Building out a course on agent skills
See my initial skeleton content here: Agent skills. I’ll be adding to this content over the next year, piece by piece. And improving it, little by little. I decided to start the content by using some sections from my post Tom’s opinionated guide to skill building 101. I also added content on the modularity of skills, testing skills, and more.
I also plan to add in activities to provide more interactivity. That’s coming, in layers and stages. Anyway, stay tuned for more updates. Just like I built out my API documentation course, I plan to approach it post by post, with many iterations and revisions. A project like this gives my blog more focus and direction.
One aspect that’s different this time, though, is that AI is incredibly capable at building out many portions of this course. Therefore, some of the course content is AI-generated. In writing this, it immediately feels like a turnoff. But it shouldn’t be, for at least a couple of reasons.
First, this is how I tend to create documentation now. I direct and steer the AI agent about what to write. I provide feedback on what it’s written, iterate on the content, and more. I’m actively guiding and shaping what AI writes.
Second, I want to build out this course to learn as much as to disseminate knowledge. In fact, learning is the main reason. Which seems odd because you’d think, why are you building out a course for yourself to learn the material? Don’t you want to learn everything first yourself, and then create the course to share that learning?
If that’s how my blog worked, it would be a one-sided, boring endeavor. I’m not engaged by knowledge dump posts. By “knowledge dump,” I mean posts where I’m just writing down everything I already know. I’m much more engaged when the writing process itself provides an act of learning and discovery.
By interacting with AI, I can steer toward gaps in my own knowledge, have a sounding board for my ideas, learn about when I’m wrong or misguided, and much more.
Usually I write out the topics first myself, using my own voice and language. Then I ask Gemini and Claude to go through and address gaps, fix content in places, ensure I’m summarizing sources correctly, and more. That blend tends to read well (I think).
About Tom Johnson
I'm an API technical writer based in the Seattle area. On this blog, I write about topics related to technical writing and communication — such as software documentation, API documentation, AI, information architecture, content strategy, writing processes, plain language, tech comm careers, and more. Check out my API documentation course if you're looking for more info about documenting APIs. Or see my posts on AI and AI course section for more on the latest in AI and tech comm.
If you're a technical writer and want to keep on top of the latest trends in the tech comm, be sure to subscribe to email updates below. You can also learn more about me or contact me. Finally, note that the opinions I express on my blog are my own points of view, not that of my employer.