Skip to main content
skill CX Codex

presentation-design · agentara — Claude Code skill: what it does, how to install

presentation-design creates a 6-slide presentation storyboard as a single 3:2 composite image. Useful for concept validation and pitch deck visuals via image generation models.

MIT 250 installs ★ 635 updated 2026-09-29

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add agentara/skills --skill presentation-design -a claude-code
Open on GitHub

What presentation-design does

The skill drafts a presentation concept arranged in a 2-column by 3-row grid, where each tile maintains a 16:9 ratio. It starts by extracting the topic and audience, then prompts you to pick between light and dark modes. Before rendering, the entire narrative arc is written to presentations/{name}.plan.md for explicit confirmation.

Once the outline is approved, it calls the image_gen tool to produce the composite PNG at presentations/{name}.png. Deterministic code and SVG scripts are skipped; the visual board depends entirely on a raster image generation model.

The skill runs a two-pass review on the rendered file to verify layout alignment and palette consistency. If issues appear, it retries up to 2 times automatically. It will not output editable PowerPoint or Keynote files.

What it helps with

  • Create a 6-slide visual storyboard on a single composite board
  • Plan slide structure and bullet points prior to rendering
  • Select matching layouts and light or dark color schemes
  • Review presentation concepts on a TV-style 3:2 layout

Example prompts for the agent

  • Create a 6-slide strategy deck visual for our executive review.
  • Design a keynote-style slide board for an AI product launch in dark mode.
  • Draft a presentation mockup analyzing recent market data.

How to install presentation-design

1Skills CLI (Vercel)

npx skills add agentara/skills --skill presentation-design -a claude-code

2Manually: put the files in place

~/.claude/skills/presentation-design/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/presentation-design/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about presentation-design

How do I install presentation-design in Claude Code?

Run npx skills add agentara/skills --skill presentation-design -a claude-code in your terminal.

What does presentation-design do?

It drafts a 6-slide presentation spec and renders a single composite PNG board in a 2x3 grid using an image generation model.

Does presentation-design produce editable PPTX or Keynote decks?

No, it only creates a rendered image file at presentations/{name}.png and a markdown plan, without exporting editable slide files.

Source text

SKILL.md · MIT
---
name: presentation-design
description: Generate a premium 6-slide presentation design board as one single composite image. Use this skill whenever the user asks for PPT design concepts, keynote-style slide mockups, a strategy deck visual, an editorial / sports / news / business analysis deck, a TV-friendly slide layout, or any "6-page slide board" / "design these slides" / "PPT 设计稿" / "幻灯片设计图" request. The skill plans the deck slide-by-slide, asks the user to pick light vs dark mode, selects layouts from a named layout library, has the user approve the plan, then generates the composite image and self-reflects on the rendered result. Do NOT trigger for text-only deck outlines (the user wants writing, not visuals), single-slide design (this skill always produces 6), or live editable PPTX/Keynote files (this skill produces a rendered image).
---

# Presentation Design

Create a **premium 6-slide presentation design board** as one single composite image — a board view that lets the user see the whole deck at a glance, TV-ready and cinematic.

Primary use cases: PPT design concepts, keynote-style slide mockups, strategy deck visuals, event / news / sports / business analysis decks, editorial data stories, executive presentations.

## Image Generation Requirement

The final board must be generated by an **image-generation model** (use the built-in `image_gen` tool by default, or an approved project image-generation workflow). Do not create the board with code, SVG, HTML/CSS, canvas, diagrams, placeholder drawings, or deterministic shape scripts. Those methods may be used only for non-visual file operations or optional post-processing after the model-generated image exists.

Save the model-generated raster output to `presentations/{name}.png`. If the model output cannot be saved directly, locate the generated raster asset and move/copy it into the required path; do not recreate it programmatically.

## Output Contract

One single image containing all 6 slides:

```text
┌──────────────┬──────────────┐
│ Slide 01     │ Slide 02     │
├──────────────┼──────────────┤
│ Slide 03     │ Slide 04     │
├──────────────┼──────────────┤
│ Slide 05     │ Slide 06     │
└──────────────┴──────────────┘
```

- **6 slides total**
- **2 columns × 3 rows**
- **each slide visually reads as 16:9**
- **overall composite board is 3:2**
- single composite PNG

## Output Location

```text
presentations/
  {name}.plan.md     # the approved deck plan (spec)
  {name}.png         # the final composite image
```

Use lowercase, hyphenated, ASCII-safe names. For revisions, suffix with `-v2`, `-final`, `-alt-a`. Do not overwrite existing files unless the user asks for replacement.

