[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EVGR2PJG9S28W2CHA8AATE":3,"skill-same:01M7EVGR2PJG9S28W2CHA8AATE":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":25,"commitSha":26,"skillDirectory":27,"forksCount":28,"repositoryHtmlUrl":29,"repositoryHomepageUrl":6,"ownerHtmlUrl":30,"ownerBlogUrl":31,"ownerDescription":6,"updatedAt":32,"install":33,"resources":46},"01M7EVGR2PJG9S28W2CHA8AATE","product-analytics-guide",null,"Implement product analytics — event tracking, funnels, retention, experimentation, and data-informed decisions.","TanNhatCMS\u002Fjarvis","TanNhatCMS","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F113796420?v=4","01M753MV17KG5CD3152G3WQEQY","KietNT","01M7EKEDYVYQ6PWVJJMZ911VMX",0,"MIT","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-product-analytics-guide\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: product-analytics-guide\ndescription: Implement product analytics — event tracking, funnels, retention, experimentation, and data-informed decisions.\ncategory: curviate\n---\n\n## Overview\n\nProduct analytics measures what users actually do: which features they use, where they drop off, what retains them, and which changes move metrics. This skill covers the practice — event taxonomy, instrumentation, funnel and retention analysis, experimentation, and building a data-informed product culture. Tool-neutral.\n\n\nProduct analytics turns user behavior data into decisions: what to build, what to fix, and what to kill.\nThis skill covers event tracking design, funnel and retention analysis, experimentation, and the cultural practices that make data actually influence roadmaps.\n## When to use\n\n- Designing event tracking taxonomies\n- Analyzing funnels and drop-offs\n- Measuring feature adoption\n- Running product experiments\n- Building product dashboards\n- Creating a metrics framework\n\n- Designing event tracking taxonomies\n- Analyzing feature adoption and retention\n- Running A\u002FB tests on product changes\n- Building product dashboards for teams\n## Core concepts\n\n**Event taxonomy.** Consistent naming (object_action: signup_completed, project_created), properties (who, what, context), and identity (anonymous → identified user stitching). Design the taxonomy upfront — retrofitting consistency is brutal. Document in a tracking plan; review every new event against it.\n\n**North Star Metric.** One metric capturing core value delivered (tasks completed, messages sent, reports generated). Everything ladders up: input metrics (activation, engagement, retention) drive the North Star. Get executive agreement — misalignment wastes quarters.\n\n**Funnels.** Step-by-step conversion (signup → setup → first value → habitual use). Analyze: overall conversion, step-to-step drops, time between steps, and segment differences (by source, plan, cohort). The biggest relative drop is the priority.\n\n**Retention.** Cohort retention curves (day 1\u002F7\u002F30), retention by action (which behaviors predict staying?), and power-user analysis. Healthy products flatten; decaying curves signal missing value. Segment ruthlessly — averages hide everything.\n\n**Experimentation.** Hypothesis → variant → randomization → primary metric + guardrails → sufficient runtime → honest analysis. Product experiments need the same discipline as marketing tests: no peeking, adequate sample, pre-registered success criteria.\n\n**Qualitative + quantitative.** Analytics shows what; user research shows why. Pair funnel drops with session replays\u002Fsurveys, and validate metric movements with user interviews. Data-informed, not data-blinded.\n\n\n**Event taxonomy.** Consistent naming (object_action: signup_completed), properties (who, what, context), and lifecycle coverage (acquisition → activation → engagement → monetization → referral).\nDesign taxonomy before instrumenting — retrofitting consistency is painful.\nDocument in a tracking plan; review quarterly as the product evolves.\n**Funnel analysis.** Step-by-step conversion with drop-off quantification and segment comparison.\nFunnels answer \"where do users drop?\" — pair with qualitative research for \"why.\"\nBuild funnels for every critical flow; review weekly.\n**Retention curves.** Cohort retention over time (day 1, 7, 30) segmented by acquisition source, behavior, and plan.\nFlattening curves indicate product-market fit; declining curves indicate leaks.\nRetention is the ultimate product metric — optimize everything toward it.\n**North star metrics.** One metric capturing core value delivery (e.g., messages sent, projects completed).\nInputs (leading indicators) feed the north star; teams own inputs, not the star itself.\nRevisit annually — north stars should evolve with strategy.\n## Practical workflow\n\n1. **Define metrics.