Streamlit agent skill

developing-with-streamlit

The official Streamlit skill bundled with the library: building, styling, debugging and speeding up apps, installed with streamlit skills

SkillLow risk

streamlit/streamlit

Install

streamlit skills --yes

Installs into the current project from the installed package.

This is third-party code. Review the repository files before installing.

What it does

The developing-with-streamlit skill ships with the streamlit pip package and matches the installed version. It is a router: depending on the task it points the agent to references on building apps, session state, caching and fragments, themes and widget styling, chat UIs for assistants and custom components with st.components.v2. It also covers server setup through st.App with ASGI, Starlette and FastAPI and debugging common errors. The streamlit skills command places the skill into agent folders in the project or installs a global version.

Who it is for. For analysts and Python developers building dashboards and internal tools on Streamlit with an agent.

Good fit when

  • You need a dashboard or internal tool on Streamlit
  • The app is slow from extra reruns and needs caching
  • You want to restyle widgets or build a chat interface

Not a fit when

  • The app uses Dash, Gradio or another framework
  • You need a public site with custom layout rather than a data app

Example request

Build a Streamlit sales dashboard from sales.csv with a region filter and cached loading

Limitations

Requires a Streamlit version that includes the streamlit skills command. Project install symlinks to the package, while global install fetches the meta skill from GitHub. The separate streamlit/agent-skills repository is archived.

How to disable. Remove the developing-with-streamlit folder from the project's .claude/skills and .agents/skills or from the global skills directory.

Security check

  • The skill consists of instructions and references

README in short

Streamlit is a Python framework for quick data apps and dashboards. The agent skill lives in the package under lib/streamlit/.agents, and the streamlit skills command installs it interactively or with --yes and --global. When an app runs locally, Streamlit suggests this command if it detects an agent without the skill. The other skills in .claude/skills serve Streamlit's own maintainers. Apache 2.0 licensed.

SKILL.md

---
name: developing-with-streamlit
description: "**[REQUIRED]** Use for ALL Streamlit tasks: creating, editing, debugging, beautifying, styling, theming, or optimizing Streamlit applications. Also required for building custom components (inline or packaged), using st.components.v2, or any HTML/JS/CSS component work. Triggers: streamlit, st., dashboard, app.py, beautify, style, CSS, color, background, theme, button, widget styling, ..."
---

# Developing with Streamlit

This is a **routing skill** that directs you to specialized references for Streamlit development.

## When to Use

Invoke this skill when the user's request involves:
- Creating a new Streamlit app
- Editing or modifying an existing Streamlit app
- Debugging Streamlit issues (errors, session state bugs, performance problems)
- Beautifying or improving the visual design of a Streamlit app
- Optimizing Streamlit performance (caching, fragments, reruns)
- Building and running Streamlit apps
- Building chat, conversational, or agentic UIs (AI assistants, thinking expanders, chain-of-thought, tool-call timelines)
- Styling widgets (button colors, backgrounds, CSS customization)
- Advanced server configuration with `st.App`, ASGI, Starlette, FastAPI integration, custom routes, middleware, or lifespan hooks
- Any question about Streamlit widgets, layouts, or components

FAQ

How does project install differ from global?

Project install links the skill from the installed Streamlit and updates with it. Global install via --global downloads the meta skill from GitHub for all projects.

Do I need Node.js?

No, streamlit skills works without Node.js.

Editors’ pick

166 skills for scientific work: bioinformatics, cheminformatics, clinical data, geospatial analysis and 100+ databases

SkillMedium risk44.9K
Editors’ pick

Google's open-source MCP server for databases: ready tools for Postgres, MySQL, BigQuery, Spanner and more, plus custom tools in tools.yaml

MCP serverHigh risk16.4K
Editors’ pick

Official Hugging Face skills: Hub operations via the hf CLI, datasets, model training, Spaces, evals and deployment

SkillHigh risk11K
Editors’ pick

A token-lean MCP server for PostgreSQL, MySQL, MariaDB, SQL Server and SQLite with a read-only mode

MCP serverHigh risk3.5K