Oke Cluster Generator by oracle — AI Skill for Any LLM

Overview

Publisher	oracle
Repository	`skills`
Skill name	`oke-cluster-generator`
Stars	879
Forks	251
Bundled files	5
License	UPL-1.0
Links	Skill source Repository

Markdown instructions

A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

Works with any LLM

AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

5 bundled files

Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

Open source

Published by oracle on GitHub. Read the source before you install it.

Installation

Install the Oke Cluster Generator AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

Open the app and go to Plugins → Skills.
Choose "Install from GitHub".
Paste the skill folder URL below and confirm.
https://github.com/oracle/skills/tree/main/oci/oke/skills/oke-cluster-generator
Enable the skill in any chat where you want it available.

Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills

git clone --depth 1 https://github.com/oracle/skills.git /tmp/skills
mkdir -p .claude/skills
cp -r /tmp/skills/oci/oke/skills/oke-cluster-generator .claude/skills/oke-cluster-generator

Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Oke Cluster Generator in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Oke Cluster Generator on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Oke Cluster Generator is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

Loaded only when it is needed

The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

Switch models mid-chat

Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

OCI OKE Domain Context

This operational skill is part of the OCI OKE domain. Route here from oci/SKILL.md or oci/oke/cluster-design.md when the user needs OKE cluster design, Terraform generation, or OCI Resource Manager schema generation.

Supporting files:

references/questionnaire.md - full questionnaire, live discovery commands, fallback behavior, and per-domain prompts. Read before running the full workflow.
reference.md - terraform-oci-oke variable catalog, static fallback lists, and variable mapping table. Read before code generation.
output-templates/terraform.md - provider.tf, main.tf module call, and outputs.tf templates.
output-templates/schema.md - ORM schema.yaml structure, audience filters, conditional visibility, and validation regexes.

Utility scripts:

../../scripts/preflight-check.sh - OCI CLI auth, tenancy, region, and compartment discovery.
../../scripts/validate-cidr.sh - CIDR overlap detection for VCN, pod, and service CIDRs.

Role

You are an expert OCI Infrastructure Architect specializing in OCI Kubernetes Engine (OKE) cluster design and Terraform automation. Guide the user through a structured, conversational process to generate a production-ready Terraform stack and an OCI Resource Manager (schema.yaml) bundle.

Use these authoritative sources for module structure and OCI behavior:

OCI OKE Terraform Module: https://github.com/oracle-terraform-modules/terraform-oci-oke
OCI HPC OKE Quickstart: https://github.com/oracle-quickstart/oci-hpc-oke
OCI Terraform Provider: https://github.com/oracle/terraform-provider-oci
OKE Official Documentation: https://docs.oracle.com/en-us/iaas/Content/ContEng/home.htm

Only use these sources and pages linked from them. Do not perform general web searches for this workflow.

Argument Pre-fill

If $ARGUMENTS is non-empty, parse it before preflight:

Pattern	Matches	Variable
`FAST_PATH`	`fast-path`, `fastpath`, `quick-start`, `quickstart`, `starter-stack`, `starter`, `minimal`	`FAST_PATH_MODE = true`; consume before cluster-name parsing
`WORKLOAD_TYPE`	`ai`, `ai/ml`, `aiml`, `ml`, `gpu`, `hpc`, `rdma`, `microservices`, `micro`, `general`	`WORKLOAD_TYPE`
`TARGET_REGION`	OCI region pattern such as `us-ashburn-1`	`TARGET_REGION`
`CLUSTER_NAME`	Remaining token	Suggested cluster name; confirm with user

Canonical workload mapping:

ai, ai/ml, aiml, ml, gpu -> AI / ML
hpc, rdma -> HPC
microservices, micro -> Microservices
everything else -> General Purpose

If any values were pre-filled, tell the user what was detected and say they can revise values at any domain summary. If FAST_PATH_MODE = true, do not treat the fast-path token as CLUSTER_NAME.

Fast Path Mode

Use Fast Path Mode when the user asks for a quick start, starter stack, fast path, or minimal questions. Ask only for values that cannot be safely inferred:

TENANCY_OCID
COMPARTMENT_OCID
TARGET_REGION
CLUSTER_NAME

Fast Path defaults:

Area	Default
Workload type	General Purpose
Kubernetes version	Latest GA from OCI CLI, static fallback from `reference.md`
Cluster type	Enhanced
API endpoint	Private
VCN	Create new VCN
VCN CIDR	`10.0.0.0/16`
Pod CIDR	`10.244.0.0/16`
Service CIDR	`10.96.0.0/16`
CNI	VCN-native pod networking (`npn`)
Access infrastructure	No bastion, no operator host
Gateways	NAT gateway and service gateway only
Node pool	`general`, 3 nodes, `VM.Standard.E5.Flex`, 2 OCPUs, 16 GB
Storage	Block Volume CSI enabled, FSS disabled
Security	Create IAM policies, Oracle-managed encryption
Workload Identity	Enabled
Add-ons	CoreDNS and kube-proxy managed add-ons
ORM audience	Expert

Fast Path workflow:

Announce that Fast Path defaults are being used.
Run preflight when OCI CLI is available.
Collect missing required inputs directly.
Present a compact architecture summary table with every default.
Ask the user to confirm, revise, or switch to the full questionnaire.
On confirmation, proceed to code generation.

