The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands date +%F and git config user.name to retrieve local metadata (current date and git username) to populate the header of the generated plan.md file.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The skill reads data from user-specified source files, local spec.md files, and external research links provided within the source content.
Boundary markers: The instructions do not specify the use of delimiters or boundary markers when processing external data, nor do they include warnings to ignore embedded instructions in those sources.
Capability inventory: The skill has the ability to read local files, execute shell commands (git, date), and write new files to the local file system (e.g., plan.md and project directories).
Sanitization: There are no instructions for sanitizing or validating content retrieved from external research links or source files before it is processed by the agent to generate implementation slices and milestones.

to-plan