{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"github-hugohe3--ppt-master","slug":"hugohe3--ppt-master","name":"ppt-master","type":"product","url":"https://hugohe3.github.io/ppt-master/","page_url":"https://unfragile.ai/hugohe3--ppt-master","categories":["app-builders","documentation"],"tags":["ai-agent","aippt","office","powerpoint","powerpoint-generation","ppt","pptx","presentation","slide","slides"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"github-hugohe3--ppt-master__cap_0","uri":"capability://planning.reasoning.multi.role.ai.collaboration.orchestration.for.presentation.generation","name":"multi-role ai collaboration orchestration for presentation generation","description":"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.","intents":["I want to generate a presentation from a document without manually designing each slide","I need an AI system that breaks down presentation creation into specialized subtasks","I want to ensure consistent design patterns across multiple slides through role-based prompts"],"best_for":["teams using AI IDEs (Claude Code, Cursor, VS Code + Copilot) for presentation automation","developers building multi-step AI workflows with specialized agent roles","organizations needing programmatic presentation generation with design consistency"],"limitations":["Requires manual role prompt maintenance — changes to design patterns require editing role templates in roles/ directory","Role handoff protocol adds latency — each role completion triggers next role invocation sequentially, not parallelized","Depends on AI IDE capabilities — only works within Cursor, Claude Code, or similar agent-capable environments"],"requires":["Python 3.10+","AI IDE with file reading and shell execution (Claude Code, Cursor, VS Code + Copilot)","Access to LLM API (OpenAI, Anthropic, or compatible)"],"input_types":["markdown","pdf","docx","url","plain text"],"output_types":["svg","pptx","json (design specification)"],"categories":["planning-reasoning","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-hugohe3--ppt-master__cap_1","uri":"capability://image.visual.svg.to.drawingml.conversion.with.powerpoint.native.shape.preservation","name":"svg-to-drawingml conversion with powerpoint native shape preservation","description":"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.","intents":["I want to generate presentations that remain fully editable in PowerPoint, not locked as images","I need to convert AI-generated SVG designs into native Office shapes for compatibility","I want to preserve vector quality and editability across the AI-to-PowerPoint pipeline"],"best_for":["enterprise users requiring Office compatibility and native shape editing","teams that need to hand off generated presentations to non-technical stakeholders for final tweaks","developers building presentation generation systems that must maintain vector fidelity"],"limitations":["SVG-to-DrawingML conversion has strict compatibility rules — certain SVG features (filters, gradients with complex stops) cannot be directly converted and require fallback to rasterization","Complex SVG paths with many bezier curves may lose precision during conversion due to DrawingML's shape model limitations","Requires Office 2016+ to open and edit generated PPTX files — older Office versions may not render all DrawingML features correctly"],"requires":["Python 3.10+","python-pptx library (for PPTX generation)","SVG source code (generated by Image Generator role)","Office 2016+ (to open and edit output)"],"input_types":["svg (with specific element types: rect, text, path, circle, polygon, group)"],"output_types":["pptx (with DrawingML shapes)","xml (DrawingML representation)"],"categories":["image-visual","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-hugohe3--ppt-master__cap_10","uri":"capability://automation.workflow.batch.presentation.generation.with.project.lifecycle.management","name":"batch presentation generation with project lifecycle management","description":"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.","intents":["I want to generate large presentations without losing progress if a slide fails","I need to iterate on specific slides without regenerating the entire presentation","I want to organize generated assets (SVG, images, PPTX) in a structured project directory"],"best_for":["teams generating large presentations (20+ slides) with complex content","projects requiring iterative refinement and slide-level control","organizations needing to track generation history and manage presentation versions"],"limitations":["Project state is file-based — requires careful file management to avoid corruption; no built-in database or version control integration","Cache invalidation is manual — if design templates or guidelines change, users must manually clear caches to regenerate affected slides","Resumable generation assumes slide independence — if a slide depends on previous slides (e.g., for numbering or cross-references), resuming from a failed slide may produce inconsistent results","Project directory structure is rigid — customizing folder organization requires modifying tools/project_utils.py"],"requires":["Python 3.10+","Project directory with proper structure (initialized via project_utils.py)","Slide specifications (from design specification document)"],"input_types":["project_config (canvas format, design guidelines, slide count)","slide_specifications (content and layout for each slide)"],"output_types":["project_directory (organized source, specs, SVG, images, PPTX)","generation_log (progress tracking and error reporting)"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-hugohe3--ppt-master__cap_11","uri":"capability://safety.moderation.quality.assurance.and.design.validation.with.automated.checks","name":"quality assurance and design validation with automated checks","description":"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).","intents":["I want to validate generated presentations against design guidelines before export","I need to ensure PowerPoint compatibility and catch shape errors early","I want to verify color contrast and typography consistency across slides"],"best_for":["teams with strict quality standards and design governance","organizations requiring accessibility compliance (WCAG color contrast)","projects where design consistency is critical"],"limitations":["Validation is rule-based — cannot catch subjective design issues (e.g., poor visual hierarchy, unbalanced composition) that require human review","Color contrast checking is automated but may produce false positives/negatives depending on background complexity and text rendering","Typography validation is limited to measurable properties (font size, weight) — cannot validate readability or appropriateness for content","Layout alignment checking assumes grid-based positioning — organic or freeform layouts may trigger false alignment warnings"],"requires":["Python 3.10+","Generated SVG or PPTX files","Design guidelines and validation rules (docs/design_guidelines.md)","QA tool configuration (strict vs. permissive mode)"],"input_types":["svg or pptx (presentation to validate)","validation_rules (design guidelines, compatibility rules)"],"output_types":["validation_report (issues, severity, remediation suggestions)","json (structured validation results for programmatic handling)"],"categories":["safety-moderation","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-hugohe3--ppt-master__cap_12","uri":"capability://image.visual.chart.template.library.with.data.driven.visualization.generation","name":"chart template library with data-driven visualization generation","description":"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).","intents":["I want to generate charts that match the presentation design system","I need to visualize data in presentations without manually creating charts","I want to reuse chart templates across multiple presentations"],"best_for":["teams creating data-heavy presentations (reports, dashboards, analytics)","analysts and data scientists needing to visualize data in presentations","organizations with standardized chart styles and design guidelines"],"limitations":["Chart templates are predefined — custom chart types not in the library require manual SVG creation and template definition","Data binding is template-specific — each chart type has different data format requirements; complex data transformations may be needed","Chart interactivity is limited — generated SVG charts are static; animations and drill-down interactions are not supported","Large datasets may produce complex SVG — charts with 100+ data points may have performance issues in PowerPoint or web viewers"],"requires":["Python 3.10+","Chart template library (templates/charts/)","Data source (CSV, JSON, or structured format)","Chart type specification (bar, line, pie, etc.)"],"input_types":["data (csv, json, or structured format)","chart_type (identifier matching templates/charts/)","styling_context (colors, fonts from design spec)"],"output_types":["svg (data-driven chart)","metadata (data range, series count, chart properties)"],"categories":["image-visual","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-hugohe3--ppt-master__cap_2","uri":"capability://automation.workflow.multi.format.canvas.adaptation.with.dynamic.layout.adjustment","name":"multi-format canvas adaptation with dynamic layout adjustment","description":"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.","intents":["I want to generate the same presentation content for multiple platforms (PowerPoint, social media, web) with appropriate aspect ratios","I need layouts to automatically adapt to different canvas dimensions without manual redesign","I want to create Xiaohongshu posts, WeChat content, and Instagram stories from a single content source"],"best_for":["content creators targeting multiple platforms (corporate presentations + social media)","marketing teams needing to repurpose content across different channels","developers building multi-format content generation systems"],"limitations":["Not all design patterns scale equally across formats — complex multi-column layouts designed for 16:9 may become unreadable at 3:4 aspect ratio and require manual intervention","Typography scaling is proportional but not intelligent — font sizes scale linearly with canvas size, which may result in illegible text on very small formats without explicit override rules","Social media format support is template-based — custom layouts for new platforms require adding entries to CANVAS_FORMATS and corresponding layout templates"],"requires":["Python 3.10+","Canvas format specification (one of: ppt169, ppt43, xiaohongshu, wechat, story, or custom dimensions)","Layout template library (templates/layouts/) with format-aware rules"],"input_types":["canvas_format_code (string identifier)","content_specification (design spec with page count and layout types)"],"output_types":["svg (with format-specific dimensions and margins)","pptx (for presentation formats)","png/jpg (for social media