** North Star + input metrics + per-team KPIs. Document definitions (what exactly counts as \"active\"?) — metric ambiguity causes endless debates.\n2. **Design taxonomy.** Events for: acquisition, activation, engagement (core actions), retention signals, monetization, and referral. Properties for segmentation. Write the tracking plan.\n3. **Instrument.** Implement per the plan, validate with debug tools (every event fires correctly with right properties), and backfill identities where possible. QA is non-negotiable — bad data poisons every analysis.\n4. **Build dashboards.** Team dashboards (their KPIs, updated automatically), funnel views, retention curves, and experiment results. One source of truth; self-serve for product teams.\n5. **Analyze routinely.** Weekly metrics review (what moved, why?), monthly deep dives (funnels, cohorts, segments), and quarterly metric health checks (are we measuring the right things?).\n6. **Experiment.** Backlog of hypotheses, prioritized by expected impact, run with discipline, and bank learnings win or lose. Feed results into the roadmap.\n\n**Tracking plan template:** event name → trigger (when it fires) → properties → identity → owner → status (planned\u002Flive\u002Fverified). Review before any release adds events.\n\n\n**Analysis workflow:** define the question → form hypotheses → pull data (funnels, cohorts, segments) → validate with qualitative (session replays, user interviews) → recommend action → measure impact.\nData without decisions is trivia — every analysis ends with a recommendation.\n**Experimentation program:** hypothesis → design (variant, audience, duration) → pre-register success criteria → run → analyze (including segments) → document learning → ship or kill.\nVelocity matters: 10+ experiments per quarter for growth-stage products.\nBuild a learning repository — failed experiments teach as much as winners.\n**Dashboard hierarchy:** company (north star + key inputs) → team (their metrics) → deep-dive (ad hoc analysis).\nDashboards answer recurring questions; analysis answers novel ones.\nReview dashboard usage — unused dashboards get archived.\n## Common pitfalls\n\n- **Tracking everything.** 500 events, no taxonomy. Track what maps to decisions; prune the rest.\n- **No definitions.** \"Active user\" means 5 different things. Define once, enforce everywhere.\n- **Vanity metrics.** Celebrating signups while activation flatlines. Metrics must tie to value.\n- **Averages.** Blended retention hiding that one segment churns entirely. Segment always.\n- **Peeking at experiments.** Calling tests early. Discipline: pre-registered criteria, full runtime.\n- **Data without why.** Shipping metric-driven changes without understanding users. Pair with qualitative research.\n- **Instrumentation debt.** Events firing wrong for months. Validate continuously; audit quarterly.\n- **Vanity metrics.** Tracking signups while retention collapses. Measure value delivery, not activity theater.\n- **Analysis without action.** Insights that never change roadmaps. Tie every analysis to a decision owner and deadline.\n- **Dirty data.** Inconsistent events, missing properties, bot traffic. Data quality is infrastructure — invest before scaling analysis.\n- **HiPPO overrides.** Ignoring data for executive opinions. Build a culture where data informs and debates are evidence-based.\n","## Overview\n\nProduct analytics measures what users actually do: which features they use, where they drop off, what retains them, and which changes move metrics. This skill covers the practice — event taxonomy, instrumentation, funnel and retention analysis, experimentation, and building a data-informed product culture. Tool-neutral.\n\n\nProduct analytics turns user behavior data into decisions: what to build, what to fix, and what to kill.\nThis skill covers event tracking design, funnel and retention analysis, experimentation, and the cultural practices that make data actually influence roadmaps.\n## When to use\n\n- Designing event tracking taxonomies\n- Analyzing funnels and drop-offs\n- Measuring feature adoption\n- Running product experiments\n- Building product dashboards\n- Creating a metrics framework\n\n- Designing event tracking taxonomies\n- Analyzing feature adoption and retention\n- Running A\u002FB tests on product changes\n- Building product dashboards for teams\n## Core concepts\n\n**Event taxonomy.** Consistent naming (object_action: signup_completed, project_created), properties (who, what, context), and identity (anonymous → identified user stitching). Design the taxonomy upfront — retrofitting consistency is brutal. Document in a tracking plan; review every new event against it.\n\n**North Star Metric.