[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M75DRVHZC8WDVNRRKJ99DFQJ":3,"skill-same:01M75DRVHZC8WDVNRRKJ99DFQJ":47},{"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":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":24,"commitSha":25,"skillDirectory":26,"forksCount":27,"repositoryHtmlUrl":28,"repositoryHomepageUrl":29,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M75DRVHZC8WDVNRRKJ99DFQJ","attribution-model",null,"Set up attribution models. Use when: multi-touch attribution, credit distribution rules, GA4 config, channel contribution.","LongLeo287\u002FSEOSONA-OS","LongLeo287","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F141803367?v=4","01M6JK75C62VCNZKR5BRZ386YV","LongLeo","01M75CK60XQGYJY3YDGGFJQDYT",2,"MIT","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fframeworks\u002Fdigital-marketing-pro\u002Fskills\u002Fattribution-model\u002FSKILL.md",[],[],"2026-11-12 13:55:43",false,"---\nname: attribution-model\ndescription: \"Set up attribution models. Use when: multi-touch attribution, credit distribution rules, GA4 config, channel contribution.\"\n---\n\n# \u002Fdigital-marketing-pro:attribution-model\n\n## Purpose\n\nDesign and recommend a multi-touch attribution model with implementation guidance, credit distribution rules, and platform-specific configuration. Produces a complete attribution strategy tailored to the business's data maturity, sales cycle, and analytics infrastructure.\n\n## Input Required\n\nThe user must provide (or will be prompted for):\n\n- **Sales cycle length**: Average number of days from first touchpoint to conversion (e.g., 7 days for e-commerce, 90+ days for B2B enterprise)\n- **Active marketing channels**: All channels currently running — paid search, paid social, organic search, email, display, video, affiliate, direct mail, events, referral, content marketing, etc.\n- **Conversion types**: The key conversion events being tracked — lead form, MQL, SQL, opportunity, customer, revenue, or e-commerce purchase\n- **Data maturity level**: Current analytics sophistication — beginner (basic GA4, limited tagging), intermediate (UTM tracking, CRM integration, multi-platform), or advanced (data warehouse, CDI, unified user IDs)\n- **Current analytics tools**: Platforms in use — GA4, HubSpot, Salesforce, Adobe Analytics, Mixpanel, custom data warehouse, or third-party attribution tools\n- **Touchpoint volume**: Approximate monthly interactions across all channels (thousands, tens of thousands, hundreds of thousands)\n- **Offline touchpoints**: Whether offline channels (trade shows, phone calls, direct mail, in-store visits, sales meetings) play a role in the customer journey\n- **Budget allocation philosophy**: How budget decisions are currently made — gut feel, last-click data, blended ROAS, executive direction, or existing attribution data\n- **Previous attribution approach**: Any existing attribution model in use and its known shortcomings or limitations\n- **Key business questions**: What specific decisions attribution data needs to inform — budget allocation, channel investment, campaign optimization, executive reporting, or vendor evaluation\n\n## Process\n\n1. **Load brand context**: Read `~\u002F.claude-marketing\u002Fbrands\u002F_active-brand.json` for the active slug, then load `~\u002F.claude-marketing\u002Fbrands\u002F{slug}\u002Fprofile.json`. Apply brand voice, compliance rules for target markets (`skills\u002Fcontext-engine\u002Fcompliance-rules.md`), and industry context. **Also check for guidelines** at `~\u002F.claude-marketing\u002Fbrands\u002F{slug}\u002Fguidelines\u002F_manifest.json` — if present, load restrictions and relevant category files. Check for custom templates at `~\u002F.claude-marketing\u002Fbrands\u002F{slug}\u002Ftemplates\u002F`. Check for agency SOPs at `~\u002F.claude-marketing\u002Fsops\u002F`. If no brand exists, ask: \"Set up a brand first (\u002Fdigital-marketing-pro:brand-setup)?\" — or proceed with defaults.\n2. **Assess data maturity and touchpoint landscape**: Map all active touchpoints across channels, evaluate tracking coverage (what percentage of interactions are captured), identify user identity resolution capabilities (logged-in vs. anonymous, cross-device stitching), and score overall data readiness on a 1-5 scale.\n3. **Evaluate attribution model options**: Score each model in the canonical taxonomy — see `skills\u002Ffunnel-architect\u002Fattribution-models.md` (the single source for model definitions, the selection decision tree, and platform implementation notes) — against the business context on data requirements, accuracy, actionability, and implementation complexity. Do not re-derive the model list here; consume it from that reference.