Viktor.comAn AI coworker that actually does the work
Promoted
AI Skills Manager
One place for all your AI skills
160 followers
One place for all your AI skills
160 followers
Browse, install, enable, and share AI agent skills across all major coding agents in one desktop app.
AI Skills Manager
@ido_evergreen Congrats on the launch! 🎉 The cross-agent sync problem is real — I’m constantly copying skills between Claude Code and other agents and it’s pure friction. The GitHub install is a smart starting point. A few things I’m curious about though: are skills shared publicly in a marketplace, or is it purely local/private? And if there’s a community skill layer coming, how do you plan to handle quality control — anyone can publish, or is there some curation? As an iOS dev building OceanMind, an AI-powered breathwork app, I’ve accumulated a solid library of SwiftUI-specific skills that I’d love to manage in one place rather than hunting through scattered files.
This solves a real annoyance. I'm using Claude Code with custom skills and every time I want to test the same skill in Cursor or another agent, it's manual file copying and adjusting paths. Having one place to manage and push skills across agents is a workflow I didn't know I needed.
Question: does it handle skill conflicts or versioning? For example, if I install the same skill from GitHub but it gets updated later – does Skills Manager detect the newer version and let me update, or is it a one-time install that I'd need to manually re-pull?
AI Skills Manager
@aaron0403 Exactly the pain we built this for that manual copy-paste loop is a real time sink.
On versioning: honest answer, right now it's a one-time install. You'd need to re-pull manually to get updates.
That said, this comment is going straight to the top of the roadmap. Detecting upstream changes and surfacing an "Update available" prompt in the app is the natural next step — and feedback like this confirms it should be prioritized.
Thanks for your comment
the skills discoverability problem is real - I end up rediscovering the same prompt patterns across projects. curious how you handle versioning when a skill gets updated but some agents were built around the old behavior. do you pin versions or is it more of a live dependency?
AI Skills Manager
@mykola_kondratiuk Discoverability is exactly why we're building a Marketplace tab — browse and install community skills in one click instead of hunting GitHub. Coming very soon.
On versioning: currently it's a snapshot install, no pinning. You control when you re-pull.
Longer term: skills are just markdown files, so "versioning" means tracking the git commit hash at install time and letting you diff/update selectively. It's on the roadmap — this is exactly the signal that helps us prioritize it 🙏
git commit hash at install time is the right call - it is basically how package managers solved this for code, skills are just a different artifact. the marketplace tab will make a big difference once there is enough community content to browse.
Okan
I always end up losing my best system prompts and agent instructions in a messy graveyard of scattered text files. Using a centralized hub to organize and tag these AI skills would definitely speed up my workflow when switching between different development environments. I would love to know if you plan to add a local API so we can dynamically pull these structured prompts directly into our codebases.
Context Overflow
Cool Idea. A dashboard to view all active global skills is very useful. I believe all the coding agents say they should auto-detect skills in .agents/skills folder but skill detection has worked better in agent specific directory. Auto-complete for skills doesnt work when in .agents which is annoying. Did you experience the same thing? Does this solution put skills in agent specific directory?
Managing prompts and skills across different AI tools is becoming a real problem as teams scale. Is this more for individual power users or teams? Would love to see version history for skills that evolve over time.
@ido_evergreen skills discoverability is genuinely underrated as a problem, you build a great system prompt for one project and then spend 20 minutes hunting for it the next time you need it. centralizing this with GitHub install is the right approach since the community is already publishing solid skill sets publicly. one thing i'd love to see: a diff view when updating a skill from upstream, so you can see what changed before accepting the update rather than blindly overwriting what's working.