developing-with-streamlit — an installable skill for AI agents, published by streamlit/agent-skills.
Routing skill for all Streamlit development tasks: app creation, editing, debugging, styling, optimization, and deployment. Routes to specialized sub-skills based on task type: performance optimization, dashboard building, design improvement, widget selection, theming, layouts, data display, multi-page apps, session state, chat UI, custom components, and Snowflake integration Includes a workflow for locating Streamlit source files, identifying entry points (streamlit_app.py, app.py), and applying sub-skill guidance Provides templates for common dashboard patterns (metrics, companies, compute, stock peers) and pre-built themes (Snowflake, Dracula, Nord, Stripe, Solarized, Spotify, GitHub, minimal) Automatically detects running Streamlit apps and offers to start or refresh them after edits Developing with Streamlit Streamlit (>=1.57) ships detailed reference documentation for building Streamlit apps inside its pip package. The bundled skill is a routing SKILL.md plus a references/ folder of topic-specific reference docs (dashboards, themes, layouts, session state, custom components, etc.). Usage Run the discovery script with the user's project directory: python <SKILL_DIR>/scripts/discover.py --project-dir <USER_PROJECT_DIR> The script prints either: A path on stdout (exit 0) — the bundled SKILL.md. Read it; it points into references/. An ERROR: block on stderr (non-zero exit). Follow the printed instructions and re-run. <SKILL_DIR> is the directory containing this file; <USER_PROJECT_DIR> is the absolute path to the user's project. Passing --project-dir matters because the script resolves .venv, ../.venv, Pipfile, poetry.lock, pdm.lock, and uv.lock relative to it.
don't have the plugin yet? install it then click "run inline in claude" again.