Oci Iot Platform

Organization

oracle

oci-iot-platform

Explore, create, and troubleshoot Oracle Cloud Infrastructure Internet of Things Platform resources, including domains, digital twin models, adapters, instances, relationships, and device publish flows. Use when requests involve OCI IoT bootstrap, digital twin inspection, safe lifecycle operations, or translating OCI IoT docs and samples into concrete commands.

Overview

Publisher	oracle
Repository	`skills`
Skill name	`oci-iot-platform`
Stars	879
Forks	251
Bundled files	16
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.
16 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 Oci Iot Platform 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/iot-platform
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/iot-platform .claude/skills/oci-iot-platform

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

Use it in TypingMind

Enable Oci Iot Platform 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 Oci Iot Platform 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 Oci Iot Platform 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 IoT Platform

Quick Start

Confirm the user is working with Oracle Cloud Infrastructure Internet of Things Platform.
Ask for the minimum context needed before giving commands:
- IOT_DOMAIN_ID when available
- OCI_CLI_PROFILE
- OCI_CLI_AUTH when the selected profile needs it, such as security_token
- OCI_REGION if it cannot be derived from the domain
- intended operation: inspect, create, update, delete, or publish test telemetry
Prefer this execution order:
- discover the domain and current state
- inspect the relevant model, adapter, or twin
- check local CLI capability with oci ... --help when using newer filters or gateway/raw-command options
- make the smallest required change
- verify the result with a fresh read

Default Workflow

Start with read-only OCI CLI discovery.
Use scripts/derive_domain_context.sh when the user only has IOT_DOMAIN_ID.
Use references/platform-surface.md when the task needs orientation on OCI IoT resource families, data flow, connectivity types, or which surface to use.
Use references/cli-workflows.md for control-plane actions:
- domains and domain groups
- digital twin models
- adapters
- instances
- relationships
- work requests
- HTTPS publish examples
Use references/mcp-optional-use.md only when an OCI IoT MCP server is already available in the user's environment. Keep CLI as the fallback and never require MCP for public workflows.
Use references/resilience-guidance.md for:
- large or ambiguous list operations
- SDK or CLI command-shape drift
- gateway-aware topology
- relationship source/target diagnosis
- work-request failures
- publish rejection triage
- raw-command final-state validation
- cleanup or rollback planning
Use references/modeling-guidance.md when the request involves DTDL authoring or adapter payload design.
Use references/data-access.md only when the user explicitly needs Data API, ORDS, direct database access, or APEX-oriented workflows.
Use references/release-validation.md before calling the skill package ready to share publicly.

Bundled Resources

Run scripts/derive_domain_context.sh to derive:
- region
- device host
- data host
- domain group OCID
- short IDs used in later commands
Run scripts/twin_tools.py for:
- last-known
- offline
- telemetry-template
Reuse templates/model.temperature-sensor.template.json, templates/adapter.default.template.json, templates/instance.template.json, and templates/publish-curl.template.sh as neutral starting points.
Use references/platform-surface.md to explain how domains, domain groups, models, adapters, twins, relationships, work requests, raw commands, and data access fit together.
Use references/resilience-guidance.md to keep operator responses bounded, active-resource focused, and explicit about final-state evidence.
Use references/mcp-optional-use.md to recognize optional OCI IoT MCP tool families, gateway-aware helper behavior, Data API wrappers, and safety rules.

Guardrails

Do not assume internal tenancy names, profiles, network access patterns, or private tooling.
Treat Oracle product docs and official samples as the source of truth for platform behavior.
Prefer read-only commands first and verify current state before recommending mutations.
When suggesting create, update, or delete operations, include a verification command immediately after the mutation.
Bound large reads with filters and --limit before using --all.
Treat asynchronous acceptance, including raw-command 202, as incomplete until final state is verified.
For digital twin instance creation, never use INDIRECT as a shortcut to avoid auth setup. Use INDIRECT only when the user explicitly asks for a gateway/downstream topology or provides a gateway routing requirement. Otherwise clarify connectivity or proceed with DIRECT when a publishing device is implied.
Keep MCP guidance optional. Do not make MCP installation or private MCP bootstrap part of the public workflow.
When MCP is already available, treat it as an accelerator for joined context, selector resolution, bounded pagination, gateway topology, Data API summaries, and polling; always be ready to fall back to CLI or SDK commands.
Treat device publishing auth modes separately:
- vault-secret-backed basic auth
- certificate-based mTLS
Do not imply OCI IoT is a general-purpose MQTT broker.
Keep examples redacted and tenant-neutral.

Authoritative References

Oracle IoT service docs:
- https://docs.oracle.com/en-us/iaas/Content/internet-of-things/home.htm
OCI CLI IoT command reference:
- https://docs.oracle.com/en-us/iaas/tools/oci-cli/latest/oci_cli_docs/cmdref/iot.html
Oracle sample repository:
- https://github.com/oracle-samples/oci-iot-samples

Output Style

For each task, return:

The exact command sequence with placeholders filled or called out.
The key IDs, state, or timestamps that matter.
The next verification step.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Oci Iot Platform AI skill do?

Why use Oci Iot Platform on TypingMind?

Because you install it once and use it with any model. Oci Iot Platform 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 Oci Iot Platform in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/oracle/skills/tree/main/oci/iot-platform. 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 Oci Iot Platform?

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 Oci Iot Platform?

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

Is the Oci Iot Platform 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.

View all

Using Superpowers

obra

CommunityPopular

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

Context And Decisions

affaan-m

CommunityPopular

Govern stable domain context with a narrowly scoped CONTEXT.md when needed, and route hard-to-reverse decisions to ECC's existing architecture-decision-records skill. Use when domain terms require…

Docs Governance

Route broad documentation-governance requests to existing ECC skills and run an opt-in, read-only audit of mapped documentation roles, links, ADR indexes, and evidence references. Use when a user asks…

Ecc Conventions

Development conventions and patterns for ECC. JavaScript project with conventional commits.

Overview

Installation

Install in TypingMind

Install in another agent

Use it in TypingMind

Works with any AI model

Skill instructions

OCI IoT Platform

Quick Start

Default Workflow

Bundled Resources

Guardrails

Authoritative References

Output Style

Bundled files

Frequently asked questions

Related AI Skills

Set up your own AI workspace now