Skill Directory: Discovery for Agent Skills — Week 2 of the Spring Into AI Build Sprint
Week 2 of the Spring Into AI Build Sprint. The theme was build something for AI to use. I didn't build one more skill — I built the place skills get discovered: Skill Directory.
What it is
Skill Directory is a small site plus an API. The landing page lists each Agent Skill: name, description, when to use it, repo, and demo. For agents: GET /api/skills returns the same list as JSON. So when an agent needs to "find the right skill," it can call the API instead of guessing. Humans get a directory; agents get machine-readable discovery.
What's listed
I included three skills: my own sprint-helper (random build ideas in JSON), seabass223's Azure SQL DTU Profiler (SQL Server metrics in the IDE), and JStrait515's Crypto Market skill (live prices, market overview, trends). All follow the Agent Skills format so any agent can plug in.
Why it matters
Week 2 was about tooling for AI tools. The Skill Directory is infrastructure — the layer that makes "which skill do I use?" answerable. Build once, and both agents and humans can discover what's available.
Links
Shout-out
Part of the sprint is referencing other builders. Shout-out to JStrait515's Crypto Market Agent Skill — live prices and market data in JSON, plus a clean demo. Exactly the kind of "for AI to use" build this week was about.
If you're in the sprint too, drop your Week 2 build in the comments. More next week.