[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7EMNNR7X2132HBDBWS7BEZS":3,"skill-same:01M7EMNNR7X2132HBDBWS7BEZS":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},"01M7EMNNR7X2132HBDBWS7BEZS","conversion-optimizer",null,"Increase conversion rates — CRO audits, A\u002FB testing, landing page optimization, and experimentation programs.","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-conversion-optimizer\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: conversion-optimizer\ndescription: Increase conversion rates — CRO audits, A\u002FB testing, landing page optimization, and experimentation programs.\ncategory: business-marketing\n---\n\n## Overview\n\nConversion rate optimization squeezes more value from existing traffic: systematic research, hypothesis-driven tests, and iterative improvements to pages and funnels. This skill covers CRO audits, building test hypotheses, running valid A\u002FB tests, landing page best practices, and running an experimentation program.\n\nCRO is research-led, not opinion-led. \"I think the button should be green\" is not a hypothesis.\n\n## When to use\n\n- Improving landing page conversion rates\n- Reducing checkout or signup abandonment\n- Building an A\u002FB testing program\n- Diagnosing why traffic doesn't convert\n- Prioritizing website improvements\n- Fixing leaky funnels\n\n- Auditing a checkout flow for abandonment points\n- Prioritizing a CRO test backlog\n- Deciding between A\u002FB testing and personalization\n- Improving trial-to-paid conversion\n- Optimizing mobile conversion specifically\n- Testing pricing page variations\n## Core concepts\n\n**The CRO process.** Research → hypothesize → prioritize → test → analyze → implement\u002Flearn. Skipping research produces random tests that rarely win.\n\n**Research methods.** Analytics (funnel drop-offs, heatmaps, session recordings), user feedback (surveys, polls, support tickets), usability testing (watch real users struggle), heuristic evaluation (expert review against best practices). Combine quantitative (what) with qualitative (why).\n\n**Hypothesis format.** \"Because [research insight], we believe changing [element] from [A] to [B] will cause [metric] to [change], measured by [primary metric].\" Testable, grounded, specific.\n\n**A\u002FB test validity.** One variable at a time (mostly), adequate sample size (use a calculator — don't guess), full business cycles (run at least 1–2 weeks to cover day-of-week effects), statistical significance (95%+), and no peeking\u002Fstopping early.\n\n**Prioritization (PIE\u002FICE).** Score ideas on Potential impact, Importance (page traffic\u002Fvalue), Ease of implementation. Test high PIE first.\n\n**Landing page anatomy.** Headline (value prop in 5 seconds), subhead, hero visual, social proof (logos, testimonials, stats), benefits (not features), single clear CTA repeated, objection handling (FAQ, guarantees), minimal navigation\u002Fdistraction.\n\n\n**Fogg Behavior Model.** Behavior = Motivation × Ability × Prompt, all at the same moment. CRO maps to this: increase motivation (value clarity, urgency), increase ability (reduce friction, simplify), and place prompts well (CTAs at decision moments). If any factor is zero, no conversion — diagnose which one is missing.\n\n**The test-result repository.** Every test documented: hypothesis, variant, results, learning, decision. This compounds into institutional knowledge — new team members learn years of insights in days, and failed tests prevent repeated mistakes.\n\n**Statistical fundamentals.** Significance (95%+ confidence), power (enough sample size — calculate before, not after), and minimum detectable effect (what lift is worth detecting?).\nPeeking at results early and stopping at first significance inflates false positives — pre-commit to sample sizes.\nFor low traffic, use sequential testing methods or go qualitative; underpowered tests are worse than no tests.\n**Segmentation of results.** Overall winners can hide segment losers: new vs. returning, mobile vs. desktop, traffic source.\nAlways segment key tests — a change that lifts desktop 10% but tanks mobile 15% is not a win.\nDocument segment findings; they become targeting rules for personalization later.\n**Prioritization (PIE\u002FICE).** Potential (how much improvement possible?) → Importance (how valuable is this page?) → Ease (how hard to implement?).\nScore ideas 1–10 on each; work top-down. Re-score quarterly — data from tests should update your priors.\n## Practical workflow\n\n1. **Research.** Pull funnel analytics: where do users drop? Watch session recordings of drop-off points. Survey exiting users (\"what stopped you?\"). Review support tickets for confusion themes.\n2. **Build the hypothesis backlog.** Convert insights into hypotheses in the standard format. Score with PIE. Keep 10–15 queued.\n3. **Design tests.** Wireframe the variant, write the copy, define primary metric + guardrails (e.g., \"conversion up, average order value not down\"). QA the test implementation thoroughly — broken tests waste weeks.\n4. **Run properly.** Calculate required sample size first. Run full weeks. Don't peek and stop early. Document everything.\n5. **Analyze honestly.** Significant win → implement and bank the learning. Inconclusive → was the hypothesis wrong or the test underpowered? Loss → what did we learn about users? Every test teaches something.