[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6HSD21S162SCGCZM121EC4X":3,"skill-same:01M6HSD21S162SCGCZM121EC4X":65},{"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":33,"linkOnly":34,"markdownContent":35,"markdownBody":36,"frontMatter":37,"refName":38,"commitSha":39,"skillDirectory":5,"forksCount":40,"repositoryHtmlUrl":41,"repositoryHomepageUrl":6,"ownerHtmlUrl":42,"ownerBlogUrl":6,"ownerDescription":43,"updatedAt":44,"install":45,"resources":58},"01M6HSD21S162SCGCZM121EC4X","quantify-impact",null,"Measure whether a change made the product or codebase meaningfully better. Use when reproducible evidence would clarify whether a feature, fix, refactor, or upgrade is worth merging.","malinskibeniamin\u002Fskills","malinskibeniamin","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F9860550?v=4","01M6HR395Z9MM67BCKMW1WKTJS","Beniamin Malinski","01M6HR39AP95WH9NHANQ91FAJ0",4,"MIT","https:\u002F\u002Fgithub.com\u002Fmalinskibeniamin\u002Fskills\u002Fblob\u002Fmain\u002Fquantify-impact\u002FSKILL.md",[],[19,20,21,22,23,24,25,26,27,28,29,30,31,32],"impact","quantify impact","change","evidence","clarify","feature","product","Reproducible","codebase","fix","upgrade","use","refactor","when","2026-11-10 10:12:30",false,"---\nname: quantify-impact\ndescription: Measure whether a change made the product or codebase meaningfully better. Use when reproducible evidence would clarify whether a feature, fix, refactor, or upgrade is worth merging.\n---\n\nRead [Poteto](..\u002Fshared\u002FPOTETO-NATIVE.md#measurement).\nFor performance optimization, read the [experiment loop](REFERENCE.md#optimization-experiments) before edits.\nFor repeated candidates, use [hill-climb](..\u002Fhill-climb\u002FSKILL.md).\n\nAssess every PR creation\u002Fupdate and [session PR check](..\u002Fpr\u002FSKILL.md#existing-pr), published or not. Reuse valid evidence; rerun invalid comparisons. Assessment grants no publication authority.\n\n## Flow\n\n1. **Evidence opportunity scan:** benchmark only when a cheap metric can clear a predeclared worthwhile delta and variance. Tiny copy\u002Fstyle\u002Ftest work gets a value sentence.\n2. **Lock claim before coding:** thesis, primary metric, guardrail, scenario, minimum worthwhile delta. Never pick the winner afterward.\n3. **Product lane + Codebase lane:** one must improve; the other must not materially regress.\n   - Product: capability, task success, repro, errors, steps, latency, resources.\n   - Codebase: verifiable contracts, change coordination, dependencies, warnings, leaks, bundle\u002Fbuild\u002Ftest cost; follow [verifiability](..\u002Fshared\u002Fverifiability.md), not size\u002Fcomplexity scores.\n4. **Proportional rigor:** sentence for obvious value; deterministic repro\u002Fcount for correctness; paired [REFERENCE.md](REFERENCE.md) benchmarks for runtime. Measure explicit performance claims.\n5. **Base:** measure before coding or reconstruct merge-base. Use the same scenario, fixture, config, and machine for base\u002Fcandidate.\n6. **Compare:** claim only threshold-clearing deltas with method, environment and noise. Diagnostic attempts are not proven impact; tests\u002Fproxies alone do not prove speed.\n7. **Decide:**\n   - Worthwhile gain: `Value proven`.\n   - Ambiguous\u002Fnegligible performance claim: `Value not proven`; no metric-shopping. Revise a hypothesis once with evidence, then scrap it; distinct supported leads remain open.\n   - No useful metric and no performance claim: normal value summary, no impact artifact.\n   - Regression: fix, narrow, or stop.\n\nFilter guardrails; omit negligible movement.\n\nFor runtime\u002Fcompiler-cost measurements, load [performance analysis](..\u002Ft3code-skills\u002Fperformance-analysis\u002FSKILL.md).\n\n## PR output\n\nState user\u002Fmaintainer value and evidence; tiny copy\u002Fstyle edits use visual proof, not invented metrics. Only threshold-clearing evidence uses:\n\n```md\n## Proven impact\n| Metric | Before | After | Delta |\n|---|---:|---:|---:|\n| \u003Cdirect metric> | \u003Cbase> | \u003Ccandidate> | \u003Cabsolute and %> |\n**Value proven:** \u003Cproduct or codebase benefit>\nMethod: `\u003Ccommand, fixture, runs, environment>`.