The Agent Skills Directory

[SAFE]: The skill is a set of instructions for the agent to generate implementation plans in Markdown format. It promotes standard development workflows and does not execute arbitrary code or access sensitive system resources.
[COMMAND_EXECUTION]: The skill defines templates for technical tasks that include common development commands (e.g., pytest, git commit). These are descriptive steps intended for an engineer or subagent and do not represent unauthorized or hidden execution.
[DATA_EXPOSURE]: Plans are stored in a local directory (docs/superpowers/plans/). This is a standard documentation practice and does not involve exfiltration of sensitive data.
[PROMPT_INJECTION]: While the skill processes user-provided specifications to generate plans, it includes built-in self-review steps and strict formatting requirements that act as logical constraints on the output generation process.

writing-plans