** One metric capturing core value delivered (tasks completed, messages sent, reports generated). Everything ladders up: input metrics (activation, engagement, retention) drive the North Star. Get executive agreement — misalignment wastes quarters.\n\n**Funnels.** Step-by-step conversion (signup → setup → first value → habitual use). Analyze: overall conversion, step-to-step drops, time between steps, and segment differences (by source, plan, cohort). The biggest relative drop is the priority.\n\n**Retention.** Cohort retention curves (day 1\u002F7\u002F30), retention by action (which behaviors predict staying?), and power-user analysis. Healthy products flatten; decaying curves signal missing value. Segment ruthlessly — averages hide everything.\n\n**Experimentation.** Hypothesis → variant → randomization → primary metric + guardrails → sufficient runtime → honest analysis. Product experiments need the same discipline as marketing tests: no peeking, adequate sample, pre-registered success criteria.\n\n**Qualitative + quantitative.** Analytics shows what; user research shows why. Pair funnel drops with session replays\u002Fsurveys, and validate metric movements with user interviews. Data-informed, not data-blinded.\n\n\n**Event taxonomy.** Consistent naming (object_action: signup_completed), properties (who, what, context), and lifecycle coverage (acquisition → activation → engagement → monetization → referral).\nDesign taxonomy before instrumenting — retrofitting consistency is painful.\nDocument in a tracking plan; review quarterly as the product evolves.\n**Funnel analysis.** Step-by-step conversion with drop-off quantification and segment comparison.\nFunnels answer \"where do users drop?\" — pair with qualitative research for \"why.\"\nBuild funnels for every critical flow; review weekly.\n**Retention curves.** Cohort retention over time (day 1, 7, 30) segmented by acquisition source, behavior, and plan.\nFlattening curves indicate product-market fit; declining curves indicate leaks.\nRetention is the ultimate product metric — optimize everything toward it.\n**North star metrics.** One metric capturing core value delivery (e.g., messages sent, projects completed).\nInputs (leading indicators) feed the north star; teams own inputs, not the star itself.\nRevisit annually — north stars should evolve with strategy.\n## Practical workflow\n\n1. **Define metrics.** North Star + input metrics + per-team KPIs. Document definitions (what exactly counts as \"active\"?) — metric ambiguity causes endless debates.\n2. **Design taxonomy.** Events for: acquisition, activation, engagement (core actions), retention signals, monetization, and referral. Properties for segmentation. Write the tracking plan.\n3. **Instrument.** Implement per the plan, validate with debug tools (every event fires correctly with right properties), and backfill identities where possible. QA is non-negotiable — bad data poisons every analysis.\n4. **Build dashboards.** Team dashboards (their KPIs, updated automatically), funnel views, retention curves, and experiment results. One source of truth; self-serve for product teams.\n5. **Analyze routinely.** Weekly metrics review (what moved, why?), monthly deep dives (funnels, cohorts, segments), and quarterly metric health checks (are we measuring the right things?).\n6. **Experiment.** Backlog of hypotheses, prioritized by expected impact, run with discipline, and bank learnings win or lose. Feed results into the roadmap.\n\n**Tracking plan template:** event name → trigger (when it fires) → properties → identity → owner → status (planned\u002Flive\u002Fverified). Review before any release adds events.\n\n\n**Analysis workflow:** define the question → form hypotheses → pull data (funnels, cohorts, segments) → validate with qualitative (session replays, user interviews) → recommend action → measure impact.\nData without decisions is trivia — every analysis ends with a recommendation.\n**Experimentation program:** hypothesis → design (variant, audience, duration) → pre-register success criteria → run → analyze (including segments) → document learning → ship or kill.\nVelocity matters: 10+ experiments per quarter for growth-stage products.\nBuild a learning repository — failed experiments teach as much as winners.\n**Dashboard hierarchy:** company (north star + key inputs) → team (their metrics) → deep-dive (ad hoc analysis).\nDashboards answer recurring questions; analysis answers novel ones.\nReview dashboard usage — unused dashboards get archived.\n## Common pitfalls\n\n- **Tracking everything.** 500 events, no taxonomy. Track what maps to decisions; prune the rest.\n- **No definitions.** \"Active user\" means 5 different things. Define once, enforce everywhere.\n- **Vanity metrics.** Celebrating signups while activation flatlines. Metrics must tie to value.