The Agent Skills Directory

[SAFE]: The skill consists purely of markdown-based instructions and reference templates. No executable scripts, binaries, or shell commands are included in the skill files.
[SAFE]: There are no network-related commands (such as curl or wget) or data exfiltration patterns. The skill does not attempt to reach out to external servers or send user data anywhere.
[SAFE]: No sensitive file paths, hardcoded credentials, or environment variable access patterns were identified. The instructions follow best practices for context gathering by looking for specific project-related documentation (e.g., product-marketing-context.md).
[SAFE]: The skill does not contain any prompt injection attempts, obfuscation, or instructions to bypass safety guidelines. Its behavior is consistent with its stated purpose of assisting in website information architecture.

site-architecture