.xyz/skills/meta-video-ad-deconstructor/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/meta-video-ad-deconstructor/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Video Ad Deconstructor",
        "body": "AI-powered deconstruction of video ad creatives into actionable marketing insights."
      },
      {
        "title": "What This Skill Does",
        "body": "Generate Summaries: Product, features, audience, CTA extraction\nDeconstruct Marketing Dimensions: Hooks, social proof, urgency, emotion, etc.\nSupport Multiple Content Types: Consumer products and gaming ads\nProgress Tracking: Callback support for long analyses\nJSON Output: Structured data for downstream processing"
      },
      {
        "title": "1. Environment Variables",
        "body": "# Required for Gemini\nGOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json"
      },
      {
        "title": "2. Dependencies",
        "body": "pip install vertexai"
      },
      {
        "title": "Basic Ad Deconstruction",
        "body": "from scripts.deconstructor import AdDeconstructor\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 deconstructor\ndeconstructor = AdDeconstructor(gemini_model=gemini_model)\n\n# Create extracted content (from video-ad-analyzer or manually)\ncontent = ExtractedVideoContent(\n    video_path=\"ad.mp4\",\n    duration=30.0,\n    transcript=\"Tired of messy cables? Meet CableFlow...\",\n    text_timeline=[{\"at\": 0.0, \"text\": [\"50% OFF TODAY\"]}],\n    scene_timeline=[{\"timestamp\": 0.0, \"description\": \"Person frustrated with tangled cables\"}]\n)\n\n# Generate summary\nsummary = deconstructor.generate_summary(\n    transcript=content.transcript,\n    scenes=\"0.0s: Person frustrated with tangled cables\",\n    text_overlays=\"50% OFF TODAY\"\n)\nprint(summary)"
      },
      {
        "title": "Full Deconstruction",
        "body": "# Deconstruct all marketing dimensions\ndef on_progress(fraction, dimension):\n    print(f\"Progress: {fraction*100:.0f}% - Analyzed {dimension}\")\n\nanalysis = deconstructor.deconstruct(\n    extracted_content=content,\n    summary=summary,\n    is_gaming=False,  # Set True for gaming ads\n    on_progress=on_progress\n)\n\n# Access dimensions\nfor dimension, data in analysis.dimensions.items():\n    print(f\"\\n{dimension}:\")\n    print(data)"
      },
      {
        "title": "Summary Output",
        "body": "Product/App: CableFlow Cable Organizer\n\nKey Features:\nMagnetic design: Keeps cables organized automatically\nUniversal fit: Works with all cable types\nPremium materials: Durable silicone construction\n\nTarget Audience: Tech users frustrated with cable management\n\nCall to Action: Order now and get 50% off"
      },
      {
        "title": "Deconstruction Output",
        "body": "{\n    \"spoken_hooks\": {\n        \"elements\": [\n            {\n                \"hook_text\": \"Tired of messy cables?\",\n                \"timestamp\": \"0:00\",\n                \"hook_type\": \"Problem Question\",\n                \"effectiveness\": \"High - directly addresses pain point\"\n            }\n        ]\n    },\n    \"social_proof\": {\n        \"elements\": [\n            {\n                \"proof_type\": \"User Count\",\n                \"claim\": \"Over 1 million happy customers\",\n                \"credibility_score\": 7\n            }\n        ]\n    },\n    # ... more dimensions\n}"
      },
      {
        "title": "Marketing Dimensions Deconstructed",
        "body": "DimensionWhat It Extractsspoken_hooksOpening hooks from transcriptvisual_hooksAttention-grabbing visualstext_hooksOn-screen text hookssocial_proofTestimonials, user counts, reviewsurgency_scarcityLimited time offers, stock warningsemotional_triggersFear, desire, belonging, etc.problem_solutionPain points and solutionscta_analysisCall-to-action effectivenesstarget_audienceWho the ad targetsunique_mechanismWhat makes product special"
      },
      {
        "title": "Customizing Prompts",
        "body": "Edit prompts in prompts/marketing_analysis.md to customize:\n\nWhat dimensions to analyze\nOutput format\nScoring criteria\nGaming vs consumer product focus"
      },
      {
        "title": "Common Questions This Answers",
        "body": "\"What hooks does this ad use?\"\n\"What's the emotional appeal?\"\n\"How does this ad create urgency?\"\n\"Who is this ad targeting?\"\n\"What social proof is shown?\"\n\"Deconstruct this competitor's ad\""
      }
    ],
