{
  "schemaVersion": "1.0",
  "item": {
    "slug": "adcp-advertising",
    "name": "Ad Context Protocol (AdCP) Advertising",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/edyyy62/adcp-advertising",
    "canonicalUrl": "https://clawhub.ai/edyyy62/adcp-advertising",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/adcp-advertising",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=adcp-advertising",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "CREATIVE.md",
      "EXAMPLES.md",
      "REFERENCE.md",
      "TARGETING.md",
      "README.md",
      "SKILL.md"
    ],
    "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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-23T16:43:11.935Z",
      "expiresAt": "2026-04-30T16:43:11.935Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=4claw-imageboard",
        "contentDisposition": "attachment; filename=\"4claw-imageboard-1.0.1.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/adcp-advertising"
    },
    "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/adcp-advertising",
    "agentPageUrl": "https://openagent3.xyz/skills/adcp-advertising/agent",
    "manifestUrl": "https://openagent3.xyz/skills/adcp-advertising/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/adcp-advertising/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. Then review README.md for any prerequisites, environment setup, or post-install checks. 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. Then review README.md for any prerequisites, environment setup, or post-install checks. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Overview",
        "body": "Automate your advertising campaigns with AI. This skill enables OpenClaw agents to discover ad inventory, launch campaigns, manage creatives, and optimize performance across display, video, CTV, audio, and more - all through natural language commands.\n\nNo dashboards. No forms. No ad platform expertise required."
      },
      {
        "title": "What You Can Do",
        "body": "🎯 Launch campaigns in minutes - \"Create a $10k display campaign targeting tech professionals in California\"\n🔍 Discover ad inventory instantly - \"Find premium video placements for luxury brands\"\n🎨 Upload ads with ease - \"Upload these banner images as creatives\"\n📊 Track ROI in real-time - \"Show me campaign performance and CTR by creative\"\n🎛️ Auto-optimize spend - \"Reallocate budget to top-performing packages\"\n🌐 Target precisely - Demographics, behaviors, interests, locations, devices, times"
      },
      {
        "title": "Perfect For",
        "body": "Marketing teams running Facebook ads, Google ads, and multi-channel campaigns\nMedia buyers managing programmatic ad spend across publishers\nAgencies automating client campaign management and reporting\nE-commerce brands launching product ads and retargeting campaigns\nStartups running lean marketing with AI-powered automation"
      },
      {
        "title": "Why Choose This Skill?",
        "body": "Skip the learning curve - No need to master complex ad platforms\nSave time - Launch in 5 minutes vs. hours of manual setup\nSpend smarter - AI automatically optimizes budgets to top performers\nScale faster - Manage unlimited campaigns through simple commands\nTest risk-free - Public test agent included, no setup required\n\nOfficial AdCP Repository: https://github.com/adcontextprotocol/adcp\nOfficial AdCP Documentation: https://docs.adcontextprotocol.org\nComplete Documentation Index: https://docs.adcontextprotocol.org/llms.txt"
      },
      {
        "title": "When to Use This Skill",
        "body": "Trigger this skill when users ask about:\n\nCampaign Management\n\n\"Create a display ad campaign\"\n\"Launch Facebook ads for my product\"\n\"Set up a $5000 video advertising campaign\"\n\"Pause my underperforming campaigns\"\n\nAd Discovery & Media Buying\n\n\"Find advertising inventory for luxury brands\"\n\"Show me CTV ad placements in major cities\"\n\"What display ad options are available?\"\n\"Buy media for a tech startup\"\n\nCreative Management\n\n\"Upload these banner images\"\n\"Which creative is performing best?\"\n\"Add video ads to my campaign\"\n\"Manage my ad library\"\n\nPerformance & Optimization\n\n\"How is my campaign performing?\"\n\"Show me ROI by channel\"\n\"Optimize my ad spend\"\n\"Reallocate budget to top performers\"\n\"Track impressions and click-through rates\"\n\nTargeting & Audiences\n\n\"Target professionals in California\"\n\"Set up demographic targeting\"\n\"Create a retargeting campaign\"\n\"Target by device type and time of day\""
      },
      {
        "title": "Launch Your First Campaign (5 Minutes)",
        "body": "No setup required. Use the included test agent to try everything:\n\nStep 1: Discover what's available\n\n\"Show me advertising capabilities\"\n\nBrowse available channels, publishers, and formats.\n\nStep 2: Find ad inventory\n\n\"Find display ads for a tech startup, budget $5000\"\n\nAI searches and shows matching products with pricing.\n\nStep 3: Launch campaign\n\n\"Create campaign with Product prod_123, $5000 budget, targeting California tech professionals\"\n\nCampaign goes live instantly.\n\nStep 4: Upload your ads\n\n\"Upload these banner images as creatives\"\n\nDrop files, get instant creative IDs.\n\nStep 5: Monitor performance\n\n\"Show campaign metrics and ROI\"\n\nReal-time impressions, clicks, CTR, spend."
