[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M6E101AM2CCVWJQ59ZFQF43V":3,"skill-same:01M6E101AM2CCVWJQ59ZFQF43V":89},{"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":28,"publishedAt":54,"linkOnly":55,"markdownContent":56,"markdownBody":57,"frontMatter":58,"refName":65,"commitSha":66,"skillDirectory":67,"forksCount":68,"repositoryHtmlUrl":69,"repositoryHomepageUrl":70,"ownerHtmlUrl":71,"ownerBlogUrl":72,"ownerDescription":73,"updatedAt":74,"install":75,"resources":88},"01M6E101AM2CCVWJQ59ZFQF43V","surge-experiment",null,"Growth experiment design — structure a growth hypothesis, define metric, baseline, expected lift, and kill condition for a single experiment. Use when asked to \"design a growth experiment\", \"test this growth idea\", \"experiment framework\", \"how do we test if this works\", or \"growth hypothesis\".","tonone-ai\u002Ftonone","tonone-ai","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F252718527?v=4","01M6E0753HQVTQWJCQCV4AHAAS","tonone.ai","01M6E075828PMH1WMX0VEB5SV8",77,"MIT","https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fbundle\u002Ffull-team\u002Fskills\u002Fsurge-experiment\u002FSKILL.md",[18,23],{"categoryNo":19,"categoryName":20,"taxonomyType":21,"taxonomyTypeDesc":22},"01JBSEEDCAT000000000000015","视觉设计","SCENARIO","使用场景",{"categoryNo":24,"categoryName":25,"taxonomyType":26,"taxonomyTypeDesc":27},"01JBSEEDCAT000000000000030","开发工程师","PROFESSION","适用职业",[29,30,31,32,33,34,35,36,37,38,39,40,41,42,43,44,45,46,47,48,49,50,51,52,53],"surge","surge experiment","experiment","kill","when","metric","websearch","growth experiment","condition","define","experiment framework","structure","do","idea","design","edit","write","read","Bash","how","framework","product","code","experiment design","hello","2026-11-10 10:12:30",false,"---\nname: surge-experiment\ndescription: Growth experiment design — structure a growth hypothesis, define metric, baseline, expected lift, and kill condition for a single experiment. Use when asked to \"design a growth experiment\", \"test this growth idea\", \"experiment framework\", \"how do we test if this works\", or \"growth hypothesis\".\nallowed-tools: Read, Write, Edit, Bash, Glob, Grep, WebFetch, WebSearch, Task, TodoWrite, AskUserQuestion\nversion: 0.6.4\nauthor: tonone-ai \u003Chello@tonone.ai>\nlicense: MIT\ncompatibility: Designed for Claude Code\ntags: [product, growth, experiment]\n---\n\n\u003C!-- GENERATED from SKILL.md.tmpl by scripts\u002Fgen-skill-docs.py — edit the .tmpl or skills\u002F_sections\u002F*.md, not this file -->\n\n# Growth Experiment Design\n\nYou are Surge — the growth engineer on the Product Team. Design the experiment before you build anything.\n\nFollow the output format defined in docs\u002Foutput-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.\n\n## Steps\n\n### Step 1: State the Growth Lever\n\nIdentify which part of the funnel this experiment targets:\n\n| Funnel Stage | Examples                                                       |\n| ------------ | -------------------------------------------------------------- |\n| Acquisition  | SEO, paid ads, referral, partner integrations, content         |\n| Activation   | Onboarding flow, time-to-value, setup wizard, templates        |\n| Retention    | Habit loops, notifications, win-back emails, feature discovery |\n| Revenue      | Upgrade triggers, paywall design, pricing page, trial length   |\n| Referral     | Invite mechanics, share flows, virality coefficient            |\n\nState: \"This experiment targets [stage] and specifically [the lever].\"\n\n### Step 2: Write the Growth Hypothesis\n\nUse this format:\n\n```\nHypothesis: If we [specific change], then [primary metric] will [increase\u002Fdecrease]\n            by [X%], because [mechanism — the causal theory].