agent-skills
andreasasprou/agent-skills
A curated collection of plugins for Claude Code that provides advanced AI consultation, destructive command blocking, and dependency source code exploration.
7 3MITUpdated 2026-06-21
70
GoodOverview
This marketplace package extends AI coding agents with specialized tools to improve development safety, code quality, and technical decision-making. It includes an oracle plugin for architectural consulting via external models and internal codebase analysis, a safety net hook that intercepts and blocks over 200 dangerous commands across cloud and database providers, and a utility to easily fetch and inspect npm package source code for deep debugging.
Capabilities
- ▸Strategic technical consulting via dual repo and web modes
- ▸Pre-execution interception and blocking of destructive CLI and database commands
- ▸Automated detection of dangerous patterns across AWS, GCP, Azure, Kubernetes, Docker, and Terraform
- ▸Fetching and managing npm package source code for deep audits
Best for
Consulting AI models on architectural choices, library comparisons, and security guidelines., Preventing accidental data loss, dropped databases, or destructive cloud infrastructure commands., Inspecting the internal implementation details of npm dependencies when type definitions are insufficient.
Works with
Claude Code
Evoa Score breakdown= Σ (score × weight)
70Task 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%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%29 → +2.3
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%25 → +1.3
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 total70.3 / 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
Includes a safety-net plugin designed to block potentially catastrophic shell commands and database mutations, enhancing the security posture of autonomous agent workflows.
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.