retort
adrianco/retort
This skill acts as a qualitative analysis tool for Retort Design of Experiments (DoE) runs, aggregating factor effects, evaluating replicate variance, and surfacing code divergence.
195 13Apache-2.0Updated 2026-08-13
83
GreatOverview
Designed to work alongside the quantitative ANOVA reports generated by Retort, this skill processes evaluated experiment runs to assess how variables like programming languages, models, and tools impact generated code quality. It groups runs by cell, calculates replicate variance and metric statistics, tracks architectural shape shifts, and identifies common patterns or failure points without re-running evaluations.
Capabilities
- ▸Discovering and parsing evaluated experiment runs and replicates
- ▸Aggregating metrics and findings by factor cell with mean and standard deviation
- ▸Isolating individual factor effects and cross-referencing with retort analysis reports
- ▸Highlighting qualitative divergence and architectural differences across replicates
- ▸Generating comprehensive markdown comparison reports
Best for
Comparing qualitative outcomes across different factor combinations in AI agent experiments, Identifying within-cell variance and architectural divergence across replicate runs, Synthesizing shared issues and failure modes across multiple experimental runs
Works with
Claude CodeCodexChatGPTGemini CLIOpenCode
Evoa Score breakdown= Σ (score × weight)
83Task usefulness20%88 → +17.6
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%90 → +13.5
実装・指示の品質。 — AIによるSKILL.md/README解析
Maintenance15%100 → +15.0
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%34 → +4.1
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%85 → +8.5
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%59 → +4.7
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 total83.4 / 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
Reads local experiment files and evaluation artifacts. Executes standard file-system discovery commands without running arbitrary evaluation code or modifying source files.
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.