Token导航 LogoToken导航

Agent Skill · 研究检索

gcp-to-aws(GCP TO AWS 搜索)

用于辅助云资源、部署、容器、基础设施和运维自动化任务。它适合让 Agent 检查配置、整理部署步骤、分析资源状态、生成排障思路或辅助云服务接入。使用时需要明确目标环境、账号权限、区域和资源组,区分本地测试与生产操作;涉及删除资源、重启服务、修改网络或权限配置时,应先确认影响范围。

gcp-to-aws 是研究检索类 Agent Skill,可用宿主为 Codex、Claude、Cursor、Gemini CLI,通过GitHub 仓库获取,权限为调用外部服务;许可证信息还不明确,第三方扫描有未通过项,按安装量在研究检索类的 73,675 个 Skill 里排第 51,536。

总安装 582周安装 24GitHub Stars 634下载 190核验 2026-05-01

安装说明

本站只整理中文说明,不托管安装包,也不代用户安装。
GitHub
许可证
unknown

安装方式

通过对话安装

复制提示词发给支持本地命令或 Skills 的 AI 助手,先确认命令和权限,再让它执行。

请帮我安装这个 Agent Skill:gcp-to-aws(GCP TO AWS 搜索)
来源仓库:https://github.com/awslabs/agent-plugins
仓库路径:skills/gcp-to-aws
安装命令:
npx skills add https://github.com/awslabs/agent-plugins --skill gcp-to-aws
安装前请先检查当前环境是否支持对应 CLI,并向我确认将要执行的命令、安装目录、联网范围和文件读写权限;确认后再执行。

命令行安装

复制命令到本机终端执行。该命令会通过 npx skills 从第三方来源获取 Skill;本站只展示命令,不托管安装包,也不自动执行。

skills.shnpx skills
npx skills add https://github.com/awslabs/agent-plugins --skill gcp-to-aws

这个 Skill 是做什么的

研究检索类 Skill 主要解决「找资料、核对事实、把来源整理清楚」的问题,通常会让助手先检索再总结。

用于将 GCP 资源或服务迁移至 AWS 云平台。提供配置转换指南、API 映射和兼容性说明。通过 GitHub 安装,无需特殊权限即可获取迁移方案。网络拓扑和安全组规则需重新适配 AWS 模型。建议先在隔离环境验证迁移结果。gcp-to-aws 属于研究检索类 Skill,可作为该场景下的辅助能力补充。

来源仓库内路径:skills/gcp-to-aws

上手步骤

4 步
  1. 1

    确认自己的宿主工具

    公开资料标注支持 Codex、Claude、Cursor、Gemini CLI;先确认自己用的是其中之一,再按对应工具的 Skills 目录放置。

  2. 2

    拿到安装命令

    可以直接复制的命令是 npx skills add https://github.com/awslabs/agent-plugins --skill gcp-to-aws;命令里的占位符换成自己的路径或密钥再执行。

  3. 3

    安装后重启宿主

    命令执行完要完全退出宿主工具再打开,让新装的 Skill 被重新扫描到,否则列表里可能看不到。

  4. 4

    按最小权限试用

    它需要调用外部服务,先在测试目录或测试账号里跑,确认没问题再放到正式项目。

常见问题

6 条

gcp-to-aws 怎么安装?

在终端执行 npx skills add https://github.com/awslabs/agent-plugins --skill gcp-to-aws。装完完全退出宿主工具再打开,让它重新扫描本地 Skill。

gcp-to-aws 支持哪些 AI 工具?

公开资料标注支持 Codex、Claude、Cursor、Gemini CLI。其他工具只要能读取本地 Skill 目录,一般也能手动放进去,但要自己确认触发方式是否一致。

gcp-to-aws 需要什么权限?

权限级别是调用外部服务。该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

gcp-to-aws 是免费的吗?

公开资料没有标注明确许可证,收费和商用限制都无法确认。正式使用前请到来源仓库核对授权说明。

gcp-to-aws 用的人多吗?

公开数据是累计安装 582 次,近一周安装 24 次,下载 190 次,GitHub 634 星。这些数字来自第三方目录统计,只能当作热度参考,不代表质量或安全性。

gcp-to-aws 安全吗?

