/ ディレクトリ / プレイグラウンド / terrashark
← 全サーバー ↗ GitHub
● コミュニティ LukasNiessen ⚡ 即起動

terrashark

作者 LukasNiessen · LukasNiessen/terrashark

Terraform skill that actually follows HashiCorp best practices — eliminates LLM hallucinations with grounded, modular IaC.

TerraShark prevents the common Claude failure mode of hallucinated Terraform resource arguments by grounding generation in official HashiCorp best practices. Biases toward modular code, sensible state layout, and security defaults. Good for greenfield IaC and for fixing up LLM-generated Terraform that doesn't terraform plan cleanly.

▶ デモを見る 📦 インストール 💡 ユースケース

なぜ使うのか

主な機能

ライブデモ

実際の動作

terrashark-skill.replay ▶ 準備完了
0/0

インストール

クライアントを選択

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

Claude Desktop → Settings → Developer → Edit Config を開く。保存後、アプリを再起動。

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

Cursor は Claude Desktop と同じ mcpServers スキーマを使用。プロジェクト設定はグローバルより優先。

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

Cline サイドバーの MCP Servers アイコンをクリックし、"Edit Configuration" を選択。

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

Claude Desktop と同じ形式。Windsurf を再起動して反映。

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

Continue はマップではなくサーバーオブジェクトの配列を使用。

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

context_servers に追加。保存時に Zed がホットリロード。

claude mcp add terrashark-skill -- git clone https://github.com/LukasNiessen/terrashark ~/.claude/skills/terrashark

ワンライナー。claude mcp list で確認、claude mcp remove で削除。

ユースケース

実用的な使い方： terrashark

How to scaffold a production-grade AWS VPC module

👤 Platform engineers starting a new environment ⏱ ~45 min intermediate

使うタイミング： Day one of a new AWS account; you want a VPC module that won't embarrass you in 6 months.

前提条件
  • Skill installed — git clone https://github.com/LukasNiessen/terrashark ~/.claude/skills/terrashark
  • terraform CLI 1.6+ — brew install terraform
フロー
  1. Generate module
    Use terrashark. AWS VPC module, 3 AZs, public + private + db subnets, NAT gateways per AZ, flow logs on.✓ コピーしました
    → Module with variables.tf, main.tf, outputs.tf — no hallucinated args
  2. Add security defaults
    Ensure default security group denies all, flow logs go to CloudWatch with KMS-CMK encryption.✓ コピーしました
    → Security group + logging + KMS wired
  3. Validate
    Run terraform init + validate + plan with example tfvars.✓ コピーしました
    → Clean plan output, no errors

結果： A VPC module that terraform validates clean and follows AWS best practices.

注意点
  • LLM suggests deprecated aws_vpc_endpoint arg — TerraShark grounds in current docs; if drift still happens, ask it to cite the HashiCorp page
  • Module too monolithic — Ask for split: networking module vs. endpoints module separately
組み合わせ： aws-skill

Fix LLM-generated Terraform that doesn't plan

👤 Engineers cleaning up AI-generated IaC ⏱ ~20 min intermediate

使うタイミング： Another LLM gave you Terraform that looks reasonable but terraform plan fails on unknown arguments.

フロー
  1. Point at the broken file
    terraform plan fails on modules/rds. Use terrashark to fix each invalid argument with the current correct form.✓ コピーしました
    → Per-error fix with HashiCorp doc reference
  2. Validate
    Re-run plan; if any errors remain, iterate.✓ コピーしました
    → Clean plan

結果： A file that plans clean.

Design a remote state layout for multi-env

👤 Teams graduating from local state ⏱ ~60 min advanced

使うタイミング： You have dev + staging + prod and one giant terraform.tfstate.

フロー
  1. Propose layout
    Design S3 remote backend with per-env state files and DynamoDB locking. 3 envs.✓ コピーしました
    → Backend config per env with key separation + locking
  2. Migration plan
    Plan the migration from a single local state to this layout, step by step.✓ コピーしました
    → terraform state mv steps + safety checkpoints

結果： A state layout you can migrate to without losing state.

注意点
  • Accidentally deleting state during migration — Always pull and back up state files before any mv operation

組み合わせ

他のMCPと組み合わせて10倍の力を

terrashark-skill + aws-skill

AWS skill sizes architecture, TerraShark implements IaC

Design the architecture with aws-skill, implement as Terraform with terrashark.✓ コピーしました
terrashark-skill + claude-code-owasp-skill

Security-review the generated IaC

After terrashark scaffolds the module, run OWASP security review on the IAM and networking blocks.✓ コピーしました

ツール

このMCPが提供する機能

ツール入力呼び出すタイミングコスト
Module scaffolding provider, resource shape Greenfield IaC Claude tokens
Hallucination fix tf file + error log Cleaning up AI-generated TF Claude tokens
State layout design envs, team shape Multi-env setups Claude tokens
Security defaults - Pre-prod review Claude tokens

コストと制限

運用コスト

APIクォータ
None
呼び出しあたりのトークン
10-30k per module
金額
Free
ヒント
Generate module by module, not whole environment in one shot.

セキュリティ

権限、シークレット、影響範囲

認証情報の保管： No credentials. TerraShark doesn't run terraform apply itself.
データ送信先： Prompts go to Claude. Terraform plan/apply hits your cloud provider using your local creds.

トラブルシューティング

よくあるエラーと対処法

terraform validate fails on unknown argument

Ask TerraShark to reconcile against the current provider doc URL; provider version may be newer than the skill's prompt context.

確認： terraform providers
Plan creates unwanted destroys

Usually state-drift or implicit renaming. Run terraform plan -target to isolate before apply.

代替案

terrashark 他との比較

代替案代わりに使う場面トレードオフ
Hand-writing with official docs openYou know the provider deeplySlower

その他

リソース

📖 GitHub の公式 README を読む

🐙 オープンな issue を見る

🔍 400以上のMCPサーバーとSkillsを見る