Have you ever wanted to use your Luxonis camera within Codex and GPT 5.6 Sol to help build a working vision application? Then this tutorial is for you!
Today we are releasing a video tutorial, Luxonis Agent Skills: Using Codex GPT 5.6 Sol, that helps you learn how to do exactly that. In this tutorial, our Director of Product, Max McLaughlin walks through using Codex and how he can build a working vision application from start to finish in roughly 15 minutes.
Max utilizes all steps that the Skills have to offer to make his own version of "Hole in the wall" where he has to make faces, poses, and hand signals to pass each level and continue on. With live feedback, interactive working models, and much more.
The Tutorial:
What are the Luxonis Skills?
They are five skills follow one simple path: get the camera working, shape your idea into a brief, build the demo. Troubleshooting sits alongside, ready whenever you need it.
/luxonis-guide
- Not sure where to start? Run this and it points you to the right skill.
/luxonis-device-setup
- Brings a camera to a verified, working state. This skill lets your agent navigate both our tools and your specific setup to find the best route to a working camera, then saves a DEVICE.md so later sessions start from a known-good state.
/luxonis-project-interview
- This skill turns an idea into a buildable brief. It interviews you one question at a time in plain language, then writes a PROJECT_BRIEF.md that becomes the shared context every later step, and every future session, can build from.
/luxonis-build-poc
- Takes that same brief and stands up the thinnest runnable slice that proves the core idea on a real device. It adapts the closest known-good Luxonis example rather than inventing a pipeline from memory, confirms it is targeting DepthAI v3, and verifies the result with a command you can re-run
/luxonis-troubleshoot
- This skill is the "something is wrong" entry point. It reproduces the problem, isolates device versus app, diffs your app against a known-good example, and changes one thing at a time until the symptom is gone. If it cannot fix things locally, it writes a clean SUPPORT_PACKET.md for our team.
Each skill primes your agent with the right approach, context, and guardrails for one specific job, so it behaves like someone who has built on OAK a hundred times. The platform's full capability is available the moment you plug in, through the agent you already use. In this example, Max utilizes Codex GPT 5.6 Sol to showcase these skills.
How to install the skills:
No server to stand up, no heavy install. The skills are deliberately small, to keep setup trivial and token usage low, and they work across whatever harness you prefer. You bring the agent you already like, the skills bring the Luxonis knowledge.
The repository lives at github.com/luxonis/skills.
Claude Code, run these in your session:
/plugin marketplace add luxonis/skills
/plugin install luxonis@luxonis
/reload-plugins
Cursor, install from the Cursor Marketplace, or add manually via Settings, Rules, Add Rule, Remote Rule (Github) with:
luxonis/skills
Any other agent (Codex and others) via the skills CLI:
npx skills@latest add luxonis/skills
How the skills stay grounded:
What makes an agent great on our OAK devices is the context. This way the skills give it real, current sources instead of relying on memory. When a skill needs something real to build or diff against, it uses our curated oak-examples repository, cloned once into a shared folder at ~/.luxonis/agent-context/ and reused across your projects.
For any Luxonis-specific fact, the skills start from our documentation map at docs.luxonis.com/llms.txt and follow its Markdown pages rather than guessing.
Feedback?
The Luxonis Skills are in early development and constantly being adjusted. Having this testing in the hands of real engineers and teams will allow us to further adapt and improve. If you have any questions, comments or suggestions, please reach out to our team to discuss further!
This is the very beginning of a much larger effort, and we believe it points to where building on OAK is headed. Install it, point it at a camera, build something, and tell us how it went. We cannot wait to see what you make.