      },
      {
        "title": "Real-World Usage Examples",
        "body": "Quick campaign launch:\n\nUser: \"I need to run display ads for my SaaS product\"\nAgent: [Discovers products] \"Found 5 display packages. Want details?\"\nUser: \"Create campaign with Product 1, $10k budget, target CTOs\"\nAgent: [Creates campaign] \"Campaign live! ID: mb_abc123\"\n\nPerformance optimization:\n\nUser: \"How are my video ads performing?\"\nAgent: [Shows metrics] \"Package A: 2.3% CTR, Package B: 0.8% CTR\"\nUser: \"Move $5k from B to A\"\nAgent: [Reallocates] \"Budget updated. Package A now $15k\"\n\nMulti-channel campaign:\n\nUser: \"Launch omnichannel campaign: display in CA, video in NYC, $50k total\"\nAgent: [Creates packages] \"3 packages created across display and video\""
      },
      {
        "title": "Natural Language Understanding",
        "body": "Speak naturally. The skill understands:\n\nBudgets: \"$5000\", \"five thousand dollars\", \"5k budget\"\nLocations: \"California\", \"major US cities\", \"New York and LA\"\nAudiences: \"tech professionals\", \"age 25-45\", \"high income\"\nGoals: \"brand awareness\", \"drive conversions\", \"increase sales\""
      },
      {
        "title": "Progressive Workflow",
        "body": "1. Discovery Phase\n\n\"Find video advertising for luxury brands\"\n\n↓ Agent searches inventory\n↓ Shows matched products with pricing\n↓ Explains targeting and formats\n\n2. Campaign Creation\n\n\"Create campaign with Product 1, $25k, target professionals\"\n\n↓ Agent creates media buy\n↓ Sets up targeting overlay\n↓ Returns campaign ID and status\n\n3. Creative Management\n\n\"Upload my banner ads\"\n\n↓ Agent syncs creatives\n↓ Assigns to campaign\n↓ Returns creative IDs\n\n4. Monitoring & Optimization\n\n\"Show performance\"\n\n↓ Agent fetches delivery data\n↓ Shows metrics by package/creative\n↓ Suggests optimizations"
      },
      {
        "title": "Create Campaign",
        "body": "const campaign = await testAgent.createMediaBuy({\n  buyer_ref: 'campaign-2026-q1',\n  brand_manifest: { url: 'https://acme.com' },\n  packages: [{ product_id: 'premium_display', budget: 10000 }]\n});"
      },
      {
        "title": "Upload Creatives",
        "body": "await testAgent.syncCreatives({\n  creatives: [{ \n    buyer_ref: 'banner-300x250',\n    url: 'https://cdn.acme.com/banner.jpg'\n  }]\n});"
      },
      {
        "title": "Monitor Performance",
        "body": "const delivery = await testAgent.getMediaBuyDelivery({\n  media_buy_id: 'mb_abc123'\n});\nconsole.log(`CTR: ${delivery.totals.ctr}%, Spend: $${delivery.totals.spend}`);\n\nSee REFERENCE.md for complete API docs and EXAMPLES.md for detailed workflows."
