Summary
Routes all Streamlit work through a single entry point: building apps, debugging widgets, theming, custom components, deployment, the works. The clever bit is it discovers your installed Streamlit version (1.57+) and loads matching reference docs bundled inside the package itself, so you're always working with documentation that matches your environment. You point it at your project directory, it handles venv detection across pip, poetry, pdm, and uv, then surfaces topic specific guides on session state, caching, layouts, whatever you need. Saves you from hunting through outdated web docs when your local install has the answers already sitting there.
Install to Claude Code
npx -y skills add streamlit/agent-skills --skill developing-with-streamlit --agent claude-codeInstalls into .claude/skills of the current project.
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Files
SKILL.mdView on GitHub
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.
Featured
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Categories