\n6. **Compound wins.** Roll out winners, update the playbook, feed learnings into the next hypotheses. CRO compounds: small wins stack into large lifts.\n\n**Quick-win audit checklist:** headline clarity (5-second test), CTA visibility and copy, form length (every field costs conversions), page speed on mobile, trust signals near the CTA, mobile layout, message match from ad\u002Femail.\n\n\n**Heuristic audit framework (per page):** value proposition (clear in 5 seconds?) → relevance (matches traffic source?) → clarity (what to do next?) → friction (what makes action hard?) → anxiety (what creates doubt?) → distraction (what pulls attention away?) → urgency (why act now?). Score each; fix the worst two first.\n\n**Test documentation template:** hypothesis (because [insight], changing [element] will [effect]) → primary metric → secondary\u002Fguardrail metrics → audience and traffic split → duration and sample size → results → decision (ship\u002Fiterate\u002Fkill) → learning.\nThe learning field is the real output — even killed tests teach.\n**Research-first testing:** analytics review → heuristic audit → user testing (5 users) → surveys\u002Fpolls → then test ideas.\nTests born from research win 2–3x more often than tests born from opinions. Research is the highest-ROI CRO activity.\n## Common pitfalls\n\n- **Testing opinions.** Random button-color tests without research. Research first, test second.\n- **Stopping tests early.** Peeking at day 3 and declaring victory. Run to significance and full cycles.\n- **Underpowered tests.** Low-traffic pages can't support A\u002FB tests — use before\u002Fafter or qualitative methods instead.\n- **Ignoring mobile.** Testing desktop while most traffic is mobile. Optimize where the users are.\n- **No guardrail metrics.** Increasing signups while destroying lead quality. Watch secondary metrics.\n- **One-and-done.** Running three tests, declaring CRO \"doesn't work.\" It's a program, not a project.\n- **Copying competitors' winners.** Their audience isn't yours. Steal test ideas, not conclusions — validate yourself.\n- **Testing without traffic.** Running A\u002FB tests on pages with 100 visitors a month. Low-traffic pages need qualitative research or sequential testing, not split tests.\n- **Novelty effects.** New variants winning briefly because they are new, then regressing. Run tests long enough for novelty to fade (2+ weeks minimum).\n- **HIPPO testing.** Testing the highest-paid person's opinion instead of research-backed hypotheses. Data beats hierarchy.\n- **Ignoring qualitative.** Numbers show what; user tests show why. Winners without understood whys do not generalize.\n","## Overview\n\nConversion rate optimization squeezes more value from existing traffic: systematic research, hypothesis-driven tests, and iterative improvements to pages and funnels. This skill covers CRO audits, building test hypotheses, running valid A\u002FB tests, landing page best practices, and running an experimentation program.\n\nCRO is research-led, not opinion-led. \"I think the button should be green\" is not a hypothesis.\n\n## When to use\n\n- Improving landing page conversion rates\n- Reducing checkout or signup abandonment\n- Building an A\u002FB testing program\n- Diagnosing why traffic doesn't convert\n- Prioritizing website improvements\n- Fixing leaky funnels\n\n- Auditing a checkout flow for abandonment points\n- Prioritizing a CRO test backlog\n- Deciding between A\u002FB testing and personalization\n- Improving trial-to-paid conversion\n- Optimizing mobile conversion specifically\n- Testing pricing page variations\n## Core concepts\n\n**The CRO process.** Research → hypothesize → prioritize → test → analyze → implement\u002Flearn. Skipping research produces random tests that rarely win.\n\n**Research methods.** Analytics (funnel drop-offs, heatmaps, session recordings), user feedback (surveys, polls, support tickets), usability testing (watch real users struggle), heuristic evaluation (expert review against best practices). Combine quantitative (what) with qualitative (why).\n\n**Hypothesis format.** \"Because [research insight], we believe changing [element] from [A] to [B] will cause [metric] to [change], measured by [primary metric].\" Testable, grounded, specific.\n\n**A\u002FB test validity.** One variable at a time (mostly), adequate sample size (use a calculator — don't guess), full business cycles (run at least 1–2 weeks to cover day-of-week effects), statistical significance (95%+), and no peeking\u002Fstopping early.\n\n**Prioritization (PIE\u002FICE).** Score ideas on Potential impact, Importance (page traffic\u002Fvalue), Ease of implementation. Test high PIE first.\n\n**Landing page anatomy.** Headline (value prop in 5 seconds), subhead, hero visual, social proof (logos, testimonials, stats), benefits (not features), single clear CTA repeated, objection handling (FAQ, guarantees), minimal navigation\u002Fdistraction.\n\n\n**Fogg Behavior Model.** Behavior = Motivation × Ability × Prompt, all at the same moment. CRO maps to this: increase motivation (value clarity, urgency), increase ability (reduce friction, simplify), and place prompts well (CTAs at decision moments). If any factor is zero, no conversion — diagnose which one is missing.\n\n**The test-result repository.