deck-design-pdf

name deck-design-pdf description Create presentation decks as high-fidelity PDF files using web technology (HTML, CSS, Tailwind, Font Awesome). Use when the user wants a polished, pixel-perfect deck with responsive layouts, rich typography, icons, and modern design. For editable PPTX output, use deck-design-ppt instead. Deck Design PDF: Operational Playbook What This Skill Does Input: a deck brief + any structured data the user provides. Output: a PDF file : pixel-perfect slides rendered from HTML/CSS via Playwright. Not editable in PowerPoint. This is the high-fidelity, print-ready format. When to use this vs deck-design-ppt Need Skill Editable slides (PowerPoint/Keynote/Slides) deck-design-ppt Pixel-perfect PDF: web typography, icons, gradients, CSS layouts deck-design-pdf (this) What the web stack unlocks (beyond pptx) CSS Grid and Flexbox: responsive layouts instead of coordinate math Google Fonts with optical sizing and variable weights Font Awesome 6 icons inline with text Gradient backgrounds, box shadows, rounded corners, opacity ECharts 6 (SVG renderer): 21 chart types, including bar, line, pie, scatter, waterfall, gauge, sankey, treemap, radar, funnel, and heatmap Tailwind utility classes: rapid, consistent styling Phase 1: Understand and Route 1. Read the room Before asking the user anything, scan the working directory for artifacts that establish context: briefs, consultant storyboards ( *-ghost.md , *-outline.md ), data files, brand specs, existing build scripts. Read what's there and form a working hypothesis about what this deck needs: objective, audience, tone, density, and data. Then ask only for what's genuinely ambiguous and would change the deck's argument or audience calibration. Frame questions as choices, not open fields: "The data suggests a Bain decision-first structure. Does that fit, or is this more of an internal working session?" One sharp question beats five vague ones. Maximum 1–3 questions, and zero is fine if the artifacts are clear. 2. Classify the deck This determines how deep the planning phase goes. Two paths: Signal Path What happens next MBB engagement, strategy consulting, due diligence, cost transformation, M&A, pricing, org restructuring Consulting Load the full consulting reference library (ghost-deck.md, engagement-archetypes.md, skeletons/, firm-dna.md, evidence-recipes.md, density-adaptation.md). Build a rigorous ghost deck with archetype classification, pillar architecture, transitions, and firm overlay. Startup pitch, board update, product narrative, conference talk, investor roadshow, internal update General Stay in this playbook. Build a ghost deck using the universal quality gates below: governing thought, action titles, helicopter test, exhibit assignment. No archetype classification or skeleton required. Consultant handoff : if a storyboard from the consultant skill already exists (governing thought, pillars, action titles, content descriptions), the argument layer is done. Skip ghost deck construction entirely. Validate the argument (run the helicopter test on the titles), then proceed to the production outline. 3. Pick style and density Style: If the deck is… Palette Surface Font Consulting / board / engagement deliverable consulting-mckinsey Light Inter Framework evaluation, process-transparent consulting-bcg Light DM Sans Diagnostic, decision support, facts-vs-perspectives consulting-bain Light Source Sans 3 Startup pitch / product narrative / growth story founder Light Plus Jakarta Sans Crisis / urgency / downturn memo / high-stakes sequoia Dark Georgia + Inter Warm, rigorous-but-human strategy work (Anthropic-adjacent ivory + clay) anthropic-consulting Light Manrope (not vendored, load via headExtra ) Google-ecosystem client engagement (muted Google Blue) meridian-google Light Inter The vendored font families are Inter, DM Sans, Plus Jakarta Sans, and Source Sans 3. The agent is not limited to these. Any Google Font can be loaded via a <link> tag in headExtra when the brief calls for a different typeface. Brand identity intake (from brand-system skill) : if an identity.js produced by the brand-system skill exists in the working directory, the style decision is already made. Do not route through the table above: Palette : identity.js emits engine-compatible palette CSS. Write it into this skill's palette directory, then pass its name to createDeck : const fs = require ( 'fs' ); const brand = require ( './identity' ); fs. writeFileSync ( '<this-skill>/palettes/' + brand. palette . name + '.css' , brand. toCSS ()); // then: createDeck({ palette: brand.palette.name, ... }) Fonts : if brand.fonts names a family outside the vendored four, load it via a Google Fonts <link> in headExtra (network required at build time) or accept the stack's system fallback. Style direction : brand.style routes composition treatment, not colors: identity.js style Compose like Treatment institutional consulting-mckinsey Restrained chrome, sharp corners, rules over boxes modern founder Cards, rounded corners, confident accent use dark sequoia Dark surfaces as default, high-contrast accents bento founder Card-grid compositions dominate, surface-muted tiles editorial none Typography-led: oversized headings, fewer panels, whitespace as structure data-forward consulting-bcg Chart-dense, panel mini-headers, minimal decoration The identity's colors and fonts are authoritative. Layout and composition belong to this skill. Density: Context Level What changes Startup pitch, roadshow, board update L1 Narrative 1 message per slide. Fewer elements, each scaled up to fill the body zone. Corporate strategy, business review L2 Structured Multi-panel layouts. Evidence density moderate. MBB engagement, due diligence, deep analysis L3 Dense Multi-evidence composites. Chained arguments. Show deck vs. working deck : infer from audience and objective, don't ask. "Board presentation" → tier: 'presentation' (body ≥15pt, room-safe). "Diligence data room" → tier: 'document' (body ≥12pt, dense but legible). The tier shifts ALL text tokens automatically. For L2+ consulting decks, apply firm-specific conventions from firm-dna.md . For density adaptation rules, see density-adaptation.md . Phase 1.5: Ghost Deck Before writing any HTML, build the ghost deck , the narrative skeleton that precedes all visualization. Charts and code are execution. The ghost deck is the thinking. The ghost deck process produces two artifacts: {slug}-ghost.md : the argument layer. Governing thought, action titles, exhibit types. A senior reviewer can approve this without knowing CSS. {slug}-outline.md : the execution layer. Ghost deck + density tiers, layout geometry, chart dimensions, column alignment. This is what the build phase reads. Process management. Building a ghost deck requires populating multiple interdependent layers and passing quality gates that may trigger backtracking. Use your task management tools to track which layers are complete, which gates have passed, and what needs revisiting. Externalize this state. Don't try to hold it all in one pass. Universal quality gates These apply to every deck : consulting, startup, board update, conference talk. They are not consulting methodology. They are good deck design. Start from the governing thought, one sentence that states the deck's answer. Build pillars that support it. Write action titles for every slide before you touch any charts. Read the titles in sequence. If they don't tell a complete story, the problem is in the pillars, not the titles. Only assign exhibits once the argument holds. Cut any slide that isn't load-bearing. What must exist in every ghost deck: Layer What it is Depends on Governing thought One sentence: the deck's answer. If you can't write it, the analysis isn't done. The brief and data Action titles Full-sentence conclusion for every slide. "Revenue grew 12% driven by pricing power", not "Revenue Overview." Governing thought Helicopter test Read all titles in sequence. Complete, persuasive story in 2 minutes? If not, fix the titles. Action titles Exhibit assignment What visual proves each slide's claim. Use chart-taxonomy.md : "What does this slide need to prove?" → exhibit type. Helicopter test passed Dead slide test Can any slide be removed without breaking the argument? If yes, remove it. All of the above Common deck patterns. For non-consulting decks, chart-taxonomy.md § Deck Archetypes provides narrative arcs and exhibit mixes for common formats: investor/roadshow (Problem → Solution → Traction → Market → Model → Team → Ask), board updates (Headlines → KPIs → Progress → Risks → Decisions), due diligence memos, transformation roadmaps, and more. Use these as starting points for the slide sequence, then write action titles and apply the quality gates above. Don't force a pattern that doesn't fit the brief. Adapt or combine as the argument requires. Backtracking, not patching. If the helicopter test fails, the problem is upstream: the pillars don't support the governing thought, or the titles are topic labels instead of conclusions. Go back to where the argument breaks. Don't patch titles to paper over a structural gap. When the brief supports multiple valid governing thoughts : surface the options and let the user choose before proceeding. Otherwise, commit to the strongest hypothesis and work forward. Consulting path For MBB engagements and strategy consulting, the ghost deck goes deeper. Load the full reference library: Doc Purpose ghost-deck.md 5-layer model, quality gates, anti-patterns engagement-archetypes.md 8 archetypes, 5 transition types, rising-stakes progression skeletons/*.md Pillar architecture, slide-by-slide index, kill conditions per archetype firm-dna.md McKinsey/BCG/Bain epistemology, communication signatures evidence-recipes.md 10 data-shape recipes, layering rules density-adaptation.md L1/L2/L3 compression/expansion rules On top of the universal quality gates, the consulting path adds: Archetype classification : classify the engagement using engagement-archetypes.md , then load the matching skeleton from skeletons/ . The skeleton provides a pillar architecture and slide-by-slide index as a starting point. Customize it to the specific brief. Pillar architecture : 3–5 MECE pillars supporting the governing thought. Work backward: "What must be true for the governing thought to hold?" Transition architecture : at each pillar boundary, select a transition type (Pivot, Narrowing, Escalation, Synthesis, Decision Gate). Verify rising-stakes progression: Recognition → Clarity → Conviction → Urgency. Firm overlay : apply firm-dna.md conventions for the target firm style. This affects header structure, communication signature, and composition patterns, not the argument itself. Evidence recipes : for each exhibit, check evidence-recipes.md for the standard composition: primary chart + supporting elements + annotation layers, governed by density level. These layers have dependencies (you can't design transitions until pillars exist, and you can't assign evidence recipes until exhibits are selected), but the agent decides the working order based on what the brief gives it. A brief with strong data might start from what the data proves and work backward to the governing thought. A brief with a clear strategic question might start top-down. Consultant handoff When a storyboard from the consultant skill already exists (governing thought, pillars, action titles, content descriptions, structured data), the argument layer is done. This skill inherits it and focuses on production: Run the helicopter test on the provided action titles. If titles read as topic labels rather than conclusions, strengthen them. For each slide, use the content description + chart-taxonomy.md decision tree to select exhibit types. The consultant describes WHAT each slide proves. This skill decides HOW to visualize it. This skill