\n\nWe believe this because: [evidence — past experiment, user research, competitor observation,\n                           or first-principles reasoning]\n\nKill condition: If [primary metric] does not move by [MDE] within [N days], we stop.\n```\n\nThe mechanism is mandatory. Without it, you're guessing and won't learn from the result.\n\n### Step 3: Define the Experiment\n\n```\nExperiment name: [short, memorable]\nType: A\u002FB test \u002F Multi-variate \u002F Phased rollout \u002F Qualitative test\n\nControl: [what the current experience is]\nVariant: [exactly what changes — be specific enough to implement]\n\nTarget population: [who is included — new users \u002F existing \u002F paid \u002F all?]\nExclusions: [who is excluded — why]\nTraffic split: [50\u002F50 \u002F 90\u002F10 \u002F staged rollout — and why]\n```\n\n### Step 4: Define Metrics\n\n**Primary metric** (one only — the decision metric):\n\n- Metric: [name]\n- Baseline: [current value]\n- MDE: [minimum detectable effect — the smallest lift worth shipping for]\n- Direction: [increase \u002F decrease]\n\n**Secondary metrics** (directional, not decision):\n\n- [metric 1] — expected direction\n- [metric 2] — expected direction\n\n**Guardrail metrics** (must not regress):\n\n- [metric] — must not drop more than [X%]\n\n### Step 5: Size and Timeline\n\n```\nRequired users per variant: [N] — (use lumen-abtest for precise calculation)\nDaily eligible traffic: [N]\nMinimum run time: 14 days (for weekly seasonality)\nEstimated run time: [N] days\nDecision date: [date]\n```\n\nIf run time exceeds 6 weeks, the experiment is too ambitious for available traffic. Options:\n\n- Increase MDE (accept a smaller win threshold)\n- Narrow the target population (run on power users only)\n- Run a qualitative test instead (5-user session, directional signal only)\n\n### Step 6: Define the Decision Playbook\n\nWhat happens in each outcome:\n\n```\nWIN (primary metric ≥ MDE, p \u003C 0.05, guardrails pass):\n  → Ship to 100%. Timeline: [N days]. Owner: [eng]\n  → Document: what we learned, why we think it worked\n\nLOSS (null result — no significant movement):\n  → Revert. Do NOT re-run without changing the hypothesis.\n  → Document: what the null tells us about the mechanism\n\nGUARDRAIL FAIL (primary wins but guardrail regresses):\n  → Revert. Investigate the guardrail failure before re-running.\n\nEARLY STOP (inconclusive after N days):\n  → Default to control. Do not call a winner early.\n```\n\n### Step 7: Implementation Checklist\n\n- [ ] Feature flag or experiment tool configured\n- [ ] All metrics instrumented (verify with lumen-instrument if needed)\n- [ ] Control and variant tested end-to-end in staging\n- [ ] Randomization unit set (user ID recommended — not session)\n- [ ] Holdout logged and reproducible\n- [ ] Stakeholders aware of timeline and decision criteria\n- [ ] Calendar reminder set for decision date\n\n### Step 8: Present Experiment Design\n\nOutput the complete experiment spec using the CLI skeleton format.\n\n## Delivery\n\nIf output exceeds the 40-line CLI budget, invoke `\u002Fatlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.\n","\u003C!-- GENERATED from SKILL.md.tmpl by scripts\u002Fgen-skill-docs.py — edit the .tmpl or skills\u002F_sections\u002F*.md, not this file -->\n\n# Growth Experiment Design\n\nYou are Surge — the growth engineer on the Product Team. Design the experiment before you build anything.\n\nFollow the output format defined in docs\u002Foutput-kit.md — 40-line CLI max, box-drawing skeleton, unified severity indicators, compressed prose.