I used to watch director's commentaries on DVDs all the time. My friends and family thought I was strange. But that's where I learned most of what I know about storytelling - why people make the choices they make, what they were going for, what did and didn't work, etc.

I make more content than I really think about. So, it might be worth talking about some of the content rather than let the vlog go dormant because I'm busy making other stuff.

That's supposed to be how content creation works...right?

I've helped a lot of people write them. And I've had a version of this prompt living in various notebooks and documents for a couple of years. It uses Bloom's taxonomy to pick the right action verbs for the course level, avoids the usual offenders ("understand," "know," "be familiar with" — none of those are measurable), and pushes for outcomes specific to the course rather than generic ones that could apply to anything.

I finally built it properly as an AI skill and a TempLight template so I'm not rewriting it every time someone asks.

What it does

Ask it for course outcomes. It'll ask you for:

• Type of institution (community college, university, trade school, etc.)
• Course level (developmental through graduate)
• Course name
• Course description — a rough draft is fine
• Any additional context (optional)

From there it generates 3–5 outcomes with example assessment types for each. It'll also note if it had to make inferences because the description was thin.

It works for any discipline. I'm in higher ed so that's where my head is, but the structure holds for K-12, corporate training, or anywhere else outcomes need to be written. After the first pass, ask it to revise individual outcomes, shift Bloom's levels up or down, or rewrite for a different audience — student-facing language reads differently than what goes in an accreditation report.

Two ways to use it

If you use Claude Code, download the skill file and drop it into ~/.claude/skills/course-outcomes/SKILL.md. After that, just ask Claude Code to help you write course outcomes and it'll handle the rest.

For OpenAI Codex, download the skill file and drop it into ~/.codex/skills/course-outcomes/SKILL.md. After that just ask Codex to help you write course outcomes and it'll handle the rest.

For Opencode, download the skill file and drop it into ~/.opencode/skills/course-outcomes/SKILL.md. After that just ask Opencode to help you write course outcomes and it'll handle the rest.

If you use Claude.ai, ChatGPT, or any other AI tool, use the TempLight version instead. It's a fill-in-the-blanks prompt — drop in your course details and paste it into whatever you're using.

Both produce the same output. The skill just integrates tighter into the Claude Code workflow.

I know how to use a camera. I work in education. I've worked in healthcare. I've run a business. I've been a photographer, a web developer, an IT director. I've done a lot of different things. None of them well enough to call myself the expert in any one of them.

What I am is an oddball with a little bit of experience in all of them at once. That gives me a weird perspective — especially in education, where I've spent most of my career. But it doesn't make me the authority on anything.

So what do you talk about when you're not really the expert?

I don't know. Sometimes I have something in my notebook worth expanding on. Sometimes I don't. My notebook went quiet around October. It's late December. My brain hasn't come up with anything particularly new in two or three months, and I've been fine just existing for a while. Maybe that's okay. Maybe that's what rest looks like.

There's one line in my bio I insist on keeping. When people in tech and education want to sound impressive, they call themselves innovators. Disruptors. Whatever the buzzword is. I'm not any of that. I just do the work. That's it. And lately I've been wondering — when you just do the work, and it's not your idea, and you're not in charge of anything, what is there to actually talk about?

I don't have an answer. I recorded this anyway.

It was weird being on the other side of the mic.

We talked about what my job actually looks like day to day — which changes depending on the time of year, but mostly revolves around being available to faculty when they need something. One-on-one support instead of workshops and events. That's kind of the whole philosophy of the Center for Teaching and Learning Excellence.

We also talked about why I ended up in education in the first place. I was a first-generation, low-income student. I didn't know how any of it was supposed to work when I started. I got through because of people who helped me figure it out. Now I'm in a position to do that for other people. That's the part that actually matters to me.

Stephanie asked about my proudest moment at UACCB. I talked about a nursing student who needed a computer science credit to graduate and had exhausted every other option. I taught a one-student independent study for him — no extra pay, just wasn't going to let him not graduate. He did great. Later, at commencement, he won the Nightingale Award and brought his family over to thank me. I held it together long enough to turn around and then completely did not hold it together.

Dr. Shonk once told me there'd be a moment that makes you understand why you do this. That was mine.

We also talked about the railroad conductor certificate and the shoes. Because of course we did.

But it’s true, more or less.

