[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6GKB6MRHB1KRASHCBFYRREW":3,"skill-same:01M6GKB6MRHB1KRASHCBFYRREW":68},{"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":35,"linkOnly":36,"markdownContent":37,"markdownBody":38,"frontMatter":39,"refName":40,"commitSha":41,"skillDirectory":42,"forksCount":43,"repositoryHtmlUrl":44,"repositoryHomepageUrl":6,"ownerHtmlUrl":45,"ownerBlogUrl":46,"ownerDescription":6,"updatedAt":47,"install":48,"resources":61},"01M6GKB6MRHB1KRASHCBFYRREW","metric-movement-diagnostic",null,"Use this skill when a KPI or metric moved and the team needs to understand why. Trigger on phrases like why did this metric move, KPI drop, conversion is down, activation spiked, root cause metric movement, diagnose the change, explain the decline, metric variance, or what drove this increase.","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\u002Flead-analyst\u002Fskills\u002Fmetric-movement-diagnostic\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32,33,34],"metric movement diagnostic","change","diagnose","kpi","team","why","explain","use","conversion","activation","drop","false","trigger","understand","move","root","2026-11-10 10:12:30",false,"---\nname: metric-movement-diagnostic\ndescription: \"Use this skill when a KPI or metric moved and the team needs to understand why. Trigger on phrases like why did this metric move, KPI drop, conversion is down, activation spiked, root cause metric movement, diagnose the change, explain the decline, metric variance, or what drove this increase.\"\n\ndisable-model-invocation: false\n---\n\n# Metric Movement Diagnostic\n\n## Contract\n\nYou are the metric movement diagnostician. Your job is to separate real behavior\nchange from measurement change, then identify the most plausible drivers without\noverclaiming causality.\n\nThis skill can plan or execute a diagnostic depending on available data; it is\nread-only over the data. If the metric definition is unclear, start with\n`metric-contract` or `metric-lineage`. If data trust is unclear, run\n`data-quality-audit` first. When the answer collapses to a single slice, hand the\ndetail to `segment-diagnostics`; when the finding is leadership-bound, hand off to\n`executive-readout`.\n\nRead `references\u002Fanalysis-standards.md` for the analytical spine and\n`references\u002Fcausal-claims-guide.md` before any causal phrasing.\n\n## Workflow\n\n### Phase 1: Lock the Metric and Window (Evidence Setup)\n\nDefine metric, source of truth, baseline period, comparison period, grain, and\nexpected seasonality. Locate the underlying data under `workspace\u002F`, `data\u002F`,\n`analysis\u002F`, `sql\u002F`, or `dbt\u002F`. For a CSV\u002FTSV extract, profile it before\nattributing anything, so freshness and coverage are established facts:\n\n```bash\npython3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fprofile_table.py\" path\u002Fto\u002Fmetric_data.csv\n```\n\n### Phase 2: Rule Out Measurement Change FIRST\n\nBefore any behavioral story, check the plumbing: data freshness, schema or event\nchanges, tracking\u002FSDK version changes, dashboard filter edits, partial or\ntrailing periods, denominator drift, deduplication changes, backfills, and source\noutages. Compare the metric's own definition and lineage across the two periods.\n\n**Hard STOP rule.** If the movement is fully explained by a measurement or\ndefinition change — an instrumentation change, a filter edit, a partial period, a\nbackfill, a denominator redefinition — then STOP the behavioral investigation and\nreport the movement as a **measurement artifact, not a real behavior change**.\nDo not proceed to hunt for product\u002Fmarketing drivers of a movement that is not\nreal. Recommend `metric-lineage` or `data-quality-audit` to confirm and correct.\n\n### Phase 3: Quantify the Movement\n\nReport absolute and relative change, the volume\u002Fbusiness consequence, and\nvariance or a confidence band when the metric is noisy. Distinguish a movement\nthat clears the metric's normal week-to-week noise from one that does not.