Claude Skills by deeleeramone

When to reach for PyWry MCP tools (native webview rendering, Plotly, TradingView, AgGrid, chat) instead of writing Flask/Streamlit/Dash/Electron code. Use at the start of any task involving interactive UI, dashboards, charts, or chat widgets driven from Python.

> Add OAuth2 authentication to PyWry apps — Google, GitHub, Microsoft, or any OIDC provider.

Autonomous PyWry application building using LLM sampling, elicitation, and progress reporting.

> **Read this before creating chat widgets.**

How an agent operates inside a PyWry chat widget — reading user messages, attachments, @-context, tool-call result cards, edit/resend, settings changes.

> **STOP. THIS IS THE AUTHORITATIVE REFERENCE FOR ALL COMPONENTS.** > **YOU MUST USE THE EXACT EVENT SIGNATURES DOCUMENTED HERE.** > **THERE ARE NO EXCEPTIONS. NO WORKAROUNDS. NO DEVIATIONS.** ---

> Target elements for `set_content` and `set_style` updates using CSS selectors or component IDs.

> Best practices for creating charts, tables, and live data displays.

> **CRITICAL**: This mode is for **production servers** serving multiple concurrent users. > Widgets are stateless. State lives externally. Scale horizontally.

The PyWry event system — namespaced events, request/response round-trips, widget IDs, component IDs, and how tool results flow back to the agent.

> Building interactive forms with validation and collecting user input.

> **CRITICAL**: This mode is for widgets **embedded as iframes in external web pages**. > This is **NOT** a native window. This is **NOT** Jupyter. The widget is sandboxed.

> **STOP. READ THIS ENTIRE FILE BEFORE CREATING ANY WIDGET.**

This skill covers building PyWry widgets for Jupyter notebooks via MCP tools. There are **two approaches** for displaying widgets in Jupyter: | Approach | Best For | Requires | |----------|----------|----------| | **AnyWidget** (recommended) | Native Jupyter integration, bidirectional comms | `pip install 'pywry[notebook]'` | | **IFrame** (fallback) | When anywidget unavailable | MCP server in headless mode | ---

> **STOP. READ THIS ENTIRE FILE BEFORE CREATING MODALS.**

> **CRITICAL**: This is a **native desktop application** using PyWry/WRY (Rust WebView). > This is **NOT** a browser. This is **NOT** Jupyter. This is **NOT** an iframe.

> Style widgets using CSS variables, theme colors, and dynamic style updates.

Drive a live TradingView Lightweight Charts widget end-to-end via PyWry MCP tools — symbol, interval, indicators, markers, price lines, layouts, state.