\n4. **Recommend primary model with rationale**: Select the best-fit model based on sales cycle length, data maturity, touchpoint volume, and business questions. Provide a clear explanation of why this model fits and where it will still have blind spots. If data maturity is low, recommend a phased approach starting with a simpler model and graduating to data-driven as tracking matures.\n5. **Define credit distribution rules**: Specify exactly how conversion credit is allocated — percentage per touchpoint position, time-decay half-life window, position-based weight splits (e.g., 40% first, 40% last, 20% distributed across middle), and rules for single-touch conversions vs. multi-touch journeys.\n6. **Design lookback window**: Set the attribution lookback window based on sales cycle data — typically 1.5-2x the average sales cycle length. Define separate windows for click-through and view-through attribution. Justify the window length with sales cycle analysis and explain the tradeoffs of shorter vs. longer windows.\n7. **Map implementation steps per analytics platform**: Create platform-specific configuration guides — GA4 attribution settings and conversion path reports, HubSpot multi-touch revenue attribution setup, Salesforce campaign influence configuration, and custom data warehouse query logic. Include step-by-step setup instructions for each tool in the stack. **GA4 truth (state this to the user):** GA4 exposes only **data-driven** and **last-click** as configurable models (the linear \u002F time-decay \u002F position-based \u002F first-click menu was removed in 2023) — any other credit rule must be modelled in the warehouse\u002FBI layer, not GA4. Also account for GA4's new **\"AI Assistant\"** default channel (referrals from ChatGPT, Gemini, Copilot, Perplexity, etc.) in the channel breakdown so AI-sourced conversions aren't misfiled under Referral\u002FDirect.\n8. **Identify data gaps and tracking requirements**: Audit current tracking against the recommended model's requirements — missing UTM parameters, untagged campaigns, broken cross-domain tracking, absent offline touchpoint capture, incomplete CRM integration, and consent management gaps. Prioritize fixes by impact on attribution accuracy.\n9. **Create attribution reporting framework**: Design the reporting structure — attribution dashboard layout, key metrics (attributed revenue per channel, cost per attributed conversion, ROAS by model), comparison views (model A vs. model B side-by-side), trend analysis over time, and executive summary format.\n10. **Define model evaluation criteria**: Set review cadence (quarterly) and criteria for reassessing the model — changes in channel mix, sales cycle shifts, new touchpoint types, data maturity improvements, or significant discrepancies between attributed performance and actual business outcomes.\n11. **Document limitations and known blind spots**: Explicitly state what the model cannot capture — cross-device gaps, walled garden limitations (Meta, Google self-reporting), view-through estimation inaccuracies, offline-to-online stitching failures, privacy regulation impacts on tracking, and the inherent impossibility of perfect attribution. Frame expectations for stakeholders.\n\n## Output\n\nA structured attribution model recommendation containing:\n\n- **Attribution model recommendation** with detailed rationale connecting the model choice to sales cycle, data maturity, and business questions\n- **Credit distribution rules** — percentage allocation per touchpoint position with examples showing how a sample multi-touch journey would be credited\n- **Lookback window recommendation** with sales cycle justification, click-through vs. view-through windows, and tradeoff analysis\n- **Implementation guide per platform** — step-by-step GA4 attribution setup, HubSpot multi-touch configuration, Salesforce campaign influence settings, and custom warehouse query templates\n- **Touchpoint taxonomy** — standardized hierarchy of channel, source, medium, and campaign with naming conventions for consistent tracking\n- **Data requirements checklist** — what must be tracked, tagged, and integrated for the model to function accurately\n- **Tracking gap analysis** — identified gaps ranked by impact on attribution accuracy, with fix recommendations and effort estimates\n- **Attribution reporting dashboard spec** — metrics, dimensions, filters, visualizations, comparison