[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7A9W8CTNTA8S2N7AWTXR0FS":3,"skill-same:01M7A9W8CTNTA8S2N7AWTXR0FS":55},{"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":24,"commitSha":25,"skillDirectory":26,"forksCount":14,"repositoryHtmlUrl":27,"repositoryHomepageUrl":28,"ownerHtmlUrl":29,"ownerBlogUrl":6,"ownerDescription":6,"updatedAt":30,"install":31,"resources":44},"01M7A9W8CTNTA8S2N7AWTXR0FS","metrics-digest",null,"Build the Monday metrics email from the analytics CLI's signups, activation, and churn numbers — pull last week and the prior week, flag any metric that moved more than 10%, and render the fixed template. Use when compiling the Monday metrics email.","StartupBros-com\u002Fskill-tuner","StartupBros-com","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F262958016?v=4","01M77WY8AH50FY939DTGZYHVE9","StartupBros.com","01M7A9SNDJZ1YQYFJBPV6RQA85",0,"MIT","https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fskill-tuner\u002Fblob\u002Fmain\u002Fexperiments\u002Fauthoring-ab\u002Fworkspace\u002Fweekly-metrics-digest\u002Fours\u002Frun-2\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: metrics-digest\ndescription: Build the Monday metrics email from the analytics CLI's signups, activation, and churn numbers — pull last week and the prior week, flag any metric that moved more than 10%, and render the fixed template. Use when compiling the Monday metrics email.\n---\n\n## Pull the numbers\n\nRun the analytics CLI for the reporting week and the week before it:\n\n```\nan4 query --metric signups,activation,churn --last 7d --json\n```\n\nFor the prior week, check `an4 query --help` for the correct offset\u002Fdate-range flag rather than guessing one — CLI flags drift and a wrong guess produces a silently wrong comparison. Run the equivalent query for the 7 days immediately before the reporting week.\n\nParse both JSON outputs before doing any comparison.\n\n## Handle missing or zero-baseline metrics\n\nThe three metrics are signups, activation, churn. For each one, check both weeks' output before computing anything:\n\n- **Metric absent from either week's JSON**: do not compute a change and do not drop the row. Write it as `\u003Cmetric>: not available in analytics output` in its section.\n- **Prior week value is 0 and current week value is nonzero**: percent change is undefined, not zero. Write the row as `\u003Cmetric>: \u003Ccurrent value> (up from 0)` instead of a percentage, and treat it as flagged.\n\n## Compute change and flag movers\n\nFor every metric with a real value in both weeks:\n\n```\npct_change = (current - prior) \u002F prior * 100\n```\n\nA metric is flagged when `abs(pct_change) > 10`. This is the only threshold — do not round it or treat 10.0 as a pass.\n\n## Render the email\n\nPlain text only — no `#`, `*`, `-`, backticks, or other markdown syntax anywhere in the output.\n\n```\nSubject: Metrics week of \u003CYYYY-MM-DD of the reporting week's start date>\n\nGrowth\nsignups: \u003Cvalue>, \u003C+\u002F-X%> vs prior week\n\nEngagement\nactivation: \u003Cvalue>, \u003C+\u002F-X%> vs prior week\nchurn: \u003Cvalue>, \u003C+\u002F-X%> vs prior week\n\nFlags\n\u003Cone line per flagged metric, e.g. \"signups moved +14% vs prior week\">\n\u003Cor, if none qualify: \"No metrics moved more than 10% this week.\">\n```\n\nEvery metric row uses the missing-data or zero-baseline wording above in place of a percentage when those cases apply, in whichever section (Growth or Engagement) it normally belongs to.\n\n## Done when\n\n- Subject line reads exactly `Metrics week of \u003Cdate>` with the real start date substituted.\n- All three metrics — signups, activation, churn — appear exactly once each, in Growth or Engagement, either with a value and percent change or with the explicit missing\u002Fzero-baseline wording. None are silently dropped.\n- Flags lists every metric with `abs(pct_change) > 10`, or the exact no-movers sentence if none qualify.\n- The rendered output contains zero markdown characters — reread it once and confirm before sending.","## Pull the numbers\n\nRun the analytics CLI for the reporting week and the week before it:\n\n```\nan4 query --metric signups,activation,churn --last 7d --json\n```\n\nFor the prior week, check `an4 query --help` for the correct offset\u002Fdate-range flag rather than guessing one — CLI flags drift and a wrong guess produces a silently wrong comparison. Run the equivalent query for the 7 days immediately before the reporting week.\n\nParse both JSON outputs before doing any comparison.\n\n## Handle missing or zero-baseline metrics\n\nThe three metrics are signups, activation, churn. For each one, check both weeks' output before computing anything:\n\n- **Metric absent from either week's JSON**: do not compute a change and do not drop the row. Write it as `\u003Cmetric>: not available in analytics output` in its section.\n- **Prior week value is 0 and current week value is nonzero**: percent change is undefined, not zero. Write the row as `\u003Cmetric>: \u003Ccurrent value> (up from 0)` instead of a percentage, and treat it as flagged.\n\n## Compute change and flag movers\n\nFor every metric with a real value in both weeks:\n\n```\npct_change = (current - prior) \u002F prior * 100\n```\n\nA metric is flagged when `abs(pct_change) > 10`. This is the only threshold — do not round it or treat 10.0 as a pass.\n\n## Render the email\n\nPlain text only — no `#`, `*`, `-`, backticks, or other markdown syntax anywhere in the output.