agentsclimarketplace

Magi test

Skill weiting-tw/MAGI-System/skills/magi-test

MAGI System — Inspired by Evangelion's MAGI supercomputer. Three AI engines (Claude, Gemini, Codex) analyze tasks in parallel, then reach consensus through voting. A Claude Code skills plugin.

Install
npx -y skills add weiting-tw/MAGI-System --skill magi-test

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • no licenseNo license file was found in the repository. Code published without one is not open source by default, so using it at work is a question for whoever answers licensing questions where you are.
  • 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

三機(Claude/Gemini/Codex)平行審查測試,評估覆蓋率、邊界條件、異常處理後投票共識

SKILL.md

1.7 KB, 686 tokens by cl100k_base, as published. Nobody here has run it

MAGI Test 快捷指令

/magi-test [feature] - 測試覆蓋評估

此指令為 /magi test [feature] 的快捷方式。

使用方式

/magi-test 用戶登入功能
/magi-test src/services/payment.ts

執行內容

自動啟動 MAGI 三機平行分析:

機體引擎分析重點
MELCHIOR-1Claude Sonnet測試策略、覆蓋完整性
BALTHASAR-2Gemini Flash測試品質、Mock 使用合理性、測試隔離性
CASPER-3Codex/GPT安全測試覆蓋、負面測試、邊界條件

🚨 強制執行規則

<MANDATORY> 執行此指令時,必須嚴格遵守以下規則:

禁止事項:

  • ❌ 禁止委派給其他 agent 處理
  • ❌ 禁止使用非指定的工具

必須使用:

  • ✅ MELCHIOR-1: Task tool with subagent_type="general-purpose", model="sonnet"
  • ✅ BALTHASAR-2: mcp__gemini__ask-gemini (先用 ToolSearch 載入)
  • ✅ CASPER-3: mcp__codex-cli__ask-codex (先用 ToolSearch 載入)

執行步驟:

  1. 先以單一 ToolSearch 載入 MCP 工具:ToolSearch(query="select:mcp__gemini__ask-gemini,mcp__codex-cli__ask-codex")
  2. 單一訊息中同時發出三個 tool calls(Task + Gemini + Codex)
  3. 等待三機回應後彙整共識報告 </MANDATORY>

模型設定(test 任務)

機體模型參數
MELCHIOR-1sonnet-
BALTHASAR-2gemini-3-flash-preview-
CASPER-3gpt-5.2-codexreasoningEffort: "medium"

完整的投票機制與共識報告格式,見主 skill magiskills/SKILL.md)。

What ships with it

Read from the repository

Just SKILL.md. No reference files, no scripts.

Keep looking

Skills are one crate of 326,984. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.