[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GKD85KFSSZ6AAM7XC336NT":3,"skill-same:01M6GKD85KFSSZ6AAM7XC336NT":110},{"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":23,"publishedAt":44,"linkOnly":45,"markdownContent":46,"markdownBody":47,"frontMatter":48,"refName":50,"commitSha":51,"skillDirectory":52,"forksCount":53,"repositoryHtmlUrl":54,"repositoryHomepageUrl":6,"ownerHtmlUrl":55,"ownerBlogUrl":56,"ownerDescription":6,"updatedAt":57,"install":58,"resources":71},"01M6GKD85KFSSZ6AAM7XC336NT","funnel-analysis",null,"Use when the user mentions funnel, conversion funnel, drop-off, drop off, conversion rate, conversion optimization, CRO, bottleneck, funnel analysis, checkout flow, signup flow, onboarding funnel, activation funnel, abandonment, cart abandonment, form abandonment, user flow, step completion, or funnel comparison. Also trigger on 'where are we losing people' or 'why is conversion low.' For site traffic sources and session behavior use web-analytics; for running the A\u002FB test that validates a CRO fix use the experimentation skill; this skill measures step-by-step drop-off and prioritizes bottlenecks. It also builds funnel health scorecards from aggregate stage metrics when sources lack a shared entity key.","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\u002Ffunnel-analysis\u002FSKILL.md",[18],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000033","数据分析师","PROFESSION","适用职业",[24,25,26,27,28,29,30,31,32,33,34,35,36,37,38,39,40,41,42,43],"funnel analysis","funnel","analysis","drop","false","people","comparison","use","traffic","fix","session","trigger","bottleneck","Optimization","event","checkout","form","sources","data-extraction","cro","2026-11-10 10:12:30",false,"---\nname: funnel-analysis\ndescription: >\n  Use when the user mentions funnel, conversion funnel, drop-off, drop off,\n  conversion rate, conversion optimization, CRO, bottleneck, funnel analysis,\n  checkout flow, signup flow, onboarding funnel, activation funnel, abandonment,\n  cart abandonment, form abandonment, user flow, step completion, or funnel\n  comparison. Also trigger on 'where are we losing people' or 'why is conversion\n  low.' For site traffic sources and session behavior use web-analytics; for\n  running the A\u002FB test that validates a CRO fix use the experimentation skill;\n  this skill measures step-by-step drop-off and prioritizes bottlenecks. It also\n  builds funnel health scorecards from aggregate stage metrics when sources\n  lack a shared entity key.\n\ndisable-model-invocation: false\n---\n\n# Funnel Analysis\n\nMulti-step funnel construction, statistical drop-off analysis, bottleneck ranking,\nrevenue-impact estimation, CRO hypothesis generation, and aggregate stage\nmonitoring.\n\n## Choose the measurement path\n\n- **Linked journey:** Use the event-based workflow below when stages can be\n  linked at a verified user or session grain. Record the eligible entry\n  population and verify identity coverage, event order, and observation windows.\n- **Stage health scorecard:** Use [the scorecard workflow](references\u002Fstage-health-scorecard.md)\n  for an operating view with independently measured stages, aggregate-only\n  sources, or incomplete entity linkage. If both views are requested, give each\n  its own inputs and report. Limit journey conversion to the population with\n  verified linkage and disclose its coverage.\n\n## Contract\n\n**Role:** Advisory analyst. Measures conversion and proposes CRO hypotheses; does\nnot ship page changes or run the experiments. All statistics run in deterministic\nPython scripts.\n\n**Mode:**\n- `quick` — construct funnel + stage conversion rates with CIs.\n- `standard` (default) — add bottleneck ranking, revenue impact, CRO hypotheses.\n- `deep` — add segment comparison and time-to-convert \u002F survival analysis.