Early in my career in education, I’d have the inklings of an idea and immediately go dig into thirty articles. By the end, my idea had basically become their idea. I’d consumed enough research that my original thought got absorbed into whatever the existing thinking was. I couldn’t tell what mine was anymore.

So I stopped doing that first.

Now when I have an idea, I let it sit. I think it through in my own weird vacuum before I look anything up. Sometimes for a week, sometimes longer. Then I do some lightweight research — I’m not writing journal articles here, I just want to know if I’m in the ballpark. And every once in a while I find out that what I thought was original is a variation on something that already exists. Which is fine. That’s usually how ideas work.

I do the same thing with AI. I avoid using it early in the process for the same reason — I don’t want it pulling from research I haven’t vetted and nudging my thinking before I’ve had a chance to develop it myself.

The downside is a lot of half-baked ideas that probably have better-researched versions out there I just haven’t found. I’m okay with that tradeoff. At least when I finally get to the research, I know what I actually think going in.

One of the things I wrote was about weird stuff I do to make younger me happy. Not in a deep, reflective way. Just — sometimes I make a decision that makes no practical sense, and the only real explanation is that some part of me needed it.

I bought a Chevy Silverado Trail Boss a few years ago. Lifted. Leather seats. Sunroof. The whole thing. I drive maybe 5,000 miles a year. I don’t haul anything. I don’t need a truck. I bought it because somewhere around age 12 or 13, I saw a nice truck and said something like "I’d love to drive something like that one day," and someone told me that with the way I was, that was never going to happen.

I don’t know exactly what they meant. But it stuck.

So I bought the truck. And it made 12-year-old me very happy.

Then a few years later I traded it for an electric car, because that actually made sense for my life. And that made me happy too — in a completely different way. Like, the thing I needed to prove was already proven. Time to make a sound financial decision.

Both moves were right. For different reasons. At different times.

I don’t have a bigger point here. It’s just something I noticed — that sometimes I do things because some version of me from a long time ago needed the win. And now I’m old enough that just knowing I could do something, and choosing not to, is kind of interesting on its own.

I read a paper — a partnership between Apple and Carnegie Mellon — about a different way to train AI. The typical approach is reinforcement learning with human feedback: AI gets a prompt, gives a response, a human scores it. What this paper proposes instead is reinforcement learning with checklist feedback. The AI builds an atomic checklist — strictly yes or no items — to accomplish a task, then works through it until everything’s done. No vague criteria. Just: did this happen or not.

That got me thinking about students.

The obvious version is: students create their own rubric, get graded on it. There’s already research on that. What I think is more interesting is the atomic checklist part specifically. Not a rubric with categories and point values — a list of yes/no steps that actually has to be completed to finish the project. To make that list, you have to genuinely understand the task. You have to be able to do it.

My theory is that builds buy-in. Students struggle to care about assessments. Faculty struggle to explain why their assessments matter. If the student makes the checklist, they’ve already done part of the thinking. Maybe that changes something.

I don’t know what this looks like in practice. It’s probably different for every course, every assessment. Might only work in capstone situations. Might create more work than it’s worth. I genuinely don’t know. I just think the atomic checklist part is interesting enough to keep stewing on.

If you’ve tried something like this or you know research that already covers it — correct me if I’m wrong — I’d actually like to hear about it.

Articles mentioned

• Checklists Are Better Than Reward Models for Aligning Language Models by Viswanathan et al., (2025)
• Increasing Student Engagement with Self-Assessment Using Student-Created Rubrics by Chambers & Harkins Monaco (2023)

That’s kind of the whole point.

Years ago, a photography client told me that if my website had shown more of who I actually was, she would’ve walked into her session way less nervous. My site at the time was neutral. Safe. The kind of thing you make when you want to seem professional and not scare anyone off. It worked, I guess. It also wasn’t me.

My website now is still a little like that. It’s what you make when you work in education and you want to be taken seriously. I haven’t fully figured out how to fix that yet.

This is my workaround.

Straight BS is where I put the stuff that doesn’t fit on a proper professional website. Notebook thoughts that needed more space. Half-baked ideas I want to think through out loud. Work stuff, personal stuff, random things that caught my attention. Not polished. Not researched to death. Not a suit-and-tie version of anything.

You’ll see a lot of the inside of my car. A lot of the inside of my brain, which is probably the scarier of the two. Shiny spots on my forehead because the car has a glass roof. Me getting distracted when someone drives past and gives me a weird look.

It’s just me. Which is why I named it what I named it.