Claude Skill

streamlit/agent-skills

Explore Streamlit Agent Skills: a collection of reusable, Python-based agent skills to accelerate AI-powered Streamlit app development. Open-source and easy to integrate.

Overview

Stars194
Forks19
LanguagePython
Last pushed2026-05-21
Last synced2026-06-21
View on GitHub

Repository

Ownerstreamlit
Repositoryagent-skills
Full namestreamlit/agent-skills
Repo ID1,134,331,214

Install this Skill

npx skills add streamlit/agent-skills -s developing-with-streamlit -g

Registry

Typecodex_skill
Quality score75/100
Verificationreadme_parsed
Last verified2026-06-21
Platforms
ClaudeCodexCursor
Capabilities
pdfterminalworkflow
Detected files
README.mdtests
Install methods
  • npx skills add streamlit/agent-skills -s developing-with-streamlit -g
  • git clone https://github.com/streamlit/agent-skills.git

Summary

A curated collection of reusable agent skills designed to accelerate the development of Streamlit applications, enabling developers to integrate AI-powered capabilities seamlessly.

Chinese description

用于开发Streamlit应用的代理技能集合。

Key features

  • Pre-built agent skills for Streamlit app development
  • Python-based, easy to integrate and extend
  • Designed for AI-powered application workflows
  • Open-source and community-contributed

Use cases

  • Rapid prototyping of AI-enhanced Streamlit apps
  • Building conversational interfaces with agent skills
  • Automating data analysis workflows in Streamlit
  • Creating interactive dashboards with AI assistance

README excerpt

# Agent Skills for Streamlit Development A lightweight **meta-skill** that teaches AI coding assistants (Claude Code, Cursor, and others) how to discover and load the Streamlit development skills bundled inside the Streamlit pip package (1.57+). ## What are Agent Skills? Agent Skills are specialized instruction sets that enhance AI coding assistants' capabilities for specific tasks. Each skill contains instructions, scripts, and resources that the AI loads dynamically to improve performance on Streamlit development workflows. The actual skill content (dashboards, themes, layouts, session state, custom components, etc.) ships with Streamlit itself — this repo only contains the entry point that bootstraps discovery. ## How it works Starting with Streamlit 1.57, the full set of Streamlit development skills ships **inside the Streamlit pip package** itself. This repository provides a lightweight **meta-skill** that teaches agents how to discover and load those bundled skills. The meta-skill ([`developing-with-streamlit/SKILL.md`](developing-with-streamlit/SKILL.md)): 1. Detects the active Python interpreter (virtualenv, conda, pipenv, poetry, pdm, uv, or system) 2. Locates the installed Streamlit package path 3. Points the agent to the bundled skills at `<streamlit_path>/.agents/skills/` 4. Falls back to the [online docs](https://docs.streamlit.io/llms-full.txt) for older Streamlit versions ### Install once, works with every project Because discovery happens dynamically against whichever interpreter is active, a single **user-level install** of this meta-skill works across every project on your machine — regardless of which Streamlit version each project pins. Upgrade a project's Streamlit and the agent automatically picks up the newer bundled skills; no re-instal

Topics

No topics yet.

Explore more

Data from GitHub. Synced on 2026-06-21