Skills DirectorySkills Directory
SkillsLearnSecurityCategoriesDocsBlogPro
Sign InSubmit Skill
Skills Directory

Security-tested agent skills for Claude, coding agents, and AI workflows.

Directory

  • Browse Skills
  • All Skills A–Z
  • Claude Skills
  • Claude Code Skills
  • Agent Skills
  • Categories
  • Authors
  • Submit a Skill

Learn

  • Learn Hub
  • Install Claude Skills
  • Write SKILL.md
  • Skills vs MCP
  • Directories Compared

Security

  • Security
  • Methodology
  • Secure Claude Skills
  • Security Badges
  • Chrome Extension
  • Skill Manager

Company

  • About
  • Community
  • Blog
  • API Docs
  • Advertise

2026 Skills Directory. All rights reserved.

ProTermsPrivacyRefunds
Back to skills

Presentation Designer

ASecurity

Design compelling slide decks with narrative structure, visual clarity, and delivery-ready polish.

2 stars
0 votes
0 copies
1 views
Added 9/29/2026
ai-agentsgo

Works with

cli

Security Analysis

A100/100

Scanned 9/29/2026

$npx -y skills add aicodedecode/awesome-muse-skills --skill presentation-designer --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Presentation Designer?

Add the live security badge to your README — it updates automatically with every re-scan.

Security grade badge for Presentation Designer
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/aicodedecode-presentation-designer/badge)](https://www.skillsdirectory.com/skills/aicodedecode-presentation-designer)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
Files
SKILL.md
---
name: presentation-designer
description: Design compelling slide decks with narrative structure, visual clarity, and delivery-ready polish.
category: creative-design
---

## Overview

Great presentations are stories with slides, not documents with animations. The
designer's job is to
make the narrative land: one idea per slide, visuals that amplify (not
duplicate) the speaker's
words, and a deck that works both presented and read. This skill covers
narrative structure, slide
design craft, and the practical details of delivery.

## When to use

- Designing pitch decks, keynote presentations, or sales decks

- Turning a dense report into a presentable slide narrative

- Fixing a "wall of text" deck

- Creating templates for team or company use

- Preparing for an important talk or investor meeting

## Core concepts

- - - **Narrative first, slides second.** Outline the story before designing
  anything: the tension
  (problem), the turn (insight), the resolution (your solution/proposal), the
ask. Slides serve the
  story arc.
- - - **One idea per slide.** If a slide needs "and also," it needs to be two
  slides. Audiences can
  hold one point at a time; decks that respect this feel effortless.
- - - **Assertion-evidence structure.** Headline states the conclusion ("Churn
  dropped 40% after
  onboarding revamp"), body provides the evidence (chart, image, 3 bullets max).
Headlines that just
  label ("Q3 Results") waste the most valuable line.
- - - **Visuals amplify, text supports.** A slide the audience must read is a
  slide competing with the
  speaker. Aim for glanceable: big number, simple chart, evocative image — with
you providing the
  narrative.
- - - **The 10/20/30-ish rule.** Keep it tight: ~10 key ideas, ~20 minutes of
  content for a 30-minute
  slot (leave room for discussion), 30pt minimum-ish for body text. Fewer,
bigger, clearer.
- - - **Design the read-alone version.** Most decks get forwarded without the
  speaker. Speaker notes
  or an appendix should let the deck survive on its own — without cluttering the
presented slides.

