ponytail

Is this entire repo satire? It's a bunch of text files in a repo with massive churn (all new version 5!), but somehow even the technical debt 'skill' (i.e. text file) has technical debt itself: https://github.com/DietrichGebert/ponytail/blob/main/skills/... > ...every ponytail shortcut is marked with a shortcut: comment ... (older code may say ponytail:).

He doesnt need that when he has Ponytail https://github.com/DietrichGebert/ponytail Right? ...

I noticed my usage spiking a lot last week but I ultimately thought I was just being negligent, but now it seems it went back to normal. Also which effort level and model are you using? It might be worth taking a look at the skills you have, I noticed improvements after installing the pony tail skill - https://github.com/dietrichgebert/ponytail

Can this be used with the ponytail skill? https://github.com/DietrichGebert/ponytail/tree/main

Ah! The GitHub trending repos usually has some rapidly rising skills projects, https://github.com/trending. https://github.com/DietrichGebert/ponytail is a good example for one gaining lots of popularity now (no affiliation, just like it). OpenAI, anthropic, lots of companies building coding agent tools, also share skills publicly. Skills can feel like a big productivity boost at first, but it's good to remember lots of times they represent the ways that a specific person works. That way of working may not always be right for you, or, it might hide how the work is actually being done. Good to always try out the general purpose tool as-is, looking for skills that help you repeat tasks without rewriting prompts, or help save tokens, or help your agent use tools that it may not know how to use already.

I haven’t used it yet but https://github.com/dietrichgebert/ponytail is somewhat popular.

You might be interested in Ponytail, which seems to address this specific problem: https://github.com/DietrichGebert/ponytail

This is great https://github.com/DietrichGebert/ponytail

My criteria is "do they measure performance, or at least even try to?". Caveman [1], RTK [2] and more recently ponytail [3] don't or use a few trivial tests. Those projects don't measure performance on widely used benchmarks (like SWE Pro and stuff), that have their issues but at least it would give some indication. They also don't measure "big model + caveman vs smaller model". I've had a few times where removing all custom instructions that I started using with model N-2 made model N perform way better, so I'm very suspicious of everything that changes how the model works, it's easy to get degraded performance silently and suddenly you're paying latest Opus costs for 6 months old Sonnet performance. [1]: https://github.com/JuliusBrussee/caveman [2]: https://github.com/rtk-ai/rtk [3]: https://github.com/DietrichGebert/ponytail

The skills dirs have some necessary content (or so I assume): https://github.com/DietrichGebert/ponytail/tree/main/skills

My thoughts exactly. The whole thing is essentially just these rules, and a metric ton of boilerplate for specific plugin systems. My own personal ponytail says this could just be this in a code block of a README https://github.com/DietrichGebert/ponytail/blob/main/.github...