
volcengine-landing-zone
Use when the user asks to analyze, consult, setup, manage, configure, or design a Volcengine Landing Zone, including organization, accounts, finance, identity, cloudtrail, or network infrastructure, or to deploy a solution/blueprint.
- Installs
- 83
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/volcengine/volcengine-agent-toolkit --skill volcengine-landing-zone- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads volcengine-landing-zone automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Volcengine Landing Zone
This skill supports consulting, analysis, setup, and management tasks for a Volcengine Landing Zone, including organization design, account structure, finance relationships, identity, audit, and network foundations.
For clarity, the skill is organized as an intent router plus shared playbooks and path-specific guidebooks.
Path Anchors (Resolve Once Before Any Real Execution)
Relative paths in this skill such as ./skills/volcengine-landing-zone/... and
./volcengine-landing-zone-workspace/... are not relative to an arbitrary current working directory.
Resolve them through these two anchors once, then reuse them throughout the run:
SKILL_ROOT: the absolute install root of this skill, which contains thisSKILL.md. Read-only assets such as built-in blueprints, HTML templates,tos_activate.py, andbaseline.schema.jsonlive here. Any./skills/volcengine-landing-zone/<x>path resolves to${SKILL_ROOT}/<x>.WORKSPACE_ROOT: the writable runtime root for this run. By default it is<current working directory>/volcengine-landing-zone-workspace/, unless the user explicitly provides another writable location. Execution copies, output files, and baseline runtime state all live here. Any./volcengine-landing-zone-workspace/<x>path resolves to${WORKSPACE_ROOT}/<x>.${WORKSPACE_ROOT}/confirmed-architecture.json: the complete versioned architecture confirmed under G1. The default and custom branches both materialize this file; it is the single source of user design intent.${WORKSPACE_ROOT}/landing-zone-context.json: the filtered, non-sensitive Phase 01 hand-off contract. It is a rebuildable cache derived from the confirmed architecture and actual Phase 01 Terraform outputs, not another resource state.
Use the resolved absolute paths for all later reads and writes. Do not rely on process cwd.
Local File Display
When a user-facing file must be delivered, choose the most appropriate method supported by the current agent client and runtime so the user can access the actual file. Keep generated or copied artifacts under ${WORKSPACE_ROOT} and never modify read-only skill assets. Do not expose sensitive file contents in chat or start a listening service solely to display a file. G1 and G4 govern any required confirmation or pause.
Entry Routing (Intent Router)
Once volcengine-landing-zone is activated, it must automatically route into the main path that matches the user's intent. Do not start by asking the user to choose a path. Ask a follow-up only when multiple paths truly match at the same time, or when the minimum information required to continue is missing.
| Trigger semantics | Route into |
|---|---|
landing zone 的方案/理念/最佳实践/阶段价值/实施顺序/组织设计建议/账号规划建议/是否值得做/怎么落地 | Consulting and Solution Design |
明确要求搭建/初始化/重构企业 Landing Zone 架构,或按 Landing Zone 建立/调整组织、OU、核心账号、财务、身份、审计、共享网络基础 | Initial Landing Zone Setup |
新增账号、开账号、创建账号、baseline、应用 baseline、设置基线、创建 baseline | Account Creation and Baseline Setup |
部署具体解决方案/蓝图、部署这个 git 仓库/本地目录/内置包、按需求生成 IaC 并部署、部署网络/安全/数据/应用方案 | Solution Deployment |
失败恢复、失败重试、修复失败执行、上次执行报错 | Failure Recovery |
Handling principles:
- The user does not need to understand directory layout, phase numbers, or blueprint structure first. The agent should directly take ownership of the goal and do the necessary reference reading and execution preparation.
Create baselineandapply baselineare not listed as a separate first-screen path, but if the user asks for them directly, take the request as-is and do not push them back into path selection.- Route by the requested outcome, not by product or resource terms. Names such as VPC, network, identity, or logging do not by themselves imply
Initial Landing Zone Setup. - Enter
Initial Landing Zone Setuponly for an explicit request to establish or reconfigure the enterprise Landing Zone architecture or foundation. EnterSolution Deploymentfor a concrete deployable solution or package, even when it manages resources also used by Landing Zone phases. - If the request could reasonably match both paths or the intended outcome is unclear, ask one clarification question before routing. Do not trigger G1 or deliver the Landing Zone setup confirmation file while the route is unresolved.
