The Agent Skills Directory

[SAFE]: The skill implements a workflow for software development hardening. It provides instructions on how to codify mistakes into permanent checks (lints, types, or tests) to prevent regressions. It does not interact with external networks or access sensitive user data.
[COMMAND_EXECUTION]: The skill mentions executing npm run verify to confirm that new checks correctly identify mistakes. This is a standard project-specific command for running tests or linters and is safe within this context.

learn