The Agent Skills Directory

[SAFE]: The skill operates as a structured prompt template for conducting a project interview and generating a local markdown file. It does not contain any malicious patterns such as remote code execution, obfuscation, or data exfiltration.
[SAFE]: All operations are localized to the current project environment. The file-writing activity (creating goal.md) is the primary intended function and follows standard documentation practices without accessing sensitive system paths or credentials.
[SAFE]: The instructions do not attempt to bypass agent safety guidelines or override system prompts. The use of 'IMPORTANT' and other directional language is for task management (maintaining a TODO list) and does not constitute a prompt injection attack.

goal