\n\n**When to use:** step-by-step drop-off, checkout\u002Fsignup\u002Fonboarding funnels,\nbottleneck prioritization, CRO backlog generation.\n\n**When NOT to use:** for traffic sources and session flows use `web-analytics`;\nfor running the A\u002FB test that validates a fix use the **experimentation** skill;\nfor email-sequence conversion use `email-analytics`. See\n`..\u002F..\u002Freferences\u002Fskill-index.md` for the portfolio map.\n\n**Evidence required for the linked journey:**\n- `workspace\u002Fraw\u002Fevents.csv` — `user_id`, `event_name`, `timestamp` (+ optional\n  properties). Required. If absent, STOP and run **data-extraction** first.\n- `workspace\u002Fconfig\u002Ffunnel_definition.json` — step sequence, time windows,\n  matching mode (optional; auto-inferred if absent).\n- `workspace\u002Fprocessed\u002Fsegments.json` — from audience-segmentation (optional;\n  enables cohort comparison).\n- `workspace\u002Fraw\u002Frevenue.csv` — revenue per converter (recommended; enables impact\n  estimation).\n\n**Depends on:** data-extraction, web-analytics (event stream). **Feeds into:**\nexperimentation, reporting, paid-media. Builder detail in\n`references\u002Fauthoring-notes.md`.\n\n**Linked journey stop condition:** if `events.csv` is missing required columns, or\nthe inferred\u002Fdeclared funnel has a step with zero entering users, stop and report\n— a funnel that can't be constructed yields meaningless conversion rates.\n\nParse `$ARGUMENTS` for inline paths, funnel definition, or window overrides.\n\n## Workflow\n\n1. **Validate inputs.** Load `events.csv`; verify `user_id`, `event_name`,\n   `timestamp`. Apply the linked journey stop condition.\n\n2. **Funnel-definition gate (AskUserQuestion).** When no\n   `funnel_definition.json` is supplied and multiple plausible step sequences\n   exist, ask before constructing:\n   - **Question:** \"Which funnel should I measure?\"\n   - **Options:** (a) *Provide the step sequence* — user names ordered steps and\n     time window; (b) *Infer from top event sequences* — I derive the dominant\n     path and show it for confirmation; (c) *A named standard funnel* (checkout \u002F\n     signup \u002F onboarding). Skip when a definition file is present.\n\n3. **Construct.** Run `scripts\u002Fbuild_funnel.py`: assign users to stages, apply\n   the time-window filter (users who don't reach the next step within the window\n   count as dropped), support strict (ordered) and relaxed (any-order) matching.\n\n4. **Stage metrics.** Run `scripts\u002Ffunnel_stats.py`: stage conversion rates with\n   Wilson score CIs, absolute and relative drop-off, overall funnel conversion.\n\n5. **Segment comparison** (deep mode, if `segments.json` present). Compute per-\n   segment funnel metrics; chi-squared tests at each stage with Bonferroni\n   correction across >2 segments.\n\n6. **Rank bottlenecks.** Composite score\n   `drop_off_rate * sqrt(volume) * revenue_proximity`. Write\n   `workspace\u002Fanalysis\u002Fbottleneck_ranking.json`.\n\n7. **Estimate revenue impact.** Run `scripts\u002Frevenue_impact.py` with historical\n   revenue-per-converter; project the gain from 1\u002F5\u002F10 pp conversion improvements\n   at the 50th-percentile (conservative) estimate.\n\n8. **Time-to-convert** (deep mode). Median\u002Fpercentile time between stages;\n   right-censor users still in funnel; flag stages where dwell correlates with\n   abandonment and bimodal distributions.\n\n9. **CRO hypotheses.** For each bottleneck emit {observation, hypothesis, test\n   type, expected impact, priority} to `workspace\u002Fanalysis\u002Fcro_hypotheses.json`.\n\n10. **Report.** Write outputs and the interactive HTML funnel report.