[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GKE5W4P4DFC38GGA5VC4VG":3,"skill-same:01M6GKE5W4P4DFC38GGA5VC4VG":115},{"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":28,"publishedAt":49,"linkOnly":50,"markdownContent":51,"markdownBody":52,"frontMatter":53,"refName":55,"commitSha":56,"skillDirectory":57,"forksCount":58,"repositoryHtmlUrl":59,"repositoryHomepageUrl":6,"ownerHtmlUrl":60,"ownerBlogUrl":61,"ownerDescription":6,"updatedAt":62,"install":63,"resources":76},"01M6GKE5W4P4DFC38GGA5VC4VG","web-analytics",null,"Use when the user mentions web analytics, GA4, Google Analytics, site traffic, page views, sessions, bounce rate, engagement rate, user behavior, session flow, site speed, traffic sources, acquisition channels, landing page performance, conversion tracking, UTM parameters, event tracking, behavioral analysis, Mixpanel, Amplitude, user journey, click path, scroll depth, or heatmap data. Also trigger on 'what's happening on our website' or 'where is traffic coming from.' For organic-search \u002F keyword performance use seo-content; for step-by-step conversion drop-off use funnel-analysis; this skill is the foundational behavioral data layer. If GA4 data is not yet in the workspace, run data-extraction first.","weisberg\u002Fagile_agentic_analytics","weisberg","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F5054710?v=4","01M6GK0MXK350SV8PMZ0D040SB","Brian Weisberg","01M6GK0N2F8X600FCTKCB3X2ZF",1,"MIT","https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fmarketing-analytics\u002Fskills\u002Fweb-analytics\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000013","分析与可视化","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48],"web analytics","web","analytics","ga4","traffic","utm","data-extraction","sources","false","click","drop","journey","google","conversion","acquisition","analysis","website","search","run","performance","2026-11-10 10:12:30",false,"---\nname: web-analytics\ndescription: >\n  Use when the user mentions web analytics, GA4, Google Analytics, site traffic,\n  page views, sessions, bounce rate, engagement rate, user behavior, session flow,\n  site speed, traffic sources, acquisition channels, landing page performance,\n  conversion tracking, UTM parameters, event tracking, behavioral analysis,\n  Mixpanel, Amplitude, user journey, click path, scroll depth, or heatmap data.\n  Also trigger on 'what's happening on our website' or 'where is traffic coming\n  from.' For organic-search \u002F keyword performance use seo-content; for step-by-step\n  conversion drop-off use funnel-analysis; this skill is the foundational\n  behavioral data layer. If GA4 data is not yet in the workspace, run\n  data-extraction first.\n\ndisable-model-invocation: false\n---\n\n# Web Analytics\n\nGA4 extraction, normalized web metrics, seasonal anomaly detection, navigation\npath analysis, and predictive audience scoring — the behavioral data layer other\nskills build on.\n\n## Contract\n\n**Role:** Advisory analyst and data layer. Extracts, normalizes, detects\nanomalies, and scores propensity; does not change the site or run experiments.\nAll statistics and models run in deterministic Python scripts.\n\n**Mode:**\n- `quick` — normalized metrics + anomaly detection.\n- `standard` (default) — add navigation path and content-affinity analysis.\n- `deep` — add predictive audiences and page-performance correlation.\n\n**When to use:** GA4\u002Ftraffic analysis, anomaly detection, session\u002Fpath behavior,\npredictive audiences, landing-page performance.\n\n**When NOT to use:** organic-search keyword\u002Franking work → `seo-content`;\nfunnel-step drop-off → `funnel-analysis`; clustering customers →\n`audience-segmentation`. See `..\u002F..\u002Freferences\u002Fskill-index.md`.\n\n**Evidence required (inputs):**\n- `workspace\u002Fraw\u002Fga4_reports.csv` — date, source, medium, page_path, sessions,\n  conversions. Required. If absent, STOP and run **data-extraction** first (or use\n  the google-analytics-mcp server \u002F `scripts\u002Fextract_ga4.py` to land it).\n- `workspace\u002Fraw\u002Fevents.csv` — event-level data (optional; enables path analysis).\n\n**Depends on:** data-extraction. **Feeds into:** funnel-analysis, seo-content,\npaid-media, audience-segmentation, experimentation, reporting. Builder detail in\n`references\u002Fauthoring-notes.md`.