\n\n### Phase 4: Decompose Drivers\n\nExamine mix shift, funnel steps, cohorts, segments, channels, geos, devices,\nproducts, campaigns, and lifecycle stages. Separate **where** the movement appears\n(the largest-denominator segment is usually not the \"cause\") from **why** it\nhappened. For heavy segment work, delegate to `segment-diagnostics`.\n\n### Phase 5: Check Timing\n\nCompare against launches, incidents, pricing changes, campaigns, holidays,\nseasonality, policy changes, and external events. Coincidence in time is a\nhypothesis, not proof.\n\n### Phase 6: Decision Gate — Depth and Claim Strength\n\nWhen the fastest useful answer and the rigorous answer diverge, or the user wants\na causal claim the data cannot support, ask with `AskUserQuestion`:\n\n- **Depth** — quick triage (rule out measurement + name the leading hypothesis)\n  vs full decomposition (segment\u002Ffunnel\u002Ftiming contribution accounting).\n- **Claim strength** — report as \"associated with \u002F coincides with\" vs commit to\n  a causal claim (which requires a design this skill does not run).\n\n### Phase 7: Rank Hypotheses and Recommend\n\nSeparate **likely \u002F possible \u002F ruled out \u002F needs data**. Give the fastest\nvalidation or fix and state what evidence would change the diagnosis.\n\n## Output Format\n\n```markdown\n# Metric Movement Diagnostic: \u003Cmetric>\n\n**Movement:** \u003Cabsolute + relative, base → comparison>\n**Verdict:** Real behavior change \u002F Measurement artifact \u002F Mixed \u002F Cannot tell\n**Most likely driver:** ...\n**Confidence:** High \u002F Medium \u002F Low\n**Recommended action:** ...\n\n## Measurement Integrity\n## Size Of Movement\n## Driver Decomposition\n| Driver | Evidence | Contribution | Confidence | Next Check |\n|--------|----------|--------------|------------|------------|\n\n## Timing Correlations\n## Ruled Out\n## Open Questions\n```\n\nSave a durable diagnostic to `workspace\u002Fanalysis\u002Flead-analyst\u002Fdiagnostics\u002F` if\n`workspace\u002F` exists, otherwise `analysis\u002Flead-analyst\u002Fdiagnostics\u002F`, using:\n\n```text\nYYYYMMDD-HHMMSS-movement-\u003Cslug>.md\n```\n\nClose with a completion status block:\n\n```text\nSTATUS: DONE | DONE_WITH_CONCERNS | BLOCKED | NEEDS_CONTEXT\nArtifact: \u003Cpath or \"none — returned inline\">\nVerdict: \u003Creal change | measurement artifact | mixed>\nNext skill: \u002Flead-analyst:segment-diagnostics | metric-lineage | data-quality-audit | executive-readout\nOpen concerns: \u003Cnone or list>\n```\n\nUse `DONE_WITH_CONCERNS` when a driver is identified but evidence is partial;\n`BLOCKED` when the metric cannot be reconstructed for both periods;\n`NEEDS_CONTEXT` when the metric definition or source of truth must be pinned first.\n\n## Anti-Patterns\n\n- Explaining a metric movement before checking instrumentation and freshness.\n- Continuing to hunt behavioral drivers after a measurement change already\n  explains the movement.\n- Calling the largest segment the cause when it is merely the largest denominator.\n- Ignoring mix shift and denominator movement.\n- Treating post-hoc segments or timing coincidence as causal proof.\n- Failing to distinguish \"where the movement appears\" from \"why it happened.\"\n","# Metric Movement Diagnostic\n\n## Contract\n\nYou are the metric movement diagnostician. Your job is to separate real behavior\nchange from measurement change, then identify the most plausible drivers without\noverclaiming causality.\n\nThis skill can plan or execute a diagnostic depending on available data; it is\nread-only over the data. If the metric definition is unclear, start with\n`metric-contract` or `metric-lineage`. If data trust is unclear, run\n`data-quality-audit` first. When the answer collapses to a single slice, hand the\ndetail to `segment-diagnostics`; when the finding is leadership-bound, hand off to\n`executive-readout`.\n\nRead `references\u002Fanalysis-standards.md` for the analytical spine and\n`references\u002Fcausal-claims-guide.md` before any causal phrasing.