I'm the creator of Agent Skills. I've been building this because I realized managing and discovering agent skills for local agents was becoming a mess.
We just hit a milestone of indexing nearly 5,000 skills. It's been a fun engineering challenge dealing with deduplication, categorization, and handling different metadata formats from GitHub.
Honestly, building this has brought back the joy of creating for me. I just launched on other platforms and the feedback has been incredibly motivating. For example, a user recently pointed out that "permission boundaries" (read-only vs write access) are a bigger bottleneck than discovery—an insight I hadn't fully considered and am now planning to build.
The Stack: It's built with Next.js, Sanity (for the structured content), and hosted on Vercel. I'm using some custom scripts to parse GitHub repos for skill.json / SKILL.md files.
I'd love to hear your thoughts on what makes an agent skill "trustworthy" to you. Is it the star count? The code visibility? Or something else?
This is such a great point. Security does become the bottleneck once you move past simple queries.
We haven't implemented safety categorization yet, but I'd love to explore it. Ideally, would you prefer to see flags like 'Filesystem: Read-Only' or 'Network: Blocked' directly on the skill card?
Thanks for the feedback!
I've been using Claude Code heavily recently for my daily dev work. While the ecosystem for "Agent Skills" is growing fast, it feels very fragmented right now. I found myself constantly digging through random GitHub repos or Twitter threads to find compatible tools.
So I built this registry to solve that discovery problem.
What it does:
Aggregates skills from verified sources (community & official).
Parses the underlying repos to show you the code structure involved.
Generates the exact install command (CLI) you need to add the skill to your agent configuration.
Tech Stack: Built with Next.js 14 (App Router) and Sanity for the content lake. It uses some custom scripts to crawl and validate the SKILL.md / repo metadata from GitHub.
I'd love to hear your feedback—especially on what other metadata you'd like to see before installing a skill into your agent's environment?
I built this because I often struggle to understand abstract concepts just by reading text. I wanted a way to 'see' the knowledge structure.
Note: You can check the Gallery on the homepage to see instant examples (no signup needed). If you generate your own, it takes about 3 minutes because the backend performs a deep analysis to ensure the visualization is accurate and comprehensive.
Feedback on the visualization quality is highly appreciated!
Thanks for the feedback! You were absolutely right. I just pushed an update to remove the login requirement for core features. You can now use the tool freely without an account (login is only needed if you want to save favorites). I hope you give it another try!
I built this tool because I often find myself staring at a blinking cursor, knowing what I want to say but stuck on how to start the sentence elegantly. I realized that having a categorized list of "sentence starters" (transition words, opening phrases, etc.) could effectively unblock my writing flow.
It's a simple tool aimed at students, writers, and non-native speakers who want to improve their sentence variety.
I'd love to hear your feedback or suggestions on how to make it more useful!
We just hit a milestone of indexing nearly 5,000 skills. It's been a fun engineering challenge dealing with deduplication, categorization, and handling different metadata formats from GitHub.
Honestly, building this has brought back the joy of creating for me. I just launched on other platforms and the feedback has been incredibly motivating. For example, a user recently pointed out that "permission boundaries" (read-only vs write access) are a bigger bottleneck than discovery—an insight I hadn't fully considered and am now planning to build.
The Stack: It's built with Next.js, Sanity (for the structured content), and hosted on Vercel. I'm using some custom scripts to parse GitHub repos for skill.json / SKILL.md files.
I'd love to hear your thoughts on what makes an agent skill "trustworthy" to you. Is it the star count? The code visibility? Or something else?