awesome-claude-code-plugins

Name: awesome-claude-code-plugins
Rating: 83 (1 reviews)
Author: ccplugins

MCP Server

ccplugins/awesome-claude-code-plugins

Facilitates structured multi-agent discussions and reviews by orchestrating various AI CLI tools to analyze proposals, challenge assumptions, and generate comprehensive decision reports.

910 357Apache-2.0Updated 2026-08-12

Great

View on GitHub Open source file

Overview

This skill acts as a meeting orchestrator, coordinating multiple specialized AI agents across different CLI providers (such as Codex, Claude Code, and others) to evaluate technical designs, business strategies, and product ideas. It enforces structured debate through multiple rounds of independent analysis and cross-examination, maintaining isolated agent workspaces, tracking state, and finally synthesizing the discussions into a robust Markdown decision report with full provenance.

Capabilities

▸Multi-agent discussion orchestration
▸Structured debate across specialized roles (builder, critic, architect, etc.)
▸Persistent session management for CLI agents
▸Automated synthesis of decision reports
▸Workspace and file isolation for secure agent execution

Best for

Conducting multi-agent technical architecture reviews, Running roundtable discussions on product feature proposals and business strategies, Challenging underlying assumptions in software design and project plans, Generating final decision logs with clear provenance and tracked evidence gaps

Works with

Claude CodeCodexCursorGemini CLICodex

Evoa Score breakdown= Σ (score × weight)

Task 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%80 → +6.4

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 total82.7 / 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

Treats all meeting materials as untrusted input and uses isolated workspaces to prevent unauthorized access or modification to the host project directory.