The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides complex shell pipelines using find, grep, sort, tail, and git log to scan the local repository for document numbers. It also instructs the agent to use mkdir and ln -s for directory and symlink management.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect injection as it ingests user-supplied titles to generate filenames and document headers.
Ingestion points: User-provided <title> parameter and design conversation content (referenced in SKILL.md).
Boundary markers: None specified for the title input interpolation.
Capability inventory: File creation, relative symlink creation, and repository scanning via shell commands (find, git, grep).
Sanitization: Instructions include a mandatory "slug" transformation (lowercase, non-alphanumerics to hyphens) to normalize user input before it is used in filenames.

llp-create