The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute standard shell commands, specifically git config user.name and date +%F, to automatically populate author and date information in the generated task documentation.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from external plan files or session history to generate task lists.
Ingestion points: User-provided plan files and session discussion context.
Boundary markers: None explicitly defined to ignore instructions within the source plan.
Capability inventory: Includes reading project source code and writing new markdown files to the local project directory.
Sanitization: No sanitization of the plan content is described before it is processed.

to-tasks