# Ivy Convert Streamlit

> Convert a Streamlit (Python) application to an Ivy project. Use when the user wants to migrate from Streamlit, convert a Streamlit app, or build an Ivy app from Streamlit Python source files. Handles .py files, folders, and GitHub URLs.

- Skill: `ivy-interactive/ivy-convert-streamlit` (Agent Skill, multi-file: 107 files)
- Install (CLI): `npx skillmds@latest add ivy-interactive/ivy-convert-streamlit`
- Raw SKILL.md: https://api.skillmd.com/api/skills/ivy-interactive/ivy-convert-streamlit/raw
- Safety review: pending
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: Coding & Dev Tools
- Author: ivy-interactive (https://skillmd.com/u/ivy-interactive)
- Updated: 2026-09-17
- Page: https://skillmd.com/skills/ivy-interactive/ivy-convert-streamlit

---


# ivy-convert-streamlit

Convert a Streamlit application to an Ivy project.

## Pre-flight: Read Learnings

If the file `.ivy/learnings/ivy-convert-streamlit.md` exists in the project directory, read it first and apply any lessons learned from previous runs of this skill.

## Reference Files

Read before implementing:
- [references/AGENTS.md](references/AGENTS.md) -- Ivy framework API reference (widgets, hooks, layouts, inputs, colors)

## Reference Files

The [references/](references/) folder contains 105 reference files with Streamlit-to-Ivy component mappings (one `.md` per `st.*` widget). Read the relevant reference files before implementing the conversion to understand how to map Streamlit features to Ivy features.

## Step 1: Locate the Streamlit Application

You need a path to a `.py` file, a folder, or a GitHub URL containing the Streamlit application. Check if a value was provided via `$ARGUMENTS`. If not, ask the user to provide one.

- If it is a **GitHub URL** (starts with `https://github.com/`): Clone it to `.ivy/source/<repo-name>/` using `git clone <url> .ivy/source/<repo-name>/` and use that as the path going forward.
- If it is a **local path**: Use it directly.
- Verify the path exists with `test -f "<path>"` or `test -d "<path>"`.

## Step 2: Research the Streamlit Application

Read all the `.py` files and build a mental model of all Streamlit `st.*` features used in the application.

Use the reference files in [references/](references/) to learn how to map Streamlit features to Ivy features.

Gather enough information to produce a complete conversion guide before proceeding to the next step.

## Step 3: Write the Conversion Guide

Write a summarized conversion guide that maps the Streamlit features used in the application to Ivy features. The conversion guide should be structured in a way that makes it easy to follow when implementing the conversion. Use markdown formatting to make it clear and organized -- but be concise and token efficient.

Present the plan to the user for approval before proceeding.

## Step 4: Implementation

Identify if there are any connections (db, auth, api) that should be set up using the appropriate connection skill (e.g., `/ivy-create-db-connection` for databases, `/ivy-create-auth-connection` for auth, `/ivy-create-any-connection` for APIs).

Given the conversion guide from the previous step, implement the conversion of the Streamlit application to an Ivy application. Use the conversion guide and the reference files to map Streamlit features to Ivy features.

## Post-run: Evaluate and Improve

After completing the task:

1. **Evaluate**: Did the build succeed? Were there compilation errors, unexpected behavior, or manual corrections needed during this run?
2. **Update learnings**: If anything required correction or was surprising, append a concise entry to `.ivy/learnings/ivy-convert-streamlit.md` (create the file and `.ivy/learnings/` directory if they don't exist). Each entry should note: the date, what went wrong, why, and what to do differently next time.
3. **Skip if clean**: If everything succeeded without issues, do not update the learnings file.