agent-smith

the agent creates and maintains the specs, doing this manually doesn't make sense. The specs are written for the agents. after execution of create-spec, review-spec skill will check against the code and add evidence of the spec's aims. Only when the aims fits to the evidence, the specs is going to be validated successful. after that apply and deliver skills can be executed. finally there is commit hooks and tests that shall ensure quality and functionality. have a look at https://github.com/holgerleichsenring/agent-smith for the quality gates.

they do work well in production. have a look at https://github.com/holgerleichsenring/agent-smith. While writing that the methodology had been created. Obviously, I didnt know upfront what I wanted to generate here. Also features are changed or removed on the way. that's not a problem, when the specifications are part of the git repository as it is done here. Actually it's the other way around: it is an advantage as the agent can have a look at everything that had been done previously and can understand what, why and how it had been implemented. give it a try :-)

Hi HN, I’m working on an idea called EmergingRepos (working name) a site for finding repos that are just starting to get momentum. The kind of repo I’m interested in is not brand new with 0 stars and not already famous. The sweet spot is something like: - small star count - small fork count - recent commits - more than one contributor The idea is that this could be a win-win. Maintainers get thoughtful early attention, and readers get to discover repos where they can jump in, make a PR and get that joining an active team feel. i.e. the days of just making your own new repo and trying to get it going might be over. There’s just too many! Here are a few examples: https://github.com/Integral-Healthcare/robin-ai-reviewer Stats: 62 stars, 4 forks, 4 contributors https://github.com/cpulvermacher/lgtm Stats: 28 stars, 11 forks, 4