rubric-evaluator
halfmoon-mind/rubric-evaluator
Assess and audit AI skill directories using a comprehensive 31-item, 6-section rubric that combines deterministic structural checks and semantic model analysis to assign a definitive S/A/B/C/F grade.
7 2No licenseUpdated 2026-07-09
63
GoodOverview
The rubric-evaluator skill audits custom skill folders containing SKILL.md files. It runs a bundled stdlib-only Python script for structural and safety validations, applies fourteen semantic model checks, and computes an automated S, A, B, C, or F grade based on blocker and major findings. The resulting report details failing conditions, explains why they matter, and provides actionable remediation guidance.
Capabilities
- ▸Deterministic structural and safety rule checking via Python scripts
- ▸Semantic model checks based on a structured rubric reference
- ▸Automated S/A/B/C/F grading logic based on severity counts
- ▸Markdown report generation from JSON findings
- ▸Graceful fallback handling for restricted runtime environments
Best for
Grade newly developed AI skill packages before release, Audit existing skill directories for security flaws and secret leaks, Review SKILL.md metadata, trigger quality, and resource structure compliance, Generate actionable remediation reports for failing agent skills
Works with
Claude CodeCodex
Evoa Score breakdown= Σ (score × weight)
63Task 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%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%38 → +4.6
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%80 → +12.0
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%27 → +2.2
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%50 → +2.5
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 total73.6 / 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
The skill executes local Python scripts to inspect file structures and scan for potential secret leaks or credential disclosures within target directories.
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.