The Agent Skills Directory

[SAFE]: The skill functions as a documentation framework and formatting guide. It contains no instructions that attempt to bypass safety filters or exfiltrate sensitive data.
[COMMAND_EXECUTION]: The instructions guide the agent to include standard development commands (such as pytest and git commit) in the generated plan's text. These commands are for documentation purposes and are not executed by the skill's runtime environment.
[DATA_EXPOSURE]: The skill prescribes saving generated documentation to a local project directory (docs/plans/). It does not request access to sensitive file paths, credentials, or network resources.

writing-plans