developing-with-streamlit
streamlit/agent-skills
Complete Streamlit development toolkit with version-matched reference docs and support for apps, styling, custom components, and deployment.
What is developing-with-streamlit?
Use this skill for all Streamlit tasks including app creation, editing, debugging, styling, theming, optimization, and deployment. It automatically discovers and loads reference documentation matched to your installed Streamlit version (>=1.57), covering dashboards, themes, layouts, session state, custom components, and more.
- Create and edit Streamlit apps with full framework support
- Debug performance issues, slow reruns, caching, and fragments
- Style and theme apps with CSS, colors, backgrounds, and widget customization
- Build custom components using st.components.v2 and HTML/JS/CSS
- Optimize session state management and app performance
- Deploy Streamlit applications
How to install developing-with-streamlit
npx skills add https://github.com/streamlit/agent-skills --skill developing-with-streamlit- Streamlit version 1.57 or higher installed
- Python environment with pip or compatible package manager
- Project directory with Streamlit app files
How to use developing-with-streamlit
- 1.Run the discovery script: python <SKILL_DIR>/scripts/discover.py --project-dir <YOUR_PROJECT_DIR>
- 2.Review the bundled SKILL.md output and reference documentation paths
- 3.Access topic-specific reference docs for dashboards, themes, layouts, session state, and custom components
- 4.Use the matched documentation to implement your Streamlit features
- 5.Refer to references for styling, performance optimization, and deployment guidance
Use cases
- Building interactive dashboards and data visualization apps
- Styling and theming Streamlit UIs with custom CSS and colors
- Creating custom components and widgets for specialized functionality
- Debugging performance bottlenecks and optimizing app reruns
- Deploying Streamlit apps to production environments
- Data scientists building interactive dashboards
- Full-stack developers creating Streamlit applications
- Frontend developers styling and customizing Streamlit UIs
- Teams deploying and maintaining Streamlit apps in production
developing-with-streamlit FAQ
Streamlit version 1.57 and higher. The skill automatically discovers and loads reference docs matched to your installed version.
The script resolves your project's Python environment by checking for .venv, Pipfile, poetry.lock, pdm.lock, and uv.lock files, then loads version-matched documentation from your installed Streamlit package.
Yes, the skill fully supports st.components.v2 and custom component development using HTML, JavaScript, and CSS.
Follow the printed instructions in the error message, ensure your Streamlit version is >=1.57, and re-run the discovery script with the correct project directory path.
Yes, the skill includes guidance on deploying Streamlit apps and references for production deployment strategies.
Full instructions (SKILL.md)
Source of truth, from streamlit/agent-skills.
name: developing-with-streamlit description: "Use for ALL Streamlit tasks: creating, editing, debugging, beautifying, styling, theming, optimizing, or deploying Streamlit apps. Also custom components, st.components.v2, HTML/JS/CSS work. Discovers and loads version-matched reference docs from the user's installed Streamlit (>=1.57). Triggers: streamlit, st., dashboard, app.py, beautify, style, CSS, color, background, theme, button, widget styling, custom component, st.components, CCv2, session state, performance, cache, fragment, slow rerun, deploy." allowed-tools: Bash(python ${CLAUDE_SKILL_DIR}/scripts/discover.py:) Bash(python3 ${CLAUDE_SKILL_DIR}/scripts/discover.py:)
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 intoreferences/. - 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.
Related skills
More from streamlit/agent-skills and the wider catalog.
stripe-best-practices
Guides Stripe integration decisions and security best practices for payments, Connect, billing, and Treasury.
stripe-projects
Provision databases, auth, hosting, and third-party services via Stripe Projects CLI.
upgrade-stripe
Guide for upgrading Stripe API versions and SDKs to the latest 2026-06-24.dahlia release.
ralph-tui-create-beads
Convert PRDs to beads for ralph-tui execution. Creates an epic with child beads for each user story. Use when you have a PRD and want to use ralph-tui with beads as the task source. Triggers on: create beads, convert prd to beads, beads for ralph, ralph beads.
ralph-tui-create-beads-rust
Convert PRDs to beads for ralph-tui execution using beads-rust (br CLI). Creates an epic with child beads for each user story. Use when you have a PRD and want to use ralph-tui with beads-rust as the task source. Triggers on: create beads, convert prd to beads, beads for ralph, ralph beads, br beads.
ralph-tui-create-json
Convert PRDs to prd.json format for ralph-tui execution. Creates JSON task files with user stories, acceptance criteria, and dependencies. Triggers on: create prd.json, convert to json, ralph json, create json tasks.