The Agent Skills Directory

[COMMAND_EXECUTION]: The skill performs extensive filesystem operations, including recursive directory copying (cp -a) and recursive deletion (rm -rf) to move skill folders to a new name. These operations are essential to the skill's purpose but involve high-privileged actions on directories.
[DYNAMIC_EXECUTION]: The workflow relies on uv run to execute various local Python scripts (e.g., skf-rewrite-skill-name.py, skf-atomic-write.py) for processing manifest files and updating skill metadata. It also supports an optional post-completion hook (on_complete) that executes a shell command from the configuration file.
[INDIRECT_PROMPT_INJECTION]: The skill processes project configuration files and interactive user inputs for skill names.
Ingestion points: Configuration is loaded from config.yaml and preferences.yaml. The old_name and new_name are provided by the user via command-line arguments or interactive prompts.
Boundary markers: Instructions specify feeding file content to helper scripts via stdin rather than command-line arguments to prevent shell interpolation or expansion of potentially malicious content in the files being processed.
Capability inventory: The skill possesses the capability to read, write, and delete directories within the project structure and execute local Python scripts.
Sanitization: The new_name input is validated using a strict kebab-case regular expression (^[a-z0-9]([a-z0-9-]*[a-z0-9])?$) and an ownership check is performed to ensure the skill only modifies directories generated by its own system.

skf-rename-skill