## Practical workflow

1. 1. 1. **Write the story.** Outline: opening (why should they care?), 3-5 key
   points in logical
   sequence, closing (what should they do/feel?). Get the narrative approved
before designing.
2. 2. 2. **Storyboard the slides.** One line per slide: the assertion headline.
   Check the headlines
   alone tell the story — they should read as an executive summary.
3. 3. 3. **Design the system.** Title layouts, section dividers, content layouts
   (big number, chart,
   image+text, quote), consistent footer/numbering. Build the master slides
first.
4. 4. 4. **Build for glanceability.** Maximum ~30 words per slide (fewer is
   better), charts simplified
   to one message (highlight the data point, gray out the rest), images
full-bleed where they earn
   it.
5. 5. 5. **Refine the details.** Alignment, consistent chart styles, readable
   font sizes from the back
   of the room (test at 50% zoom), accessible color contrast, alt text for key
visuals.
6. 6. 6. **Rehearse with the deck.** Time it, note where slides fight the
   narration, cut ruthlessly.
   Every slide that doesn't advance the story is a candidate for the appendix.
7. 7. 7. **Prep delivery files.** PDF backup (fonts embedded), 16:9 and 4:3
   versions if the venue is
   unknown, videos embedded (not linked), clicker tested, notes printed or on a
second device.

## Common pitfalls

- - - **The document-deck.** 200 words per slide, 60 slides, read aloud to the
  audience. If it's a
  document, send a document; if it's a presentation, present.
- - - **Bullet-point anesthesia.** Slide after slide of undifferentiated
  bullets. Vary layouts, use
  visuals, and remember: bullets are for grocery lists.
- - - **Chart junk.** 3D effects, excessive gridlines, legends requiring
  cross-referencing. Simplify
  every chart to one message; annotate directly on the data.
- - - **Tiny text.** If the back row can't read it, it shouldn't be on the
  slide. 24pt minimum for
  body, bigger for headlines.
- - - **Inconsistent styling.** Five chart styles, three bullet styles, random
  image treatments. The
  template exists to be used — enforce it.
- - - **No clear ask.** Ending with "Questions?" or "Thank you" instead of the
  decision, action, or
  feeling you need. The last slide should point forward, not just stop.

Attribution

aicodedecodeaicodedecode
View sourceSee grades on GitHubMore from aicodedecode →
SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments (0)

No comments yet. Be the first to comment!

SSkills DirectorySkills Directory

Ship a skill? Prove it's safe.

Free 120-pattern security scan, letter grade, and an embeddable README badge.

Submit a skill

Related Skills

Caveman

Terse caveman voice: answer first, fluff gone, every technical fact kept. Use for /caveman, "caveman mode", "talk like caveman", "be brief", "less tokens". Stays on until "stop caveman" or "normal mode".

1100021 votes

Hyperplan

Adversarial multi-agent planning skill. Self-orchestrates 5 hostile category members (unspecified-low, unspecified-high, deep, ultrabrain, artistry) via team-mode for ruthless cross-critique debate, distills only the defensible insights, then MANDATORILY hands the distilled insight bundle to the `plan` agent for executable plan formalization. Use when planning needs maximum rigor and surfacing of weak assumptions, blind spots, and over-engineering. Triggers: 'hyperplan', 'hpp', '/hyperplan', ...

698621 votes

Writing Skills

Create and manage Claude Code skills in HASH repository following Anthropic best practices. Use when creating new skills, modifying skill-rules.json, understanding trigger patterns, working with hooks, debugging skill activation, or implementing progressive disclosure. Covers skill structure, YAML frontmatter, trigger types (keywords, intent patterns), UserPromptSubmit hook, and the 500-line rule. Includes validation and debugging with SKILL_DEBUG. Examples include rust-error-stack, cargo-dep...

3931 votes

Mcp Code Execution

Routes multi-tool workflows through MCP servers for large datasets and pipelines. Use when Bash tool overhead is limiting throughput on data-heavy tasks.

3421 votes

catchup

Recovers the conversation and failed tool calls of a previous Codex, Amp, Claude Code, Antigravity, Cline, Copilot CLI, Cursor, DeepSeek Harness, Grok Build, Kimi, OpenCode, Pi Agent, or ZCode session. Use when the user says "catch up", "what did the last session do", "get me up to speed", "I switched agents", asks to recover/summarize a previous session before continuing, or asks to diagnose or report a catchup failure. Do NOT use for the current conversation, git history, or any non-agent log.

741 votes
View all in ai-agents →