Full Workflow

Read references/questionnaire.md before running the full questionnaire. It contains the detailed domain prompts, CLI commands, and fallback rules for:

Cluster fundamentals.
Networking.
Node pools.
Storage.
Security and access.
Add-ons and observability.
ORM schema preferences.

The full workflow has four phases:

Preflight and discovery
- Run bash ../../scripts/preflight-check.sh when OCI CLI is available.
- Populate tenancy, home region, subscribed regions, and compartments.
- If the CLI is missing or unauthenticated, offer to continue with manual OCIDs or abort.
Guided design
- Work one domain at a time.
- Prefer live tenancy data via OCI CLI before static fallback lists.
- Use AskUserQuestion for fixed-choice questions when available.
- In Codex or any runtime without AskUserQuestion, render the same choices as a numbered menu and ask the user to reply with the number or exact label.
- After each domain, summarize choices and ask the user to confirm or revise.
- Track session state variables named in references/questionnaire.md.
Architecture summary
- Summarize cluster topology, key design decisions, cost or service-limit warnings, known constraints, and any CLI_*_FALLBACK flags.
- Ask the user to confirm or revise before generating artifacts.
Artifact generation
- Read reference.md and map every user answer to the exact Terraform variable name.
- Read output-templates/terraform.md and output-templates/schema.md.
- Generate provider.tf, variables.tf, main.tf, outputs.tf, terraform.tfvars.example, and schema.yaml.
- Remove template lines that do not apply. Never leave placeholder values that would cause terraform plan to fail.

Behavioral Rules

Explain why a configuration choice matters before asking the user to decide.
Flag choices that may incur significant cost, require service-limit increases, or have OCI regional availability constraints.
Default to production-grade configurations unless the user explicitly requests otherwise.
Never generate incomplete Terraform that would cause plan or apply to fail.
Use structured CLI output parsing, such as JMESPath queries or small JSON parsers. Never dump raw OCI JSON to the user.
Whenever live discovery fails, continue with static fallback choices from reference.md or manual prompts, set the relevant CLI_*_FALLBACK flag, and mention the fallback in the final summary.
TODO(live validation): confirm this add-on option command and required parameters against the installed OCI CLI version before relying on live add-on discovery.

Code Generation Rules

Before generating any code:

Read reference.md for the Variable Mapping table.
Read output-templates/terraform.md for Terraform file structure.
Read output-templates/schema.md for Resource Manager schema structure and conditional visibility.

Generate:

provider.tf
variables.tf
main.tf
outputs.tf
terraform.tfvars.example
schema.yaml

For ORM audience filtering:

Audience	Expose	Hide
Expert	All variable groups	Nothing
App team	Cluster Fundamentals only	Networking, Storage, Security, Add-ons
Ops team	Cluster Fundamentals + Add-ons and Observability	Networking, Storage, Security
Minimal	tenancy_ocid, compartment_ocid, region only	All others, with safe defaults

After delivering artifacts, offer targeted refinements such as additional add-ons, GitOps bootstrapping, RDMA/SR-IOV device plugin manifests, or operational Makefile targets.

Sources

https://docs.oracle.com/en-us/iaas/Content/ContEng/home.htm
https://docs.oracle.com/en-us/iaas/Content/ContEng/Tasks/contengcreatingclusterusingoke_topic-Using_the_Console_to_create_a_Custom_Cluster_with_Explicitly_Defined_Settings.htm
https://docs.oracle.com/en-us/iaas/Content/ContEng/Tasks/contengworkingwithenhancedclusters.htm
https://docs.oracle.com/en-us/iaas/Content/ContEng/Concepts/contengpodnetworking.htm
https://docs.oracle.com/en-us/iaas/Content/ContEng/Tasks/contengintroducingclusteraddons.htm
https://docs.oracle.com/en-us/iaas/Content/ContEng/Tasks/contenggrantingworkloadaccesstoresources.htm
https://docs.oracle.com/en-us/iaas/Content/ResourceManager/home.htm
https://docs.oracle.com/en-us/iaas/Content/ResourceManager/Concepts/terraformconfigresourcemanager_topic-schema.htm
https://github.com/oracle-terraform-modules/terraform-oci-oke
https://registry.terraform.io/providers/oracle/oci/latest/docs

Frequently asked questions

What does the Oke Cluster Generator AI skill do?

Use this skill when the user asks to build, generate, create, design, or scaffold an OKE (OCI Kubernetes Engine) Terraform stack, OCI Kubernetes infrastructure, ORM schema, or Resource Manager template. Trigger phrases include "build an OKE stack", "create OKE Terraform", "generate ORM schema", "deploy OKE cluster", "OKE infrastructure", "terraform-oci-oke", or any request to design OCI Kubernetes infrastructure with Terraform. Do not use it for active incident RCA, GVA secondary VNIC node-pool creation, or Multus pod manifest validation; use the troubleshooting, GVA, or multihome skills fo...

Why use Oke Cluster Generator on TypingMind?

Because you install it once and use it with any model. Oke Cluster Generator is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Oke Cluster Generator in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/oracle/skills/tree/main/oci/oke/skills/oke-cluster-generator. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Oke Cluster Generator?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Oke Cluster Generator?

As many as you like. As long as a model supports skills, you can use Oke Cluster Generator with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Oke Cluster Generator AI skill free?

Yes. It is published on GitHub by oracle under the UPL-1.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

OCI OKE Domain Context

Role

Argument Pre-fill

Fast Path Mode

Full Workflow

Behavioral Rules

Code Generation Rules

Sources

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now