Rosamund - A/B 測試分析師 AI Skill
$29.00
特價
$29.00
原價
$43.99
跳至產品資訊
Start All-Access
Rosamund - A/B 測試分析師 AI Skill
$29.00
this skill
vs
$43.99
hiring an A/B testing analyst
Complete skill package instant downloadrosamund-experimentation-ab-testing-analyst.skill
Choose how to get it
Start All-Access, from $8.25/mo$99 a year, or $19 a month. 14-day refund on the first charge.
// all-access
You do not download skills. Your AI fetches them.
The KissMySkills connector is a small server your AI chat talks to. Add it once to Claude, ChatGPT, Claude Code or Cursor. From then on, any of our 1,000+ skills is one sentence away.
- 01Add the connector. Settings, Connectors, paste one link. A minute.
- 02Sign in once. The email from your subscription. Nothing installs.
- 03Ask for a skill. "Load Rosamund." It arrives in the conversation and your AI answers as that specialist.
$99/yr $8.25 a month
$19/mo month to month
Every skill, prompt pack and agent, new releases included. Single files can still be bought and kept. Cancel any time from your account. Compare plans
Secure checkout by Shopify
⚡ 立即下載
∞ 永遠保留
✎ 由我們撰寫
Add it once. Your AI works like a specialist.
將其加入 Claude、ChatGPT 或 Gemini - 您的 AI 會在此領域中擔任專家。
立即下載 · 30 天退款保證。 一次付費，永久使用 - 無需訂閱。由我們撰寫並測試，絕非從 GitHub 抓取。 退款政策
Ask Rosamund something hard.
Two-week test: variant +9% on Tuesday, -4% by Friday. PM refreshes the dashboard hourly asking if it's done. When is it done?
CLAUDE · AS ROSAMUND, A/B 測試分析師
It's done at the pre-computed sample size, not when the line looks good - swings from +9% to -4% in week one are textbook noise at small n. If nobody computed power up front, do it now: baseline rate, an MDE you'd actually act on, 80% power - that yields the end date, and my bet is 3-4 weeks, not Friday. Mid-flight, only integrity checks are legitimate: SRM on the allocation ratio, novelty effect in the returning-versus-new split, instrumentation parity between arms. And take the dashboard away from the PM - peeking is how +9% ships and 0% arrives. What was the planned MDE?
Trademarks of their respective owners. KissMySkills is not affiliated with or endorsed by them.
你不需要閱讀。由你的 AI 代勞。
只需將技能檔案新增至 Claude、ChatGPT 或 Gemini 一次。從那之後，它就會以這個領域的專家身分運作，並從下一則訊息開始以 Rosamund 的身分回答。
購買一次，檔案便永久歸您所有。或者訂閱 All-Access，讓 KissMySkills 連接器在您提出要求時，將該檔案及其他所有技能載入您的聊天中。
// what's inside
這項技能包含什麼
- Validity check on how the test was built and run
- Sample ratio mismatch and peeking diagnostics
- A corrected read of what the result actually says
- A clear ship, extend or rerun recommendation
Growth teams and product analysts about to ship a test on a shaky result
A senior experimentation / A-B testing analyst bills $132+/hr, the complete skill is yours forever.
// what's inside
What you're actually buying
資深實驗與 A/B 測試分析師，會先檢查測試的建立與執行方式，再相信儀表板最後顯示的結果。
Rosamund 涵蓋完整的實驗生命週期：樣本數與檢定力計算、最小可偵測效果（MDE）規模估算、隨機化單位與分派完整性檢查、樣本比例不匹配（SRM）偵測、統計顯著性與實務顯著性、新奇效應與窺探／提前停止問題、護欄指標設計，以及 Simpson 悖論與多重比較等分析陷阱。
適用對象
執行 A/B 測試的成長與產品團隊，在做出上線決策前，需要預先註冊的樣本數、SRM 檢查，以及護欄指標報告，而不是把綠色的 p 值照單全收。
主要功能
- 在測試開始前，根據明確指定的 MDE、基準率與檢定力計算樣本數與執行時間
- 在相信任何結果前，針對實際觀察到的分流比例進行卡方樣本比例不匹配檢查
- 每個 p 值都會附帶信賴區間與以業務語言呈現的效果量，絕不單獨報告
- 在宣布某項提升為持久的勝出結果前，進行新奇效應與窺探檢查
- 在提出任何上線建議前，執行護欄指標與子群組 Simpson 悖論檢查
使用方式
將 Rosamund 的 SKILL.md 貼到你的 Claude Project Instructions（或任何 AI system prompt）中，然後描述你的實驗與 A/B 測試分析師問題。適用於 Claude、ChatGPT，以及任何 AI 聊天工具。安裝時間不到 2 分鐘。
// how to install
不到 2 分鐘
四個步驟。任何 AI 聊天。
- 01下載檔案
結帳後，下載連結會寄到您的收件匣。將檔案儲存至裝置上的任意位置。
- 02開啟你的 AI 聊天功能
Claude、ChatGPT、Gemini、Grok 或 Copilot - 無論你目前使用哪一個。
- 03貼上檔案內容
將其放入系統 prompt、專案指示或自訂指示欄位中。
- 04開始工作
您的 AI 現已設定為專業助手。您可以詢問它任何與其專業領域相關的問題。
不需要技術知識。不需訂閱。一次付費，永久使用。
// compatible with
支援所有主要的 AI 聊天服務。
將檔案放入您的 AI system prompt、專案指示或自訂指示中。無需設定。無需程式碼。不受供應商綁定。
// faq
關於此產品的問題
What AI tools does this work with?+
Claude, ChatGPT, or any AI chat that accepts a system prompt or project instructions. Claude Projects gives the best results.
How do I install it?+
Paste the SKILL.md content into your Claude Project Instructions or your AI's system prompt. Under 2 minutes, no setup required.
Is this a course or a tool?+
It's a skill file, not a course. One file that turns your AI into a configured Experimentation & A/B Testing Analyst ready to work on your Experimentation & A/B Testing Analyst problem immediately.
Our test shows a winner but something feels off about it, what does Rosamund check first?+
She runs a chi-square sample ratio mismatch check on the observed versus intended split before trusting anything else, since a silent bucketing bug can invalidate the whole test while every downstream metric still looks plausible on the surface.
Do I have to read it myself?+
No. The file is written for your AI to read, not for you. Upload it or paste it in once and the AI takes on the role. After that you just ask it questions the way you normally would. You're welcome to open it and read it, but nothing here depends on you doing that.
Is this a physical book?+
No, it's digital. You download it the moment the order goes through and it's yours permanently. The cover is styled like a book because each edition is written and edited as one self-contained piece of work. The reading part is your AI's job, not yours.
準備好讓您的 AI 專精了嗎？
一個即插即用的檔案。一次付費，永久保留 - 適用於 Claude 和 ChatGPT。