      },
      {
        "title": "The 8 Media Buy Tasks",
        "body": "AdCP provides 8 standardized tasks for the complete advertising lifecycle. Learn more in the Media Buy Protocol documentation.\n\nget_adcp_capabilities - Discover agent features and portfolio (~1s)\nget_products - Find inventory using natural language (~60s)\nlist_creative_formats - View creative specifications (~1s)\ncreate_media_buy - Launch campaigns (minutes-days, may require approval)\nupdate_media_buy - Modify campaigns (minutes-days)\nsync_creatives - Upload creative assets (minutes-days)\nlist_creatives - Query creative library (~1s)\nget_media_buy_delivery - Track performance (~60s)\n\nComplete task reference: https://docs.adcontextprotocol.org/docs/media-buy/task-reference/"
      },
      {
        "title": "Brand Manifest",
        "body": "Brand context can be provided two ways:\n\nURL reference (recommended - agent fetches brand info):\n\n{\n  \"brand_manifest\": {\n    \"url\": \"https://brand.com\"\n  }\n}\n\nInline manifest (full brand details):\n\n{\n  \"brand_manifest\": {\n    \"name\": \"Brand Name\",\n    \"url\": \"https://brand.com\",\n    \"tagline\": \"Brand tagline\",\n    \"colors\": { \"primary\": \"#FF0000\" },\n    \"logo\": { \"url\": \"https://cdn.brand.com/logo.png\" }\n  }\n}"
      },
      {
        "title": "Pricing Models",
        "body": "Products support various pricing models:\n\nCPM (Cost Per Mille/Thousand) - Fixed price per 1000 impressions\nCPM-Auction - Bid-based pricing for impressions\nCPCV (Cost Per Completed View) - Video completions\nFlat-Fee - Fixed campaign cost\nCPP (Cost Per Point) - Percentage of audience reached\n\nFor auction pricing, include bid_price in your package."
      },
      {
        "title": "Asynchronous Operations",
        "body": "AdCP is not a real-time protocol. Operations may take:\n\n~1 second - Simple lookups (formats, creative lists)\n~60 seconds - AI/inference operations (product discovery)\nMinutes to days - Operations requiring human approval (campaign creation)\n\nAlways check the status field in responses:\n\ncompleted - Operation finished successfully\npending - Awaiting approval or processing\nfailed - Operation failed (check error details)"
      },
      {
        "title": "Targeting Capabilities",
        "body": "Apply targeting overlays to campaigns:\n\n{\n  targeting_overlay: {\n    geo: {\n      included: ['US-CA', 'US-NY'],  // DMA codes or regions\n      excluded: ['US-TX']\n    },\n    demographics: {\n      age_ranges: [{ min: 25, max: 44 }],\n      genders: ['M', 'F']\n    },\n    behavioral: {\n      interests: ['technology', 'gaming'],\n      purchase_intent: ['consumer_electronics']\n    },\n    contextual: {\n      keywords: ['innovation', 'design'],\n      categories: ['IAB19'] // Technology & Computing\n    }\n  }\n}"
      },
      {
        "title": "Workflow 1: Campaign Discovery to Launch",
        "body": "// 1. Discover capabilities\nconst caps = await agent.getAdcpCapabilities({});\n\n// 2. Find products\nconst products = await agent.getProducts({\n  brief: 'Q1 2026 brand awareness campaign for tech startup',\n  brand_manifest: { url: 'https://startup.com' },\n  filters: { channels: ['display', 'video'] }\n});\n\n// 3. Check creative formats\nconst formats = await agent.listCreativeFormats({\n  format_types: ['display', 'video']\n});\n\n// 4. Create campaign\nconst campaign = await agent.createMediaBuy({\n  buyer_ref: 'q1-2026-awareness',\n  brand_manifest: { url: 'https://startup.com' },\n  packages: [\n    {\n      buyer_ref: 'pkg-001',\n      product_id: products.products[0].product_id,\n      pricing_option_id: 'cpm-standard',\n      budget: 15000\n    }\n  ],\n  start_time: { type: 'asap' },\n  end_time: '2026-03-31T23:59:59Z'\n});\n\n// 5. Upload creatives\nawait agent.syncCreatives({\n  creatives: [...], // Your creative assets\n  assignments: {\n    'creative_001': ['pkg-001']\n  }\n});\n\n// 6. Monitor performance\nconst delivery = await agent.getMediaBuyDelivery({\n  media_buy_id: campaign.media_buy_id\n});"
      },
      {
        "title": "Workflow 2: Update Running Campaign",
        "body": "// Pause, adjust budget, and resume campaign\nawait agent.updateMediaBuy({\n  media_buy_id: 'mb_abc123',\n  updates: {\n    status: 'paused',\n    budget_change: 5000, // Add $5000\n    end_time: '2026-04-30T23:59:59Z'\n  }\n});\n\n// Resume after adjustments\nawait agent.updateMediaBuy({\n  media_buy_id: 'mb_abc123',\n  updates: { status: 'active' }\n});\n\nMore workflow examples: See EXAMPLES.md for complete campaign scenarios including creative management, multi-channel campaigns, and optimization workflows."