\n\n```\nSubject: Metrics week of \u003CYYYY-MM-DD of the reporting week's start date>\n\nGrowth\nsignups: \u003Cvalue>, \u003C+\u002F-X%> vs prior week\n\nEngagement\nactivation: \u003Cvalue>, \u003C+\u002F-X%> vs prior week\nchurn: \u003Cvalue>, \u003C+\u002F-X%> vs prior week\n\nFlags\n\u003Cone line per flagged metric, e.g. \"signups moved +14% vs prior week\">\n\u003Cor, if none qualify: \"No metrics moved more than 10% this week.\">\n```\n\nEvery metric row uses the missing-data or zero-baseline wording above in place of a percentage when those cases apply, in whichever section (Growth or Engagement) it normally belongs to.\n\n## Done when\n\n- Subject line reads exactly `Metrics week of \u003Cdate>` with the real start date substituted.\n- All three metrics — signups, activation, churn — appear exactly once each, in Growth or Engagement, either with a value and percent change or with the explicit missing\u002Fzero-baseline wording. None are silently dropped.\n- Flags lists every metric with `abs(pct_change) > 10`, or the exact no-movers sentence if none qualify.\n- The rendered output contains zero markdown characters — reread it once and confirm before sending.",{"name":5,"description":7},"main","cef05d1097f6e747e5c18bd5e7f3d6dba1f3d952","experiments\u002Fauthoring-ab\u002Fworkspace\u002Fweekly-metrics-digest\u002Fours\u002Frun-2","https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fskill-tuner","https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fhov-stack\u002Ftree\u002Fmain\u002Fplugins\u002Fskill-tuner","https:\u002F\u002Fgithub.com\u002FStartupBros-com","2026-11-02 17:58:56",{"source":8,"skillName":5,"commands":32,"prompt":42,"zipAvailable":43},[33,36,39],{"tool":34,"command":35},"npx","npx skills add StartupBros-com\u002Fskill-tuner --skill metrics-digest",{"tool":37,"command":38},"bunx","bunx skills add StartupBros-com\u002Fskill-tuner --skill metrics-digest",{"tool":40,"command":41},"pnpm","pnpm dlx skills add StartupBros-com\u002Fskill-tuner --skill metrics-digest","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fskill-tuner\u002Fblob\u002Fmain\u002Fexperiments\u002Fauthoring-ab\u002Fworkspace\u002Fweekly-metrics-digest\u002Fours\u002Frun-2\u002FSKILL.md",true,[45,51],{"path":46,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":49,"sourceHtmlUrl":50},"grading.json","REFERENCE","参考文档",1040,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fskill-tuner\u002Fblob\u002Fmain\u002Fexperiments\u002Fauthoring-ab\u002Fworkspace\u002Fweekly-metrics-digest\u002Fours\u002Frun-2\u002Fgrading.json",{"path":52,"resourceType":47,"resourceTypeDesc":48,"sizeBytes":53,"sourceHtmlUrl":54},"meta.json",215,"https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fskill-tuner\u002Fblob\u002Fmain\u002Fexperiments\u002Fauthoring-ab\u002Fworkspace\u002Fweekly-metrics-digest\u002Fours\u002Frun-2\u002Fmeta.json",[56,63,70,77,84,89],{"skillNo":57,"name":58,"nameZh":6,"description":59,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":60,"categories":61,"keywords":62,"publishedAt":19},"01M7AA3WSSMWKNAWDHSD5VMVQZ","tune","Find and fix real defects in a skill, AGENTS.md, or CLAUDE.md, then prove the description still routes. Runs the bundled token-spending runner, so it starts only on the human's explicit instruction.","https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fskill-tuner\u002Fblob\u002Fmain\u002Fskills\u002Ftune\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},"01M7AA3T3WEM4JV9F1YM7SXWXK","skill-tuner","Evidence-tagged rules for writing documents agents consume. Use when creating, editing, or shortening skills, AGENTS.md, or CLAUDE.md.","https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fskill-tuner\u002Fblob\u002Fmain\u002Fskills\u002Fskill-tuner\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},"01M7AA3PXA6T3T6CC0S7P6RH5P","portfolio","Inventory every skill the agent is shown, with its per-turn listing cost, usage count and visibility knob, then decide one skill at a time whether the model should start it on its own. Reads files only; starts on the human's explicit instruction.","https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fskill-tuner\u002Fblob\u002Fmain\u002Fskills\u002Fportfolio\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},"01M7AA3MG60GEBYXM4N2EK2H43","shipit","Release builds with the shipit CLI. Use when releasing or promoting a build to staging or prod, checking a release manifest, or rolling back a shipit deployment.","https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fskill-tuner\u002Fblob\u002Fmain\u002Fexperiments\u002Ftrigger-improving-2026-10-29\u002Fresults\u002Fruns\u002Flive-imp-solo-imp-3\u002FSKILL.md",[],[],{"skillNo":85,"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":86,"categories":87,"keywords":88,"publishedAt":19},"01M7AA3GGJHVGJJ4RHRDMEXAWY","https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fskill-tuner\u002Fblob\u002Fmain\u002Fexperiments\u002Ftrigger-improving-2026-10-29\u002Fresults\u002Fruns\u002Flive-imp-solo-imp-2\u002FSKILL.md",[],[],{"skillNo":90,"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":91,"categories":92,"keywords":93,"publishedAt":19},"01M7AA3E53RC5PWWNC5265WS84","https:\u002F\u002Fgithub.com\u002FStartupBros-com\u002Fskill-tuner\u002Fblob\u002Fmain\u002Fexperiments\u002Ftrigger-improving-2026-10-29\u002Fresults\u002Fruns\u002Flive-imp-solo-imp-1\u002FSKILL.md",[],[]]