The Agent Skills Directory

[SAFE]: The skill operates on local project files using relative paths for environment authoring and feature discovery, posing no risk of unauthorized file access outside the project scope.
[SAFE]: No network operations, external downloads, or remote code execution patterns were detected. All resources are referenced via local filesystem paths.
[SAFE]: The use of command-line tools like rg (ripgrep) is limited to discovery and inspection of the local codebase and documentation.
[SAFE]: Instructions emphasize following established factory patterns, schemas, and maintained examples, promoting secure and predictable environment generation.
[SAFE]: Validation and execution are delegated to other local skills (such as dev-container and run-tests), ensuring that activities occur within a controlled runtime environment.

author-environment