views, and executive summary format\n- **Model comparison table** — 6-7 models compared side-by-side on pros, cons, data requirements, best-fit scenarios, and implementation complexity\n- **Evaluation framework** — quarterly review criteria, model reassessment triggers, and maturity graduation path from simple to advanced models\n- **Known limitations and blind spots** — explicit documentation of what the model cannot measure with stakeholder expectation-setting guidance\n- **Cross-device and cross-platform considerations** — user identity resolution approaches, deterministic vs. probabilistic matching, and platform-specific limitations\n- **Offline-to-online stitching recommendations** — methods for incorporating trade shows, phone calls, direct mail, and in-person interactions into the digital attribution model\n\n## Agents Used\n\n- **analytics-analyst** — Data maturity assessment, attribution model evaluation, credit distribution design, lookback window analysis, platform implementation guidance, tracking gap identification, reporting framework design, and limitation documentation\n","# \u002Fdigital-marketing-pro:attribution-model\n\n## Purpose\n\nDesign and recommend a multi-touch attribution model with implementation guidance, credit distribution rules, and platform-specific configuration. Produces a complete attribution strategy tailored to the business's data maturity, sales cycle, and analytics infrastructure.\n\n## Input Required\n\nThe user must provide (or will be prompted for):\n\n- **Sales cycle length**: Average number of days from first touchpoint to conversion (e.g., 7 days for e-commerce, 90+ days for B2B enterprise)\n- **Active marketing channels**: All channels currently running — paid search, paid social, organic search, email, display, video, affiliate, direct mail, events, referral, content marketing, etc.\n- **Conversion types**: The key conversion events being tracked — lead form, MQL, SQL, opportunity, customer, revenue, or e-commerce purchase\n- **Data maturity level**: Current analytics sophistication — beginner (basic GA4, limited tagging), intermediate (UTM tracking, CRM integration, multi-platform), or advanced (data warehouse, CDI, unified user IDs)\n- **Current analytics tools**: Platforms in use — GA4, HubSpot, Salesforce, Adobe Analytics, Mixpanel, custom data warehouse, or third-party attribution tools\n- **Touchpoint volume**: Approximate monthly interactions across all channels (thousands, tens of thousands, hundreds of thousands)\n- **Offline touchpoints**: Whether offline channels (trade shows, phone calls, direct mail, in-store visits, sales meetings) play a role in the customer journey\n- **Budget allocation philosophy**: How budget decisions are currently made — gut feel, last-click data, blended ROAS, executive direction, or existing attribution data\n- **Previous attribution approach**: Any existing attribution model in use and its known shortcomings or limitations\n- **Key business questions**: What specific decisions attribution data needs to inform — budget allocation, channel investment, campaign optimization, executive reporting, or vendor evaluation\n\n## Process\n\n1. **Load brand context**: Read `~\u002F.claude-marketing\u002Fbrands\u002F_active-brand.json` for the active slug, then load `~\u002F.claude-marketing\u002Fbrands\u002F{slug}\u002Fprofile.json`. Apply brand voice, compliance rules for target markets (`skills\u002Fcontext-engine\u002Fcompliance-rules.md`), and industry context. **Also check for guidelines** at `~\u002F.claude-marketing\u002Fbrands\u002F{slug}\u002Fguidelines\u002F_manifest.json` — if present, load restrictions and relevant category files. Check for custom templates at `~\u002F.claude-marketing\u002Fbrands\u002F{slug}\u002Ftemplates\u002F`. Check for agency SOPs at `~\u002F.claude-marketing\u002Fsops\u002F`. If no brand exists, ask: \"Set up a brand first (\u002Fdigital-marketing-pro:brand-setup)?\" — or proceed with defaults.\n2. **Assess data maturity and touchpoint landscape**: Map all active touchpoints across channels, evaluate tracking coverage (what percentage of interactions are captured), identify user identity resolution capabilities (logged-in vs. anonymous, cross-device stitching), and score overall data readiness on a 1-5 scale.\n3. **Evaluate attribution model options**: Score each model in the canonical taxonomy — see `skills\u002Ffunnel-architect\u002Fattribution-models.md` (the single source for model definitions, the selection decision tree, and platform implementation notes) — against the business context on data requirements, accuracy, actionability, and implementation complexity. Do not re-derive the model list here; consume it from that reference.