\n\n## Output Format\n\nArtifacts:\n\n| File | Contents |\n|------|----------|\n| `workspace\u002Fanalysis\u002Ffunnel_results.json` | Stage conversion rates, drop-offs, CIs |\n| `workspace\u002Fanalysis\u002Fbottleneck_ranking.json` | Priority-ranked bottlenecks with impact |\n| `workspace\u002Fanalysis\u002Fcro_hypotheses.json` | Test ideas linked to findings |\n| `workspace\u002Fanalysis\u002Ftime_to_convert.json` | Per-stage time distributions and censoring |\n| `workspace\u002Freports\u002Ffunnel_report.html` | Interactive funnel with drill-down |\n\n**Financial services mode:** account-opening funnels see 50–70% abandonment;\nKYC\u002FAML and suitability steps are mandatory. Never recommend removing or shortening\na compliance\u002Fdisclosure\u002Fconsent step. Regulated-step CRO must target UX clarity,\nprogress indicators, and save-and-resume, not step elimination. CRO copy that will\nbe published routes through **compliance-review**.\n\n**Completion status:**\n- `DONE` — funnel constructed, metrics + bottlenecks + hypotheses written.\n- `DONE_WITH_CONCERNS` — e.g., no revenue data (impact omitted), thin volume at a\n  stage, inferred funnel unconfirmed.\n- `BLOCKED` — bad or missing linked event data prevents construction; state the fix.\n- `NEEDS_CONTEXT` — funnel definition unresolved by the user.\n\n## Anti-Patterns\n\n- Quoting conversion rates from a funnel that couldn't be validly constructed.\n- Normal-approximation CIs at low conversion rates instead of Wilson score.\n- Optimistic revenue projections — always use the conservative 50th-percentile\n  estimate.\n- Ranking bottlenecks by raw drop-off alone, ignoring volume and revenue\n  proximity.\n- Recommending removal of a regulated step to lift conversion.\n- Segment chi-squared tests across many segments without Bonferroni correction.\n- Letting the model estimate conversion rates or p-values instead of the scripts.\n","# Funnel Analysis\n\nMulti-step funnel construction, statistical drop-off analysis, bottleneck ranking,\nrevenue-impact estimation, CRO hypothesis generation, and aggregate stage\nmonitoring.\n\n## Choose the measurement path\n\n- **Linked journey:** Use the event-based workflow below when stages can be\n  linked at a verified user or session grain. Record the eligible entry\n  population and verify identity coverage, event order, and observation windows.\n- **Stage health scorecard:** Use [the scorecard workflow](references\u002Fstage-health-scorecard.md)\n  for an operating view with independently measured stages, aggregate-only\n  sources, or incomplete entity linkage. If both views are requested, give each\n  its own inputs and report. Limit journey conversion to the population with\n  verified linkage and disclose its coverage.\n\n## Contract\n\n**Role:** Advisory analyst. Measures conversion and proposes CRO hypotheses; does\nnot ship page changes or run the experiments. All statistics run in deterministic\nPython scripts.\n\n**Mode:**\n- `quick` — construct funnel + stage conversion rates with CIs.\n- `standard` (default) — add bottleneck ranking, revenue impact, CRO hypotheses.\n- `deep` — add segment comparison and time-to-convert \u002F survival analysis.\n\n**When to use:** step-by-step drop-off, checkout\u002Fsignup\u002Fonboarding funnels,\nbottleneck prioritization, CRO backlog generation.\n\n**When NOT to use:** for traffic sources and session flows use `web-analytics`;\nfor running the A\u002FB test that validates a fix use the **experimentation** skill;\nfor email-sequence conversion use `email-analytics`. See\n`..\u002F..\u002Freferences\u002Fskill-index.md` for the portfolio map.\n\n**Evidence required for the linked journey:**\n- `workspace\u002Fraw\u002Fevents.csv` — `user_id`, `event_name`, `timestamp` (+ optional\n  properties). Required. If absent, STOP and run **data-extraction** first.\n- `workspace\u002Fconfig\u002Ffunnel_definition.json` — step sequence, time windows,\n  matching mode (optional; auto-inferred if absent).\n- `workspace\u002Fprocessed\u002Fsegments.json` — from audience-segmentation (optional;\n  enables cohort comparison).