Developing with Streamlit

SkillCloud & infra

Developing with Streamlit skill is a skill for AI agents that guides them through Streamlit work: creating, editing, debugging, styling, theming, optimizing, and deploying Python web apps. It discovers and loads version-matched reference documentation from the Streamlit package installed in the project, so guidance matches the version in use.

Use Developing with Streamlit in Claude, ChatGPT or Ahel Desktop

Free. Sign in, add Developing with Streamlit and connect your AI. About a minute.

Also: Claude Code · Cursor · Codex

Then ask your AI: use the Developing with Streamlit skill

Details

Instructions available. Your AI can read the instructions. Execution depends on the setup they require.

Have Streamlit 1.57 or newer installed in the project environment.

Developing with StreamlitStart free

What your AI can do with it

  • Create, edit, and debug Streamlit apps
  • Style, theme, and beautify Streamlit apps
  • Optimize and deploy Streamlit apps
  • Build custom components, including st.components.v2
  • Handle HTML/JS/CSS work within Streamlit apps
  • Load version-matched reference docs for Streamlit >=1.57

Getting started

  1. Have Streamlit 1.57 or newer installed in the project environment.
  2. Add the developing-with-streamlit skill to the agent's available skills.
  3. Ask the agent to perform a Streamlit task; it runs a discovery script to locate the docs matching the installed version.
  4. The agent then uses the loaded reference docs to complete the task.

What this skill tells your AI

The instructions your AI receives, as published by streamlit/streamlit in lib/streamlit/.agents/meta-skill/developing-with-streamlit/SKILL.md and read by ahel’s review.

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.

Signals

GitHub stars
46k
Forks
4k
Last commit
Oct 2026

ahel review

  • K1binfo
    installs-packages (in scripts/discover.py)

Automated review, not a security audit. Ruleset v1+k2.

Questions

Which Streamlit versions does it support?
It works with Streamlit 1.57 or newer, since it loads reference docs from the installed package.
How does it find the right documentation?
A discovery script locates version-matched reference docs based on the Streamlit package installed in the project environment.
What topics do the reference docs cover?
Topics include dashboards, themes, session state, caching, and custom components.
When does the skill trigger?
It triggers on Streamlit tasks, including work involving st and st.components.v2.
Advanced
Item type
skill
Key
developing-with-streamlit-streamlit
Source
github.com/streamlit/streamlit