Most of the coding agents support reading skills in ~/.agents/skills. It seems that only Claude code hasn't adopted this spec. I am not sure about the future of this. Anyway good work, we need a unified skill marketplace for different agents.
Interesting tool. One thing I've noticed managing rules across Claude Code and Copilot: the same instruction produces very different results depending on the agent. Claude follows multi-step rules well, Copilot tends to ignore anything beyond the first line.
Does Skills Manager handle this at all, or is it purely format/distribution?
Seems like the hard problem isn't syncing files — it's that the same "skill" needs different phrasing per agent to actually work.
As someone using agents (like Claude Code), but really not being at home with NPM (never did anything with javascript) etc, I do like this. But, I'm on Linux ;)
I've made some containers for my agents atm (asking them to `ls` and seeing my private ssh key coming by is too scary). My next step is to figure out how to add skills...
Linux support is on the roadmap — you're not the first to ask! The app is Electron-based, so cross-platform is very doable, just haven't packaged it yet.
The fragmentation problem across agents is real, we ran into the exact same issue managing rules across different dev environments. The unified view approach makes sense, but curious about sync conflicts: if you update a skill file via Cursor and then via Claude Code, does Skills Manager detect the diff or does last-write win? Also wondering if you plan to support team-level skill sharing, not just individual installs from GitHub repos.
Most of the coding agents support reading skills in ~/.agents/skills. It seems that only Claude code hasn't adopted this spec. I am not sure about the future of this. Anyway good work, we need a unified skill marketplace for different agents.
Interesting tool. One thing I've noticed managing rules across Claude Code and Copilot: the same instruction produces very different results depending on the agent. Claude follows multi-step rules well, Copilot tends to ignore anything beyond the first line.
Does Skills Manager handle this at all, or is it purely format/distribution? Seems like the hard problem isn't syncing files — it's that the same "skill" needs different phrasing per agent to actually work.
As someone using agents (like Claude Code), but really not being at home with NPM (never did anything with javascript) etc, I do like this. But, I'm on Linux ;)
I've made some containers for my agents atm (asking them to `ls` and seeing my private ssh key coming by is too scary). My next step is to figure out how to add skills...
Linux support is on the roadmap — you're not the first to ask! The app is Electron-based, so cross-platform is very doable, just haven't packaged it yet.
Stay tuned
The fragmentation problem across agents is real, we ran into the exact same issue managing rules across different dev environments. The unified view approach makes sense, but curious about sync conflicts: if you update a skill file via Cursor and then via Claude Code, does Skills Manager detect the diff or does last-write win? Also wondering if you plan to support team-level skill sharing, not just individual installs from GitHub repos.