unicorn-team
aj-geddes/unicorn-team
A comprehensive Claude Code plugin that encodes advanced software engineering expertise into a coordinated team of 6 specialized agents and 15 composable skills.
Overview
Unicorn Team bridges the gap between basic AI coding assistants and expert software engineering by handling complex development workflows. It features cost-aware model tiering, MCP-aware routing, long-running task orchestration, strict test-driven development protocols, and multi-agent workflows for reviews, features, and research.
Capabilities
- ▸Cost-aware model tiering across haiku, sonnet, opus, and fable
- ▸MCP-aware tool and server routing
- ▸Multi-agent workflow fan-out for reviews, features, and research
- ▸Long-running task orchestration with loop-assist quality gates
- ▸Strategic code reading and legacy comprehension protocols
Best for
Executing complex multi-agent feature implementation, Running automated adversarial code reviews and security analysis, Conducting strategic code comprehension and legacy code refactoring, Managing long-horizon coding tasks with durable checkpoints
Works with
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
実装・指示の品質。 — AIによるSKILL.md/README解析
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
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
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
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
コミュニティの採用度。 — GitHub Stars/Forks(対数スケール)
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
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
Implements STRIDE threat modeling, multi-layer code review, and QA verification gates to ensure code safety and security compliance.
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.