      },
      {
        "title": "Test Agent",
        "body": "For development and testing, use the public test agent:\n\nAgent URL: https://test-agent.adcontextprotocol.org/mcp\nAuth Token: 1v8tAhASaUYYp4odoQ1PnMpdqNaMiTrCRqYo9OJp6IQ\n\nimport { testAgent } from '@adcp/client/testing';\n\n// No authentication needed for test agent\nconst result = await testAgent.getProducts({\n  brief: 'Test campaign',\n  brand_manifest: { url: 'https://example.com' }\n});\n\nInteractive testing available at: testing.adcontextprotocol.org"
      },
      {
        "title": "Error Handling",
        "body": "Common error patterns:\n\n400 Bad Request - Invalid parameters:\n\n{\n  \"error\": {\n    \"code\": \"VALIDATION_ERROR\",\n    \"message\": \"budget must be greater than 0\",\n    \"field\": \"packages[0].budget\"\n  }\n}\n\n401 Unauthorized - Missing or invalid auth:\n\n{\n  \"error\": {\n    \"code\": \"UNAUTHORIZED\",\n    \"message\": \"Invalid authentication token\"\n  }\n}\n\n404 Not Found - Invalid ID reference:\n\n{\n  \"error\": {\n    \"code\": \"NOT_FOUND\",\n    \"message\": \"Product not found\",\n    \"resource\": \"product_id: premium_video_30s\"\n  }\n}\n\nAlways check for errors before processing responses:\n\nif (result.error) {\n  console.error(`Error: ${result.error.message}`);\n  return;\n}"
      },
      {
        "title": "1. Always Start with Capabilities",
        "body": "Call get_adcp_capabilities first to understand what the agent supports before making other requests."
      },
      {
        "title": "2. Use Clear Buyer References",
        "body": "Use descriptive buyer_ref values for tracking:\n\nGood: 'campaign-2026-q1-tech-launch'\nAvoid: 'c1', 'test', 'abc'"
      },
      {
        "title": "3. Handle Async Operations",
        "body": "Check status field and implement polling for pending operations:\n\nlet status = 'pending';\nwhile (status === 'pending') {\n  await sleep(5000); // Wait 5 seconds\n  const update = await agent.getMediaBuyDelivery({\n    media_buy_id: campaign.media_buy_id\n  });\n  status = update.status;\n}"
      },
      {
        "title": "4. Write Detailed Briefs",
        "body": "Better briefs lead to better product matches:\n\nGood: 'Premium video inventory for luxury automotive brand targeting high-income professionals aged 35-54 in major metros. Focus on brand awareness with completion rates above 70%.'\nAvoid: 'video ads', 'need advertising'"
      },
      {
        "title": "5. Validate Creative Formats",
        "body": "Always check list_creative_formats to ensure your creatives meet requirements before uploading."
      },
      {
        "title": "6. Monitor Budget Pacing",
        "body": "Regularly check delivery metrics to ensure campaigns are pacing properly:\n\nconst delivery = await agent.getMediaBuyDelivery({\n  media_buy_id: campaign.media_buy_id\n});\n\nconst pacing = delivery.delivery.spend / delivery.delivery.budget;\nconsole.log(`Budget pacing: ${(pacing * 100).toFixed(1)}%`);"
      },
      {
        "title": "Official AdCP Documentation",
        "body": "Main Documentation: https://docs.adcontextprotocol.org\nComplete Index: https://docs.adcontextprotocol.org/llms.txt\nMedia Buy Protocol: https://docs.adcontextprotocol.org/docs/media-buy/\nQuick Reference: https://docs.adcontextprotocol.org/docs/media-buy/quick-reference\nTask Reference: https://docs.adcontextprotocol.org/docs/media-buy/task-reference/\nQuickstart Guide: https://docs.adcontextprotocol.org/docs/quickstart"
      },
      {
        "title": "This Skill's Documentation",
        "body": "REFERENCE.md - Complete API reference and schemas\nEXAMPLES.md - Real-world campaign examples\nPROTOCOLS.md - MCP vs A2A protocol details\nTARGETING.md - Advanced targeting strategies\nCREATIVE.md - Creative asset management guide"
      },
      {
        "title": "Key Reminders",
