faos-skills-marketplace
frank-luongt/faos-skills-marketplace
This skill analyzes A/B test results using statistical rigor to determine whether to ship, extend, or stop an experiment. It enforces disciplined evaluation by verifying sample sizes, checking guardrail metrics, and calculating confidence intervals.
29 13Apache-2.0Updated 2026-07-08
80
GreatOverview
Designed to prevent premature test conclusions and common statistical fallacies, the A/B test analysis skill provides a clear step-by-step workflow for assessing experiment outcomes. It guides users through validating setup parameters like sample ratio mismatches and test durations, computing core metrics such as relative lift and p-values, evaluating guardrail degradation, and applying a robust decision matrix.
Capabilities
- ▸Statistical significance calculation
- ▸Sample Ratio Mismatch (SRM) detection
- ▸Guardrail metric assessment
- ▸Decision matrix execution for ship/extend/stop recommendations
Best for
Evaluating completed A/B test conversion data to decide whether to roll out a variant, Assessing statistical and practical significance against predefined Minimum Detectable Effect thresholds, Checking guardrail metrics to ensure primary wins do not negatively impact other critical business metrics
Works with
Claude CodeCodexGemini CLICursorGitHub CopilotOpenCode
Evoa Score breakdown= Σ (score × weight)
80Task usefulness20%77 → +15.4
実タスクにどれだけ役立つか（機能の豊富さ・用途の明確さ）。 — AIによるcapabilities/use-cases解析
Code quality15%95 → +14.3
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%85 → +12.8
リポジトリがどれだけ活発に保守されているか。 — GitHub 最終push日時の新しさ
Documentation12%48 → +5.8
ドキュメントの充実度・分かりやすさ。 — README/独自要約の情報量
Security15%100 → +15.0
危険・不審な挙動が無いか。 — AIによるセキュリティレビュー
Originality10%80 → +8.0
ありふれたラッパーではない独自性。 — AIによる独自性判定
Popularity8%44 → +3.5
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%100 → +5.0
対応AIエージェントの広さ。 — AIによる対応エージェント判定
Weighted total79.7 / 100
ライセンス不明/制限あり（Red）のSkillは総合スコアに0.85倍の補正を適用します。 ランキングはこのScoreのみで決まり、広告で変わりません。 算出方法の詳細 →
Security considerations
Processes statistical conversion numbers and test parameters locally without requiring external API calls or handling sensitive user personal identifiable information.
Categories
Summary and analysis are original content generated by AI Skills Rank. The skill's source text is not reproduced here — view it on the linked repository.