Eric Siu discusses automating research workflows by saving them as reusable skills. One example: a competitor-watch skill that finds top YouTube videos, records data, and highlights gaps. The conversation covers using screen monitoring to spot automation candidates and capturing value from internal conversations.
This last one I think is interesting to talk about because it's, it's the last thing that I usually do.
Save that whole workflow as a skill so the agent can run the same research on any topic without you having to type the long prompt again. So now we'll say save that workflow as a skill called competitor-watch. From now on, when I give you a search term, find the top 5 YouTube videos, save the same info to the file, and call out the gaps.
I think trying to be prescriptive, to use your word, and saying, hey, like doing it manually, that's where I've kind of struggled a little. Like occasionally like where it makes sense, like, hey, should we Skillify this, right? But I think having to think like this would probably give me a little too anxiety because I'm not a detail-oriented person. What I will say is that thing that I mentioned earlier where it's watching my screen the whole time, right? So it's a screen monitor for myself and it's figuring out what to Skillify at the end of the day. So my point of saying that, sharing that example is like, we just don't know how much gold we have coming from these conversations. And oftentimes it's like one-on-one conversations like this or internal conversations.