        "body": "AdCP is asynchronous - Operations may take minutes to days\nHuman approval may be required - Check for pending status\nStart with capabilities - Always call get_adcp_capabilities first\nBrand context matters - Provide detailed brand manifests for better results\nTargeting is additive - Product targeting + your overlay = final targeting\nCreative formats are strict - Always validate against format specifications\nMonitor performance - Regular delivery checks ensure campaign success"
      },
      {
        "title": "Support",
        "body": "For help with AdCP:\n\nOfficial Repository: https://github.com/adcontextprotocol/adcp\nDocumentation: https://docs.adcontextprotocol.org\nInteractive Testing: https://testing.adcontextprotocol.org\nComplete API Docs: https://docs.adcontextprotocol.org/llms.txt"
      }
    ],
    "body": "Ad Context Protocol (AdCP) Advertising Skill\nOverview\n\nAutomate your advertising campaigns with AI. This skill enables OpenClaw agents to discover ad inventory, launch campaigns, manage creatives, and optimize performance across display, video, CTV, audio, and more - all through natural language commands.\n\nNo dashboards. No forms. No ad platform expertise required.\n\nWhat You Can Do\n🎯 Launch campaigns in minutes - \"Create a $10k display campaign targeting tech professionals in California\"\n🔍 Discover ad inventory instantly - \"Find premium video placements for luxury brands\"\n🎨 Upload ads with ease - \"Upload these banner images as creatives\"\n📊 Track ROI in real-time - \"Show me campaign performance and CTR by creative\"\n🎛️ Auto-optimize spend - \"Reallocate budget to top-performing packages\"\n🌐 Target precisely - Demographics, behaviors, interests, locations, devices, times\nPerfect For\n\nMarketing teams running Facebook ads, Google ads, and multi-channel campaigns\nMedia buyers managing programmatic ad spend across publishers\nAgencies automating client campaign management and reporting\nE-commerce brands launching product ads and retargeting campaigns\nStartups running lean marketing with AI-powered automation\n\nWhy Choose This Skill?\n\nSkip the learning curve - No need to master complex ad platforms\nSave time - Launch in 5 minutes vs. hours of manual setup\nSpend smarter - AI automatically optimizes budgets to top performers\nScale faster - Manage unlimited campaigns through simple commands\nTest risk-free - Public test agent included, no setup required\n\nOfficial AdCP Repository: https://github.com/adcontextprotocol/adcp\nOfficial AdCP Documentation: https://docs.adcontextprotocol.org\nComplete Documentation Index: https://docs.adcontextprotocol.org/llms.txt\n\nWhen to Use This Skill\n\nTrigger this skill when users ask about:\n\nCampaign Management\n\n\"Create a display ad campaign\"\n\"Launch Facebook ads for my product\"\n\"Set up a $5000 video advertising campaign\"\n\"Pause my underperforming campaigns\"\n\nAd Discovery & Media Buying\n\n\"Find advertising inventory for luxury brands\"\n\"Show me CTV ad placements in major cities\"\n\"What display ad options are available?\"\n\"Buy media for a tech startup\"\n\nCreative Management\n\n\"Upload these banner images\"\n\"Which creative is performing best?\"\n\"Add video ads to my campaign\"\n\"Manage my ad library\"\n\nPerformance & Optimization\n\n\"How is my campaign performing?\"\n\"Show me ROI by channel\"\n\"Optimize my ad spend\"\n\"Reallocate budget to top performers\"\n\"Track impressions and click-through rates\"\n\nTargeting & Audiences\n\n\"Target professionals in California\"\n\"Set up demographic targeting\"\n\"Create a retargeting campaign\"\n\"Target by device type and time of day\"\nQuick Start\nLaunch Your First Campaign (5 Minutes)\n\nNo setup required. Use the included test agent to try everything:\n\nStep 1: Discover what's available\n\n\"Show me advertising capabilities\"\n\n\nBrowse available channels, publishers, and formats.\n\nStep 2: Find ad inventory\n\n\"Find display ads for a tech startup, budget $5000\"\n\n\nAI searches and shows matching products with pricing.