\n\n**Hard STOP (analysis validity):** anomaly detection requires ≥8 weeks of history\nfor a stable seasonal baseline. If history is shorter, STOP the anomaly step,\nreport descriptive trends only, and label the seasonal baseline as unavailable —\ndo not emit anomaly flags from an unstable decomposition.\n\nParse `$ARGUMENTS` for inline paths, date range, or Z-score threshold overrides.\n\n## Workflow\n\n1. **Validate inputs.** Load `ga4_reports.csv` and\u002For `events.csv`; verify\n   required columns. Normalize UTM parameters (lowercase source\u002Fmedium, trim,\n   URL-decode).\n\n2. **Extract-source gate (AskUserQuestion).** When fresh data is needed and both\n   a live source and a stale file exist, ask before pulling:\n   - **Question:** \"How should I source GA4 data?\"\n   - **Options:** (a) *Use the workspace CSV as-is* — fastest, may be stale;\n     (b) *Pull fresh via google-analytics-mcp* — when the MCP server is connected;\n     (c) *Run `scripts\u002Fextract_ga4.py`* — Data API fallback with named dimensions.\n   Skip when the workspace file is fresh and sufficient.\n\n3. **Normalize metrics.** Aggregate to daily traffic\u002Fengagement\u002Fconversion; write\n   `workspace\u002Fprocessed\u002Fweb_metrics.json`.\n\n4. **Anomaly detection.** Run `scripts\u002Fweb_anomaly_detection.py`: STL seasonal\n   decomposition (period=7) then Z-score residual flags. Apply the Hard STOP gate\n   on history length first.\n\n5. **Root-cause decomposition.** For each anomaly, break the deviation down by\n   source\u002Fmedium, device, geography, and landing page; suppress known events\n   (holidays, launches) when a suppression calendar is provided.\n\n6. **Navigation paths.** Run `scripts\u002Fpath_analysis.py`: second-order (bigram)\n   Markov transition matrices; top conversion paths, loops, dead-ends.\n\n7. **Content affinity & exit pages.** Conversion-lift ratio\n   P(convert|category)\u002FP(convert), ranked; exit-rate ranking weighted by\n   conversion proximity. See `references\u002Fbehavioral_patterns.md`.\n\n8. **Predictive audiences** (deep mode). Run `scripts\u002Fpredictive_scoring.py`:\n   logistic regression for convert\u002Fchurn propensity on behavioral features;\n   temporal holdout validation (target AUC > 0.70).\n\n9. **Page performance** (deep mode). Correlate load time with bounce rate,\n   segmented by device.\n\n10. **Write outputs.**\n\n## Output Format\n\nArtifacts:\n\n| File | Contents |\n|------|----------|\n| `workspace\u002Fprocessed\u002Fweb_metrics.json` | Normalized traffic\u002Fengagement\u002Fconversion metrics |\n| `workspace\u002Fanalysis\u002Fweb_anomalies.json` | Anomalies with root-cause decomposition |\n| `workspace\u002Fanalysis\u002Fnavigation_paths.json` | Common paths with conversion correlation |\n| `workspace\u002Fanalysis\u002Fpredictive_audiences.json` | Convert\u002Fchurn propensity scores |\n\nReport states: history length used, anomaly threshold, path-analysis order, and\npredictive-model holdout AUC (or that scoring was skipped).\n\n**Financial services mode:** track regulatory disclosure page views for compliance\nverification; authenticated investor-portal analytics require PII handling (GDPR,\nCCPA, SEC); report cookie-consent rate as a data-quality metric; verify required\ndisclosures rendered before conversion events. Any customer-facing output routes\nthrough **compliance-review**.\n\n**Completion status:**\n- `DONE` — metrics, anomalies, and requested behavioral artifacts written.\n- `DONE_WITH_CONCERNS` — e.g., short history (anomalies skipped), missing events\n  (no path analysis), or low predictive AUC.\n- `BLOCKED` — no GA4 data and extraction unavailable; state the fix.\n- `NEEDS_CONTEXT` — extraction-source choice unresolved by the user.\n\n## Anti-Patterns\n\n- Emitting anomaly flags from fewer than 8 weeks of history.\n- First-order Markov chains where bigram transitions are specified.\n- Random (non-temporal) holdouts in predictive scoring — they leak the future.\n- Skipping UTM normalization, so `Google` and `google` split traffic.\n- Reporting raw exit rate without conversion-proximity weighting.\n- Letting the model estimate anomaly thresholds or propensity scores instead of\n  the scripts.