may tighten action titles, add transition slides, or adjust slide count for density. The consultant's governing thought and pillar architecture are authoritative. Exhibit selection and layout composition belong to this skill. Presenting the ghost deck Once the ghost deck is complete, present it to the user as the storyline : just the action titles in sequence. This is the helicopter test output: Here is the argument this deck makes, read top to bottom: 1. [Action title] 2. [Action title] ... Does this story hold? Anything missing, out of order, or unconvincing? Don't print the full outline with density tiers and exhibit types. That's implementation detail. The user's job is to validate the argument, not review the geometry. If they approve, proceed to the production outline. If they redirect, revise and present again. Production outline The production outline ( {slug}-outline.md ) extends the ghost deck by adding geometry to every slide. This is the contract between thinking and building: the build phase copies these numbers, no sizing reasoning required at code time. For every slide in the ghost deck, add: Density tier : which CSS class governs typography Layout : composition type + percentage split (e.g., "asymmetric split, left 60% / right 40%") Column alignment : items-start when columns differ in content height, items-center only for visually balanced columns Chart spec : explicit dimensions derived from the space budget (see § Space audit below) Evidence layers : 1 for L1, 1–2 for L2, 2–4 for L3 N. **Action title (full sentence conclusion)** - Density: sd-medium - Layout: asymmetric split, left 60% / right 40% - Column alignment: items-start - Exhibit: clustered bars (market share by segment) - Chart spec: 700px × 480px. Body 600px − 120px (top labels + gap) = 480px - Data: SWE-bench scores, coding market share - Evidence layers: 2 Save as {slug}-outline.md . The ghost deck is not modified. It remains the clean argument document. Outlines that omit exhibit types produce decks dominated by KPI cards and text bullets, the most common quality failure. The outline must have Layout + Exhibit before the build starts. Space audit Before writing any code, run a space audit on every slide that contains a chart or diagram. The slide canvas is 1280×720px. After header (~76px) and footer (~44px), the body zone is ≈ 600px tall, ≈ 1168px wide (56px margins each side). In a two-column layout, each column is ≈ 576px. For each chart slide: subtract any non-chart content (card rows, KPI strips, table rows, gaps) from the 600px body height. The remainder is the chart height. Write this math in the outline. The build agent copies the number directly. body height 600px − top content Apx − bottom content Bpx = chart height Key rules: If chart height > chart width for that column, the chart is portrait. That's correct. Portrait orientation eliminates blank space structurally. If two columns have different content heights, set align-items:start . Don't default to center. If the computed chart height exceeds the density class default, override it. The space budget wins. Estimation reference (1280×720): Content element Estimated height 3-card row (compact) ~120px KPI metric strip (3–4 numbers) ~80px Table (5 rows) ~180px Gap between elements 16–24px Phase 2: Build How to build slides Read {slug}-outline.md . Each slide entry has an action title, exhibit type, layout, and chart dimensions. The build phase executes these specs. It does not re-derive them. Sizing decisions were made in the outline. The build agent copies the numbers. You are composing custom HTML for each slide based on the user's actual data and the outline's argument. You are NOT filling in a template. The examples under examples/*.js are visual pattern references. Study their approach, then write original HTML that serves the specific argument. Space budget reference. At 1280×720, the available zones are: Zone Pixels Notes Slide canvas 720px tall, 1280px wide Fixed Header zone ~76px Section label + title + accent bar + padding Footer zone ~44px Source line, fixed by grid shell Body height ≈ 600px What remains. This is your working space Horizontal margin 56px each side Tailwind px-14 Content width ≈ 1168px 1280 − 112px margins Each column (2-col) ≈ 576px (1168 − gap) ÷ 2 For each slide in the outline: Set the tier : 'presentation' for any deck projected in a room or read by executives. 'document' (default) for working sessions and analysis. The tier shifts all text baselines automatically. Do not adjust individual font sizes. Infer from audience and objective. Don't ask. The action title tells you what to prove . The exhibit type tells you how to prove it . The chart spec tells you the exact dimensions . Read the relevant example file to learn the visual pattern: the ECharts config structure, the CSS layout approach, the annotation placement. Do not copy its data or dimensions. Compose the slide HTML with the user's real data. Use the slide shell (header → body → footer). Apply palette CSS custom properties. Never hardcode brand colors. Size slide text through the Tailwind type roles (build-reference.md § Typography scale). Inside ECharts config, compute font sizes and geometry from the chart's actual width and height the way the examples do: declared [min, max] ranges with clamped interpolation, not fixed magic numbers. What to learn from each example: Look at To understand ECharts setOption({...}) structure Which config keys produce this chart type The "Brand variables" block Which colors and fonts are meant to be swapped from the palette The "Sizing limits" + computed sizing block How fonts and geometry interpolate with canvas width/height The "ECharts gotchas" header comment Library pitfalls this pattern already solved: label colors, wrapping, containLabel Semantic color usage Accent for focus, gray for context, green/red for deltas The proves field What analytical question this pattern answers