\n\nStep 3: Launch campaign\n\n\"Create campaign with Product prod_123, $5000 budget, targeting California tech professionals\"\n\n\nCampaign goes live instantly.\n\nStep 4: Upload your ads\n\n\"Upload these banner images as creatives\"\n\n\nDrop files, get instant creative IDs.\n\nStep 5: Monitor performance\n\n\"Show campaign metrics and ROI\"\n\n\nReal-time impressions, clicks, CTR, spend.\n\nReal-World Usage Examples\n\nQuick campaign launch:\n\nUser: \"I need to run display ads for my SaaS product\"\nAgent: [Discovers products] \"Found 5 display packages. Want details?\"\nUser: \"Create campaign with Product 1, $10k budget, target CTOs\"\nAgent: [Creates campaign] \"Campaign live! ID: mb_abc123\"\n\n\nPerformance optimization:\n\nUser: \"How are my video ads performing?\"\nAgent: [Shows metrics] \"Package A: 2.3% CTR, Package B: 0.8% CTR\"\nUser: \"Move $5k from B to A\"\nAgent: [Reallocates] \"Budget updated. Package A now $15k\"\n\n\nMulti-channel campaign:\n\nUser: \"Launch omnichannel campaign: display in CA, video in NYC, $50k total\"\nAgent: [Creates packages] \"3 packages created across display and video\"\n\nHow It Works\nNatural Language Understanding\n\nSpeak naturally. The skill understands:\n\nBudgets: \"$5000\", \"five thousand dollars\", \"5k budget\"\nLocations: \"California\", \"major US cities\", \"New York and LA\"\nAudiences: \"tech professionals\", \"age 25-45\", \"high income\"\nGoals: \"brand awareness\", \"drive conversions\", \"increase sales\"\nProgressive Workflow\n\n1. Discovery Phase\n\n\"Find video advertising for luxury brands\"\n\n\n↓ Agent searches inventory ↓ Shows matched products with pricing ↓ Explains targeting and formats\n\n2. Campaign Creation\n\n\"Create campaign with Product 1, $25k, target professionals\"\n\n\n↓ Agent creates media buy ↓ Sets up targeting overlay ↓ Returns campaign ID and status\n\n3. Creative Management\n\n\"Upload my banner ads\"\n\n\n↓ Agent syncs creatives ↓ Assigns to campaign ↓ Returns creative IDs\n\n4. Monitoring & Optimization\n\n\"Show performance\"\n\n\n↓ Agent fetches delivery data\n↓ Shows metrics by package/creative\n↓ Suggests optimizations\n\nCore Operations\nCreate Campaign\nconst campaign = await testAgent.createMediaBuy({\n  buyer_ref: 'campaign-2026-q1',\n  brand_manifest: { url: 'https://acme.com' },\n  packages: [{ product_id: 'premium_display', budget: 10000 }]\n});\n\nUpload Creatives\nawait testAgent.syncCreatives({\n  creatives: [{ \n    buyer_ref: 'banner-300x250',\n    url: 'https://cdn.acme.com/banner.jpg'\n  }]\n});\n\nMonitor Performance\nconst delivery = await testAgent.getMediaBuyDelivery({\n  media_buy_id: 'mb_abc123'\n});\nconsole.log(`CTR: ${delivery.totals.ctr}%, Spend: $${delivery.totals.spend}`);\n\n\nSee REFERENCE.md for complete API docs and EXAMPLES.md for detailed workflows.\n\nCore Concepts\nThe 8 Media Buy Tasks\n\nAdCP provides 8 standardized tasks for the complete advertising lifecycle. Learn more in the Media Buy Protocol documentation.\n\nget_adcp_capabilities - Discover agent features and portfolio (~1s)\nget_products - Find inventory using natural language (~60s)\nlist_creative_formats - View creative specifications (~1s)\ncreate_media_buy - Launch campaigns (minutes-days, may require approval)\nupdate_media_buy - Modify campaigns (minutes-days)\nsync_creatives - Upload creative assets (minutes-days)\nlist_creatives - Query creative library (~1s)\nget_media_buy_delivery - Track performance (~60s)\n\nComplete task reference: https://docs.adcontextprotocol.org/docs/media-buy/task-reference/\n\nBrand Manifest\n\nBrand context can be provided two ways:\n\nURL reference (recommended - agent fetches brand info):\n\n{\n  \"brand_manifest\": {\n    \"url\": \"https://brand.com\"\n  }\n}\n\n\nInline manifest (full brand details):\n\n{\n  \"brand_manifest\": {\n    \"name\": \"Brand Name\",\n    \"url\": \"https://brand.com\",\n    \"tagline\": \"Brand tagline\",\n    \"colors\": { \"primary\": \"#FF0000\" },\n    \"logo\": { \"url\": \"https://cdn.brand.com/logo.png\" }\n  }\n}\n\nPricing Models\n\nProducts support various pricing models:\n\nCPM (Cost Per Mille/Thousand) - Fixed price per 1000 impressions\nCPM-Auction - Bid-based pricing for impressions\nCPCV (Cost Per Completed View) - Video completions\nFlat-Fee - Fixed campaign cost\nCPP (Cost Per Point) - Percentage of audience reached\n\nFor auction pricing, include bid_price in your package.