Accidentally in Code

Tag: github

  • Skills for a more leveraged workflow

    Adapted from Mix and Match Robot expressions by anarres (Openclipart, CC0)

    I’ve been skeptical in general about sharing workflow skills. I have a bunch I share with direct collaborators, but there are a lot of “AI skills” repos out there and I’ve only found 2 of them really useful to me (#1, #2). I thought working out what you wanted and making your own was important – but I kept packaging up a similar set of skills to share with specific people, because I underestimated the value of having a starting point. So finally I accepted – I too would make an AI skills repo: ai-dev-starter-kit.

    The conversation I was having is how to go from leveraging AI to leveraged by AI. I think it’s a question of what do you hand off, and what do you keep? AI can do a lot of work, but it can also generate a lot of work for you. You have to figure out how to manage that so you’re not just scattered and getting less done (been there).

    At the core of it is a board configured a certain way, and three terminals. The board is the source of truth, and work is issues moving through a status workflow. Two of the terminals are the skills that generate and validate code: the orchestrator, which fans work out across the board, and the merge queue, which serialises the landings and does final validation before anything goes in – things that can run for hours with periodic checkins. The third terminal is the one that requires thinking and engagement, and the work I do in it is to make work agentable (i.e. push it into the queue the other two terminals run).

    The other thing in it is a sample CLAUDE.md – talking to people in mid-sized orgs, I consistently notice it’s under-leveraged, and it’s much easier to change robot behaviour than human behaviour.

    The others are smaller. One goes through what went in overnight and flags anything I should worry about – review isn’t required before merge, but I still want to know what landed.. fable-audit-prompts is my answer to “what is Fable even for”: I use it to audit things where I have vibes but not concrete ideas, and it generates a report that makes that work agentable by less expensive models.

    If you’re looking for a starting point for a more leveraged workflow, I hope this can be helpful – whether you take some pieces as they are or just as inspiration. Feedback or ideas always welcome.

  • My Completely Unscientific GitHub Survey

    I was a software engineer without a GitHub account. I know, shocking, because everyone is supposed to have one – and actually the reason why I had to get resulted in me receiving a set of questions which assumed I would have a GitHub account, but Twitter account was optional.

    I didn’t have a GitHub account because I had never felt any need for one, and my reaction to needing one was slight panic, because I had this impression that it was a space where women got harassed. Of course, this is a statement that could be applied to The Internet in general, and I Internet a lot. Or Twitter, and I tweet a lot. But those things I would feel a sense of loss to do without.

    Also, I really had my fill of men patronising me and assuming I didn’t know what I was talking about during University, and it’s not like this experience has stopped since then. I don’t need to put myself in a position for men to make me feel like I shouldn’t be an engineer. The voice in my head is doing a perfectly adequate job, and does not need a chorus line.

    Anyway, I thought about why I had GitHub pegged as a Bad Space, and I came up with three main things:

    And so I tweeted.

    I have to get a github account. I've so far avoided it in part as my impression is that it's a place where women are harassed. Am I wrong?

    Pleased to say that I got replies from 6 women saying that their experience has been fine.

    Which is obviously completely unscientific, and not a representative sample. But it was enough to quash the feeling of dread I had. So hey, now I have a GitHub account.