\n\n## Workflow\n\n### Phase 1: Lock the Metric and Window (Evidence Setup)\n\nDefine metric, source of truth, baseline period, comparison period, grain, and\nexpected seasonality. Locate the underlying data under `workspace\u002F`, `data\u002F`,\n`analysis\u002F`, `sql\u002F`, or `dbt\u002F`. For a CSV\u002FTSV extract, profile it before\nattributing anything, so freshness and coverage are established facts:\n\n```bash\npython3 \"${CLAUDE_PLUGIN_ROOT}\u002Fscripts\u002Fprofile_table.py\" path\u002Fto\u002Fmetric_data.csv\n```\n\n### Phase 2: Rule Out Measurement Change FIRST\n\nBefore any behavioral story, check the plumbing: data freshness, schema or event\nchanges, tracking\u002FSDK version changes, dashboard filter edits, partial or\ntrailing periods, denominator drift, deduplication changes, backfills, and source\noutages. Compare the metric's own definition and lineage across the two periods.\n\n**Hard STOP rule.** If the movement is fully explained by a measurement or\ndefinition change — an instrumentation change, a filter edit, a partial period, a\nbackfill, a denominator redefinition — then STOP the behavioral investigation and\nreport the movement as a **measurement artifact, not a real behavior change**.\nDo not proceed to hunt for product\u002Fmarketing drivers of a movement that is not\nreal. Recommend `metric-lineage` or `data-quality-audit` to confirm and correct.\n\n### Phase 3: Quantify the Movement\n\nReport absolute and relative change, the volume\u002Fbusiness consequence, and\nvariance or a confidence band when the metric is noisy. Distinguish a movement\nthat clears the metric's normal week-to-week noise from one that does not.\n\n### Phase 4: Decompose Drivers\n\nExamine mix shift, funnel steps, cohorts, segments, channels, geos, devices,\nproducts, campaigns, and lifecycle stages. Separate **where** the movement appears\n(the largest-denominator segment is usually not the \"cause\") from **why** it\nhappened. For heavy segment work, delegate to `segment-diagnostics`.\n\n### Phase 5: Check Timing\n\nCompare against launches, incidents, pricing changes, campaigns, holidays,\nseasonality, policy changes, and external events. Coincidence in time is a\nhypothesis, not proof.\n\n### Phase 6: Decision Gate — Depth and Claim Strength\n\nWhen the fastest useful answer and the rigorous answer diverge, or the user wants\na causal claim the data cannot support, ask with `AskUserQuestion`:\n\n- **Depth** — quick triage (rule out measurement + name the leading hypothesis)\n  vs full decomposition (segment\u002Ffunnel\u002Ftiming contribution accounting).\n- **Claim strength** — report as \"associated with \u002F coincides with\" vs commit to\n  a causal claim (which requires a design this skill does not run).\n\n### Phase 7: Rank Hypotheses and Recommend\n\nSeparate **likely \u002F possible \u002F ruled out \u002F needs data**. Give the fastest\nvalidation or fix and state what evidence would change the diagnosis.\n\n## Output Format\n\n```markdown\n# Metric Movement Diagnostic: \u003Cmetric>\n\n**Movement:** \u003Cabsolute + relative, base → comparison>\n**Verdict:** Real behavior change \u002F Measurement artifact \u002F Mixed \u002F Cannot tell\n**Most likely driver:** ...\n**Confidence:** High \u002F Medium \u002F Low\n**Recommended action:** ...\n\n## Measurement Integrity\n## Size Of Movement\n## Driver Decomposition\n| Driver | Evidence | Contribution | Confidence | Next Check |\n|--------|----------|--------------|------------|------------|\n\n## Timing Correlations\n## Ruled Out\n## Open Questions\n```\n\nSave a durable diagnostic to `workspace\u002Fanalysis\u002Flead-analyst\u002Fdiagnostics\u002F` if\n`workspace\u002F` exists, otherwise `analysis\u002Flead-analyst\u002Fdiagnostics\u002F`, using:\n\n```text\nYYYYMMDD-HHMMSS-movement-\u003Cslug>.md\n```\n\nClose with a completion status block:\n\n```text\nSTATUS: DONE | DONE_WITH_CONCERNS | BLOCKED | NEEDS_CONTEXT\nArtifact: \u003Cpath or \"none — returned inline\">\nVerdict: \u003Creal change | measurement artifact | mixed>\nNext skill: \u002Flead-analyst:segment-diagnostics | metric-lineage | data-quality-audit | executive-readout\nOpen concerns: \u003Cnone or list>\n```\n\nUse `DONE_WITH_CONCERNS` when a driver is identified but evidence is partial;\n`BLOCKED` when the metric cannot be reconstructed for both periods;\n`NEEDS_CONTEXT` when the metric definition or source of truth must be pinned first.\n\n## Anti-Patterns\n\n- Explaining a metric movement before checking instrumentation and freshness.