\n\nAsynchronous Operations\n\nAdCP is not a real-time protocol. Operations may take:\n\n~1 second - Simple lookups (formats, creative lists)\n~60 seconds - AI/inference operations (product discovery)\nMinutes to days - Operations requiring human approval (campaign creation)\n\nAlways check the status field in responses:\n\ncompleted - Operation finished successfully\npending - Awaiting approval or processing\nfailed - Operation failed (check error details)\nTargeting Capabilities\n\nApply targeting overlays to campaigns:\n\n{\n  targeting_overlay: {\n    geo: {\n      included: ['US-CA', 'US-NY'],  // DMA codes or regions\n      excluded: ['US-TX']\n    },\n    demographics: {\n      age_ranges: [{ min: 25, max: 44 }],\n      genders: ['M', 'F']\n    },\n    behavioral: {\n      interests: ['technology', 'gaming'],\n      purchase_intent: ['consumer_electronics']\n    },\n    contextual: {\n      keywords: ['innovation', 'design'],\n      categories: ['IAB19'] // Technology & Computing\n    }\n  }\n}\n\nCommon Workflows\nWorkflow 1: Campaign Discovery to Launch\n// 1. Discover capabilities\nconst caps = await agent.getAdcpCapabilities({});\n\n// 2. Find products\nconst products = await agent.getProducts({\n  brief: 'Q1 2026 brand awareness campaign for tech startup',\n  brand_manifest: { url: 'https://startup.com' },\n  filters: { channels: ['display', 'video'] }\n});\n\n// 3. Check creative formats\nconst formats = await agent.listCreativeFormats({\n  format_types: ['display', 'video']\n});\n\n// 4. Create campaign\nconst campaign = await agent.createMediaBuy({\n  buyer_ref: 'q1-2026-awareness',\n  brand_manifest: { url: 'https://startup.com' },\n  packages: [\n    {\n      buyer_ref: 'pkg-001',\n      product_id: products.products[0].product_id,\n      pricing_option_id: 'cpm-standard',\n      budget: 15000\n    }\n  ],\n  start_time: { type: 'asap' },\n  end_time: '2026-03-31T23:59:59Z'\n});\n\n// 5. Upload creatives\nawait agent.syncCreatives({\n  creatives: [...], // Your creative assets\n  assignments: {\n    'creative_001': ['pkg-001']\n  }\n});\n\n// 6. Monitor performance\nconst delivery = await agent.getMediaBuyDelivery({\n  media_buy_id: campaign.media_buy_id\n});\n\nWorkflow 2: Update Running Campaign\n// Pause, adjust budget, and resume campaign\nawait agent.updateMediaBuy({\n  media_buy_id: 'mb_abc123',\n  updates: {\n    status: 'paused',\n    budget_change: 5000, // Add $5000\n    end_time: '2026-04-30T23:59:59Z'\n  }\n});\n\n// Resume after adjustments\nawait agent.updateMediaBuy({\n  media_buy_id: 'mb_abc123',\n  updates: { status: 'active' }\n});\n\n\nMore workflow examples: See EXAMPLES.md for complete campaign scenarios including creative management, multi-channel campaigns, and optimization workflows.\n\nTest Agent\n\nFor development and testing, use the public test agent:\n\nAgent URL: https://test-agent.adcontextprotocol.org/mcp\nAuth Token: 1v8tAhASaUYYp4odoQ1PnMpdqNaMiTrCRqYo9OJp6IQ\n\nimport { testAgent } from '@adcp/client/testing';\n\n// No authentication needed for test agent\nconst result = await testAgent.getProducts({\n  brief: 'Test campaign',\n  brand_manifest: { url: 'https://example.com' }\n});\n\n\nInteractive testing available at: testing.adcontextprotocol.org\n\nError Handling\n\nCommon error patterns:\n\n400 Bad Request - Invalid parameters:\n\n{\n  \"error\": {\n    \"code\": \"VALIDATION_ERROR\",\n    \"message\": \"budget must be greater than 0\",\n    \"field\": \"packages[0].budget\"\n  }\n}\n\n\n401 