The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes package management commands such as poetry install and uv pip install to set up the developer's environment. It also runs ruff for linting and formatting. These operations are essential to the skill's primary function of scaffolding and validating new Python projects.
[EXTERNAL_DOWNLOADS]: The skill configures pre-commit hooks that fetch configuration from well-known repositories, including astral-sh/ruff-pre-commit and pre-commit/mirrors-mypy. These downloads target official, reputable sources for established development tools.
[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text to dynamically generate project files. While this presents a surface for indirect injection, the risk is addressed through automated validation steps using ast.parse and task runners like just check. The impact is limited to the local development context of the new project.
[DATA_EXFILTRATION]: No evidence of data exfiltration was found. The skill facilitates secure secret management by generating .env.example templates and instructing users to maintain their own local .env files, which are correctly added to the .gitignore configuration.

create-py-project