\n- **Averages.** Blended retention hiding that one segment churns entirely. Segment always.\n- **Peeking at experiments.** Calling tests early. Discipline: pre-registered criteria, full runtime.\n- **Data without why.** Shipping metric-driven changes without understanding users. Pair with qualitative research.\n- **Instrumentation debt.** Events firing wrong for months. Validate continuously; audit quarterly.\n- **Vanity metrics.** Tracking signups while retention collapses. Measure value delivery, not activity theater.\n- **Analysis without action.** Insights that never change roadmaps. Tie every analysis to a decision owner and deadline.\n- **Dirty data.** Inconsistent events, missing properties, bot traffic. Data quality is infrastructure — invest before scaling analysis.\n- **HiPPO overrides.** Ignoring data for executive opinions. Build a culture where data informs and debates are evidence-based.\n",{"name":5,"category":24,"description":7},"curviate","main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-product-analytics-guide",1,"https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis","https:\u002F\u002Fgithub.com\u002FTanNhatCMS","https:\u002F\u002Fmrkiet.name.vn","2026-11-07 14:23:08",{"source":8,"skillName":5,"commands":34,"prompt":44,"zipAvailable":45},[35,38,41],{"tool":36,"command":37},"npx","npx skills add TanNhatCMS\u002Fjarvis --skill product-analytics-guide",{"tool":39,"command":40},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill product-analytics-guide",{"tool":42,"command":43},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill product-analytics-guide","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-product-analytics-guide\u002FSKILL.md",true,[],[48,55,63,70,77,84],{"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},"01M7EWYJR0J8DARY7E59Z6Y9MV","web-scrape","Turn web pages into LLM-ready markdown via the Firecrawl API (renders JS, anti-bot handling). Use when browser_open\u002Ffetch fails on JS-heavy pages, or when you need clean markdown\u002Fstructured extraction from a site. Requires FIRECRAWL_API_KEY.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fweb-scrape\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":59,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7EWYBN5P6F2AJG3FR24T9BP","design-taste-frontend","tasteskill v2, the anti-slop frontend skill. Art direction for websites, distilled from a study of 247 curated gallery sites (One Page Love, Awwwards Sites of the Day). Deals researched directions (idea, composition, type, palette, photographs, section blueprints) from a library, enforces a strict no-slop house style with a real-browser inspector, and runs a look-and-fix loop on screenshots. Use this whenever you build, design, redesign, restyle, polish or review a landing page, marketing site, portfolio, product page, one-pager, hero or any public-facing web page, in any stack (HTML\u002FCSS, React, Next.js, Vue, Svelte, Astro, Tailwind) — also when the user says a page looks generic, templated, \"AI-made\", sloppy, or asks to make it look designed, premium, award-level or less like every other site. Not for dashboards or app screens.","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FLICENSE","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Ftaste-design\u002FSKILL.md",[],[],{"skillNo":64,"name":65,"nameZh":6,"description":66,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":67,"categories":68,"keywords":69,"publishedAt":19},"01M7EWY8FQFNQ2GB7NZZWGSSDX","test-driven-development","Use when implementing any feature or bugfix, before writing implementation code","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-tdd\u002FSKILL.md",[],[],{"skillNo":71,"name":72,"nameZh":6,"description":73,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":74,"categories":75,"keywords":76,"publishedAt":19},"01M7EWY5SHBFRH1HDHVWM9K7TV","systematic-debugging","Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-debugging\u002FSKILL.md",[],[],{"skillNo":78,"name":79,"nameZh":6,"description":80,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":81,"categories":82,"keywords":83,"publishedAt":19},"01M7EWY3NM0Z0JAKS7HDZ24K66","requesting-code-review","Use when completing tasks, implementing major features, or before merging to verify work meets requirements","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-code-review\u002FSKILL.md",[],[],{"skillNo":85,"name":86,"nameZh":6,"description":87,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":88,"categories":89,"keywords":90,"publishedAt":19},"01M7EWY0WRMWX4M9ZFY0WKC593","brainstorming","You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).","https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fsuperpowers-brainstorming\u002FSKILL.md",[],[]]