\n","# Web Analytics\n\nGA4 extraction, normalized web metrics, seasonal anomaly detection, navigation\npath analysis, and predictive audience scoring — the behavioral data layer other\nskills build on.\n\n## Contract\n\n**Role:** Advisory analyst and data layer. Extracts, normalizes, detects\nanomalies, and scores propensity; does not change the site or run experiments.\nAll statistics and models run in deterministic Python scripts.\n\n**Mode:**\n- `quick` — normalized metrics + anomaly detection.\n- `standard` (default) — add navigation path and content-affinity analysis.\n- `deep` — add predictive audiences and page-performance correlation.\n\n**When to use:** GA4\u002Ftraffic analysis, anomaly detection, session\u002Fpath behavior,\npredictive audiences, landing-page performance.\n\n**When NOT to use:** organic-search keyword\u002Franking work → `seo-content`;\nfunnel-step drop-off → `funnel-analysis`; clustering customers →\n`audience-segmentation`. See `..\u002F..\u002Freferences\u002Fskill-index.md`.\n\n**Evidence required (inputs):**\n- `workspace\u002Fraw\u002Fga4_reports.csv` — date, source, medium, page_path, sessions,\n  conversions. Required. If absent, STOP and run **data-extraction** first (or use\n  the google-analytics-mcp server \u002F `scripts\u002Fextract_ga4.py` to land it).\n- `workspace\u002Fraw\u002Fevents.csv` — event-level data (optional; enables path analysis).\n\n**Depends on:** data-extraction. **Feeds into:** funnel-analysis, seo-content,\npaid-media, audience-segmentation, experimentation, reporting. Builder detail in\n`references\u002Fauthoring-notes.md`.\n\n**Hard STOP (analysis validity):** anomaly detection requires ≥8 weeks of history\nfor a stable seasonal baseline. If history is shorter, STOP the anomaly step,\nreport descriptive trends only, and label the seasonal baseline as unavailable —\ndo not emit anomaly flags from an unstable decomposition.\n\nParse `$ARGUMENTS` for inline paths, date range, or Z-score threshold overrides.\n\n## Workflow\n\n1. **Validate inputs.** Load `ga4_reports.csv` and\u002For `events.csv`; verify\n   required columns. Normalize UTM parameters (lowercase source\u002Fmedium, trim,\n   URL-decode).\n\n2. **Extract-source gate (AskUserQuestion).** When fresh data is needed and both\n   a live source and a stale file exist, ask before pulling:\n   - **Question:** \"How should I source GA4 data?\"\n   - **Options:** (a) *Use the workspace CSV as-is* — fastest, may be stale;\n     (b) *Pull fresh via google-analytics-mcp* — when the MCP server is connected;\n     (c) *Run `scripts\u002Fextract_ga4.py`* — Data API fallback with named dimensions.\n   Skip when the workspace file is fresh and sufficient.\n\n3. **Normalize metrics.** Aggregate to daily traffic\u002Fengagement\u002Fconversion; write\n   `workspace\u002Fprocessed\u002Fweb_metrics.json`.\n\n4. **Anomaly detection.** Run `scripts\u002Fweb_anomaly_detection.py`: STL seasonal\n   decomposition (period=7) then Z-score residual flags. Apply the Hard STOP gate\n   on history length first.\n\n5. **Root-cause decomposition.** For each anomaly, break the deviation down by\n   source\u002Fmedium, device, geography, and landing page; suppress known events\n   (holidays, launches) when a suppression calendar is provided.\n\n6. **Navigation paths.** Run `scripts\u002Fpath_analysis.py`: second-order (bigram)\n   Markov transition matrices; top conversion paths, loops, dead-ends.\n\n7. **Content affinity & exit pages.** Conversion-lift ratio\n   P(convert|category)\u002FP(convert), ranked; exit-rate ranking weighted by\n   conversion proximity. See `references\u002Fbehavioral_patterns.md`.\n\n8. **Predictive audiences** (deep mode). Run `scripts\u002Fpredictive_scoring.py`:\n   logistic regression for convert\u002Fchurn propensity on behavioral features;\n   temporal holdout validation (target AUC > 0.70).\n\n9. **Page performance** (deep mode). Correlate load time with bounce rate,\n   segmented by device.\n\n10. **Write outputs.**\n\n## Output Format\n\nArtifacts:\n\n| File | Contents |\n|------|----------|\n| `workspace\u002Fprocessed\u002Fweb_metrics.json` | Normalized traffic\u002Fengagement\u002Fconversion metrics |\n| `workspace\u002Fanalysis\u002Fweb_anomalies.json` | Anomalies with root-cause decomposition |\n| `workspace\u002Fanalysis\u002Fnavigation_paths.json` | Common paths with conversion correlation |\n| `workspace\u002Fanalysis\u002Fpredictive_audiences.json` | Convert\u002Fchurn propensity scores |\n\nReport states: history length used, anomaly threshold, path-analysis order, and\npredictive-model holdout AUC (or that scoring was skipped).