/ 目錄 / 演練場 / Spartan AI Toolkit
● 社群 spartan-stratos ⚡ 即開即用

Spartan AI Toolkit

作者 spartan-stratos · spartan-stratos/spartan-ai-toolkit

Engineering workflow commands with quality gates and TDD enforcement.

Spartan AI Toolkit is a no-nonsense skill bundle of engineering workflow commands: forced TDD red-green-refactor, quality gates (lint, test, type-check), and an opinionated agile loop. Built for teams that want discipline by default.

為什麼要用

核心特性

即時演示

實際使用效果

spartan-ai-toolkit-skill.replay ▶ 就緒
0/0

安裝

選擇你的客戶端

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "spartan-ai-toolkit-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/spartan-stratos/spartan-ai-toolkit",
        "~/.claude/skills/spartan-ai-toolkit"
      ],
      "_inferred": true
    }
  }
}

開啟 Claude Desktop → Settings → Developer → Edit Config。儲存後重啟應用。

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "spartan-ai-toolkit-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/spartan-stratos/spartan-ai-toolkit",
        "~/.claude/skills/spartan-ai-toolkit"
      ],
      "_inferred": true
    }
  }
}

Cursor 使用與 Claude Desktop 相同的 mcpServers 格式。專案級設定優先於全域。

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "spartan-ai-toolkit-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/spartan-stratos/spartan-ai-toolkit",
        "~/.claude/skills/spartan-ai-toolkit"
      ],
      "_inferred": true
    }
  }
}

點擊 Cline 側欄中的 MCP Servers 圖示,然後選 "Edit Configuration"。

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "spartan-ai-toolkit-skill": {
      "command": "git",
      "args": [
        "clone",
        "https://github.com/spartan-stratos/spartan-ai-toolkit",
        "~/.claude/skills/spartan-ai-toolkit"
      ],
      "_inferred": true
    }
  }
}

格式與 Claude Desktop 相同。重啟 Windsurf 生效。

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "spartan-ai-toolkit-skill",
      "command": "git",
      "args": [
        "clone",
        "https://github.com/spartan-stratos/spartan-ai-toolkit",
        "~/.claude/skills/spartan-ai-toolkit"
      ]
    }
  ]
}

Continue 使用伺服器物件陣列,而非映射。

~/.config/zed/settings.json
{
  "context_servers": {
    "spartan-ai-toolkit-skill": {
      "command": {
        "path": "git",
        "args": [
          "clone",
          "https://github.com/spartan-stratos/spartan-ai-toolkit",
          "~/.claude/skills/spartan-ai-toolkit"
        ]
      }
    }
  }
}

加入 context_servers。Zed 儲存後熱重載。

claude mcp add spartan-ai-toolkit-skill -- git clone https://github.com/spartan-stratos/spartan-ai-toolkit ~/.claude/skills/spartan-ai-toolkit

一行命令搞定。用 claude mcp list 驗證,claude mcp remove 移除。

使用場景

實戰用法: Spartan AI Toolkit

Force a coding agent into actual TDD discipline

👤 Teams whose agents skip tests ⏱ ~15 min intermediate

何時使用: Your agent keeps writing code first and tests later (or never).

前置條件
  • Server/skill installed and authenticated — See repo README
步驟
  1. Enable the gate
    Activate spartan-ai-toolkit. Set the TDD gate to strict.✓ 已複製
    → Gate registered
  2. Try to skip
    Add a new feature without a test first.✓ 已複製
    → Gate refuses; demands a failing test

結果: Real TDD instead of theater.

注意事項
  • Hard gates can frustrate exploratory work. Toggle to 'soft' during spikes; 'strict' on main branches. — Hard gates can frustrate exploratory work. Toggle to 'soft' during spikes; 'strict' on main branches.

成本與限制

運行它的成本

API 配額
See provider docs for rate limits
每次呼叫 Token 數
Varies by tool
費用
See repo README for pricing details
提示
Cache tool results and avoid repeated identical calls.

安全

權限、密鑰、影響範圍

憑證儲存: Use environment variables; never commit secrets
資料出站: Tool calls go to the provider's API as documented

故障排查

常見錯誤與修復

gate flags an unrelated change as missing tests

Tune gate scope in spartan.config — exclude refactors with no semantic change.

驗證: Re-run with scope changes
quality gate too slow

Profile which step is slow (usually type-check on big repos). Cache or skip locally.

驗證: Per-step timings printed

替代方案

Spartan AI Toolkit 對比其他方案

替代方案何時用它替代權衡
agent-skill-tddYou want a lighter touchAdvisory, not enforcing

更多

資源

📖 閱讀 GitHub 上的官方 README

🐙 查看未解決的 issue

🔍 瀏覽全部 400+ MCP 伺服器和 Skills