\n```\n\nPublish via `\u002Fcommit-push-pr` or `\u002Fstacked-prs`; `\u002Fmake-pr-easy-to-review` reuses on request. Keep raw data locally. No empty tables or negligible claimed gains; unproven claims say `Value not proven`.\n","Read [Poteto](..\u002Fshared\u002FPOTETO-NATIVE.md#measurement).\nFor performance optimization, read the [experiment loop](REFERENCE.md#optimization-experiments) before edits.\nFor repeated candidates, use [hill-climb](..\u002Fhill-climb\u002FSKILL.md).\n\nAssess every PR creation\u002Fupdate and [session PR check](..\u002Fpr\u002FSKILL.md#existing-pr), published or not. Reuse valid evidence; rerun invalid comparisons. Assessment grants no publication authority.\n\n## Flow\n\n1. **Evidence opportunity scan:** benchmark only when a cheap metric can clear a predeclared worthwhile delta and variance. Tiny copy\u002Fstyle\u002Ftest work gets a value sentence.\n2. **Lock claim before coding:** thesis, primary metric, guardrail, scenario, minimum worthwhile delta. Never pick the winner afterward.\n3. **Product lane + Codebase lane:** one must improve; the other must not materially regress.\n   - Product: capability, task success, repro, errors, steps, latency, resources.\n   - Codebase: verifiable contracts, change coordination, dependencies, warnings, leaks, bundle\u002Fbuild\u002Ftest cost; follow [verifiability](..\u002Fshared\u002Fverifiability.md), not size\u002Fcomplexity scores.\n4. **Proportional rigor:** sentence for obvious value; deterministic repro\u002Fcount for correctness; paired [REFERENCE.md](REFERENCE.md) benchmarks for runtime. Measure explicit performance claims.\n5. **Base:** measure before coding or reconstruct merge-base. Use the same scenario, fixture, config, and machine for base\u002Fcandidate.\n6. **Compare:** claim only threshold-clearing deltas with method, environment and noise. Diagnostic attempts are not proven impact; tests\u002Fproxies alone do not prove speed.\n7. **Decide:**\n   - Worthwhile gain: `Value proven`.\n   - Ambiguous\u002Fnegligible performance claim: `Value not proven`; no metric-shopping. Revise a hypothesis once with evidence, then scrap it; distinct supported leads remain open.\n   - No useful metric and no performance claim: normal value summary, no impact artifact.\n   - Regression: fix, narrow, or stop.\n\nFilter guardrails; omit negligible movement.\n\nFor runtime\u002Fcompiler-cost measurements, load [performance analysis](..\u002Ft3code-skills\u002Fperformance-analysis\u002FSKILL.md).\n\n## PR output\n\nState user\u002Fmaintainer value and evidence; tiny copy\u002Fstyle edits use visual proof, not invented metrics. Only threshold-clearing evidence uses:\n\n```md\n## Proven impact\n| Metric | Before | After | Delta |\n|---|---:|---:|---:|\n| \u003Cdirect metric> | \u003Cbase> | \u003Ccandidate> | \u003Cabsolute and %> |\n**Value proven:** \u003Cproduct or codebase benefit>\nMethod: `\u003Ccommand, fixture, runs, environment>`.\n```\n\nPublish via `\u002Fcommit-push-pr` or `\u002Fstacked-prs`; `\u002Fmake-pr-easy-to-review` reuses on request. Keep raw data locally. No empty tables or negligible claimed gains; unproven claims say `Value not proven`.\n",{"name":5,"description":7},"main","33ce54f34e30fc6576782912ce0d571729558427",1,"https:\u002F\u002Fgithub.com\u002Fmalinskibeniamin\u002Fskills","https:\u002F\u002Fgithub.com\u002Fmalinskibeniamin","Software Engineer ","2026-11-14 01:57:41",{"source":8,"skillName":5,"commands":46,"prompt":56,"zipAvailable":57},[47,50,53],{"tool":48,"command":49},"npx","npx skills add malinskibeniamin\u002Fskills --skill quantify-impact",{"tool":51,"command":52},"bunx","bunx skills add malinskibeniamin\u002Fskills --skill quantify-impact",{"tool":54,"command":55},"pnpm","pnpm dlx skills add malinskibeniamin\u002Fskills --skill