The Agent Skills Directory

[SAFE] (SAFE): The skill contains architectural instructions and code templates that do not perform any network operations, file system modifications outside of project setup, or execution of external code.
[EXTERNAL_DOWNLOADS] (SAFE): No external downloads or remote script executions are present. The skill uses standard package references in its code examples.
[PROMPT_INJECTION] (SAFE): While the skill uses strong language like 'Absolute Law' to enforce architectural patterns, these instructions are scoped to software design and do not attempt to bypass agent safety filters or system instructions.

architect-nextjs