\n4. **Recommend primary model with rationale**: Select the best-fit model based on sales cycle length, data maturity, touchpoint volume, and business questions. Provide a clear explanation of why this model fits and where it will still have blind spots. If data maturity is low, recommend a phased approach starting with a simpler model and graduating to data-driven as tracking matures.\n5. **Define credit distribution rules**: Specify exactly how conversion credit is allocated — percentage per touchpoint position, time-decay half-life window, position-based weight splits (e.g., 40% first, 40% last, 20% distributed across middle), and rules for single-touch conversions vs. multi-touch journeys.\n6. **Design lookback window**: Set the attribution lookback window based on sales cycle data — typically 1.5-2x the average sales cycle length. Define separate windows for click-through and view-through attribution. Justify the window length with sales cycle analysis and explain the tradeoffs of shorter vs. longer windows.\n7. **Map implementation steps per analytics platform**: Create platform-specific configuration guides — GA4 attribution settings and conversion path reports, HubSpot multi-touch revenue attribution setup, Salesforce campaign influence configuration, and custom data warehouse query logic. Include step-by-step setup instructions for each tool in the stack. **GA4 truth (state this to the user):** GA4 exposes only **data-driven** and **last-click** as configurable models (the linear \u002F time-decay \u002F position-based \u002F first-click menu was removed in 2023) — any other credit rule must be modelled in the warehouse\u002FBI layer, not GA4. Also account for GA4's new **\"AI Assistant\"** default channel (referrals from ChatGPT, Gemini, Copilot, Perplexity, etc.) in the channel breakdown so AI-sourced conversions aren't misfiled under Referral\u002FDirect.\n8. **Identify data gaps and tracking requirements**: Audit current tracking against the recommended model's requirements — missing UTM parameters, untagged campaigns, broken cross-domain tracking, absent offline touchpoint capture, incomplete CRM integration, and consent management gaps. Prioritize fixes by impact on attribution accuracy.\n9. **Create attribution reporting framework**: Design the reporting structure — attribution dashboard layout, key metrics (attributed revenue per channel, cost per attributed conversion, ROAS by model), comparison views (model A vs. model B side-by-side), trend analysis over time, and executive summary format.\n10. **Define model evaluation criteria**: Set review cadence (quarterly) and criteria for reassessing the model — changes in channel mix, sales cycle shifts, new touchpoint types, data maturity improvements, or significant discrepancies between attributed performance and actual business outcomes.\n11. **Document limitations and known blind spots**: Explicitly state what the model cannot capture — cross-device gaps, walled garden limitations (Meta, Google self-reporting), view-through estimation inaccuracies, offline-to-online stitching failures, privacy regulation impacts on tracking, and the inherent impossibility of perfect attribution. Frame expectations for stakeholders.\n\n## Output\n\nA structured attribution model recommendation containing:\n\n- **Attribution model recommendation** with detailed rationale connecting the model choice to sales cycle, data maturity, and business questions\n- **Credit distribution rules** — percentage allocation per touchpoint position with examples showing how a sample multi-touch journey would be credited\n- **Lookback window recommendation** with sales cycle justification, click-through vs. view-through windows, and tradeoff analysis\n- **Implementation guide per platform** — step-by-step GA4 attribution setup, HubSpot multi-touch configuration, Salesforce campaign influence settings, and custom warehouse query templates\n- **Touchpoint taxonomy** — standardized hierarchy of channel, source, medium, and campaign with naming conventions for consistent tracking\n- **Data requirements checklist** — what must be tracked, tagged, and integrated for the model to function accurately\n- **Tracking gap analysis** — identified gaps ranked by impact on attribution accuracy, with fix recommendations and effort estimates\n- **Attribution reporting dashboard spec** — metrics, dimensions, filters, visualizations, comparison