The Agent Skills Directory

[SAFE]: The skill implements a purely instructional workflow for collaborative design. It does not utilize external dependencies, perform network requests, or execute arbitrary code.
[COMMAND_EXECUTION]: The skill instructs the agent to write design documents to the docs/plans/ directory. This is a standard project management task and does not involve sensitive file paths or elevated privileges.
[PROMPT_INJECTION]: The skill processes user input in the form of topics and ideas. While it lacks explicit delimiters for this untrusted data, the skill's lack of dangerous capabilities (such as network access or shell execution) prevents this surface from being exploited maliciously.

brainstorming