第三方扫描有未通过项,风险较高。除非你确认过源码,否则不建议直接安装到常用环境。

值得选的地方和要先想清楚的地方

值得选的地方

  • 同时适配 4 种工具,换客户端不用重新找替代品。

先想清楚的地方

  • 许可证没有明确标注,能不能商用、能不能再分发都不确定。
  • 第三方扫描存在提醒项或未通过项,需要人工逐条确认。
  • 第三方目录整理,版本更新和行为细节以来源仓库为准。

适不适合你

更适合

  • 已经在用 Codex,想直接扩展它能力的人。
  • 需要处理研究检索类任务、又不想每次都手写提示词的人。

不太适合

  • 需要明确授权才能用到公司项目里的场景。
  • 需要厂商级技术支持和 SLA 的生产系统。

研究检索类 Skill 对比

6 个同类
Skill总安装GitHub 星权限许可证扫描
find-skills

寻找技能 · Codex、Claude

31,199,81316,486操作浏览器MIT有提醒
self-improving-agent

自我改进 Agent · OpenClaw

16,464,0023,396接触敏感数据MIT-0通过
soultrace

灵魂追踪 · Codex、Claude

7,588,94412需要联网未明确有提醒
self-improving

自我完善 · OpenClaw

6,829,2841,046需要联网MIT-0通过
microsoft-foundry

微软代工厂 · Codex、Claude

6,614,144764调用外部服务未明确有提醒
gcp-to-aws

GCP TO AWS 搜索 · 本页

582634调用外部服务未明确未通过

按安装量取同分类前几名;数字来自第三方目录统计,只作热度参考,不代表质量结论。

SKILL.md 原文

GCP-to-AWS Migration Skill

Philosophy

  • Re-platform by default: Select AWS services that match GCP workload types (e.g., Cloud Run → Fargate, Cloud SQL → RDS).
  • Dev sizing unless specified: Default to development-tier capacity (e.g., db.t4g.micro, single AZ). Upgrade only on user direction.
  • Infrastructure-first approach: v1.0 migrates Terraform-defined infrastructure only. App code scanning and billing import are v1.1+.

Prerequisites

User must provide GCP infrastructure-as-code:

  • One or more .tf files (Terraform)
  • Optional: .tfvars or .tfstate files

If no Terraform files are found, stop immediately and ask user to provide them.

State Management

Migration state lives in .migration/[MMDD-HHMM]/ directory (created by Phase 1, persists across invocations):

.migration/
├── .gitignore                       # Auto-created to protect state files from git
└── 0226-1430/                       # MMDD-HHMM timestamp
    ├── .phase-status.json           # Current phase tracking
    ├── gcp-resource-inventory.json  # All GCP resources found
    ├── gcp-resource-clusters.json   # Clustered resources by affinity
    ├── clarified.json               # User answers (Phase 2 output)
    ├── aws-design.json              # AWS services mapping (Phase 3 output)
    ├── estimation.json              # Cost breakdown (Phase 4 output)
    └── execution.json               # Timeline + risks (Phase 5 output)

Note: The .migration/ directory is automatically protected by a .gitignore file created in Phase 1. Migration state files will not be accidentally committed to version control.

.phase-status.json schema:

{
  "phase": "discover|clarify|design|estimate|execute",
  "status": "in-progress|completed",
  "timestamp": "2026-02-26T14:30:00Z",
  "version": "1.0.0"
}

If .phase-status.json exists:

  • If status is completed: advance to next phase (discover→clarify, clarify→design, etc.)
  • If status is in-progress: resume from that phase

Phase Routing

  1. On skill invocation: Check for .migration/*/ directory

- If none exist: Initialize Phase 1 (Discover), set status to in-progress - If multiple exist: STOP. Output: "Multiple migration sessions detected in .migration/:" then for each directory, display its name and the contents of its .phase-status.json (phase + status). Output: "Pick one to continue: [list with phase info]" - If exists: Load .phase-status.json and validate: - If empty file (0 bytes): STOP. Output: "State file is empty. Delete .migration/[MMDD-HHMM]/.phase-status.json and restart." - If invalid JSON: STOP. Output: "State file corrupted (invalid JSON). Delete .migration/[MMDD-HHMM]/.phase-status.json and restart Phase [X]." - If missing required fields (phase, status, timestamp, version): STOP. Output: "State file incomplete (missing [field]). Delete and restart." - If version!= "1.0.0": STOP. Output: "Incompatible state file version: [version]. This skill requires version 1.0.0." - If unrecognized phase value: STOP. Output: "Unrecognized phase: [value]. Valid values: discover, clarify, design, estimate, execute." - If status not in {in-progress, completed}: STOP. Output: "Unrecognized status: [value]. Valid values: in-progress, completed." - If valid: Determine next action: - If phase status is in-progress: Resume that phase - If phase status is completed: Advance to next phase

  1. Phase transition mapping (when phase is completed):

- discover (completed) → Route to clarify - clarify (completed) → Route to design - design (completed) → Route to estimate - estimate (completed) → Route to execute - execute (completed) → Migration complete; offer summary and cleanup options

  1. Phase gate checks: If prior phase incomplete, do not advance (e.g., cannot enter estimate without completed design)

Phase Summary Table

PhaseInputsOutputsReference
Discover.tf filesgcp-resource-inventory.json, gcp-resource-clusters.json, .phase-status.json updatedreferences/phases/discover/discover.md
Clarifygcp-resource-inventory.json, gcp-resource-clusters.jsonclarified.json, .phase-status.json updatedreferences/phases/clarify.md
Designgcp-resource-inventory.json, gcp-resource-clusters.json, clarified.jsonaws-design.json, aws-design-report.md, .phase-status.json updatedreferences/phases/design.md
Estimateaws-design.json, clarified.jsonestimation.json, estimation-report.md, .phase-status.json updatedreferences/phases/estimate.md
Executeaws-design.json, estimation.jsonexecution.json, execution-timeline.md, .phase-status.json updatedreferences/phases/execute.md