    "body": "Video Ad Deconstructor\n\nAI-powered deconstruction of video ad creatives into actionable marketing insights.\n\nWhat This Skill Does\nGenerate Summaries: Product, features, audience, CTA extraction\nDeconstruct Marketing Dimensions: Hooks, social proof, urgency, emotion, etc.\nSupport Multiple Content Types: Consumer products and gaming ads\nProgress Tracking: Callback support for long analyses\nJSON Output: Structured data for downstream processing\nSetup\n1. Environment Variables\n# Required for Gemini\nGOOGLE_APPLICATION_CREDENTIALS=/path/to/service-account.json\n\n2. Dependencies\npip install vertexai\n\nUsage\nBasic Ad Deconstruction\nfrom scripts.deconstructor import AdDeconstructor\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 deconstructor\ndeconstructor = AdDeconstructor(gemini_model=gemini_model)\n\n# Create extracted content (from video-ad-analyzer or manually)\ncontent = ExtractedVideoContent(\n    video_path=\"ad.mp4\",\n    duration=30.0,\n    transcript=\"Tired of messy cables? Meet CableFlow...\",\n    text_timeline=[{\"at\": 0.0, \"text\": [\"50% OFF TODAY\"]}],\n    scene_timeline=[{\"timestamp\": 0.0, \"description\": \"Person frustrated with tangled cables\"}]\n)\n\n# Generate summary\nsummary = deconstructor.generate_summary(\n    transcript=content.transcript,\n    scenes=\"0.0s: Person frustrated with tangled cables\",\n    text_overlays=\"50% OFF TODAY\"\n)\nprint(summary)\n\nFull Deconstruction\n# Deconstruct all marketing dimensions\ndef on_progress(fraction, dimension):\n    print(f\"Progress: {fraction*100:.0f}% - Analyzed {dimension}\")\n\nanalysis = deconstructor.deconstruct(\n    extracted_content=content,\n    summary=summary,\n    is_gaming=False,  # Set True for gaming ads\n    on_progress=on_progress\n)\n\n# Access dimensions\nfor dimension, data in analysis.dimensions.items():\n    print(f\"\\n{dimension}:\")\n    print(data)\n\nOutput Structure\nSummary Output\nProduct/App: CableFlow Cable Organizer\n\nKey Features:\nMagnetic design: Keeps cables organized automatically\nUniversal fit: Works with all cable types\nPremium materials: Durable silicone construction\n\nTarget Audience: Tech users frustrated with cable management\n\nCall to Action: Order now and get 50% off\n\nDeconstruction Output\n{\n    \"spoken_hooks\": {\n        \"elements\": [\n            {\n                \"hook_text\": \"Tired of messy cables?\",\n                \"timestamp\": \"0:00\",\n                \"hook_type\": \"Problem Question\",\n                \"effectiveness\": \"High - directly addresses pain point\"\n            }\n        ]\n    },\n    \"social_proof\": {\n        \"elements\": [\n            {\n                \"proof_type\": \"User Count\",\n                \"claim\": \"Over 1 million happy customers\",\n                \"credibility_score\": 7\n            }\n        ]\n    },\n    # ... more dimensions\n}\n\nMarketing Dimensions Deconstructed\nDimension\tWhat It Extracts\nspoken_hooks\tOpening hooks from transcript\nvisual_hooks\tAttention-grabbing visuals\ntext_hooks\tOn-screen text hooks\nsocial_proof\tTestimonials, user counts, reviews\nurgency_scarcity\tLimited time offers, stock warnings\nemotional_triggers\tFear, desire, belonging, etc.\nproblem_solution\tPain points and solutions\ncta_analysis\tCall-to-action effectiveness\ntarget_audience\tWho the ad targets\nunique_mechanism\tWhat makes product special\nCustomizing Prompts\n\nEdit prompts in prompts/marketing_analysis.md to customize:\n\nWhat dimensions to analyze\nOutput format\nScoring criteria\nGaming vs consumer product focus\nCommon Questions This Answers\n\"What hooks does this ad use?\"\n\"What's the emotional appeal?\"\n\"How does this ad create urgency?\"\n\"Who is this ad targeting?\"\n\"What social proof is shown?\"\n\"Deconstruct this competitor's ad\""
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/fortytwode/meta-video-ad-deconstructor",
    "publisherUrl": "https://clawhub.ai/fortytwode/meta-video-ad-deconstructor",
    "owner": "fortytwode",
    "version": "1.0.0",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/meta-video-ad-deconstructor",
    "downloadUrl": "https://openagent3.xyz/downloads/meta-video-ad-deconstructor",
    "agentUrl": "https://openagent3.xyz/skills/meta-video-ad-deconstructor/agent",
    "manifestUrl": "https://openagent3.xyz/skills/meta-video-ad-deconstructor/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/meta-video-ad-deconstructor/agent.md"
  }
}