formats)"],"categories":["automation-workflow","image-visual"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-hugohe3--ppt-master__cap_3","uri":"capability://automation.workflow.template.driven.design.consistency.enforcement.with.library.based.components","name":"template-driven design consistency enforcement with library-based components","description":"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.","intents":["I want to ensure all generated slides follow a consistent visual language and design system","I need to reuse chart templates and icon libraries across multiple presentations","I want to enforce design guidelines programmatically rather than through manual review"],"best_for":["enterprises with strict brand guidelines requiring design consistency","teams generating high-volume presentations that need to maintain visual coherence","designers building reusable component libraries for AI-driven generation"],"limitations":["Template library is static — adding new chart types or icons requires manual creation and integration into templates/ directory","Design guidelines are documented but not fully automated — complex CRAP principle violations (e.g., poor visual hierarchy) require human review, not just rule-based validation","Icon library is limited to 640 icons — custom icons or domain-specific symbols require manual SVG creation and addition to templates/icons/"],"requires":["Python 3.10+","Template library files (templates/charts/, templates/icons/)","Design guidelines documentation (docs/design_guidelines.md)","Access to template metadata (JSON or YAML describing template properties)"],"input_types":["chart_type (string identifier matching templates/charts/)","icon_name (string identifier matching templates/icons/)","design_context (color scheme, typography rules from design spec)"],"output_types":["svg (template-based chart or icon SVG)","json (template metadata with dimensions and styling rules)"],"categories":["automation-workflow","image-visual"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-hugohe3--ppt-master__cap_4","uri":"capability://data.processing.analysis.source.document.parsing.and.content.extraction.with.format.normalization","name":"source document parsing and content extraction with format normalization","description":"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).","intents":["I want to convert a PDF report or Word document into a presentation without manual content extraction","I need to parse web content or Markdown files and structure them for presentation generation","I want to preserve document structure (headings, lists, tables) during conversion to presentation format"],"best_for":["teams converting existing documentation into presentations","researchers transforming academic papers or reports into visual formats","content creators repurposing web articles or blog posts as presentations"],"limitations":["PDF text extraction is lossy — scanned PDFs or PDFs with complex layouts may lose structural information; OCR is not built-in and requires external tools","DOCX parsing preserves basic formatting but loses advanced features (embedded charts, complex tables with merged cells, VBA macros)","URL parsing depends on page structure — JavaScript-rendered content or paywalled sites may not extract correctly; requires static HTML or server-side rendering","Table extraction is limited — complex tables with merged cells or nested structures may be flattened or lose semantic meaning"],"requires":["Python 3.10+","Source document (PDF, DOCX, Markdown, URL, or plain text)","python-docx library (for DOCX parsing)","PyPDF2 or pdfplumber (for PDF extraction)","requests library (for URL fetching)"],"input_types":["pdf","docx","markdown","url","plain_text"],"output_types":["normalized_json (with extracted text, structure, metadata)","markdown (intermediate representation)","design_specification (input to Strategist role)"],"categories":["data-processing-analysis","text-generation-language"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-hugohe3--ppt-master__cap_5","uri":"capability://image.visual.ai.driven.image.generation.with.style.consistency.and.template.integration","name":"ai-driven image generation with style consistency and template integration","description":"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.","intents":["I want to generate custom images for presentation slides that match the design theme","I need to integrate external image generation APIs (DALL-E, Midjourney) into the presentation pipeline","I want to ensure generated images are properly sized and positioned within slide layouts"],"best_for":["teams creating visually rich presentations without access to stock photo libraries","designers wanting to generate custom imagery that matches specific brand aesthetics","organizations with image generation API subscriptions (OpenAI, Midjourney, Stability AI)"],"limitations":["Image generation quality depends on prompt quality — vague or poorly structured prompts result in inconsistent or off-brand imagery; requires careful prompt engineering in Image Generator role","API costs scale with image count — generating high-quality images for 20+ slide presentations can be expensive ($5-50+ depending on API and quality settings)","Style consistency is prompt-based, not enforced — generated images may drift from design guidelines if prompts don't explicitly reference color schemes or visual style","Image generation latency is high — each image takes 10-60 seconds to generate, making real-time iteration slow"],"requires":["Python 3.10+","Image generation API key (OpenAI, Midjourney, Stability