pptx-generation
Enterprise-grade PowerPoint deck generation system using evidence-based prompting techniques, workflow enforcement, and constraint-based design. Use when creating professional presentations (board decks, reports, analyses) requiring consistent visual quality, accessibility compliance, and integration of complex data from multiple sources. Implements html2pptx workflow with spatial layout optimization, validation gates, and multi-chat architecture for 30+ slide decks.
What this skill does
# PowerPoint Generation Skill
## Overview
This skill implements a systematic framework for generating professional-quality PowerPoint presentations using AI. It addresses the unique challenges of PowerPoint as a medium that combines data analysis, narrative structure, visual design, and spatial layout—making it one of the most complex AI generation tasks in corporate knowledge work.
The skill applies evidence-based prompting techniques (plan-and-solve, program-of-thought, self-consistency), structural optimization principles (workflow enforcement, constraint-based design, validation gates), and proven spatial layout patterns to ensure consistent, high-quality outputs.
## Core Principles
### 1. Workflow Enforcement
AI systems exhibit tool degradation—silently switching to suboptimal alternatives when primary tools encounter difficulties. For spatial/visual tasks, this creates unreliable outputs.
**Implementation**: Explicitly specify the html2pptx technical workflow and prohibit alternative approaches. Require documentation review before execution.
**Rationale**: PowerPoint generation requires precise spatial calculations. The html2pptx skill provides reliable pixel-level control. Preventing tool switching eliminates the primary source of layout inconsistencies.
### 2. Constraint-Based Design Over Decorative Specification
Simple visual rules scale reliably; complex decorative elements create brittleness in AI generation.
**Implementation**: Define what NOT to do (negative constraints) before specifying positive behaviors. Prohibit border boxes, outline shapes, and rounded rectangles. Emphasize spacing, typography, and subtle color blocks.
**Rationale**: Visual design has exponentially more failure modes than success modes. Eliminating known problematic patterns focuses generative capacity within reliable boundaries. Clean design enables AI to prioritize content synthesis over visual parsing.
### 3. Pre-Execution Design Planning
Separating planning from execution prevents premature commitment to suboptimal visual approaches.
**Implementation**: Require written design plan specifying layout approach, color palette, typography hierarchy, and visual emphasis strategy before code generation.
**Rationale**: Mimics human design process. Creates audit trail for review. Establishes coherent visual system before implementation begins. Dramatically improves consistency across multi-slide decks.
### 4. Quantified Visual Specifications
Vague instructions ("clean margins") force the AI to guess intent. Precise specifications eliminate ambiguity.
**Implementation**: Convert qualitative requirements to measurable parameters (contrast ratios, font sizes, margin measurements, element counts).
**Rationale**: Spatial relationships are inherently quantitative. Explicit measurements create reproducible results and enable automated validation.
### 5. Multi-Chat Architecture for Complex Decks
Visual elements consume tokens faster than text or data. Single-context generation becomes unreliable beyond ~15 slides.
**Implementation**: Separate architect (narrative structure), generator (slide production), and assembly (consistency validation) into distinct conversations for 30+ slide decks.
**Rationale**: Manages context window limitations. Allows focused expertise in each phase. Enables section-level iteration without full deck regeneration.
## When to Use This Skill
**Primary Use Cases**:
- Board decks and executive presentations requiring professional polish
- Financial reports integrating data from multiple sources
- Strategic analyses combining quantitative and qualitative content
- Project updates demanding consistent visual language
- Any presentation where visual quality impacts stakeholder perception
**Skill Triggers**:
- User requests "create a presentation," "make slides," "build a deck"
- User asks to "analyze [data] and present findings"
- User mentions specific output formats: .pptx, PowerPoint, slides
- User provides business data (CSV, financial reports, memos) requesting visualization
- Task requires integrating analysis with narrative in visual format
**When NOT to Use**:
- Simple 1-3 slide requests (use default PowerPoint generation without full workflow)
- Requests for slide content only without visual implementation
- Non-presentation visualization tasks (use charts, graphs, or documents instead)
