presentation-design

A method for designing 16:9 presentation slides as standalone HTML files that can be exported to PDF. It separates slides meant to be presented aloud from slides meant to be read without narration.

In plain words
What is it for?
Creating board updates, project reviews, findings summaries, proposals, and conference talks, or converting a report into a presentation.
Why use it?
It helps turn information into slides with one clear point at a time, instead of treating a presentation like a document split across pages.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/avinava/document-design-system/presentation-design
Any agent
npx skills add Avinava/document-design-system --skill presentation-design
Clone the repo
git clone --depth 1 https://github.com/Avinava/document-design-system

Made for: Claude Code, Codex.

Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,776 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00126 $0.01776
Opus 5 $0.00063 $0.00888
Sonnet 5 $0.00025 $0.00355
Haiku 4.5 $0.00013 $0.00178

Measured 2d ago against content hash fc8b15bf26ab, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

presentation-design scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/presentation-design/SKILL.md · 139 lines

How it starts

The opening of the file, as written. The whole thing — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Presentation Design

A slide is seen for as long as it takes to say one thing. That constraint drives every rule here.

A deck is not a document with page breaks. If the content only makes sense when read closely, it is a document — say so and use analytical-document-design or writing-documents instead. Converting a document into slides by cutting it into pieces produces a deck that is bad to present and worse to read.

One idea per slide

The title states the idea as a claim, not a topic. Everything else on the slide supports that claim.

  • "Ingestion is our concentration risk" — a claim. The audience knows what to look for.
  • "Ingestion metrics" — a topic. The audience has to work out what they are meant to conclude.

If a slide needs two titles, it is two slides. Slides are free; attention is not.

Reading and presenting are different jobs

Decide which deck this is, because the answer changes the design and you cannot have both in one artifact:

Presented — you are speaking over it. Slides carry few words, large type, and one visual. The detail lives in what you say.

Read (sent, not presented) — nobody narrates it. Slides need enough text to stand alone, which means more words and smaller type, and the deck is longer.

When both are needed, build the presented deck and pair it with a document, or add a speaker-notes block that prints but does not project. Do not compromise into a deck that is too dense to present and too sparse to read alone — the common failure that produces a wall of bullets nobody can use for either purpose.

Slide types

Use a small set. A deck where every slide has a different layout reads as a collection of unrelated files.

Type Use
Title Deck title, presenter, date, context
Section divider Marks a shift; a few words on an accent field
Statement One sentence at large size. The argument's turning points
Metric One to three numbers with labels and their denominators
Chart One chart, one takeaway title
Diagram One diagram, one takeaway title
Comparison Two or three columns on a consistent set of criteria
Table Small tables only — six rows and four columns is the practical ceiling
Agenda / summary Structural orientation
Closing The ask, the decision needed, or next steps

Read the full file on GitHub · 139 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 2d ago First seen · 139 lines · 126 tokens per session scan A fc8b15bf26ab

Subscribe to this mod's changes

presentation-design is a skill published in the GitHub repository Avinava/document-design-system (2 stars, last pushed 7d ago), licensed MIT. It adds 126 tokens to every session and 1,776 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

chart-description-writer

Writes a precise, accessible text description of a data visualization — covering the chart type, what it shows, the key finding, and the data range — suitable for publication as a caption, alt-text, or standfirst alongside the chart.

ur-grue/autopunk-media-skills · 52 tokens

web-design-guidelines

Review UI code for Web Interface Guidelines compliance. Use when asked to "review my UI", "check accessibility", "audit design", "review UX", or "check my site against best practices".

FlorianBruniaux/starmapper · 44 tokens

semiotic-charts

Generate trustworthy, accessible, agent-legible charts with Semiotic. Use whenever you produce a data visualization in a React/TypeScript app, stream a chart as generative UI, or pick a chart type for a dataset. Emit a validated config and run the trust loop — never hand-write chart JSX that breaks on first paint.

nteract/semiotic · 71 tokens

seo

Optimize for search engine visibility and ranking. Use when asked to "improve SEO", "optimize for search", "fix meta tags", "add structured data", "sitemap optimization", or "search engine optimization".

addyosmani/web-quality-skills · 46 tokens

selecting-vizro-charts

Use this skill when choosing chart types, applying Plotly Express conventions, configuring colors, building KPI cards, or adding tables (AG Grid) to Vizro dashboards. Activate when the user asks which chart fits their data, needs custom chart functions, wants to set colors or palettes, is creating KPI metric cards, or…

mckinsey/vizro · 78 tokens

release

Cut a sim-use release end-to-end. Use when the user runs /release or asks to "ship a release", "publish a version", "cut a release", or "release to homebrew". Drives scripts/local-release.sh; never reimplement its build/sign/tarball logic.

lycorp-jp/sim-use · 61 tokens