User-Facing Communication
- Use business language and adapt the response to the current task. Default to conclusions, material impact, and the next useful action; expose commands, paths, state details, or orchestration mechanics only when the user asks or troubleshooting requires them.
- Resolve safe defaults and discoverable values from the confirmed design and live read-only state. Ask only for inputs that cannot be derived reliably and are required for the current step; group related questions instead of turning the workflow into a field-by-field interview.
- When permitted by the hard gates, keep discovery, preflight, workspace preparation, and plan generation in the background. Do not request confirmation for read-only preparation; G2 governs authorization for cloud writes.
- Use a natural response structure rather than a fixed status template. Clearly distinguish completed work, blockers, material follow-up, and the next action when those distinctions are relevant.
Hard Gates Before Any Real Execution
These gates protect user decisions and cloud state. Keep them strict; adapt the surrounding conversation naturally.
G1. Solution Confirmation (Initial Landing Zone Setup)
- G1 applies only after routing has conclusively selected
Initial Landing Zone Setup; skill activation or mention of organization/network resources is not sufficient. Then deliver${SKILL_ROOT}/assets/html/landing-zone-solution-plan.html, ask the user to confirm the recommended architecture or request changes, and wait. Do not begin preflight or cloud operations first. - A direct confirmation selects
recommended-v1. Resolve only missing execution settings, materialize the complete design as${WORKSPACE_ROOT}/confirmed-architecture.json, validate it against contract.schema.json, and record its exact SHA-256. - For requested changes, apply only the business differences to
recommended-v1, generate the complete architecture JSON and its Markdown projection, deliver the Markdown, and obtain confirmation of that actual design. The user should not need to author internal keys or Terraform objects. - Any later change to the confirmed architecture bytes invalidates G1 and requires the updated design to be displayed and confirmed again.
G2. Phase Confirmation (Every Deployment Task / Phase)
- Before each cloud-writing phase, complete all permitted read-only discovery, reconciliation, state inspection, initialization, and planning. Present the resolved targets, target-to-identity strategy, and material create, update, replace, delete, and non-Terraform write impact, then obtain explicit confirmation.
- A confirmation authorizes only the saved plan and listed CLI/API writes for that phase. It does not carry into another phase or task. Any change to the target, inputs, blueprint revision, confirmed architecture digest, write set, or saved plan requires a new confirmation.
- After confirmation, execute all covered writes continuously without per-resource prompts.
01-organizationthrough05-networkare separate phases; account creation and baseline application are separate phases; one Solution Deployment is one phase.
G3. Workspace Isolation
Trigger: any Terraform or write action.
Action: real execution happens only inside ${WORKSPACE_ROOT}/ (that is, ./volcengine-landing-zone-workspace/). See the path anchors above.
Forbidden: do not execute from or write back into ${SKILL_ROOT}/assets/blueprints/. Built-in blueprint sources are always read-only.
Self-check: am I running from a workspace copy under ${WORKSPACE_ROOT}, rather than from the built-in blueprint source? If not, stop.
G4. File Review Pause
Trigger: a phase produces a local file that the user needs to view, such as an initial password, login information, or a summary report. Action: deliver the actual file using the Local File Display rule above, tell the user to review it, and pause there waiting for the next instruction. Forbidden: do not skip the pause because you want to show multiple files later together. G2 does not exempt this pause. Do not echo the full initial password in chat, and do not replace file delivery with a text restatement. Self-check: after producing a sensitive or user-review file, have I opened or delivered it according to the display protocol and then stopped? If not, stop.
G5. Consulting Is Read-Only
Trigger: the user intent is consulting, design, evaluation, or learning about concepts, ordering, or value. Action: provide explanation and recommendations only. Forbidden: do not run preflight, do not start credential setup, do not run Terraform, and do not perform any write action, even if it would be convenient. Self-check: has the user clearly asked for real execution? If not, explain only and do not act.
Always design and implement against the official Volcengine Landing Zone methodology.
Paths
Consulting and Solution Design
- Use this path when the user wants to understand concepts, phase value, rollout order, organization design suggestions, or a practical landing path before real execution.
Initial Landing Zone Setup
- Complete G1 before following the execution flow in guidebook.md. Apply G2 to each cloud-writing phase.
- Phase-specific instructions:
- 01-organization.md
- 02-finance.md
- 03-identity.md
- 04-log.md
- 05-network.md
Account Creation and Baseline Setup
- The overall execution flow is in guidebook.md.
- Account creation and baseline application have separate plans and G2 confirmations.