\n\n**Financial services mode:** track regulatory disclosure page views for compliance\nverification; authenticated investor-portal analytics require PII handling (GDPR,\nCCPA, SEC); report cookie-consent rate as a data-quality metric; verify required\ndisclosures rendered before conversion events. Any customer-facing output routes\nthrough **compliance-review**.\n\n**Completion status:**\n- `DONE` — metrics, anomalies, and requested behavioral artifacts written.\n- `DONE_WITH_CONCERNS` — e.g., short history (anomalies skipped), missing events\n  (no path analysis), or low predictive AUC.\n- `BLOCKED` — no GA4 data and extraction unavailable; state the fix.\n- `NEEDS_CONTEXT` — extraction-source choice unresolved by the user.\n\n## Anti-Patterns\n\n- Emitting anomaly flags from fewer than 8 weeks of history.\n- First-order Markov chains where bigram transitions are specified.\n- Random (non-temporal) holdouts in predictive scoring — they leak the future.\n- Skipping UTM normalization, so `Google` and `google` split traffic.\n- Reporting raw exit rate without conversion-proximity weighting.\n- Letting the model estimate anomaly thresholds or propensity scores instead of\n  the scripts.\n",{"name":5,"description":54,"disable-model-invocation":50},"Use when the user mentions web analytics, GA4, Google Analytics, site traffic, page views, sessions, bounce rate, engagement rate, user behavior, session flow, site speed, traffic sources, acquisition channels, landing page performance, conversion tracking, UTM parameters, event tracking, behavioral analysis, Mixpanel, Amplitude, user journey, click path, scroll depth, or heatmap data. Also trigger on 'what's happening on our website' or 'where is traffic coming from.' For organic-search \u002F keyword performance use seo-content; for step-by-step conversion drop-off use funnel-analysis; this skill is the foundational behavioral data layer. If GA4 data is not yet in the workspace, run data-extraction first.\n","main","8d9ce3e8c80ddfea03af44bb5b900afc16b07c19","plugins\u002Fmarketing-analytics\u002Fskills\u002Fweb-analytics",0,"https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics","https:\u002F\u002Fgithub.com\u002Fweisberg","www.betafactory.com","2026-11-11 22:15:54",{"source":8,"skillName":5,"commands":64,"prompt":74,"zipAvailable":75},[65,68,71],{"tool":66,"command":67},"npx","npx skills add weisberg\u002Fagile_agentic_analytics --skill web-analytics",{"tool":69,"command":70},"bunx","bunx skills add weisberg\u002Fagile_agentic_analytics --skill web-analytics",{"tool":72,"command":73},"pnpm","pnpm dlx skills add weisberg\u002Fagile_agentic_analytics --skill web-analytics","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fmarketing-analytics\u002Fskills\u002Fweb-analytics\u002FSKILL.md",true,[77,83,87,91,97,103,107,111],{"path":78,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":81,"sourceHtmlUrl":82},"references\u002Fauthoring-notes.md","REFERENCE","参考文档",1788,"https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fmarketing-analytics\u002Fskills\u002Fweb-analytics\u002Freferences\u002Fauthoring-notes.md",{"path":84,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":85,"sourceHtmlUrl":86},"references\u002Fbehavioral_patterns.md",5433,"https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fmarketing-analytics\u002Fskills\u002Fweb-analytics\u002Freferences\u002Fbehavioral_patterns.md",{"path":88,"resourceType":79,"resourceTypeDesc":80,"sizeBytes":89,"sourceHtmlUrl":90},"references\u002Fga4_api.md",5802,"https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fmarketing-analytics\u002Fskills\u002Fweb-analytics\u002Freferences\u002Fga4_api.md",{"path":92,"resourceType":93,"resourceTypeDesc":94,"sizeBytes":95,"sourceHtmlUrl":96},"routing-eval.jsonl","OTHER","其他",930,"https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fmarketing-analytics\u002Fskills\u002Fweb-analytics\u002Frouting-eval.jsonl",{"path":98,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":101,"sourceHtmlUrl":102},"scripts\u002Fextract_ga4.py","SCRIPT","脚本",14483,"https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fmarketing-analytics\u002Fskills\u002Fweb-analytics\u002Fscripts\u002Fextract_ga4.py",{"path":104,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":105,"sourceHtmlUrl":106},"scripts\u002Fpath_analysis.py",28932,"https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fmarketing-analytics\u002Fskills\u002Fweb-analytics\u002Fscripts\u002Fpath_analysis.py",{"path":108,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":109,"sourceHtmlUrl":110},"scripts\u002Fpredictive_scoring.py",17472,"https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fmarketing-analytics\u002Fskills\u002Fweb-analytics\u002Fscripts\u002Fpredictive_scoring.py",{"path":112,"resourceType":99,"resourceTypeDesc":100,"sizeBytes":113,"sourceHtmlUrl":114},"scripts\u002Fweb_anomaly_detection.py",15218,"https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fmarketing-analytics\u002Fskills\u002Fweb-analytics\u002Fscripts\u002Fweb_anomaly_detection.py",[116,133,161,176,201,220],{"skillNo":117,"name":118,"nameZh":6,"description":119,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":120,"categories":121,"keywords":125,"publishedAt":49},"01M6GKH0CNX0V8JYCFTFT0C8TJ","minimal-skill","Minimal shared skill fixture for marketplace renderer and validator examples.","https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Ftests\u002Ffixtures\u002Fminimal-plugin\u002Fskills\u002Fminimal-skill\u002FSKILL.md",[122],{"categoryNo":123,"categoryName":124,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000023","Skill与智能体开发",[126,127,128,129,130,37,131,132],"minimal","minimal skill","shared","examples","fixture","marketplace","shared skill",{"skillNo":134,"name":135,"nameZh":6,"description":136,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":137,"categories":138,"keywords":142,"publishedAt":49},"01M6GKGW83KH0GN15MQGXM4596","roadmap","Use this skill when the user wants a product roadmap, initiative sequencing, Now\u002FNext\u002FLater plan, quarterly roadmap, release theme map, product strategy-to-roadmap translation, or executive roadmap narrative. Trigger on phrases like \"build a roadmap\", \"roadmap these initiatives\", \"what should be now next later\", \"sequence this backlog\", \"quarterly product roadmap\", \"theme-based roadmap\", or \"plan the next two quarters\". Do NOT trigger for drafting or reviewing a single PRD (use prd-writer or prd-review), converting a PRD into an agentic PLAN.md (use prd-to-plan), or scoring\u002Franking a set of options without a time horizon (use prioritization).","https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fproduct-manager\u002Fskills\u002Froadmap\u002FSKILL.md",[139],{"categoryNo":140,"categoryName":141,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000031","产品经理",[135,143,144,145,146,147,148,149,150,151,152,153,154,155,156,157,37,158,159,160],"writer","SET","do","translation","theme","time","backlog","trigger","ranking","true","strategy","map","now","use","sequencing","agentic","Bash","scoring",{"skillNo":162,"name":163,"nameZh":6,"description":164,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":165,"categories":166,"keywords":168,"publishedAt":49},"01M6GKGQTF57NFBDM5NZ89CV06","prioritization","Use this skill when the user wants to rank, score, triage, or compare product opportunities, features, PRD requirements, backlog items, roadmap candidates, or initiatives using RICE, impact-effort, confidence, reach, value, effort, risk, or tradeoff analysis. Trigger on phrases like \"prioritize these features\", \"rank this backlog\", \"RICE score\", \"impact effort matrix\", \"what should we build first\", \"compare these initiatives\", or \"stack rank product bets\". Do NOT trigger for a time-based roadmap (use roadmap), writing or reviewing one PRD (use prd-writer or prd-review), turning a PRD into an agentic plan (use prd-to-plan), or analyzing experiment results (use ab-testing or experimentation skills).","https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fproduct-manager\u002Fskills\u002Fprioritization\u002FSKILL.md",[167],{"categoryNo":140,"categoryName":141,"taxonomyType":26,"taxonomyTypeDesc":27},[163,143,145,169,148,149,150,170,152,171,172,156,37,135,158,159,173,44,174,175],"risk","testing","writing","impact","requirements","compare","review",{"skillNo":177,"name":178,"nameZh":6,"description":179,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":180,"categories":181,"keywords":184,"publishedAt":49},"01M6GKGHEHWG9PF8EZHC7F1R21","prd-writer","Use