\n- `workspace\u002Fraw\u002Frevenue.csv` — revenue per converter (recommended; enables impact\n  estimation).\n\n**Depends on:** data-extraction, web-analytics (event stream). **Feeds into:**\nexperimentation, reporting, paid-media. Builder detail in\n`references\u002Fauthoring-notes.md`.\n\n**Linked journey stop condition:** if `events.csv` is missing required columns, or\nthe inferred\u002Fdeclared funnel has a step with zero entering users, stop and report\n— a funnel that can't be constructed yields meaningless conversion rates.\n\nParse `$ARGUMENTS` for inline paths, funnel definition, or window overrides.\n\n## Workflow\n\n1. **Validate inputs.** Load `events.csv`; verify `user_id`, `event_name`,\n   `timestamp`. Apply the linked journey stop condition.\n\n2. **Funnel-definition gate (AskUserQuestion).** When no\n   `funnel_definition.json` is supplied and multiple plausible step sequences\n   exist, ask before constructing:\n   - **Question:** \"Which funnel should I measure?\"\n   - **Options:** (a) *Provide the step sequence* — user names ordered steps and\n     time window; (b) *Infer from top event sequences* — I derive the dominant\n     path and show it for confirmation; (c) *A named standard funnel* (checkout \u002F\n     signup \u002F onboarding). Skip when a definition file is present.\n\n3. **Construct.** Run `scripts\u002Fbuild_funnel.py`: assign users to stages, apply\n   the time-window filter (users who don't reach the next step within the window\n   count as dropped), support strict (ordered) and relaxed (any-order) matching.\n\n4. **Stage metrics.** Run `scripts\u002Ffunnel_stats.py`: stage conversion rates with\n   Wilson score CIs, absolute and relative drop-off, overall funnel conversion.\n\n5. **Segment comparison** (deep mode, if `segments.json` present). Compute per-\n   segment funnel metrics; chi-squared tests at each stage with Bonferroni\n   correction across >2 segments.\n\n6. **Rank bottlenecks.** Composite score\n   `drop_off_rate * sqrt(volume) * revenue_proximity`. Write\n   `workspace\u002Fanalysis\u002Fbottleneck_ranking.json`.\n\n7. **Estimate revenue impact.** Run `scripts\u002Frevenue_impact.py` with historical\n   revenue-per-converter; project the gain from 1\u002F5\u002F10 pp conversion improvements\n   at the 50th-percentile (conservative) estimate.\n\n8. **Time-to-convert** (deep mode). Median\u002Fpercentile time between stages;\n   right-censor users still in funnel; flag stages where dwell correlates with\n   abandonment and bimodal distributions.\n\n9. **CRO hypotheses.** For each bottleneck emit {observation, hypothesis, test\n   type, expected impact, priority} to `workspace\u002Fanalysis\u002Fcro_hypotheses.json`.\n\n10. **Report.** Write outputs and the interactive HTML funnel report.\n\n## Output Format\n\nArtifacts:\n\n| File | Contents |\n|------|----------|\n| `workspace\u002Fanalysis\u002Ffunnel_results.json` | Stage conversion rates, drop-offs, CIs |\n| `workspace\u002Fanalysis\u002Fbottleneck_ranking.json` | Priority-ranked bottlenecks with impact |\n| `workspace\u002Fanalysis\u002Fcro_hypotheses.json` | Test ideas linked to findings |\n| `workspace\u002Fanalysis\u002Ftime_to_convert.json` | Per-stage time distributions and censoring |\n| `workspace\u002Freports\u002Ffunnel_report.html` | Interactive funnel with drill-down |\n\n**Financial services mode:** account-opening funnels see 50–70% abandonment;\nKYC\u002FAML and suitability steps are mandatory. Never recommend removing or shortening\na compliance\u002Fdisclosure\u002Fconsent step. Regulated-step CRO must target UX clarity,\nprogress indicators, and save-and-resume, not step elimination. CRO copy that will\nbe published routes through **compliance-review**.\n\n**Completion status:**\n- `DONE` — funnel constructed, metrics + bottlenecks + hypotheses written.