The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using uvx to remove the black dependency and pre-commit to verify the new configuration. These commands are standard for managing Python project tooling.\n- [DYNAMIC_CONTEXT_INJECTION]: The skill uses the !command`` syntax to run find commands at load time. These are used to identify the presence of project configuration files and are benign in nature.\n- [EXTERNAL_DOWNLOADS]: The skill references the official ruff-pre-commit repository from Astral to configure pre-commit hooks. Astral is a well-known organization in the Python ecosystem, and this download is documented as a standard part of the migration process.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes project configuration files (pyproject.toml, .pre-commit-config.yaml), which represents an ingestion surface for potentially untrusted data.\n
Ingestion points: The skill reads local configuration files during Step 1 to audit existing settings.\n
Boundary markers: No delimiters or specific warnings are used when reading these files.\n
Capability inventory: The skill has permissions to read, write, and edit files, as well as execute commands via uvx and pre-commit.\n
Sanitization: The skill does not perform explicit sanitization of the configuration data before processing it.

black-to-ruff-format