AI, or compatible)","Design specification with color scheme and style guidelines","Image embedding tools (for SVG integration)"],"input_types":["image_prompt (text description of desired image)","design_context (color scheme, style guidelines, canvas format)","slide_template (layout specification with image placement rules)"],"output_types":["png/jpg (generated image)","svg (image embedded in slide layout)","metadata (image dimensions, generation parameters, API usage)"],"categories":["image-visual","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-hugohe3--ppt-master__cap_6","uri":"capability://image.visual.svg.code.generation.with.layout.template.application.and.responsive.design","name":"svg code generation with layout template application and responsive design","description":"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.","intents":["I want to generate SVG code for presentation slides that follows a consistent layout template","I need to apply responsive design rules that adapt layouts to different canvas formats","I want to ensure generated SVG is compatible with PowerPoint conversion without manual fixes"],"best_for":["developers building presentation generation systems with template-based layouts","teams needing programmatic SVG generation with design consistency","organizations requiring responsive presentation layouts for multiple platforms"],"limitations":["Template-based generation is rigid — complex custom layouts not covered by existing templates require creating new template files and corresponding Executor role logic","Responsive design rules are proportional scaling — intelligent content reflow (e.g., wrapping text, adjusting column counts) requires explicit layout rules per template, not automatic","SVG validation is rule-based — some PowerPoint compatibility issues (e.g., complex gradient definitions) are only caught at conversion time, not during SVG generation","Font embedding in SVG may cause rendering differences — fonts must be available on the system generating PPTX or specified as web-safe alternatives"],"requires":["Python 3.10+","Layout template library (templates/layouts/)","Design specification with content and styling rules","SVG generation libraries (e.g., svgwrite or manual XML generation)"],"input_types":["slide_type (identifier matching templates/layouts/)","content_data (text, images, charts, tables)","design_context (colors, fonts, spacing rules)","canvas_format (for responsive layout adjustment)"],"output_types":["svg (slide layout with embedded content)","validation_report (PowerPoint compatibility check results)"],"categories":["image-visual","code-generation-editing"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-hugohe3--ppt-master__cap_7","uri":"capability://planning.reasoning.design.specification.generation.through.seven.confirmations.analysis.process","name":"design specification generation through seven confirmations analysis process","description":"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.","intents":["I want to ensure design decisions are explicit and documented before visual generation begins","I need a structured process to analyze content and determine appropriate visual treatment","I want to audit and approve design specifications before committing to generation"],"best_for":["teams requiring design review and approval before generation","organizations with strict design governance and audit requirements","projects where design decisions must be documented and traceable"],"limitations":["Seven Confirmations process adds latency — requires an additional LLM call and human review step before visual generation can begin","Process is sequential, not parallelizable — cannot start image generation or SVG generation until specification is approved","Specification document is human-readable but not machine-executable — downstream roles must parse and interpret the specification, which can introduce inconsistencies if parsing logic is imperfect","Requires human approval — automated specification generation without review may produce suboptimal design decisions"],"requires":["Python 3.10+","Source document (PDF, DOCX, Markdown, URL, or plain text)","Strategist role prompt (roles/strategist.md or equivalent)","Human reviewer for specification approval (optional but recommended)"],"input_types":["source_document (any format)","user_context (target audience, use case, constraints)"],"output_types":["design_specification_markdown (设计规范与内容大纲.md)","json (structured specification for downstream roles)"],"categories":["planning-reasoning","text-generation-language"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-hugohe3--ppt-master__cap_8","uri":"capability://automation.workflow.pptx.export.with.drawingml.shape.validation.and.office.compatibility.enforcement","name":"pptx export with drawingml shape validation and office compatibility enforcement","description":"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.","intents":["I want to export generated presentations to PPTX format that opens correctly in PowerPoint","I need to validate that generated shapes are compatible with Office before export","I want to embed metadata (notes, speaker notes) in the PPTX file"],"best_for":["teams generating presentations for Office environments","developers building PPTX export pipelines with strict compatibility requirements","organizations requiring validated, production-ready PPTX files"],"limitations":["PPTX export is one-way — cannot round-trip (PPTX → SVG → PPTX) without data loss due to DrawingML-to-SVG conversion