views, and executive summary format\n- **Model comparison table** — 6-7 models compared side-by-side on pros, cons, data requirements, best-fit scenarios, and implementation complexity\n- **Evaluation framework** — quarterly review criteria, model reassessment triggers, and maturity graduation path from simple to advanced models\n- **Known limitations and blind spots** — explicit documentation of what the model cannot measure with stakeholder expectation-setting guidance\n- **Cross-device and cross-platform considerations** — user identity resolution approaches, deterministic vs. probabilistic matching, and platform-specific limitations\n- **Offline-to-online stitching recommendations** — methods for incorporating trade shows, phone calls, direct mail, and in-person interactions into the digital attribution model\n\n## Agents Used\n\n- **analytics-analyst** — Data maturity assessment, attribution model evaluation, credit distribution design, lookback window analysis, platform implementation guidance, tracking gap identification, reporting framework design, and limitation documentation\n",{"name":5,"description":7},"main","4fd50b1281e8cd978866b6b4556242605cabf708","2_KNOWLEDGE\u002Fframeworks\u002Fdigital-marketing-pro\u002Fskills\u002Fattribution-model",1,"https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS","https:\u002F\u002Fseosona-os.vercel.app","https:\u002F\u002Fgithub.com\u002FLongLeo287","https:\u002F\u002Fwww.facebook.com\u002FResourceRookie2023","2026-10-09 15:14:13",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add LongLeo287\u002FSEOSONA-OS --skill attribution-model",{"tool":39,"command":40},"bunx","bunx skills add LongLeo287\u002FSEOSONA-OS --skill attribution-model",{"tool":42,"command":43},"pnpm","pnpm dlx skills add LongLeo287\u002FSEOSONA-OS --skill attribution-model","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fframeworks\u002Fdigital-marketing-pro\u002Fskills\u002Fattribution-model\u002FSKILL.md",true,[],[48,55,62,69,76,83],{"skillNo":49,"name":50,"nameZh":6,"description":51,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":52,"categories":53,"keywords":54,"publishedAt":19},"01M75F0T3V3W7JQQ05X26NNN2T","web_crawler_katana","High-speed web crawling using Katana patterns for deep site mapping, URL discovery, and content extraction.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Fweb_crawler_katana\u002FSKILL.md",[],[],{"skillNo":56,"name":57,"nameZh":6,"description":58,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":59,"categories":60,"keywords":61,"publishedAt":19},"01M75F0Q2QJXDGAFKC7D84GT88","server_log_analyzer","Analyzes Nginx\u002FApache server logs to identify Googlebot crawl patterns, errors, and performance bottlenecks.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Fserver_log_analyzer\u002FSKILL.md",[],[],{"skillNo":63,"name":64,"nameZh":6,"description":65,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":66,"categories":67,"keywords":68,"publishedAt":19},"01M75F0KZP6D8R8XPN2YT35BAJ","schema_markup_generator","Auto-generates JSON-LD structured data for any page type (Article, Product, FAQ, LocalBusiness, etc.).","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Fschema_markup_generator\u002FSKILL.md",[],[],{"skillNo":70,"name":71,"nameZh":6,"description":72,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":73,"categories":74,"keywords":75,"publishedAt":19},"01M75F0G3KX4Y86AXJXTKXVEVA","internal_linking_optimizer","Analyzes and optimizes the internal link graph of a website for SEO authority distribution.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Finternal_linking_optimizer\u002FSKILL.md",[],[],{"skillNo":77,"name":78,"nameZh":6,"description":79,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":80,"categories":81,"keywords":82,"publishedAt":19},"01M75F0CS1RYX4YPJC7N6RAAQJ","google_trends_analyzer","Detects trending topics and seasonal patterns using Google Trends data for content planning and keyword strategy.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Fgoogle_trends_analyzer\u002FSKILL.md",[],[],{"skillNo":84,"name":85,"nameZh":6,"description":86,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":87,"categories":88,"keywords":89,"publishedAt":19},"01M75F0ASMQ1GKPFX82D19SRTN","brand_context_analyzer","Tracks brand mentions, sentiment, and online reputation across web sources.","https:\u002F\u002Fgithub.com\u002FLongLeo287\u002FSEOSONA-OS\u002Fblob\u002Fmain\u002F2_KNOWLEDGE\u002Fskills\u002Fseo_technical\u002Fbrand_context_analyzer\u002FSKILL.md",[],[]]