Skills ab-test-setup
📦

ab-test-setup

Content revision r1 Safe ⚙️ External commands🌐 Network access

設計可靠的 A/B 測試

當假設、指標和樣本大小不明確時，團隊可能得到無定論的實驗結果。此技能會結構化 A/B 測試，讓決策能使用可靠證據。

Supports: Claude Codex Code(CC)
Maintain this Skill? Claim it 🥉 77 Bronze

Install with my Agent

Copy this request to your Agent. It includes the canonical Skill page and manifest.

Agent request
Review the Skillstore skill "ab-test-setup" from https://skillstore.io/skills/coreyhaines31-ab-test-setup.md and its manifest at https://skillstore.io/api/skills/coreyhaines31-ab-test-setup/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.

Your Agent should still show its plan and request any confirmation required by the security policy.

Agent-readable resources

Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.

Markdown detail GET /skills/coreyhaines31-ab-test-setup.md Signed manifest GET /api/skills/coreyhaines31-ab-test-setup/manifest Signed lockfile GET /api/skills/coreyhaines31-ab-test-setup/lockfile

Test it

Using "ab-test-setup". 為定價頁標題規劃 A/B 測試，每日訪客 8,000 人，方案選擇率為 4%。

Expected outcome:

  • 假設將標題變更連結到更清楚的價值感知和更高的方案選擇率。
  • 建議設計為 50/50 A/B 測試，只變更一個標題，並維持定價內容穩定。
  • 指標包含方案選擇作為主要指標、頁面停留時間作為次要指標，以及退款率作為防護指標。
  • 持續時間取決於最小可偵測效果，且應涵蓋至少一個業務週期。

Using "ab-test-setup". 審查已完成的註冊流程測試，註冊提升 6%，但註冊後啟用表現較弱。

Expected outcome:

  • 結果在推出前需要同時具備統計顯著性和實際顯著性。
  • 較低的啟用率是防護指標疑慮，可能抵消註冊提升的價值。
  • 建議行動是在全面上線前進行客群審查、品質分析和後續測試。

Using "ab-test-setup". 為登陸頁 CTA 實驗建立文件。

Expected outcome:

  • 文件包含測試名稱、日期、負責人、假設、變體、指標、決策、行動和學習成果。
  • 變體備註描述 CTA 文案和位置變更，而不改動無關的頁面元素。
  • 學習知識庫備註記錄為何執行此測試，以及接下來應測試什麼。

Security Audit

Safe
v4 • 7/6/2026 Open versioned report

The flagged external command findings are Markdown code fences used for templates, formulas, and output examples. The hardcoded URLs are public A/B testing calculator references, and the reconnaissance findings are ordinary experimentation guidance.

1
Files scanned
509
Lines analyzed
0
Review items
0
False positives ignored

Risk Factors

⚙️ External commands (9)
SKILL.md:59-65 SKILL.md:65-134 SKILL.md:134-138 SKILL.md:138-222 SKILL.md:222-231 SKILL.md:231-393 SKILL.md:393-417 SKILL.md:417-432 SKILL.md:432-460
🌐 Network access (2)
SKILL.md:129 SKILL.md:130
No confirmed security findings were detected by the latest completed static and semantic audit. This does not prove the skill has no side effects.
Audited by: codex View Audit History →
Share & cite this report

Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.

Open versioned report
Security Assessment

Copy report link

https://skillstore.io/skills/coreyhaines31-ab-test-setup/audits/4?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_report

Markdown badge

[![Skillstore security assessment](https://skillstore.io/badges/skills/coreyhaines31-ab-test-setup/security.svg)](https://skillstore.io/skills/coreyhaines31-ab-test-setup?utm_source=security_passport_badge)

HTML badge

<a href="https://skillstore.io/skills/coreyhaines31-ab-test-setup?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/coreyhaines31-ab-test-setup/security.svg" alt="Skillstore security assessment" loading="lazy"></a>

Embed card

<iframe src="https://skillstore.io/embed/skills/coreyhaines31-ab-test-setup.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>
Academic citations (APA · BibTeX · CFF)

APA citation

coreyhaines31. (2026). ab-test-setup security audit report (audit version 4) [Author version unspecified]. Skillstore. https://skillstore.io/skills/coreyhaines31-ab-test-setup/audits/4

