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.
Inherits all available tools
Additional assets for this skill
This skill inherits all available tools. When active, it can use any tool Claude has access to.
examples/board-deck-example.pyexamples/data-visualization-example.pyexamples/technical-presentation-example.pyreferences/brand-integration.mdreferences/complex-deck-architecture.mdreferences/design-principles.mdreferences/simple-deck-template.mdreferences/validation-checklist.mdreferences/workflow-diagram.dotresources/chart-config.jsonresources/chart-creator.pyresources/pptx-builder.shresources/presentation-template.pptxresources/slide-generator.pyresources/slide-layout.yamlresources/template-engine.jstests/test_integration.shtests/test_slide_generator.pytests/test_template_engine.jsYou are executing a specialized skill with domain expertise. Apply evidence-based prompting techniques: plan-and-solve decomposition, program-of-thought reasoning, and self-consistency validation. Prioritize systematic execution over ad-hoc solutions. Validate outputs against success criteria before proceeding. You are executing a specialized skill with domain expertise. Apply evidence-based prompting techniques: plan-and-solve decomposition, program-of-thought reasoning, and self-consistency validation. Prioritize systematic execution over ad-hoc solutions. Validate outputs against success criteria before proceeding. name: pptx-generation description: 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. version: 1.0.0 category: tooling tags:
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.
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.
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.
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.
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.
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.
Primary Use Cases:
Skill Triggers:
When NOT to Use:
Objective: Establish scope, constraints, and success criteria before design.
Process:
Decision Point: Simple deck (≤15 slides, single context) vs. Complex deck (30+ slides, multi-chat architecture)?
Objective: Establish coherent visual system before implementation.
Required Elements:
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).
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:
Technical Requirements:
Automated Checks:
Manual Review Points:
Failure Response: If validation fails, identify root cause, adjust design plan or implementation approach, and regenerate affected sections. Never apply band-aid fixes.
These constraints are absolute and apply to every slide in every deck. They eliminate known failure modes and ensure reliable spatial layout.
NEVER include these in any slide:
ALWAYS implement these in every deck:
Quantified requirements for every slide:
Non-negotiable standards:
Root Cause: Design plan not established before implementation, or not referenced during generation.
Solution: Always complete pre-execution design plan. Include design plan in context for each generator chat. Explicitly validate against design plan after each section.
Root Cause: AI switched from html2pptx to alternative tool without notification (tool degradation).
Solution: Enforce html2pptx workflow explicitly in prompt. Include statement: "Debug any installation issues; do not switch to alternative approaches." If problem persists, confirm tool is actually being used.
Root Cause: Positive instructions ("use clean design") given without corresponding negative constraints.
Solution: Lead with negative constraints in CAPITAL LETTERS at top of prompt. Repeat critical prohibitions in multiple sections. Make restrictions more prominent than positive instructions.
Root Cause: Validation gates not implemented or skipped.
Solution: Require explicit contrast ratio verification (show calculations). Test at thumbnail size before considering deck complete. Make accessibility validation non-optional.
Root Cause: Attempting complex deck in single conversation without multi-chat architecture.
Solution: Implement multi-chat architecture for decks >15 slides. Separate planning, generation, and assembly phases. Generate slides in sections of 10-15, not all at once.
This skill works synergistically with:
When used together, these skills enable complete board package generation (deck + memo + analysis) from raw data sources.
This skill includes comprehensive reference documentation:
references/simple-deck-template.md - Complete prompt template for ≤15 slide decksreferences/complex-deck-architecture.md - Multi-chat architecture for 30+ slide decksreferences/design-principles.md - Deep dive on constraint-based design philosophyreferences/validation-checklist.md - Detailed validation proceduresreferences/brand-integration.md - Process for applying brand guidelinesreferences/workflow-diagram.dot - Visual process flow (GraphViz format)Load relevant references as needed during implementation.
PowerPoint generation represents the intersection of data analysis, narrative structure, visual design, and spatial layout. This skill addresses the unique challenges through systematic workflow enforcement, evidence-based prompting techniques, and constraint-based design principles.
The key insight: Make constraints more explicit, not more complex.
Simple visual rules + Clear prohibitions + Forced planning = Reliable professional outputs
Success metrics: