ppt-master

Coordinates a specialized multi-role agent system (Strategist, Image Generator, Executor roles) through a role collaboration protocol that decomposes presentation generation into discrete AI tasks. Each role operates with a dedicated prompt template stored in roles/ directory and communicates through a structured handoff protocol where outputs from one role become inputs to the next, enabling complex visual content generation through sequential AI reasoning rather than monolithic LLM calls.

Converts AI-generated SVG code into natively editable PowerPoint DrawingML objects through a specialized SVG processing pipeline (tools/svg_processor.py and related converters). Rather than embedding SVG as flat images, the system parses SVG elements (rectangles, text, paths, groups) and maps them to PowerPoint shape primitives, preserving vector editability. This enables users to click and modify individual shapes, text boxes, and charts directly in PowerPoint after generation, maintaining design fidelity while enabling post-generation customization.

Manages multi-slide presentation generation through a project lifecycle system that tracks generation state, caches intermediate results, and enables resumable generation if failures occur. The system maintains a project directory structure with organized folders for source documents, generated specifications, SVG assets, images, and final PPTX output. Project utilities (tools/project_utils.py) provide functions for initializing projects, tracking generation progress, and managing file dependencies. This enables users to generate large presentations (20+ slides) without losing progress if a single slide fails, and to iterate on specific slides without regenerating the entire presentation.

Validates generated presentations against design guidelines and PowerPoint compatibility rules through automated QA tools (documented in Quality Assurance Tools section). The system performs checks including: SVG syntax validation, PowerPoint shape compatibility, color contrast verification (WCAG compliance), typography consistency (font sizes, weights), layout alignment (grid-based positioning), and content completeness (all placeholders filled). Validation results are reported with specific issues and remediation suggestions, enabling users to identify and fix problems before export. The QA system can be configured to enforce strict rules (fail on any violation) or permissive rules (warn on violations but allow export).

Provides 33 pre-built chart templates (templates/charts/) organized by complexity (Common, Advanced, Professional) that Executor roles use to visualize data in presentations. Each template defines SVG structure, data binding points, and styling rules for common chart types (bar, line, pie, scatter, etc.). The system supports data-driven chart generation where users provide data (CSV, JSON, or structured format) and the system selects an appropriate template, binds data to the template, and generates the final SVG chart. Chart templates are designed to match the overall presentation design system, ensuring visual consistency. The library includes templates for both simple charts (single series) and complex charts (multiple series, dual axes).

Supports 10+ canvas formats (business presentations 16:9, legacy 4:3, Xiaohongshu 3:4, WeChat Moments 1:1, Instagram Stories 9:16, etc.) through a CANVAS_FORMATS dictionary in tools/project_utils.py that defines dimensions and aspect ratios. Executor roles dynamically adjust SVG layouts, margins, card sizes, and typography based on selected format at generation time, ensuring content reflows correctly for different platforms without requiring separate design passes. The system maintains design consistency across formats through template-aware layout rules that scale proportionally.

Enforces design consistency across generated presentations through three interconnected libraries: 33 chart templates (templates/charts/) organized by complexity (Common, Advanced, Professional), 640+ SVG icons (templates/icons/) with standardized 16×16 viewBox, and documented design guidelines (docs/design_guidelines.md) covering color systems, typography, layout grids, and CRAP principles. Executor roles reference these templates when generating SVG code, ensuring all charts use approved visual patterns and all icons maintain consistent styling. The system validates generated SVG against design rules before conversion to PPTX, preventing design drift.

Converts multiple source document formats (PDF, DOCX, Markdown, URLs, plain text) into a normalized internal representation through specialized source conversion tools (tools/source_converter.py and related modules). The system extracts text content, identifies structural elements (headings, lists, tables), and preserves semantic relationships while normalizing formatting. This normalized representation becomes input to the Strategist role, which performs the Seven Confirmations process to analyze content and generate a design specification. The extraction pipeline handles encoding issues, malformed documents, and format-specific quirks (e.g., PDF text extraction challenges, DOCX embedded objects).

Generates images for presentation slides through an Image Generator role that uses LLM-based prompting to create visual assets matching the design specification. The system integrates with external image generation APIs (DALL-E, Midjourney, Stable Diffusion) through a configurable provider interface, enabling users to select their preferred image generation backend. Generated images are embedded into SVG layouts with automatic sizing and positioning based on slide templates. The Image Generator role maintains style consistency by referencing color schemes and design guidelines from the design specification, ensuring generated images complement rather than clash with slide layouts.

Generates SVG code for presentation slides through Executor roles that apply layout templates from templates/layouts/ to structured content. The system uses template-aware code generation where each slide type (title slide, content slide, chart slide, etc.) has a corresponding SVG template with placeholder regions for text, images, and data. Executor roles fill these placeholders with content from the design specification, applying responsive layout rules that adjust spacing, font sizes, and element positioning based on canvas format. The generated SVG is validated against PowerPoint compatibility rules before export, ensuring all shapes can be converted to DrawingML without errors.

The Strategist role performs a Seven Confirmations process to analyze source content and generate a comprehensive design specification document (设计规范与内容大纲.md) before any visual generation occurs. This process confirms: content structure, key messages, target audience, visual tone, color scheme, layout patterns, and resource requirements. The specification document becomes the single source of truth for all downstream roles (Image Generator, Executor), ensuring design decisions are explicit, auditable, and consistent. The Seven Confirmations approach forces deliberate design thinking rather than letting LLM outputs drift based on implicit assumptions.

Exports generated SVG presentations to native PPTX format through a conversion pipeline that validates DrawingML shape definitions against Office compatibility rules before writing the final file. The system uses python-pptx library to construct PPTX files with proper XML structure, enforcing constraints documented in README.md 561-571 that prevent invalid shape combinations, unsupported gradient definitions, and other Office rendering issues. The export process includes metadata embedding (slide notes, speaker notes, custom properties) and supports batch export of multiple slides with consistent formatting. Validation errors are reported with specific remediation steps rather than silent failures.

Generates interactive web galleries from presentation SVG assets, enabling users to view and share generated presentations without requiring PowerPoint. The system exports SVG slides as a web-viewable format with navigation controls, full-screen mode, and responsive layout that adapts to different screen sizes. The web viewer (documented in Web Viewer and Examples Gallery section) provides a lightweight alternative to PPTX for sharing and reviewing presentations, with support for embedding in websites or sharing via URL. The gallery generation process includes metadata extraction (slide titles, notes) and optional thumbnail generation for preview.