## PowerPoint Generation Workflow
### Phase 1: Requirements Analysis
**Objective**: Establish scope, constraints, and success criteria before design.
**Process**:
1. Identify data sources and required analyses
2. Determine slide count and narrative structure
3. Establish visual constraints (brand guidelines, accessibility requirements, template restrictions)
4. Clarify audience expertise level and presentation context
5. Define output quality standards
**Decision Point**: Simple deck (≤15 slides, single context) vs. Complex deck (30+ slides, multi-chat architecture)?
### Phase 2: Pre-Execution Design Plan
**Objective**: Establish coherent visual system before implementation.
**Required Elements**:
- **Layout Philosophy**: Describe approach to spacing, element positioning, visual hierarchy
- **Color Palette**: Specify exact hex values, contrast ratios, usage rules
- **Typography System**: Font families, size hierarchy (titles, headers, body, captions), line spacing
- **Visual Emphasis Strategy**: How information priority translates to visual weight (color blocks, spacing, sizing)
**Format**: Written description in structured format. Must be completed before any code generation begins.
**Validation**: Design plan must explicitly address all items in Design Restrictions (see below).
### Phase 3: Implementation
**For Simple Decks (≤15 slides)**:
Execute in single conversation following the prompt template in `references/simple-deck-template.md`.
**For Complex Decks (30+ slides)**:
Follow multi-chat architecture in `references/complex-deck-architecture.md`:
1. Architect Chat: Generate narrative structure and slide-level outline
2. Generator Chat(s): Produce sections of 10-15 slides each
3. Assembly Chat: Ensure consistency, validate against design plan
**Technical Requirements**:
- Always use html2pptx workflow
- Generate slides iteratively (never all at once for complex decks)
- Validate after each section before proceeding
- Maintain state document tracking completed slides and remaining work
### Phase 4: Validation
**Automated Checks**:
- Contrast ratio verification (minimum 4.5:1 for all text)
- Font size validation (18pt minimum, 24pt titles)
- Margin measurements (0.5" minimum all sides)
- Element overlap detection
- Bullet count per slide (maximum 3)
**Manual Review Points**:
- Thumbnail readability test
- Visual consistency across slides
- Narrative flow and logical progression
- Data accuracy and source attribution
**Failure Response**: If validation fails, identify root cause, adjust design plan or implementation approach, and regenerate affected sections. Never apply band-aid fixes.
## Design Restrictions
These constraints are absolute and apply to every slide in every deck. They eliminate known failure modes and ensure reliable spatial layout.
### Prohibited Elements
**NEVER include these in any slide**:
- Border boxes around text elements
- Outline shapes containing text content
- Rounded rectangles with text inside
- Text containers or frames
- Decorative borders or dividing lines as separate elements
- Overlapping text elements
- Dark text on dark backgrounds
### Required Patterns
**ALWAYS implement these in every deck**:
- Text directly on slide background or solid color areas
- Visual separation through spacing and typography (not containers)
- Colored accent bars or background sections (not outlined boxes)
- Subtle background color zones for emphasis (not bordered elements)
- Clean white or light-colored backgrounds
- High-contrast text (4.5:1 minimum ratio)
- Single visual element per slide (maxiRelated in Design
contribute
IncludedLocal-only OSS contribution command center. Auto-refreshes the user's in-flight PR and issue state on invoke so conversations start with full context — no need to brief Claude on what's in flight. Helps the user find issues to contribute to on GitHub, builds per-repo dossiers of what each upstream expects (CLA, DCO, branch convention, AI policy, draft-first, review bots, issue templates), runs deterministic gates before any external action so AI-assisted contributions don't reach maintainers as slop. State is markdown-only: candidate files at ~/.contribute-system/candidates/, repo dossiers at ~/.contribute-system/research/, append-only event log at ~/.contribute-system/log.jsonl. No database, no cloud calls. Use when the user asks about their PRs / issues / contributions, wants to find new work to take on, claim an issue, build/refresh a repo's dossier, or draft a Design Issue or PR. Trigger with "/contribute", "what's my PR status", "find a contribution", "claim issue X", "draft a Design Issue for Y", "refresh dossier for Z".