quantify-impact","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fmalinskibeniamin\u002Fskills\u002Fblob\u002Fmain\u002Fquantify-impact\u002FSKILL.md",true,[59],{"path":60,"resourceType":61,"resourceTypeDesc":62,"sizeBytes":63,"sourceHtmlUrl":64},"REFERENCE.md","REFERENCE","参考文档",14118,"https:\u002F\u002Fgithub.com\u002Fmalinskibeniamin\u002Fskills\u002Fblob\u002Fmain\u002Fquantify-impact\u002FREFERENCE.md",[66,87,109,114,119,143],{"skillNo":67,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":33},"01M70WY35N42VJT16W9MA8CCGX","hill-climb","Optimize a defined outcome through bounded evaluation loops. Use for hill-climb requests or repeated improvement against an executable eval, benchmark, or visual comparison; not a one-pass review.","https:\u002F\u002Fgithub.com\u002Fmalinskibeniamin\u002Fskills\u002Fblob\u002Fmain\u002Fhill-climb\u002FSKILL.md",[],[73,74,75,76,77,78,30,79,80,81,82,83,84,85,86],"hill climb","bounded","improvement","review","visual","comparison","eval","benchmark","Evaluation","outcome","for","requests","optimize","loops",{"skillNo":88,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":91,"sourceHtmlUrl":92,"categories":93,"keywords":94,"publishedAt":33},"01M70WXTA2JQ9SN3QZPHHCYB90","gestures","Build or fix web drag, swipe, sheet, reorder, and hold interactions: direct tracking, rubber banding, release velocity, momentum, snap points, and interruption. Not native React Native or Swift.","https:\u002F\u002Fgithub.com\u002Fmalinskibeniamin\u002Fskills\u002Fblob\u002Fmain\u002Fgestures\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fmalinskibeniamin\u002Fskills\u002Fblob\u002Fmain\u002Fgestures\u002FSKILL.md",[],[89,95,96,97,98,99,100,101,102,103,104,105,106,107,28,108],"build","native","velocity","web","drag","react native","snap","release","swift","react","swipe","direct","tracking","sheet",{"skillNo":110,"name":68,"nameZh":6,"description":69,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":111,"categories":112,"keywords":113,"publishedAt":33},"01M70WKSB2PTJGVH7C9XC1FEED","https:\u002F\u002Fgithub.com\u002Fmalinskibeniamin\u002Fskills\u002Fblob\u002Fmain\u002Fcodex-skills\u002Fhill-climb\u002FSKILL.md",[],[73,83,74,76,77,78,30,79,80,82,81,75,85,86,84],{"skillNo":115,"name":89,"nameZh":6,"description":90,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":116,"categories":117,"keywords":118,"publishedAt":33},"01M70WKGYKGN1J786GK8N3RGH1","https:\u002F\u002Fgithub.com\u002Fmalinskibeniamin\u002Fskills\u002Fblob\u002Fmain\u002Fcodex-skills\u002Fgestures\u002FSKILL.md",[],[89,102,103,104,105,106,107,28,108,95,96,97,98,99,100,101],{"skillNo":120,"name":121,"nameZh":6,"description":122,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":123,"sourceHtmlUrl":124,"categories":125,"keywords":126,"publishedAt":33},"01M6HS2326AZFPF8G9C2KW4AT0","improve-animations","Audit existing web UI motion and prioritize concrete improvements or self-contained implementation plans. Use for a motion roadmap; animate owns implementation and diff review.","https:\u002F\u002Fgithub.com\u002Fmalinskibeniamin\u002Fskills\u002Fblob\u002Fmain\u002Fimprove-animations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fmalinskibeniamin\u002Fskills\u002Fblob\u002Fmain\u002Fimprove-animations\u002FSKILL.md",[],[127,128,83,129,130,131,30,132,133,134,135,136,137,138,139,140,98,141,142,76],"improve animations","improve","ui","roadmap","Existing","animate","motion","implementation","plans","diff review","prioritize","web ui","audit","diff","self","ui motion",{"skillNo":144,"name":145,"nameZh":6,"description":146,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":147,"sourceHtmlUrl":148,"categories":149,"keywords":150,"publishedAt":33},"01M6HS0AADDXBB0S8B42R0G82K","effect-ts","Use when setting up a repository that uses the Effect TypeScript library.","https:\u002F\u002Fgithub.com\u002Fmalinskibeniamin\u002Fskills\u002Fblob\u002Fmain\u002Feffect-ts\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fmalinskibeniamin\u002Fskills\u002Fblob\u002Fmain\u002Feffect-ts\u002FSKILL.md",[],[151,152,153,30,154,155,156],"effect ts","effect","library","typescript","up","repository"]