limitations","Validation is rule-based — some Office compatibility issues (e.g., rendering differences across Office versions) are only discovered at runtime, not during validation","Large presentations (100+ slides) may have slow export times due to XML generation and validation overhead","Custom fonts must be embedded or available on target systems — font substitution may occur if fonts are not available"],"requires":["Python 3.10+","python-pptx library","SVG source (from SVG generation step)","DrawingML shape definitions (from SVG-to-DrawingML conversion)"],"input_types":["svg (with validated DrawingML-compatible shapes)","slide_metadata (title, notes, speaker notes)","export_options (compression, metadata embedding)"],"output_types":["pptx (Office Open XML format)","validation_report (compatibility check results)"],"categories":["automation-workflow","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-hugohe3--ppt-master__cap_9","uri":"capability://automation.workflow.web.gallery.generation.and.interactive.presentation.viewing","name":"web gallery generation and interactive presentation viewing","description":"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.","intents":["I want to share generated presentations with people who don't have PowerPoint installed","I need to create an interactive web gallery of presentation slides","I want to embed presentations in websites or share them via URL"],"best_for":["teams sharing presentations with non-technical stakeholders","content creators wanting to publish presentations on websites","organizations preferring web-based presentation sharing over email attachments"],"limitations":["Web viewer is read-only — users cannot edit shapes or content in the web gallery (unlike PPTX which is fully editable)","Interactive features are limited — animations, transitions, and speaker notes are not fully supported in web viewer","Browser compatibility varies — older browsers may not render SVG correctly; requires modern browser with SVG support","Responsive design is CSS-based — complex layouts may not reflow correctly on very small screens without explicit mobile layout rules"],"requires":["Python 3.10+","SVG slide assets (from SVG generation step)","Web server or static hosting (GitHub Pages, Vercel, etc.)","HTML/CSS/JavaScript for web viewer (provided in repository)"],"input_types":["svg (slide assets)","slide_metadata (titles, notes, order)"],"output_types":["html (interactive web gallery)","png (thumbnail previews)","json (slide metadata for web viewer)"],"categories":["automation-workflow","image-visual"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":41,"verified":false,"data_access_risk":"high","permissions":["Python 3.10+","AI IDE with file reading and shell execution (Claude Code, Cursor, VS Code + Copilot)","Access to LLM API (OpenAI, Anthropic, or compatible)","python-pptx library (for PPTX generation)","SVG source code (generated by Image Generator role)","Office 2016+ (to open and edit output)","Project directory with proper structure (initialized via project_utils.py)","Slide specifications (from design specification document)","Generated SVG or PPTX files","Design guidelines and validation rules (docs/design_guidelines.md)"],"failure_modes":["Requires manual role prompt maintenance — changes to design patterns require editing role templates in roles/ directory","Role handoff protocol adds latency — each role completion triggers next role invocation sequentially, not parallelized","Depends on AI IDE capabilities — only works within Cursor, Claude Code, or similar agent-capable environments","SVG-to-DrawingML conversion has strict compatibility rules — certain SVG features (filters, gradients with complex stops) cannot be directly converted and require fallback to rasterization","Complex SVG paths with many bezier curves may lose precision during conversion due to DrawingML's shape model limitations","Requires Office 2016+ to open and edit generated PPTX files — older Office versions may not render all DrawingML features correctly","Project state is file-based — requires careful file management to avoid corruption; no built-in database or version control integration","Cache invalidation is manual — if design templates or guidelines change, users must manually clear caches to regenerate affected slides","Resumable generation assumes slide independence — if a slide depends on previous slides (e.g., for numbering or cross-references), resuming from a failed slide may produce inconsistent results","Project directory structure is rigid — customizing folder organization requires modifying tools/project_utils.py","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.3530442970616146,"quality":0.5,"ecosystem":0.7000000000000001,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.1,"match_graph":0.35,"freshness":0.05}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:21.550Z","last_scraped_at":"2026-05-03T13:57:04.027Z","last_commit":"2026-05-02T14:59:04Z"},"community":{"stars":10887,"forks":1130,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=hugohe3--ppt-master","compare_url":"https://unfragile.ai/compare?artifact=hugohe3--ppt-master"}},"signature":"unH+glkIejc+DJrK6iw5Wm/zVLX6nGLdYQSy6jruyxQr9qoUFpA7sZWNqJMhziWb3CdWYbrPjJDpmhju91z/CA==","signedAt":"2026-06-22T02:48:48.107Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/hugohe3--ppt-master","artifact":"https://unfragile.ai/hugohe3--ppt-master","verify":"https://unfragile.ai/api/v1/verify?slug=hugohe3--ppt-master","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}