simonair
Joined 15 years ago
Joined 15 years ago
Now if I ask “why did you not use the skill”, the answer typically starts with an apology, the insight which skill it should have used, and it will proceed using the skill.
In contrast, asking “what can we change in the skill description so you use it next time I ask you to commit”, it will typically explain how it selects skills and how to modify the skill in question’s description so it would pick it on its own.
The detection is based on dumb string literal heuristics, but has proven rather effective. Example patterns:
const hardcodedInfrastructure = { url: /^https?:\/\/(localhost|127\.0\.0\.1|192\.168\.\d+\.\d+|10\.\d+\.\d+\.\d+|172\.(1[6-9]|2\d|3[01])\.\d+\.\d+)(:\d+)?/i, dbUrl: /^(postgresql|postgres|mysql|mongodb):\/\/.*@(localhost|127\.0\.0\.1|192\.168\.\d+\.\d+|10\.\d+\.\d+\.\d+|172\.(1[6-9]|2\d|3[01])\.\d+\.\d+)/i, localhost: /^localhost$/i, localhostPort: /^localhost:\d+$/i, };
It achieves instant startup by rendering the prompt before the full shell initializes. Since adopting it, I am done fiddling with my shell config and the fact that `zsh4humans` is in maintenance-mode is actually an advantage as it keeps me from wasting time refactoring `zshrc`.
This implies that if you were replaced by someone else, they would inherit your OKRs but not your performance management including your performance reviews, personal development goals and career aspirations.
One way to do this is by rating performance based on both contributions to OKRs owned by the individual as well as those of others and rating performance as high only if both are exceptional.
In my mind, the gold standard for engaging summaries is Seeking Alpha. As a random example, see https://seekingalpha.com/article/4633758-sell-amazon-before-...
If you could train the model to come up with well structured bullet points, the summaries would be amenable to scanning before committing to fully engage. This is just an idea, I am not sure what fraction of your readers would prefer bullet points.
Here are some thoughts on the execution.
1. Optimize the core UX loop for mobile so it can be used on popular smartphones without scrolling. Maybe put the actual voting on a single page that fits entirely on the screen. 2. Allow dissenters to vote “What’s wrong with you, I actually love this tool”, which I would have clicked for Claude Code. 3. Group tools by category so I can hate on corporate productivity tools much quicker. You could even adapt categories once the user skips pairs a few times so those blessed souls who do not have to use productivity tools are not shown them to vote as often.