The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands and a bundled Python script (scripts/init_pencil_design_system_skill.py) to automate the creation of new skill directories and files.
Evidence: SKILL.md provides bash examples for directory creation (mkdir) and script execution.
[DYNAMIC_EXECUTION]: The bundled Python script generates new files, including SKILL.md and reference markdown files, by interpolating user-provided design system names into pre-defined templates.
Evidence: scripts/init_pencil_design_system_skill.py contains a PENCIL_SKILL_TEMPLATE and logic to write this content to the filesystem using Path.write_text.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied input (the name of the design system) which is used to generate filenames and content for new skills.
Ingestion points: The <name> argument provided by the user in the command line instructions.
Boundary markers: The generated content is placed within a structured markdown template, but there are no explicit instructions to the agent to ignore potentially malicious embedded content in the user-provided name.
Capability inventory: The skill has the capability to create directories and write files to the local filesystem via the Python script.
Sanitization: The Python script includes a normalize_skill_name function that uses regex (re.sub) to enforce kebab-case and a specific naming prefix, which helps mitigate basic path traversal or injection attempts through the name parameter.

pencil-skill-creator