architectural-analysis
IncludedUser-triggered deep architectural analysis of a codebase or scoped subtree across eight modes — information architecture, data flow, integration points, UI surfaces, interaction patterns, data model, control flow, and failure modes. This skill should be used when the user asks to "diagram this codebase," "map the architecture," "show the data flow," "give me an ERD," "trace control flow," "find the integration points," "verify the layout pattern," "audit the UX architecture," or any similar request whose primary deliverable is mermaid diagrams plus cited reports under docs/architecture/. Dispatches haiku/sonnet sub-agents in parallel for per-mode exploration, then verifies every citation mechanically before any node lands in a diagram. Not for one-off prose explanations of code (use code-explanation) or for high-level system design from scratch (use system-design).
mcp
IncludedModel Context Protocol (MCP) server development and tool management. Languages: Python, TypeScript. Capabilities: build MCP servers, integrate external APIs, discover/execute MCP tools, manage multi-server configs, design agent-centric tools. Actions: create, build, integrate, discover, execute, configure MCP servers/tools. Keywords: MCP, Model Context Protocol, MCP server, MCP tool, stdio transport, SSE transport, tool discovery, resource provider, prompt template, external API integration, Gemini CLI MCP, Claude MCP, agent tools, tool execution, server config. Use when: building MCP servers, integrating external APIs as MCP tools, discovering available MCP tools, executing MCP capabilities, configuring multi-server setups, designing tools for AI agents.
react-native-skia
IncludedDesign, build, debug, and optimise high-polish animated graphics in React Native or Expo using @shopify/react-native-skia, Reanimated, and Gesture Handler. Use when the user wants canvas-driven UI, shaders, paths, rich text, image filters, sprite fields, Skottie, video frames, snapshots, web CanvasKit setup, or performance tuning for custom motion-heavy elements such as loaders, hero art, cards, charts, progress indicators, particle systems, or gesture-driven surfaces. Also use when the user asks for fluid, glow, glass, blob, parallax, 60fps/120fps, or GPU-friendly animated effects in React Native, even if they do not explicitly say "Skia". Do not use for ordinary form/layout work with standard views.
plaid
IncludedProduct Led AI Development — guides founders from idea to launched product. Six capabilities: Idea (discover a product idea), Validate (pressure-test the idea against fatal flaws, problem reality, competition, and 2-week MVP feasibility), Plan (vision intake + document generation), Design (translate image references into a design.md spec), Launch (go-to-market strategy), and Build (roadmap execution). Use when someone says "PLAID", "plaid idea", "help me find an idea", "product idea", "idea from my business", "idea from my expertise", "plaid validate", "validate my idea", "pressure-test", "is this idea good", "find fatal flaws", "validate the problem", "plan a product", "define my vision", "generate a PRD", "product strategy", "plaid design", "design from image", "translate image to design", "create design.md", "extract design tokens", "plaid launch", "go-to-market", "launch plan", "GTM strategy", "launch playbook", "plaid build", "build the app", "start building", or "execute the roadmap".
nextjs-framer-motion-animations
IncludedAdds production-safe Motion for React or Framer Motion animations to Next.js apps, including reveal, hover and tap micro-interactions, whileInView, stagger, AnimatePresence, layout and layoutId transitions, reorder, scroll-linked UI, and lightweight route-content transitions. Use when the user asks to add, refactor, or debug Motion or Framer Motion in App Router or Pages Router codebases, especially around server/client boundaries, reduced motion, LazyMotion, bundle size, hydration, or route transitions. Avoid for GSAP-style timelines, WebGL or 3D scenes, heavy scroll storytelling, or CSS-only effects unless Motion is explicitly requested.