The Agent Skills Directory

[SAFE]: The skill does not contain any detected malicious patterns, obfuscation, or unauthorized access attempts. All instructions are focused on legitimate requirement gathering and documentation tasks.
[COMMAND_EXECUTION]: The skill instructs the agent to create and maintain documentation files (e.g., 现状与参照流程.md, 变更记录.md) and requirement bodies within the workplace/ directory. This is consistent with its stated purpose as a documentation assistant.
[PROMPT_INJECTION]: The skill handles external data (project materials, code, and user input) which presents a surface for indirect prompt injection. However, the instructions include rigorous logic to distinguish between 'confirmed facts' and 'understanding', which serves as a functional control against accidental obedience to instructions embedded in project data.

project-requirements