BibTeX citation

@techreport{coreyhaines31-coreyhaines31-ab-test-setup-2026, author = {coreyhaines31}, title = {ab-test-setup security audit report (audit version 4)}, institution = {Skillstore}, year = {2026}, number = {4}, url = {https://skillstore.io/skills/coreyhaines31-ab-test-setup/audits/4}, note = {Author version unspecified} }

CITATION.cff

cff-version: 1.2.0 message: "If you use this Skill, cite its author and this versioned security audit report." title: "ab-test-setup security audit report (audit version 4)" version: "unspecified" type: report authors: - name: "coreyhaines31" date-released: "2026-07-06" url: "https://skillstore.io/skills/coreyhaines31-ab-test-setup/audits/4" identifiers: - type: other value: "skillstore:coreyhaines31-ab-test-setup:audit:4" description: "Skillstore immutable audit report identifier"

Compare variants

2 installable variants

Each author remains a separate installable skill. The recommended variant is ranked by Skillstore evidence.

Why this variant is first

Highest Skillstore Score
sickn33 Recommended

sickn33-ab-test-setup

Skillstore Score 78
Evidence Confidence High
Skillstore usage 14
Updated

2026-09-09

coreyhaines31 Current

coreyhaines31-ab-test-setup

Skillstore Score 77
Evidence Confidence High
Skillstore usage 14
Updated

2026-09-09

Skillstore Score

Why this score Evidence Confidence: High
55
Architecture
85
Maintainability
87
Content
69
Community
78
Spec Compliance

What You Can Build

規劃登陸頁測試

為標題、CTA、版面配置或社會證明變更建立清楚的測試計畫。

排定產品實驗優先順序

將產品想法轉化為具有變體、指標和決策規則的可衡量實驗。

審查實驗結果

在測試結束後評估顯著性、實際影響、防護指標和後續行動。

Try These Prompts

建立基本測試計畫 
協助我為 [page or flow] 規劃 A/B 測試。目前轉換率是 [rate]，每日流量是 [number]，提議的變更是 [change]。
精煉假設和指標 
審查這個測試想法：[idea]。將它轉化為清楚的假設，並定義主要、次要和防護指標。
估算樣本大小和持續時間 
為包含 [baseline rate]、[MDE]、[daily traffic]、[variants]、95% 信心水準和 80% 檢定力的測試設計樣本大小方法。
建立實驗計畫簡報 
為 [business goal] 建立完整的實驗簡報。包含假設、變體、分配、QA、分析計畫、風險、決策規則和學習知識庫備註。

Best Practices

  • 在上線前預先定義假設、樣本大小、持續時間和決策標準。
  • 使用一個主要指標，以及與營收、留存或使用者品質相關的防護指標。
  • 在測試期間保持變體穩定，並記錄外部因素。

Avoid

  • 因為目前結果看起來顯著就提早停止測試。
  • 在沒有足夠流量進行可靠歸因的情況下，測試多個無關變更。
  • 從上線前未規劃的區隔資料中判定勝出者。

Frequently Asked Questions

此技能可以選擇正確的 A/B 測試類型嗎？
可以。它會根據流量、範圍和複雜度比較 A/B、A/B/n、多變量和分流 URL 測試。
它會計算精確的樣本大小嗎？
它提供規劃估算和輸入項。最終樣本大小應使用統計工具或計算器驗證。
它可以實作追蹤程式碼嗎？
不會。它可以定義追蹤需求，但分析設定應由追蹤或工程工作流程處理。
我應該先提供哪些資訊？
請提供目前轉換率、流量規模、提議變更、目標指標，以及最小有用改善幅度。
測試完成後它還能協助嗎？
可以。它可以結構化結果摘要、審查防護指標、說明無定論的結果，並建議後續測試。
它可以搭配 Claude、Codex 和 Claude Code 使用嗎？
可以。此技能內容相容於 Claude、Codex 和 Claude Code 市集工作流程。

Developer Details

License

MIT

Skillstore revision

r1

Version notice

The author did not declare a version.

Repository

https://github.com/coreyhaines31/marketingskills/tree/main/skills/ab-test-setup

Ref

d11af420e07cd866fe39cfa937efef3223896c06

Maintenance freshness

7/18/2026

Usage

4 downloads · 139 views

File structure

📄 SKILL.md

More from coreyhaines31

View all

Related Skills

View all