What it does
A small CLI ranks local Agent Skills against a request, then returns suggestions without invoking anything automatically.
Agent tooling
Only you can see your notes.
Screenshot unavailable. Open the experiment ↗
A small CLI ranks local Agent Skills against a request, then returns suggestions without invoking anything automatically.
Start by writing out a short list of skills or tasks your assistant can handle, along with a one-sentence description for each. A developer can install the tool and supply a secret connection key from TypeSafe, the online service that calculates the match scores.
When someone enters a request, the program asks TypeSafe how closely each task fits and prints the ranked options. It only suggests choices for you to review, so it never starts any task or runs code on its own.