## Inputs to Extract

Before designing, identify:

- Topic / subject of the deck.
- Audience (executives, fans, general public, B2B buyers, students, etc.).
- Tone (cinematic, analytical, celebratory, urgent, premium, playful).
- Brand colors or required accents, if any.
- Required language for slide text (English, Chinese, bilingual, etc.).
- Any specific data, charts, maps, portraits, products, or symbolic visuals that must appear.
- Output name, if specified.

If the user does not specify language, use the user's local language.

## Workflow

1. **Extract inputs** from the user's brief (see *Inputs to Extract*).
2. **Ask the user for style mode: `light` or `dark`** — always ask via `AskUserQuestion` (do not silently infer). Offer `dark cinematic` as the default suggestion when the topic is ambiguous.
3. **Load `references/style-modes.md`** and pick the most appropriate sub-mode (e.g. `dark sports broadcast` for an NBA recap, `light minimal keynote` for a B2B SaaS pitch). Briefly state the chosen palette and typography direction to the user.
4. **Load `references/slide-layouts.md`** and select **6 layouts** that together form a coherent narrative arc. Mix layouts — do not repeat the same one across all 6. Always use `hero-title` for slide 01 and `closer` for slide 06 unless the topic demands otherwise. State the chosen layout sequence.
5. **Write the deck plan** (mandatory) to `presentations/{name}.plan.md`. For each of the 6 slides include:
   - `slide_no` — `01`–`06`.
   - `layout` — one of the names from the layout library.
   - `title` — the headline that will appear on the slide.
   - `subtitle` — optional one-line framing.
   - `content` — 3–6 short bullets / key points in slide-native language (no essay paragraphs).
   - `visual` — description of the hero image, chart, map, portrait, or symbolic visual that occupies the tile, plus how it integrates with the text.
   - `accent_use` — where the accent color appears on this slide (title, divider, chart highlight, etc.).

   Show the plan to the user and **wait for confirmation or revisions**. If the user revises, update `presentations/{name}.plan.md` and re-confirm before proceeding.
6. **After the user approves the plan, generate the first composite image** with `image_gen`. Build the prompt by composing:
   - Output contract (3:2 board, 2×3 grid of 16:9 tiles, single PNG).
   - Selected style mode + palette + typography direction from `references/style-modes.md`.
   - For each of the 6 slides: layout name + title + content bullets + visual description + accent usage from the approved plan.
   - Content density rules and board-level composition rules (see below).

   Save the result to `presentations/{name}.png`.
7. **Self-reflect on the rendered image** (mandatory). Inspect the saved PNG and run both passes — *Pass 1: Structure & Story* and *Pass 2: Visual Polish* — against the actual rendered result, not just the plan. Check specifically for:
   - Grid is 2×3 and each tile reads as 16:9.
   - Slide titles are present, legible, and match the plan.
   - Accent color is used consistently across all 6 slides.
   - Image treatment looks integrated, not pasted-on stock-photo.
   - Layouts on each tile match the assigned layout names.
   - No redundant or off-topic slides.
   - Charts, maps, numbers, and quotes are readable on a TV-sized screen.
8. **Decide: ship or regenerate.** If self-reflection finds material issues, regenerate — either re-render the full board with a tightened prompt, or do a targeted fix (re-prompt focused on the broken slide(s), instructing the model to preserve the rest of the board). Cap automatic regeneration at **2 retries** before surfacing remaining issues to the user. Save the final accepted image to `presentations/{name}.png` (overwrite prior drafts); optionally keep `presentations/{name}-v1.png` etc. for debugging.
9. **Respond to the user** with: the saved image path, the deck plan path, the style mode chosen, the layout sequence, and a short note on anything the self-reflection could not fully resolve.

## Content Density Rules

Each slide should be rich but not cluttered. Preferred density per slide:

- 1 main title.
- 1 short subtitle or framing line (optional).
- 3–6 short content points.
- 1 dominant visual system (hero image, chart, map, portrait, product, or symbolic scene).
- Optional chart, metric card, or timeline element.

Avoid: essay-like writing, too many bullet points, overexplaining, raw article summaries, tiny unreadable text, excessive icons, inconsistent information density.

Use slide-native language: short, sharp, visual, structured, easy to scan.

## Board-Level Composition Rules

- The full image is **3:2**.
- The 6 slides are arranged in **2 columns × 3 rows**.
- Slides have clean gutters or subtle borders between tiles.
- Consistent margins across the board.
- All 6 tiles share the same style mode, accent system, and typography — the deck must feel unified at a glance.
- Accent color usage must be consistent across all 6 slides.
- Each slide should have a clear focal point, strong title hierarchy, enough breathing room, integrated visuals, readable text, and the premium presentation feel defined in *Quality Bar*.

## Self-Reflection Loop

Always run both passes before declaring the board final.

