Visual-explainer is an agent skill that transforms complex technical output into polished, self-contained HTML pages. It serves as a plugin for AI coding agents (Claude Code, Pi, Cursor, Antigravity, Codex, OpenCode, MCP hosts) to generate diagrams, diff reviews, plan reviews, slide decks, narrated videos, and data tables instead of ASCII art. The architecture is modular: a core skill definition (`SKILL.md`) provides workflow and design rules, while separate subsystems handle plan rendering (`plan/render.mjs`), quick-mode JSON-to-HTML conversion (`quick/render.mjs`), a local stdio MCP server (`mcp/server.mjs`), a best-effort PPTX exporter (`pptx/export.mjs`), and a Playwright-based video renderer (`video/render.mjs`). The Pi agent integration includes a native TypeScript extension (`extension.ts`) with `prepare`, `render`, and `render_quick` actions. The codebase demonstrates high craftsmanship with thorough input validation, security-conscious file handling (symlink rejection, atomic writes, output jail), clear error messages, and extensive documentation. The plan renderer is particularly notable as a zero-dependency HTML generator that validates plan structure, reads cited code from disk, and produces interactive pages with decision trees, comments, and keyboard navigation. The quick renderer validates JSON specs against a JSON Schema and produces complete HTML. The MCP server follows the Model Context Protocol strictly and exposes tools, prompts, and resources without calling an LLM or starting an HTTP listener. The video renderer uses Playwright to drive a virtual clock, ensuring frame-perfect timing. The repository is actively maintained with recent commits, a detailed changelog, and version consistency checks across all metadata files.
Slidev is a developer-oriented slide presentation tool that turns Markdown files into interactive, web-based slide decks. The system is built as a monorepo with several packages: a Node.js CLI and Vite-based dev server (`packages/slidev`), a Vue 3 client application (`packages/client`), a markdown parser (`packages/parser`), shared type definitions (`packages/types`), a VS Code extension (`packages/vscode`), and scaffolding tools (`create-app`, `create-theme`). The core workflow involves parsing Markdown slides with frontmatter, rendering them as Vue components with support for code highlighting (Shiki), diagrams (Mermaid, PlantUML, KaTeX), interactive editors (Monaco), animations (v-click, v-mark), and drawing tools. Export capabilities include PDF, PPTX (both raster and editable), PNG, and Markdown via Playwright. The system also includes a Model Context Protocol (MCP) server for AI agent integration, enabling programmatic slide editing. The architecture is modular: the parser handles slide splitting and feature detection, the client provides a rich presentation UI with presenter mode, and the CLI orchestrates build, serve, and export commands. The VS Code extension adds language support, a preview panel, and AI tools. Overall, Slidev is a mature, feature-rich application for creating technical presentations with minimal friction.
Spiel is a terminal-based framework for creating and presenting slide decks using Python. It enables users to define slides as functions that return renderable objects (via Rich), and presents them in a navigable terminal user interface built with Textual. The framework supports features like live reloading during development, slide transitions, and dynamic content generation through a trigger system. The architecture centers around a `Deck` class that manages a sequence of `Slide` objects. Each slide's content is defined by a function that can optionally receive a `Triggers` object for time-based or interactive effects. The presentation is driven by a custom Textual application (`SpielApp`) that handles user input, screen transitions (including slide-to-slide animations), and automatic reloading of the deck when source files change. Key components include the CLI for launching presentations, a flexible slide definition system, and reusable widgets for rendering content such as syntax-highlighted code and images. Notable reusable components include the `Triggers` class for managing interactive state, the `Swipe` transition for slide animations, the `Image` widget for terminal image display, and a set of utility functions (`clamp`, `filter_join`, `chunks`) that solve common programming problems. These components are designed with low coupling and could be extracted for use in other projects with minimal modification.
This repository is a Python library and Claude Code plugin for generating McKinsey-style PowerPoint (PPTX) presentations. It provides ~40 slide templates (executive summaries, charts, matrices, org charts, roadmaps, etc.) with a consistent deep-navy/bright-blue design system. The core architecture is a builder pattern: `PresentationBuilder` accepts slide specs (as dicts or keyword arguments) and delegates to slide-specific drawing functions in the `slides/` subpackage. A CLI (`mckinsey_pptx.cli`) reads JSON specs and produces `.pptx` files. The Claude Code integration includes an agent definition (`mckinsey-slide-agent.md`) that reads a template catalog, plans a deck story arc, generates a Python build script, executes it, and optionally renders PNG previews via LibreOffice/Poppler. The code is well-structured with a clean separation of concerns: theme dataclasses, base primitives, slide templates, and a builder. The adaptive slide type inference (`infer_slide_type`) is a clever design pattern that allows the same API to accept loosely-typed payloads. The library is production-ready, with provenance from a real consulting tool (AX Labs).