designing-real-world-ai-agents-workshop: Skill for Claude Code

Using the Streamlit CLI

The Streamlit CLI is the primary tool for running Streamlit applications and managing configuration. This skill covers all essential commands and configuration options.

Running Streamlit apps

Basic syntax

streamlit run [<entrypoint>] [-- config options] [script args]

Entrypoint options

Examples

# Run default app in current directory
streamlit run

# Run a specific file
streamlit run app.py

# Run from a URL
streamlit run https://raw.githubusercontent.com/streamlit/demo-uber-nyc-pickups/master/streamlit_app.py

# Alternative: run as Python module (useful for IDE configuration)
python -m streamlit run app.py

Running with uv (recommended)

Use uv run to run Streamlit in a virtual environment with automatic dependency management:

# Run with uv (automatically uses/creates virtual environment)
uv run streamlit run app.py

# With configuration options
uv run streamlit run app.py --server.headless=true

# With script arguments
uv run streamlit run app.py -- arg1 arg2

Using uv run is the recommended approach because it:

• Automatically manages virtual environments
• Resolves and installs dependencies from pyproject.toml
• Ensures reproducible environments across machines
• Avoids manual activation/deactivation of virtual environments

Setting configuration with streamlit run

Configuration options follow the pattern --<section>.<option>=<value> and must come after the script name.

Recommendation: For persistent configuration, use .streamlit/config.toml in your project directory instead of command-line flags. This keeps your run command simple and makes configuration easier to manage and share with your team.