Solution Deployment
- The overall execution flow is in guidebook.md.
- Use this path to validate and deploy a solution package. Apply G2 after the targets, source revision, and actual impact are resolved.
Failure Recovery
- The recovery flow is in failure-recovery.md.
- Use this path for recovery of
landing-zone-setup,account-factory account create,account-factory baseline apply, andsolution-deploymentfailures.
Reference Files
Soft vs. hard layering: all hard execution requirements such as solution confirmation, phase-scoped authorization, workspace isolation, file pause, and read-only consulting are defined only by G1-G5 above. The reference files below contain only path-specific details and should reference hard-gate numbers instead of restating the rules.
- Mechanical preflight checks: preflight-checks.md
- Landing Zone setup: guidebook.md
- Account factory workflow: guidebook.md
- Solution deployment workflow: guidebook.md
- Failure recovery: failure-recovery.md
- Landing Zone runtime contract: contract.schema.json
FAQ
What does the volcengine-landing-zone skill do?
Use when the user asks to analyze, consult, setup, manage, configure, or design a Volcengine Landing Zone, including organization, accounts, finance, identity, cloudtrail, or network infrastructure, or to deploy a solution/blueprint.
How do I install volcengine-landing-zone?
Run npx skills add https://github.com/volcengine/volcengine-agent-toolkit --skill volcengine-landing-zone in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/volcengine-landing-zone/ (personal) or .claude/skills/volcengine-landing-zone/ (project).
Which AI agents can use volcengine-landing-zone?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is volcengine-landing-zone safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains volcengine-landing-zone?
It is published by volcengine in volcengine/volcengine-agent-toolkit. It has 83 recorded installs.
More from volcengine/volcengine-agent-toolkit
volcengine-cli
volcengine/volcengine-agent-toolkit
Create and manage Volcengine cloud resources using the Volcengine CLI (ve command). Supports all Volcengine services including ECS, VPC, CLB, RDS, Redis, and more. Trigger this skill whenever the user asks to create, query, modify, or delete cloud resources on Volcengine, mentions the ve command, says "volcengine CLI", or describes infrastructure tasks such as "create an ECS instance", "set up a VPC", "list security groups", "allocate an EIP". Also trigger on Chinese prompts mentioning "火山引擎" or "火山" (e.g., "火山引擎上有哪些 ECS"、"查一下我火山的云服务器"、 "火山引擎创建一个 VPC"、"火山的 Redis 实例列一下"). Also trigger when the user encounters errors from ve commands and needs troubleshooting help. Also use for TOS bucket/object operations, tosutil (sometimes written tosutils), Ark CLI / arkcli model discovery, inference, generation, endpoints, fine-tuning, plans, or usage, and TLS (日志服务) / volclog log search, analysis, ingest, export, or LogCollector collection, through ve tosutil, ve arkcli and ve volclog.
volcengine-tosutil
volcengine/volcengine-agent-toolkit
Open the skill to read its SKILL.md instructions.
volcengine-knowledge-search
volcengine/volcengine-agent-toolkit
使用 ve docs search/fetch 检索火山引擎官方文档并获取全文。Use when 用户咨询火山引擎产品的概念、用法、计费规则、部署步骤、最佳实践或服务条款,或提供 www.volcengine.com/docs/、docs.volcengine.com/docs/ 链接需要阅读正文时。
volcengine-api
volcengine/volcengine-agent-toolkit
Query and answer questions about Volcengine API specifications. Use when the user asks about API parameters, error codes, request methods, enum values, required fields, response structures, pagination, parameter dependencies, service capability lists, API availability, or API comparisons, even if they do not explicitly say "API". Typical intent includes checking what an action supports, which fields are required, what values a parameter accepts, why an API returns a specific error, how to pass nested or body parameters, how pagination works, what an API response contains, whether a batch operation exists, what services or versions expose an operation, or how two APIs differ. Use API Explorer data as the authoritative source and preserve constraints, examples, and caveats found in the spec. Answer in Chinese or English. When the user needs runnable SDK code, language-specific examples, or SDK configuration, hand off to volcengine-sdk-generator. When they need CLI operations, hand off to
volcengine-troubleshooting
volcengine/volcengine-agent-toolkit
Open the skill to read its SKILL.md instructions.
volcengine-find-skills
volcengine/volcengine-agent-toolkit
List, select, and install Volcengine skills from the volcengine-skills marketplace. Use when a user asks which Volcengine skill or plugin handles a task, wants to browse every available skill, needs an optional skill that is not currently installed, or asks to install or check the installation status of a Volcengine skill. Also use to discover any core skill, including this finder. Use as a fallback during a Volcengine operation when the currently loaded or installed skills cannot cover the required product, tool, or workflow; inspect the full catalog, select the missing capability, and install it.
