managing-python-dependencies
Ensures proper Python dependency management, avoiding global `pip install` and adhering to project-specific tooling. Use this skill if any of the following are true: 1. Attempting to run `pip install {package_name}`. 2. Python packages or dependencies need to be added or modified. 3. Initiating a new Python project. 4. Installing missing packages inside a notebook or Python project. 5. Generating Python code that includes `import` statements for third-party libraries. 6. Before executing Python scripts via the terminal to ensure the correct virtual environment is active.
Install
With your agent
Install OMGSkills skill "googlecloudplatform/data-agent-kit-plugin:skills/managing-python-dependencies" into this agent's normal skills directory: call the OMGSkills MCP get_install_plan tool for your agent and run the script it returns (it installs only the pinned commit and verifies SKILL.md), and stop if MCP or the pin is unavailable. Do not overwrite or change existing skills without asking me.
Manual command
git clone https://github.com/GoogleCloudPlatform/data-agent-kit-plugin /tmp/data-agent-kit-plugin && ln -s /tmp/data-agent-kit-plugin/skills/managing-python-dependencies ~/.claude/skills/managing-python-dependenciesFrom README
Python Dependency Management Rule [!CAUTION] BEFORE any pip You MUST first detect the project's existing dependency manager and use it correctly. Do NOT override the project's established tooling. [!NOTE] Reactive Environment Check Bundling (Only When Installing): Do NOT run environment or package availability checks (importlib.util.findspec, pip list, ls uv.lock...) proactively before writing code or creating a notebook. Only probe the environment when a package actually needs to be installed (for example, on ModuleNotFoundError / ImportError or an explicit user request to dependencies). In Notebooks: When a notebook cell execution tool (executecell / notebookexecutecell) is available, check package availability (import or %pip list) and missing packages (%pip ) inside notebook cells, never via python3 -c or pip in the shell.
More from this repo
accidental-data-loss-prevention
**STOP AND VERIFY**: Before running any command or tool that results in irreversible data loss, you MUST obtain...
bigquery-ai-ml
Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics.
bigquery-bigframes
Generates Python code using BigQuery DataFrames (BigFrames).