you don't have to maintain it. Especially in the age of ai, just giving people inspiration and something to vibe from is more than sufficient and appreciated
That would be awesome. I believe with AI it's all about tailoring everything to your specific workflow and style, especially anything to do with the dev environment.
No worries if it's untenable or too much though, but I'll keep an eye on the commend thread in case!
For my part, I'm currently using oh-my-opencode harness with various skills extracted and tailored from superpowers / simonw / matt pocock. Working well enough so far, but keen to really evolve the skill flow and how they connect and are used in coordination with the various subagents.
Or biology class to learn that resources grow linearly (arithmetically) but populations grow geometrically (exponentially). So it is possible for everyone to grow exponentially, it's just not sustainable and generally leads to mass famine, disease or war.
Is "roughly exponential growth" being used as a synonym for "growth"?
Exponential is used as a scare word. It's not just growth, it's exponential growth! Run and scream in fright! Because if you don't do what I say you must do, we are exponentially doomed. Dooooomed!
i can't speak for everyone, but in the above assertion am using 'roughly exponential' to mean that world population between say 1880 and 1960 followed a curve that is, roughly, exponential, in the technical sense. much of the discourse 50 years ago, e.g. the population bomb, was predicated on this observation.
Rough is doing heavy lifting there, so much so that I suggest it doesn't have any meaning except to say the population was growing. The growth from 1980 to 1960 certainly was not exponential: the percentage growth per year was all over the place, varying on the same time scale as the doubling time (or even faster).
I suspect it's not a coincidence that the population bomb scare occurred right after the collapse of European colonialism, although teasing out the causation could be interesting.
Or a transition form exponential to sigmoid grow, if it's slow enough. I remember cases of exponential grow of bacteria in lakes that ends in a disaster, but an unchecked garden will get a lot of plants and tree grow but I think it will stabilize softly.
This is the malthusian argument, and in a vacuum it sounds right but didn’t account for decreasing family size with wealth and the ability of the economy to just barely eke out something like a percent or two of surplus.
In China, the one child policy, for better or worse, was instituted to ensure that gains from industrialization were not eaten up immediately, leaving no surplus for quality of life and reinvestment.
malthus had a point but it is not destiny and the real world reflects that. his was an avoidable trap
now if we can gain control over capitalism we can save the earth
Canadian leaders are currently very consciously choosing to partner with China as opposed to the U.S.
I get diversification, that’s a good call, but adopting policies that actively harm Canada to the benefit of China is where we’re at and it’s so far beyond the pale. Just take a look at Canada, who for as long as I have known, have tried to maintain its industrial base in Ontario, eg the cross-border supply chain for automobiles, but then this "new" government comes in and is like y’know what we really need right now? To compound the effects of tariffs, piss off our biggest trading partner, risk NAFTA (CUSMA) and our entire cross-border supply chains with the US all so we can get some cheap electric cars from China, which won't even be manufactured here (atleast not with Canadian jobs); meanwhile we just spent close to $100 billion in subsidies explicitly to try and kickstart electric vehicle manufacturing in Canada. May have been more productive to turn that $100 billion into pennies and throw them down a wishing well...
Check out Mike Pocock’s work, he’s done excellent work writing about red green refactor and has a GitHub repo for his skills. Read and take what you need from his tdd skill and incorporate it into your own tdd skill tailored for your project.
This is just ai slop. If you follow what the actual designers of Claude/GPT tell you it flys in the face of building out over engineered harnesses for agents.
You don't need a harness beyond Claude Code, but honestly it's foolish to think you shouldn't be building out extra skills to help your workflow. A TDD skill that does red-green-refactoring is using Claude Code exactly as how it's meant to be used. They pioneered skills.
Works better than standard claude / gpt, which doesn't do red-green-refactor. Doesn't seem like slop when it meaningfully changes the results for the better, consistently. Really is a game-changer. You should consider trying it.
I don't think just saying it's an anti-pattern for a multitude of reasons and then not naming any is sufficiently going to convince anyone it's an anti-pattern.
This is in fact precisely what skills is meant for and is the opposite of an anti-pattern, but more like best practice now. It's explicitly using the skills framework precisely how it was meant to be used.
reply