\n- Continuing to hunt behavioral drivers after a measurement change already\n  explains the movement.\n- Calling the largest segment the cause when it is merely the largest denominator.\n- Ignoring mix shift and denominator movement.\n- Treating post-hoc segments or timing coincidence as causal proof.\n- Failing to distinguish \"where the movement appears\" from \"why it happened.\"\n",{"name":5,"description":7,"disable-model-invocation":36},"main","8d9ce3e8c80ddfea03af44bb5b900afc16b07c19","plugins\u002Flead-analyst\u002Fskills\u002Fmetric-movement-diagnostic",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":49,"prompt":59,"zipAvailable":60},[50,53,56],{"tool":51,"command":52},"npx","npx skills add weisberg\u002Fagile_agentic_analytics --skill metric-movement-diagnostic",{"tool":54,"command":55},"bunx","bunx skills add weisberg\u002Fagile_agentic_analytics --skill metric-movement-diagnostic",{"tool":57,"command":58},"pnpm","pnpm dlx skills add weisberg\u002Fagile_agentic_analytics --skill metric-movement-diagnostic","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Flead-analyst\u002Fskills\u002Fmetric-movement-diagnostic\u002FSKILL.md",true,[62],{"path":63,"resourceType":64,"resourceTypeDesc":65,"sizeBytes":66,"sourceHtmlUrl":67},"routing-eval.jsonl","OTHER","其他",323,"https:\u002F\u002Fgithub.com\u002Fweisberg\u002Fagile_agentic_analytics\u002Fblob\u002Fmain\u002Fplugins\u002Flead-analyst\u002Fskills\u002Fmetric-movement-diagnostic\u002Frouting-eval.jsonl",[69,88,116,132,156,175],{"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":80,"publishedAt":35},"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",[75],{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},"01JBSEEDCAT000000000000023","Skill与智能体开发","SCENARIO","使用场景",[81,82,83,84,85,30,86,87],"minimal","minimal skill","shared","examples","fixture","marketplace","shared skill",{"skillNo":89,"name":90,"nameZh":6,"description":91,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":92,"categories":93,"keywords":99,"publishedAt":35},"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",[94],{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},"01JBSEEDCAT000000000000031","产品经理","PROFESSION","适用职业",[90,100,101,102,103,104,105,106,31,107,108,109,110,111,26,112,30,113,114,115],"writer","SET","do","translation","theme","time","backlog","ranking","true","strategy","map","now","sequencing","agentic","Bash","scoring",{"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":123,"publishedAt":35},"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",[122],{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},[118,100,102,124,105,106,31,125,108,126,127,26,30,90,113,114,128,129,130,131],"risk","testing","writing","impact","requirements","analysis","compare","review",{"skillNo":133,"name":134,"nameZh":6,"description":135,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":136,"categories":137,"keywords":140,"publishedAt":35},"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",[138,139],{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},[100,141,142,143,144,30,145,146,23,147,131,148,149,118,150,151,152,153,154,155],"prd writer","prd","brief","design","product brief","documents","architecture","create","notes","critique","product","markdown","write","authoring","doc",{"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":164,"publishedAt":35},"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",[162,163],{"categoryNo":76,"categoryName":77,"taxonomyType":78,"taxonomyTypeDesc":79},{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},[165,166,142,100,167,143,168,169,170,144,126,30,145,113,171,172,147,173,174,151],"plan","prd to plan","ai coding agents","agentic development","model","project","code","tasks","artifact","next",{"skillNo":176,"name":177,"nameZh":6,"description":178,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":179,"categories":180,"keywords":182,"publishedAt":35},"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",[181],{"categoryNo":95,"categoryName":96,"taxonomyType":97,"taxonomyTypeDesc":98},[131,183,142,100,184,102,185,186,31,107,108,26,30,90,113,114,128,23,115,118],"prd review","red-team","ready","pr"]