Popular devops & cloud skills
microsoft-foundry
microsoft/azure-skills
Build, deploy, evaluate, optimize, fine-tune, and manage Microsoft Foundry agents, models, and resources end to end. USE FOR: foundry, azd ai agent, azd provision/deploy, hosted agent scaffold/develop/run/deploy/troubleshoot, prompt agent create, managed harness agent create, GitHub Copilot harness agent, create agent, update agent, add tool to agent, invoke agent, agent insights, evaluate agent, batch eval, continuous eval, continuous monitoring, agent CI/CD, optimize prompt, improve prompt, optimize agent instructions, Agent Optimizer scaffold, dataset curation from traces, deploy model, model fine-tuning (SFT/DPO/RFT), Foundry project, RBAC, role assignment, permissions, quota, capacity, region, deployment failure, AI Services, create Foundry resource, knowledge index, customize deployment, onboard, availability, training-data, grader, distillation, large file upload. DO NOT USE FOR: Azure Functions, App Service, general Azure deploy (use azure-deploy), general Azure prep (use azure
azure-diagnostics
microsoft/azure-skills
Debug Azure production issues on Azure using AppLens, Azure Monitor, resource health, and safe triage. WHEN: debug production issues, troubleshoot app service, app service high CPU, app service deployment failure, troubleshoot container apps, container app 503 or target port mismatch, troubleshoot functions, function telemetry missing or stopped after a config/connection-string change, troubleshoot AKS, VM RDP, Linux SSH, VM black screen, can't connect to VM, reset VM password, NSG or firewall blocking, kubectl cannot connect, kube-system/CoreDNS failures, pod pending, crashloop, node not ready, upgrade failures, analyze logs, KQL, insights, image pull failures, cold start issues, health probe failures, resource health, root cause of errors, troubleshoot event hubs, troubleshoot service bus, messaging SDK error, AMQP connection failure, message lock lost, lock renewal during long-running processing, service bus dead letter.
azure-prepare
microsoft/azure-skills
Prepare azd-based Azure projects for deployment: generates azure.yaml, infrastructure (Bicep/Terraform), and Dockerfiles for the Azure Developer CLI (azd) workflow. USE ONLY when the user explicitly wants to use azd as the deployment tool, or the project already has an azure.yaml file. DO NOT USE FOR: non-azd deployments, Python App Service code-only deploys (use python-appservice-deploy), or cross-cloud migration (use azure-cloud-migrate). WHEN: prepare app for azd, create azure.yaml, set up azd infrastructure, modernize app for Azure with azd, deploy with azd, function app, timer trigger, service bus trigger, event-driven function, managed identity, generate Bicep, generate Terraform, create and deploy to Azure.
azure-ai
microsoft/azure-skills
Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech.
azure-deploy
microsoft/azure-skills
Execute Azure deployments for ALREADY-PREPARED applications that have existing .azure/deployment-plan.md and infrastructure files. DO NOT use this skill when the user asks to CREATE a new application — use azure-prepare instead. This skill runs azd up, azd deploy, terraform apply, and az deployment commands with built-in error recovery. Requires .azure/deployment-plan.md from azure-prepare and validated status from azure-validate. WHEN: "run azd up", "run azd deploy", "execute deployment", "push to production", "push to cloud", "go live", "ship it", "bicep deploy", "terraform apply", "publish to Azure", "launch on Azure". DO NOT USE WHEN: "create and deploy", "build and deploy", "create a new app", "set up infrastructure", "create and deploy to Azure using Terraform" — use azure-prepare for these.
azure-validate
microsoft/azure-skills
Pre-deployment validation for Azure readiness. Run deep checks on configuration, infrastructure (Bicep or Terraform), RBAC role assignments, managed identity permissions, and prerequisites before deploying. WHEN: validate my app, check deployment readiness, run preflight checks, verify configuration, check if ready to deploy, validate azure.yaml, validate Bicep, test before deploying, troubleshoot deployment errors, validate Azure Functions, validate function app, validate serverless deployment, verify RBAC roles, check role assignments, review managed identity permissions, what-if analysis, validate Container Apps deployment.