### Pass 1 — Structure & Story

Check:

- Is the 6-slide story coherent?
- Does each slide have a clear role?
- Is the order logical?
- Is anything missing?
- Is any slide redundant?
- Is the content too vague or too crowded?

Improve: slide sequence, narrative clarity, content hierarchy, factual compression, section naming.

### Pass 2 — Visual Polish

Check:

- Does the board look premium?
- Is the chosen mode (dark or light) elegant, not muddy or flat?
- Is the design suitable for TV display?
- Are the images naturally embedded?
- Are there repeated or boring layouts?
- Is the contrast strong enough?
- Do all 6 slides feel like one deck?

Improve: contrast, spacing, typography, color balance, hero image integration, chart readability, cinematic depth, consistency.

## Quality Bar

The final design **should** feel like:

- a premium conference deck
- a high-end sports broadcast graphic package
- a cinematic strategy presentation
- an editorial data story
- a TV-ready executive presentation

The final design **must not** feel like:

- a random collage
- six unrelated posters
- a comic page
- a low-effort infographic
- a plain document
- a cluttered dashboard
- a generic template

## References

Load these on-demand during the workflow — they are not read by default to keep this file lean.

- [`references/slide-layouts.md`](references/slide-layouts.md) — named layout library. Load at workflow step 4 when choosing the 6-slide composition.
- [`references/style-modes.md`](references/style-modes.md) — light / dark sub-modes with concrete palettes and typography direction. Load at workflow step 3 after the user picks light or dark.

© agentara · MIT · agentara/skills

Similar skills

All skills for Design →

presentation-design by other authors comes first.

presentation-design jwynia presentation-design — a skill that shapes presentations around the audience: structure, visual clarity, cognitive load. Use it before building a deck or to review existing slides. CX Codex +1 2,800installs presentation-design aaronvanston presentation-design sets visual rules for bold, minimal decks: dark theme, oversized headlines, per-section accent colors. Useful when you need to turn content into a slide structure. CX Codex +1 823installs presentation-deck WHOISABHISHEKADHIKARI presentation-deck is a Claude Code skill that builds structured slide registers and narrative flows. Generates evidence-backed pitch decks, board updates, and speaker notes. CX Codex +1 ★ 85repo stars presentation-design-enhancer OneWave-AI presentation-design-enhancer turns text-heavy slides into visual storytelling, suggesting layout changes, icons and ways to show data. CX Codex +1 603installs presentation-generation eachlabs The presentation-generation skill sends slide-generation requests to each::sense AI. Use it to draft a pitch deck, business presentation, training material, or conference talk. CX Codex +1 309installs canva-branded-presentation official Canva Pty Ltd. canva-branded-presentation creates on-brand Canva presentation decks from briefs, raw outlines, or design links. Useful when you need slides formatted to your brand kit. CX Codex GP ChatGPT +1 26installs presentation-master krishagel presentation-master guides presentation planning, slide visuals, and quality checks. Use it to shape a talk, training deck, or executive update before building the slides. CX Codex +1 3installs slide genspark-ai slide is a prompt for Claude Code and ChatGPT that handles page-level presentation edits: deleting, duplicating, inserting by layout, moving, and changing backgrounds. GP ChatGPT ★ 12,746repo stars

From the same set20

The whole set →
video-character-design video-character-design creates character design sheets and markdown specs for storyboards and AI video. It writes a spec for your approval before generating any character images. CX Codex +1 396installs video-plan video-plan turns rough concepts into timed, scene-by-scene plans for short videos, vlogs, and social clips. It splits footage into 4-15 second cuts and sets a visual tone. CX Codex +1 321installs lab-interpreter lab-interpreter is a Claude Code skill that reads lab reports and explains abnormal results in plain language when you upload test results. CX Codex +1 284installs video-poster-design video-poster-design creates cinematic poster concepts and final images from a brief, storyboard, or project context. Useful for key art, teaser posters, and video campaigns. CX Codex +1 271installs article-to-html article-to-html turns Markdown or a document from the conversation into one self-contained HTML file. Use it for a static article page, not slides or a backend. CX Codex +1 220installs doctor-strange doctor-strange runs multi-branch causal scenario simulations using subagents and records synthetic projections into persistent assistant memory. CX Codex +1 212installs mega-goal-prompt mega-goal-prompt interviews you step by step to build a structured /goal mega prompt for autonomous tasks in Claude Code or Codex CLI. CX Codex +1 195installs soviet-storybook-grotesque soviet-storybook-grotesque transforms photos into strange retro storybook drawings with shaky ink lines, faded watercolor, and nonsensical English rhymes. CX Codex +1 190installs

Project sponsors

Companies that keep this analytics open