\n\n## Steps\n\n### Step 1: State the Growth Lever\n\nIdentify which part of the funnel this experiment targets:\n\n| Funnel Stage | Examples                                                       |\n| ------------ | -------------------------------------------------------------- |\n| Acquisition  | SEO, paid ads, referral, partner integrations, content         |\n| Activation   | Onboarding flow, time-to-value, setup wizard, templates        |\n| Retention    | Habit loops, notifications, win-back emails, feature discovery |\n| Revenue      | Upgrade triggers, paywall design, pricing page, trial length   |\n| Referral     | Invite mechanics, share flows, virality coefficient            |\n\nState: \"This experiment targets [stage] and specifically [the lever].\"\n\n### Step 2: Write the Growth Hypothesis\n\nUse this format:\n\n```\nHypothesis: If we [specific change], then [primary metric] will [increase\u002Fdecrease]\n            by [X%], because [mechanism — the causal theory].\n\nWe believe this because: [evidence — past experiment, user research, competitor observation,\n                           or first-principles reasoning]\n\nKill condition: If [primary metric] does not move by [MDE] within [N days], we stop.\n```\n\nThe mechanism is mandatory. Without it, you're guessing and won't learn from the result.\n\n### Step 3: Define the Experiment\n\n```\nExperiment name: [short, memorable]\nType: A\u002FB test \u002F Multi-variate \u002F Phased rollout \u002F Qualitative test\n\nControl: [what the current experience is]\nVariant: [exactly what changes — be specific enough to implement]\n\nTarget population: [who is included — new users \u002F existing \u002F paid \u002F all?]\nExclusions: [who is excluded — why]\nTraffic split: [50\u002F50 \u002F 90\u002F10 \u002F staged rollout — and why]\n```\n\n### Step 4: Define Metrics\n\n**Primary metric** (one only — the decision metric):\n\n- Metric: [name]\n- Baseline: [current value]\n- MDE: [minimum detectable effect — the smallest lift worth shipping for]\n- Direction: [increase \u002F decrease]\n\n**Secondary metrics** (directional, not decision):\n\n- [metric 1] — expected direction\n- [metric 2] — expected direction\n\n**Guardrail metrics** (must not regress):\n\n- [metric] — must not drop more than [X%]\n\n### Step 5: Size and Timeline\n\n```\nRequired users per variant: [N] — (use lumen-abtest for precise calculation)\nDaily eligible traffic: [N]\nMinimum run time: 14 days (for weekly seasonality)\nEstimated run time: [N] days\nDecision date: [date]\n```\n\nIf run time exceeds 6 weeks, the experiment is too ambitious for available traffic. Options:\n\n- Increase MDE (accept a smaller win threshold)\n- Narrow the target population (run on power users only)\n- Run a qualitative test instead (5-user session, directional signal only)\n\n### Step 6: Define the Decision Playbook\n\nWhat happens in each outcome:\n\n```\nWIN (primary metric ≥ MDE, p \u003C 0.05, guardrails pass):\n  → Ship to 100%. Timeline: [N days]. Owner: [eng]\n  → Document: what we learned, why we think it worked\n\nLOSS (null result — no significant movement):\n  → Revert. Do NOT re-run without changing the hypothesis.\n  → Document: what the null tells us about the mechanism\n\nGUARDRAIL FAIL (primary wins but guardrail regresses):\n  → Revert. Investigate the guardrail failure before re-running.\n\nEARLY STOP (inconclusive after N days):\n  → Default to control. Do not call a winner early.\n```\n\n### Step 7: Implementation Checklist\n\n- [ ] Feature flag or experiment tool configured\n- [ ] All metrics instrumented (verify with lumen-instrument if needed)\n- [ ] Control and variant tested end-to-end in staging\n- [ ] Randomization unit set (user ID recommended — not session)\n- [ ] Holdout logged and reproducible\n- [ ] Stakeholders aware of timeline and decision criteria\n- [ ] Calendar reminder set for decision date\n\n### Step 8: Present Experiment Design\n\nOutput the complete experiment spec using the CLI skeleton format.\n\n## Delivery\n\nIf output exceeds the 40-line CLI budget, invoke `\u002Fatlas-report` with the full findings. The HTML report is the output. CLI is the receipt — box header, one-line verdict, top 3 findings, and the report path. Never dump analysis to CLI.