\n- `DONE_WITH_CONCERNS` — e.g., no revenue data (impact omitted), thin volume at a\n  stage, inferred funnel unconfirmed.\n- `BLOCKED` — bad or missing linked event data prevents construction; state the fix.\n- `NEEDS_CONTEXT` — funnel definition unresolved by the user.\n\n## Anti-Patterns\n\n- Quoting conversion rates from a funnel that couldn't be validly constructed.\n- Normal-approximation CIs at low conversion rates instead of Wilson score.\n- Optimistic revenue projections — always use the conservative 50th-percentile\n  estimate.\n- Ranking bottlenecks by raw drop-off alone, ignoring volume and revenue\n  proximity.\n- Recommending removal of a regulated step to lift conversion.\n- Segment chi-squared tests across many segments without Bonferroni correction.\n- Letting the model estimate conversion rates or p-values instead of the scripts.\n",{"name":5,"description":49,"disable-model-invocation":45},"Use when the user mentions funnel, conversion funnel, drop-off, drop off, conversion rate, conversion optimization, CRO, bottleneck, funnel analysis, checkout flow, signup flow, onboarding funnel, activation funnel, abandonment, cart abandonment, form abandonment, user flow, step completion, or funnel comparison. Also trigger on 'where are we losing people' or 'why is conversion low.' For site traffic sources and session behavior use web-analytics; for running the A\u002FB test that validates a CRO fix use the experimentation skill; this skill measures step-by-step drop-off and prioritizes bottlenecks. It also builds funnel health scorecards from aggregate stage metrics when sources lack a shared entity key.\n","main","620031c5572a1f84fed2823ab8d77bb7702cd5c7","plugins\u002Fmarketing-analytics\u002Fskills\u002Ffunnel-analysis",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":59,"prompt":69,"zipAvailable":70},[60,63,66],{"tool":61,"command":62},"npx","npx skills add weisberg\u002Fagile_agentic_analytics --skill funnel-analysis",{"tool":64,"command":65},"bunx","bunx skills add weisberg\u002Fagile_agentic_analytics --skill funnel-analysis",{"tool":67,"command":68},"pnpm","pnpm dlx skills add weisberg\u002Fagile_agentic_analytics --skill funnel-analysis","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fmarketing-analytics\u002Fskills\u002Ffunnel-analysis\u002FSKILL.md",true,[72,78,82,86,90,96,102,106],{"path":73,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":76,"sourceHtmlUrl":77},"references\u002Fauthoring-notes.md","REFERENCE","参考文档",2254,"https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fmarketing-analytics\u002Fskills\u002Ffunnel-analysis\u002Freferences\u002Fauthoring-notes.md",{"path":79,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":80,"sourceHtmlUrl":81},"references\u002Fcro_patterns.md",7284,"https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fmarketing-analytics\u002Fskills\u002Ffunnel-analysis\u002Freferences\u002Fcro_patterns.md",{"path":83,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":84,"sourceHtmlUrl":85},"references\u002Ffunnel_methodology.md",4891,"https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fmarketing-analytics\u002Fskills\u002Ffunnel-analysis\u002Freferences\u002Ffunnel_methodology.md",{"path":87,"resourceType":74,"resourceTypeDesc":75,"sizeBytes":88,"sourceHtmlUrl":89},"references\u002Fstage-health-scorecard.md",3188,"https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fmarketing-analytics\u002Fskills\u002Ffunnel-analysis\u002Freferences\u002Fstage-health-scorecard.md",{"path":91,"resourceType":92,"resourceTypeDesc":93,"sizeBytes":94,"sourceHtmlUrl":95},"routing-eval.jsonl","OTHER","其他",1034,"https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fmarketing-analytics\u002Fskills\u002Ffunnel-analysis\u002Frouting-eval.jsonl",{"path":97,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":100,"sourceHtmlUrl":101},"scripts\u002Fbuild_funnel.py","SCRIPT","脚本",23692,"https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fmarketing-analytics\u002Fskills\u002Ffunnel-analysis\u002Fscripts\u002Fbuild_funnel.py",{"path":103,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":104,"sourceHtmlUrl":105},"scripts\u002Ffunnel_stats.py",28531,"https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fmarketing-analytics\u002Fskills\u002Ffunnel-analysis\u002Fscripts\u002Ffunnel_stats.py",{"path":107,"resourceType":98,"resourceTypeDesc":99,"sizeBytes":108,"sourceHtmlUrl":109},"scripts\u002Frevenue_impact.py",20140,"https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Fmarketing-analytics\u002Fskills\u002Ffunnel-analysis\u002Fscripts\u002Frevenue_impact.py",[111,130,156,171,196,215],{"skillNo":112,"name":113,"nameZh":6,"description":114,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":115,"categories":116,"keywords":122,"publishedAt":44},"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",[117],{"categoryNo":118,"categoryName":119,"taxonomyType":120,"taxonomyTypeDesc":121},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[123,124,125,126,127,28,128,129],"minimal","minimal skill","shared","examples","fixture","marketplace","shared skill",{"skillNo":131,"name":132,"nameZh":6,"description":133,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":134,"categories":135,"keywords":139,"publishedAt":44},"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",[136],{"categoryNo":137,"categoryName":138,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000031","产品经理",[132,140,141,142,143,144,145,146,35,147,148,149,150,151,31,152,28,153,154,155],"writer","SET","do","translation","theme","time","backlog","ranking","true","strategy","map","now","sequencing","agentic","Bash","scoring",{"skillNo":157,"name":158,"nameZh":6,"description":159,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":160,"categories":161,"keywords":163,"publishedAt":44},"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",[162],{"categoryNo":137,"categoryName":138,"taxonomyType":21,"taxonomyTypeDesc":22},[158,140,142,164,145,146,35,165,148,166,167,31,28,132,153,154,168,26,169,170],"risk","testing","writing","impact","requirements","compare","review",{"skillNo":172,"name":173,"nameZh":6,"description":174,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":175,"categories":176,"keywords":179,"publishedAt":44},"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",[177,178],{"categoryNo":118,"categoryName":119,"taxonomyType":120,"taxonomyTypeDesc":121},{"categoryNo":137,"categoryName":138,"taxonomyType":21,"taxonomyTypeDesc":22},[140,180,181,182,183,28,184,185,186,187,170,188,189,158,190,191,192,193,194,195],"prd writer","prd","brief","design","product brief","documents","team","architecture","create","notes","critique","product","markdown","write","authoring","doc",{"skillNo":197,"name":198,"nameZh":6,"description":199,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":200,"categories":201,"keywords":204,"publishedAt":44},"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",[202,203],{"categoryNo":118,"categoryName":119,"taxonomyType":120,"taxonomyTypeDesc":121},{"categoryNo":137,"categoryName":138,"taxonomyType":21,"taxonomyTypeDesc":22},[205,206,181,140,207,182,208,209,210,183,166,28,184,153,211,212,187,213,214,191],"plan","prd to plan","ai coding agents","agentic development","model","project","code","tasks","artifact","next",{"skillNo":216,"name":217,"nameZh":6,"description":218,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":219,"categories":220,"keywords":222,"publishedAt":44},"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",[221],{"categoryNo":137,"categoryName":138,"taxonomyType":21,"taxonomyTypeDesc":22},[170,223,181,140,224,142,225,226,35,147,148,31,28,132,153,154,168,186,155,158],"prd review","red-team","ready","pr"]