MCP Servers

awspricing (for cost estimation):

  1. Call get_pricing_service_codes() to detect availability
  2. If success: use live AWS pricing
  3. If timeout/error: fall back to references/shared/pricing-fallback.json (includes 2026 on-demand rates for major services)

awsknowledge (for design validation):

  1. Use for regional availability checks (e.g., service available in target region?)
  2. Use for feature parity checks (e.g., do required features exist in AWS service?)
  3. Use for service constraints and best practices
  4. Fallback: if unavailable, set validation_status: "skipped" in aws-design.json with note in design report
  5. Important: Validation is informational; design proceeds either way (not blocking)

Error Handling

ConditionAction
No .tf files foundStop. Output: "No Terraform files detected. Please provide .tf files with your GCP resources and try again."
.phase-status.json missing phase gateStop. Output: "Cannot enter Phase X: Phase Y-1 not completed. Start from Phase Y or resume Phase Y-1."
awspricing unavailable after 3 attemptsDisplay user warning about ±15-25% accuracy. Use pricing-fallback.json. Add pricing_source: fallback to estimation.json.
User does not answer all Q1-8Offer Mode C (defaults) or Mode D (free text). Phase 2 completes either way.
aws-design.json missing required clustersStop Phase 4. Output: "Re-run Phase 3 to generate missing cluster designs."

Defaults

  • IaC output: None (v1.0 produces design, cost estimates, and execution plans — no IaC code generation)
  • Region: us-east-1 (unless user specifies, or GCP region → AWS region mapping suggests otherwise)
  • Sizing: Development tier (e.g., Aurora Serverless v2 0.5 ACU for databases, 0.5 CPU for Fargate)
  • Migration mode: Full infrastructure path (no AI-only subset path in v1.0)
  • Cost currency: USD
  • Timeline assumption: 8-12 weeks total

Workflow Execution

When invoked, the agent MUST follow this exact sequence:

  1. Load phase status: Read .phase-status.json from .migration/*/.

- If missing: Initialize for Phase 1 (Discover) - If exists: Determine current phase based on phase field and status value

  1. Determine phase to execute:

- If status is in-progress: Resume that phase (read corresponding reference file) - If status is completed: Advance to next phase (read next reference file) - Phase mapping for advancement: - discover (completed) → Execute clarify (read references/phases/clarify.md) - clarify (completed) → Execute design (read references/phases/design.md) - design (completed) → Execute estimate (read references/phases/estimate.md) - estimate (completed) → Execute execute (read references/phases/execute.md) - execute (completed) → Migration complete

  1. Read phase reference: Load the full reference file for the target phase.
  2. Execute ALL steps in order: Follow every numbered step in the reference file. Do not skip, optimize, or deviate.
  3. Validate outputs: Confirm all required output files exist with correct schema before proceeding.
  4. Update phase status: Each phase reference file specifies the final .phase-status.json update (records the phase that just completed).
  5. Display summary: Show user what was accomplished, highlight next phase, or confirm migration completion.

Critical constraint: Agent must strictly adhere to the reference file's workflow. If unable to complete a step, stop and report the exact step that failed.

User can invoke the skill again to resume from last completed phase.

Scope Notes

v1.0 includes:

  • Terraform infrastructure discovery (no app code scanning)
  • User requirement clarification (8 structured questions)
  • Structured Design (cluster-based mapping from Terraform)
  • AWS cost estimation (from pricing API or fallback)
  • Execution timeline and risk assessment

Deferred to v1.1+:

  • App code scanning (runtime detection of compute workload types)
  • AI-only fast-track path in Clarify/Design
  • Billing data import from GCP
  • Flat Design path (for non-Terraform codebases)

平台分布

Codex

35.23%
按下载量换算67

Claude

32.65%
按下载量换算62

Cursor

18.83%
按下载量换算36

Gemini CLI

9.98%
按下载量换算19

安全审计

Gen Agent Trust Hub

可疑

Socket

通过

Snyk

未通过

权限和风险

调用外部服务

该 Skill 可能调用第三方服务、云服务或外部模型 API,使用前需要确认账号、额度、数据发送范围和服务条款。

安装前确认

本站仅展示第三方公开信息,不托管安装包,不提供自动安装或运行环境。安装前应自行审查源码、依赖和命令行为。来源安全扫描存在提醒或未通过项,安装前请自行复核。目前只有一个公开来源,建议同时核对源仓库。

继续浏览同类 Skills