** Every test documented: hypothesis, variant, results, learning, decision. This compounds into institutional knowledge — new team members learn years of insights in days, and failed tests prevent repeated mistakes.\n\n**Statistical fundamentals.** Significance (95%+ confidence), power (enough sample size — calculate before, not after), and minimum detectable effect (what lift is worth detecting?).\nPeeking at results early and stopping at first significance inflates false positives — pre-commit to sample sizes.\nFor low traffic, use sequential testing methods or go qualitative; underpowered tests are worse than no tests.\n**Segmentation of results.** Overall winners can hide segment losers: new vs. returning, mobile vs. desktop, traffic source.\nAlways segment key tests — a change that lifts desktop 10% but tanks mobile 15% is not a win.\nDocument segment findings; they become targeting rules for personalization later.\n**Prioritization (PIE\u002FICE).** Potential (how much improvement possible?) → Importance (how valuable is this page?) → Ease (how hard to implement?).\nScore ideas 1–10 on each; work top-down. Re-score quarterly — data from tests should update your priors.\n## Practical workflow\n\n1. **Research.** Pull funnel analytics: where do users drop? Watch session recordings of drop-off points. Survey exiting users (\"what stopped you?\"). Review support tickets for confusion themes.\n2. **Build the hypothesis backlog.** Convert insights into hypotheses in the standard format. Score with PIE. Keep 10–15 queued.\n3. **Design tests.** Wireframe the variant, write the copy, define primary metric + guardrails (e.g., \"conversion up, average order value not down\"). QA the test implementation thoroughly — broken tests waste weeks.\n4. **Run properly.** Calculate required sample size first. Run full weeks. Don't peek and stop early. Document everything.\n5. **Analyze honestly.** Significant win → implement and bank the learning. Inconclusive → was the hypothesis wrong or the test underpowered? Loss → what did we learn about users? Every test teaches something.\n6. **Compound wins.** Roll out winners, update the playbook, feed learnings into the next hypotheses. CRO compounds: small wins stack into large lifts.\n\n**Quick-win audit checklist:** headline clarity (5-second test), CTA visibility and copy, form length (every field costs conversions), page speed on mobile, trust signals near the CTA, mobile layout, message match from ad\u002Femail.\n\n\n**Heuristic audit framework (per page):** value proposition (clear in 5 seconds?) → relevance (matches traffic source?) → clarity (what to do next?) → friction (what makes action hard?) → anxiety (what creates doubt?) → distraction (what pulls attention away?) → urgency (why act now?). Score each; fix the worst two first.\n\n**Test documentation template:** hypothesis (because [insight], changing [element] will [effect]) → primary metric → secondary\u002Fguardrail metrics → audience and traffic split → duration and sample size → results → decision (ship\u002Fiterate\u002Fkill) → learning.\nThe learning field is the real output — even killed tests teach.\n**Research-first testing:** analytics review → heuristic audit → user testing (5 users) → surveys\u002Fpolls → then test ideas.\nTests born from research win 2–3x more often than tests born from opinions. Research is the highest-ROI CRO activity.\n## Common pitfalls\n\n- **Testing opinions.** Random button-color tests without research. Research first, test second.\n- **Stopping tests early.** Peeking at day 3 and declaring victory. Run to significance and full cycles.\n- **Underpowered tests.** Low-traffic pages can't support A\u002FB tests — use before\u002Fafter or qualitative methods instead.\n- **Ignoring mobile.** Testing desktop while most traffic is mobile. Optimize where the users are.\n- **No guardrail metrics.** Increasing signups while destroying lead quality. Watch secondary metrics.\n- **One-and-done.** Running three tests, declaring CRO \"doesn't work.\" It's a program, not a project.\n- **Copying competitors' winners.** Their audience isn't yours. Steal test ideas, not conclusions — validate yourself.\n- **Testing without traffic.** Running A\u002FB tests on pages with 100 visitors a month. Low-traffic pages need qualitative research or sequential testing, not split tests.\n- **Novelty effects.** New variants winning briefly because they are new, then regressing. Run tests long enough for novelty to fade (2+ weeks minimum).\n- **HIPPO testing.** Testing the highest-paid person's opinion instead of research-backed hypotheses. Data beats hierarchy.\n- **Ignoring qualitative.** Numbers show what; user tests show why. Winners without understood whys do not generalize.\n",{"name":5,"category":24,"description":7},"business-marketing","main","af388a77c2fe5e0b4fd879cca4300a0ffa9a6579","skills\u002Fams-conversion-optimizer",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 conversion-optimizer",{"tool":39,"command":40},"bunx","bunx skills add TanNhatCMS\u002Fjarvis --skill conversion-optimizer",{"tool":42,"command":43},"pnpm","pnpm dlx skills add TanNhatCMS\u002Fjarvis --skill conversion-optimizer","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FTanNhatCMS\u002Fjarvis\u002Fblob\u002Fmain\u002Fskills\u002Fams-conversion-optimizer\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",[],[]]