The Agent Skills Directory

[SAFE]: No security issues were detected. The skill is entirely instructional and uses markdown templates to organize project tasks.
[COMMAND_EXECUTION]: The skill provides templates for standard development commands, such as git commit and bun test, within implementation plans. These are intended for developer-led workflows and do not present a security risk in the context provided.
[PROMPT_INJECTION]: The skill operates on user-approved design documents. While it ingests external data to generate tasks, it follows a rigid, self-auditing workflow that significantly mitigates the risk of indirect instruction injection.

writing-plans