pomasa
eXtremeProgramming-cn/pomasa
POMASA is a pattern language and generator toolkit used to rapidly build declarative multi-agent systems guided by established architectural patterns. It enables AI assistants to construct structured agent pipelines, research workflows, and knowledge bases following specific design blueprints.
48 12No licenseUpdated 2026-07-18
68
GoodOverview
POMASA (Pattern-Oriented Multi-Agent System Architecture) functions as an architectural generator for multi-agent workflows. It guides AI agents through requirements gathering, pattern selection, and file generation to produce fully runnable declarative multi-agent systems with predefined orchestrators, worker agents, reference materials, and output pipelines.
Capabilities
- ▸Declarative multi-agent system generation
- ▸Interactive requirements gathering via files or conversation
- ▸Architectural pattern selection based on project needs
- ▸Agent blueprint creation following prompt-defined standards
- ▸Provenance and metadata embedding for standalone execution
Best for
Building automated multi-agent research pipelines for complex topics, Generating scaffolded multi-agent system project directories with declarative blueprints, Orchestrating specialized worker agents through structured execution flows and data buses
Works with
Claude CodeCodexChatGPTGemini CLICursorGitHub CopilotOpenCode
Evoa Score breakdown= Σ (score × weight)
68Task 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%39 → +4.7
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%47 → +3.8
コミュニティの採用度。 — GitHub Stars/Forks（対数スケール）
Compatibility5%100 → +5.0
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 total80.0 / 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 generated multi-agent systems operate within local filesystems and execute standard agent prompts, requiring standard caution regarding generated code execution.
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.