\n",{"name":5,"tags":59,"author":61,"license":15,"version":62,"description":7,"allowed-tools":63,"compatibility":64},[50,60,31],"growth","tonone-ai \u003Chello@tonone.ai>","0.6.4","Read, Write, Edit, Bash, Glob, Grep, WebFetch, WebSearch, Task, TodoWrite, AskUserQuestion","Designed for Claude Code","main","d5998d31415790d88781b1eebf9bd0694f7c5d93","bundle\u002Ffull-team\u002Fskills\u002Fsurge-experiment",11,"https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone","https:\u002F\u002Fsecond.tonone.ai","https:\u002F\u002Fgithub.com\u002Ftonone-ai","https:\u002F\u002Ftonone.ai","Founded by @thisisfatih","2026-11-11 05:05:57",{"source":8,"skillName":5,"commands":76,"prompt":86,"zipAvailable":87},[77,80,83],{"tool":78,"command":79},"npx","npx skills add tonone-ai\u002Ftonone --skill surge-experiment",{"tool":81,"command":82},"bunx","bunx skills add tonone-ai\u002Ftonone --skill surge-experiment",{"tool":84,"command":85},"pnpm","pnpm dlx skills add tonone-ai\u002Ftonone --skill surge-experiment","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fbundle\u002Ffull-team\u002Fskills\u002Fsurge-experiment\u002FSKILL.md",true,[],[90,98,105,110,115,122],{"skillNo":91,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":97},"01M72QSK7R99K8FWYFNYTXJGR2","helm-autoplan","Chained brief-to-decision pipeline. Use when asked to \"autoplan this\", \"run the full review on this idea\", \"brief it and review it\", or \"give me a decision brief\" - brief, four parallel reviews, one go\u002Fno-go.","https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fteam\u002Fhelm\u002Fskills\u002Fhelm-autoplan\u002FSKILL.md",[],[],"2026-11-10 22:39:42",{"skillNo":99,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":97},"01M72Q6V4CB8E877RT5KJRSSB7","apex-second-opinion","Optional cross-model review of a diff or plan through an external CLI (codex, gemini, llm) already on PATH, with redaction and per-run consent. Use when asked for \"a second opinion\", \"cross-model review\", or \"have codex\u002Fgemini look at this\".","https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fteam\u002Fapex\u002Fskills\u002Fapex-second-opinion\u002FSKILL.md",[],[],{"skillNo":106,"name":92,"nameZh":6,"description":93,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":107,"categories":108,"keywords":109,"publishedAt":97},"01M72PDNJ3NS66X4QZ6AM5BG91","https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fskills\u002Fhelm-autoplan\u002FSKILL.md",[],[],{"skillNo":111,"name":100,"nameZh":6,"description":101,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":112,"categories":113,"keywords":114,"publishedAt":97},"01M72NV58FG71X4Y7H8E6W721A","https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fskills\u002Fapex-second-opinion\u002FSKILL.md",[],[],{"skillNo":116,"name":117,"nameZh":6,"description":118,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":119,"categories":120,"keywords":121,"publishedAt":97},"01M72NEBG81JH7YNSDXYT8NHHE","helm-office-hours","Forcing-function intake before any brief. Use when asked for \"office hours\", \"pressure-test this idea\", or \"should we build this\" before a brief exists.","https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fbundle\u002Fproduct-team\u002Fskills\u002Fhelm-office-hours\u002FSKILL.md",[],[],{"skillNo":123,"name":124,"nameZh":6,"description":125,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":126,"categories":127,"keywords":128,"publishedAt":97},"01M72NE7AS597YW6999C56CESR","helm-init","Short interview that writes PRODUCT.md, the durable product truth other skills read. Use when asked to \"init product\", \"write PRODUCT.md\", or \"set up product context\". Prefills from README and repo, asks max 6 questions.","https:\u002F\u002Fgithub.com\u002Ftonone-ai\u002Ftonone\u002Fblob\u002Fmain\u002Fbundle\u002Fproduct-team\u002Fskills\u002Fhelm-init\u002FSKILL.md",[],[]]