this skill whenever the user wants to write, draft, create, or scaffold a PRD (Product Requirements Document), spec, product brief, one-pager, or \"working backwards\" PR\u002FFAQ from an idea, rough notes, discovery inputs, or an existing partial draft that needs authoring. Trigger on phrases like \"write a PRD\", \"draft a spec\", \"product doc for X\", \"one-pager\", \"PR\u002FFAQ\", \"feature brief\", or when the user describes a feature\u002Fproduct idea and asks for it to be turned into a written requirements document. Do NOT trigger for critique or approval-readiness review of an existing PRD (use prd-review), engineering design docs, RFCs, ADRs, prioritization, roadmaps, or technical architecture documents. The output of this skill is always a markdown file (or section thereof) that a real product team could ship from.","https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fproduct-manager\u002Fskills\u002Fprd-writer\u002FSKILL.md",[182,183],{"categoryNo":123,"categoryName":124,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":140,"categoryName":141,"taxonomyType":26,"taxonomyTypeDesc":27},[143,185,186,187,188,37,189,190,191,192,175,193,194,163,195,196,197,198,199,200],"prd writer","prd","brief","design","product brief","documents","team","architecture","create","notes","critique","product","markdown","write","authoring","doc",{"skillNo":202,"name":203,"nameZh":6,"description":204,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":205,"categories":206,"keywords":209,"publishedAt":49},"01M6GKGBFB5FMNWY3TH3TDMMKR","prd-to-plan","Use this skill when the user has a PRD (Product Requirements Document), spec, or product brief and wants to turn it into an executable plan for agentic development — a plan that AI coding agents (Claude Code, sub-agents, orchestrators) can actually run. Trigger on phrases like \"turn this PRD into a plan\", \"agentic plan\", \"execution plan\", \"task graph\", \"break this down for Claude Code\", \"decompose this spec\", \"build plan\", \"implementation plan from PRD\", \"scrum-master plan\", or when the user provides a PRD\u002Fspec and asks \"what's next\" or \"how do we build this with agents\". The output is always a structured `PLAN.md` artifact with phases, tasks, dependencies, validation gates, sub-agent assignments, and context bundles. Do NOT trigger for: writing the PRD itself (use prd-writer), pure engineering design \u002F RFC \u002F ADR (architecture is a separate artifact), or generic project management plans without an agentic execution model.","https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fproduct-manager\u002Fskills\u002Fprd-to-plan\u002FSKILL.md",[207,208],{"categoryNo":123,"categoryName":124,"taxonomyType":21,"taxonomyTypeDesc":22},{"categoryNo":140,"categoryName":141,"taxonomyType":26,"taxonomyTypeDesc":27},[210,211,186,143,212,187,213,214,215,188,171,37,189,158,216,217,192,218,219,196],"plan","prd to plan","ai coding agents","agentic development","model","project","code","tasks","artifact","next",{"skillNo":221,"name":222,"nameZh":6,"description":223,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":224,"categories":225,"keywords":227,"publishedAt":49},"01M6GKG6WJ5ZPAR121DC1GBR70","prd-review","Use this skill when the user has an existing PRD, product spec, one-pager, or PR\u002FFAQ and wants critique, approval-readiness review, quality-bar scoring, required changes, or a red-team pass. Trigger on phrases like \"review this PRD\", \"critique my product spec\", \"is this PRD ready\", \"PRD quality bar\", \"red-team this requirements doc\", \"find gaps in this PR\u002FFAQ\", or \"what would block approval\". Do NOT trigger for drafting a new PRD from an idea (use prd-writer), converting an approved PRD into an agentic implementation plan (use prd-to-plan), building a roadmap (use roadmap), or ranking multiple initiatives (use prioritization).","https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fproduct-manager\u002Fskills\u002Fprd-review\u002FSKILL.md",[226],{"categoryNo":140,"categoryName":141,"taxonomyType":26,"taxonomyTypeDesc":27},[175,228,186,143,229,145,230,231,150,151,152,156,37,135,158,159,173,191,160,163],"prd review","red-team","ready","pr"]