codex-team-mode
oil-oil/codex-team-mode
This skill coordinates complex development and research tasks by decomposing work and dispatching specialized subagents in parallel. It maintains strict control over subagent routing using specific roles like Explorer, Executor, and Reviewer.
96 9MITUpdated 2026-08-02
80
GreatOverview
Designed to optimize large-scale development, analysis, and content creation, this skill introduces a structured team mode for AI agents. It guides the main thread in evaluating when to parallelize work, ensuring proper context isolation, minimal coordination overhead, and targeted code reviews. By defining clear dispatch contracts and leveraging specialized subagent profiles, it enhances throughput and quality while keeping high-level architectural and acceptance decisions centralized.
Capabilities
- ▸Task decomposition and parallelism assessment
- ▸Subagent dispatch with strict role enforcement (Explorer, Executor, Reviewer)
- ▸File and resource ownership tracking for parallel writers
- ▸Structured code review and simplification workflows
- ▸Transient error recovery and verification management
Best for
Coordinating multi-module code implementations and refactoring, Running parallel exploratory research across disparate documentation or data sources, Executing structured multi-lens code reviews for significant pull requests, Isolating noisy or repetitive tasks into bounded subagent threads
Works with
Claude CodeCursorGitHub Copilot
Evoa Score breakdown= Σ (score × weight)
80Task 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%44 → +5.3
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%52 → +4.2
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%75 → +3.8
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 total79.8 / 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
Ensures subagents do not receive copied credentials and operate under the parent task's live permission boundaries.
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.