sionic-maestro-skills
sionic-ai/sionic-maestro-skills
An advanced multi-LLM orchestration workflow based on recent agent systems research, implementing a 5-stage coding process controlled by Claude Code as the central orchestrator.
48 4No licenseUpdated 2026-06-10
58
FairOverview
This skill implements a centralized consultation architecture where Claude Code acts as the primary agent handling tool execution, while sub-agents like Codex and Gemini provide textual advice and insights. It uses a structured 5-stage workflow consisting of example analysis, hypothesis generation, implementation, iterative debugging, and recursive improvement, while incorporating human-in-the-loop approvals and measured coordination limits to prevent error amplification.
Capabilities
- ▸Multi-LLM orchestration and consultation
- ▸Structured 5-stage coding workflow execution
- ▸Human-in-the-loop (HITL) approvals per workflow stage
- ▸Ensemble candidate generation and testing-first selection
- ▸Workflow state tracking and metrics evaluation
Best for
Debugging complex software issues requiring diverse model perspectives, Refactoring codebases with multi-model validation and verification tests, Running comprehensive code reviews and security audits with ensemble feedback
Works with
Claude Code
Evoa Score breakdown= Σ (score × weight)
58Task 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%33 → +4.0
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%50 → +7.5
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%44 → +3.5
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 total68.6 / 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 manages multiple external LLM providers and executes code modifications. Ensure appropriate API keys are secured and review all file edits and test executions during the implementation stage.
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.