I published the Claude Code hands-on session from Kyushu University as a workshop kit that allows even a single person to build a product.
This page has been translated by machine translation. View original
Hello, I'm Wada.
In April 2026, I was in charge of a Claude Code hands-on session for the special lecture "Social Innovation Studio" at Kyushu University QREC. I wrote about that experience in the following article.
This time, that initiative has been published as a case study.
As of August 2026, an AI utilization contest is being held within Classmethod, and I decided to reorganize the skills used in the lecture and submit them. Based on the survey feedback from the lecture and retrospective feedback from the organizing members, I refined everything and published it on GitHub as a "workshop kit" that anyone can hold.
In this article, I'll write about what I fixed after the lecture, what the kit can do, and how to use it. Since you can experience it solo, I hope those who want to go through "turning an idea into something with Claude Code" from start to finish will also give it a read.
What happened at the lecture (from the case study)
Since numbers appear on the case study page, I'll quote from there.
- Approximately 60 graduate students, a mix of information systems and non-information systems majors, participated in a two-day intensive lecture
- 80 to 90 percent of participants completed a prototype within the two days
- Post-event survey satisfaction score was 4.59 out of 5
The participants had quite varied backgrounds, and there were also working professionals among them. The fact that most people were still able to implement something working and even reach mutual feedback sessions, I believe, is because the skill design that had participants ask Claude Code "what should I do next" one question at a time worked effectively. At the retrospective meeting, the organizing members also said, "By laying the rails with Skills, we were able to run the lecture smoothly even with a small staff." However, as I'll mention later, there were also many challenges.
Incorporating feedback
The month after the lecture, the organizing members held a retrospective meeting.
Feedback:
Guiding participants through operation checks was difficult. It would be great if the kit could cover how to launch and check the generated app, since we had to guide each participant individually.
What I did:
I prepared an implementation skill /build-app that, after generation, guides participants on the launch command and URL, and moves on to the next question only after the launch is confirmed.
Feedback:
The app had too much flexibility, so we probably should have narrowed down the framework more.
What I did:
I fixed the standard configuration to Next.js (App Router / TypeScript) + pnpm.
Feedback:
There were many cases where participants got stuck because they weren't aware of the current directory.
What I did:
I fixed the locations for design documents and the app itself, and made the skill always guide using absolute paths.
One more thing: "creating a landing page," which I added on the fly on the day of the lecture, was well-received, so I incorporated LP creation into the main flow. The goal is to have participants verbalize not just "something that works" but also "who to pitch this to and how." It was also utilized at presentation time.
How the hands-on proceeds
Participants simply bring "one sentence about a problem" and "one sentence about a solution," then call six skills in order.
/scope-design: Answer one sentence each about the problem and solution, choose from multiple implementation approaches, and narrow down the MVP/build-app: Generate the MVP all at once, then refine the experience one piece at a time while playing the role of one assumed user/verify-project: Verify by actually using it whether the problem is truly solved, and turn that into the pitch outline/landing-page-design: Work on copy from a buyer's perspective, and generate the LP HTML/study-plan: Take stock of what's missing "if you were to actually deliver this," and turn it into a take-home study plan
Experience it solo (starts in 5 minutes)
The prerequisites on your local PC are Claude Code, Node.js 20 or higher, and pnpm.
git clone https://github.com/cm-wada-yusuke/claude-code-product-workshop-kit.git
cd claude-code-product-workshop-kit
claude
Once Claude Code launches, install the plugin used for LP generation and call the first skill.
/plugin install frontend-design@claude-plugins-official
/scope-design
When it asks for a project name, you're ready to go. The dialogue starts with "describe the problem you want to solve in one sentence," and the deliverables accumulate in projects/<project-name>/.
When doing this solo, I recommend proceeding with the intention of going all the way through to the pitch presentation. The verification.md that /verify-project generates becomes a ready-to-use script for a 3-minute pitch. Even if you're not presenting to anyone, getting to the point where you can put into your own words "is this truly solving the problem" and "who to pitch this to and how" makes what you take away completely different. In the lecture too, this was the part where hands stopped most, and where the most learning happened.
Trying it out
I ran through it once on my machine. I used the following as the problem and solution.
- Problem in one sentence: After developing a product, it's difficult to collect feedback
- Solution in one sentence: A web app where you can embed a button on the screen being used to send a quick one-line piece of feedback on the spot, and view all the feedback received in a list
Web app screen
LP
After trying it out, impressions came up that only emerged from actually using it, such as "I'd want to add a login," "Since it would be distributed via JS, that might be tough in an era where security is increasingly strict," and "I want to make it as visible as possible, but if it interferes with the original experience, it defeats the purpose."
Hosting for large groups requires the power of tutors
Since pitch presentations and pair feedback are built in, the more participants there are, the more it resembles a hackathon format, and the more opportunities there are to "have others spot what you can't notice yourself." That is clearly more effective from a learning standpoint.
However, what inevitably comes up as numbers grow are troubles due to individual PC environment differences and cases where people get stuck on how to do operation checks. Node.js versions, package managers, browser behavior. No matter how thorough the documentation, this can never be reduced to zero. When we ran it at Kyushu University, the tutors were truly invaluable in this area.
…So, if you want to scale up, you need the power of tutors.
In closing
We've reached an era where working things can be built instantly with AI. I believe that in product development, the areas where people should spend their time are:
- Who should we deliver this to
- How far should we take this
- How did it actually go
- What do we do next
These are the things to think about and try. That's precisely why I want the part of turning ideas into form to be executable in the shortest and most reproducible way possible. I hope the workshop kit can serve as one step toward that.
For those planning hands-on sessions or training programs inside or outside your organization, please try it out yourself first. Of course, we can also plan and host sessions as Classmethod. Feel free to reach out.