Unauthorized - Missing or invalid auth:\n\n{\n  \"error\": {\n    \"code\": \"UNAUTHORIZED\",\n    \"message\": \"Invalid authentication token\"\n  }\n}\n\n\n404 Not Found - Invalid ID reference:\n\n{\n  \"error\": {\n    \"code\": \"NOT_FOUND\",\n    \"message\": \"Product not found\",\n    \"resource\": \"product_id: premium_video_30s\"\n  }\n}\n\n\nAlways check for errors before processing responses:\n\nif (result.error) {\n  console.error(`Error: ${result.error.message}`);\n  return;\n}\n\nBest Practices\n1. Always Start with Capabilities\n\nCall get_adcp_capabilities first to understand what the agent supports before making other requests.\n\n2. Use Clear Buyer References\n\nUse descriptive buyer_ref values for tracking:\n\nGood: 'campaign-2026-q1-tech-launch'\nAvoid: 'c1', 'test', 'abc'\n3. Handle Async Operations\n\nCheck status field and implement polling for pending operations:\n\nlet status = 'pending';\nwhile (status === 'pending') {\n  await sleep(5000); // Wait 5 seconds\n  const update = await agent.getMediaBuyDelivery({\n    media_buy_id: campaign.media_buy_id\n  });\n  status = update.status;\n}\n\n4. Write Detailed Briefs\n\nBetter briefs lead to better product matches:\n\nGood: 'Premium video inventory for luxury automotive brand targeting high-income professionals aged 35-54 in major metros. Focus on brand awareness with completion rates above 70%.'\nAvoid: 'video ads', 'need advertising'\n5. Validate Creative Formats\n\nAlways check list_creative_formats to ensure your creatives meet requirements before uploading.\n\n6. Monitor Budget Pacing\n\nRegularly check delivery metrics to ensure campaigns are pacing properly:\n\nconst delivery = await agent.getMediaBuyDelivery({\n  media_buy_id: campaign.media_buy_id\n});\n\nconst pacing = delivery.delivery.spend / delivery.delivery.budget;\nconsole.log(`Budget pacing: ${(pacing * 100).toFixed(1)}%`);\n\nAdditional Resources\nOfficial AdCP Documentation\nMain Documentation: https://docs.adcontextprotocol.org\nComplete Index: https://docs.adcontextprotocol.org/llms.txt\nMedia Buy Protocol: https://docs.adcontextprotocol.org/docs/media-buy/\nQuick Reference: https://docs.adcontextprotocol.org/docs/media-buy/quick-reference\nTask Reference: https://docs.adcontextprotocol.org/docs/media-buy/task-reference/\nQuickstart Guide: https://docs.adcontextprotocol.org/docs/quickstart\nThis Skill's Documentation\nREFERENCE.md - Complete API reference and schemas\nEXAMPLES.md - Real-world campaign examples\nPROTOCOLS.md - MCP vs A2A protocol details\nTARGETING.md - Advanced targeting strategies\nCREATIVE.md - Creative asset management guide\nKey Reminders\nAdCP is asynchronous - Operations may take minutes to days\nHuman approval may be required - Check for pending status\nStart with capabilities - Always call get_adcp_capabilities first\nBrand context matters - Provide detailed brand manifests for better results\nTargeting is additive - Product targeting + your overlay = final targeting\nCreative formats are strict - Always validate against format specifications\nMonitor performance - Regular delivery checks ensure campaign success\nSupport\n\nFor help with AdCP:\n\nOfficial Repository: https://github.com/adcontextprotocol/adcp\nDocumentation: https://docs.adcontextprotocol.org\nInteractive Testing: https://testing.adcontextprotocol.org\nComplete API Docs: https://docs.adcontextprotocol.org/llms.txt"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/edyyy62/adcp-advertising",
    "publisherUrl": "https://clawhub.ai/edyyy62/adcp-advertising",
    "owner": "edyyy62",
    "version": "1.0.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/adcp-advertising",
    "downloadUrl": "https://openagent3.xyz/downloads/adcp-advertising",
    "agentUrl": "https://openagent3.xyz/skills/adcp-advertising/agent",
    "manifestUrl": "https://openagent3.xyz/skills/adcp-advertising/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/adcp-advertising/agent.md"
  }
}