make-deck

make-deck is a command for coding agents from ca-who-codes/ultimate.UIUX.design.skills. It costs 34 tokens per session (451 once invoked), scanned A, original, MIT.

A presentation-building command for creating pitch, sales, conference, or internal slide decks, from the main message through slide design and an editable or exportable result.

In plain words
What is it for?
Use it to plan and produce slide decks, choose a suitable format, design slides one by one, and create outputs such as PowerPoint files, HTML slides, or PDFs.
Why use it?
It helps turn scattered information into a clear story with readable slides, so you do not have to plan the structure and visual layout from scratch.

Command

Part of the ui-ux-design-pro plugin — 1 skill, 6 commands, 4 agents shipped together

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 commands/ca-who-codes/ultimate.uiux.design.skills/make-deck
Clone the repo
git clone --depth 1 https://github.com/ca-who-codes/ultimate.UIUX.design.skills

Or install ui-ux-design-pro, the plugin that ships this one along with the rest of its 1 skill, 6 commands, 4 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for make-deck

README.md
[![agentmods](https://agentmods.dev/badge/commands/ca-who-codes/ultimate.uiux.design.skills/make-deck.svg)](https://agentmods.dev/commands/ca-who-codes/ultimate.uiux.design.skills/make-deck)
Your own site
<a href="https://agentmods.dev/commands/ca-who-codes/ultimate.uiux.design.skills/make-deck"><img src="https://agentmods.dev/badge/commands/ca-who-codes/ultimate.uiux.design.skills/make-deck.svg" alt="Measured on agentmods" height="20"></a>
Per session 34 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 451 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 5.1 $0.00034 $0.00451
Opus 5 $0.00017 $0.00226
Sonnet 5 $0.00007 $0.00090
Haiku 4.5 $0.00003 $0.00045

Measured 5d ago against content hash 17d5373d592c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

make-deck 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 5d 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.

commands/make-deck.md · 17 lines

What it actually says

Design a presentation: $ARGUMENTS

Work the deck through the Design Pro loop:

  1. Orient — read knowledge/INDEX.md, knowledge/01-principles/decision-framework.md, and knowledge/09-presentations/decks.md. Set the format from knowledge/08-visual-composition/format-specs.md (default 16:9, 1920×1080; vertical only if it's a social/mobile deck).
  2. Find the through-line — the single core message and the narrative arc. Pick the deck type (pitch/sales/conference/internal) and design accordingly (speaker-support = sparse & visual, not a leave-behind wall of text). Use the standard pitch sequence as a checklist when relevant.
  3. Design slide-by-slide — assertion-evidence titles (the takeaway as the title, not a label), one idea per slide, big readable type (title ~40–54pt, body ~24–32pt, min ~18pt), one accent color, consistent master/grid, generous margins, direct-labeled charts. Apply the brand system (knowledge/08-visual-composition/brand-systems.md); derive one if none exists.
  4. Produce — per knowledge/13-production/production-and-tools.md: generate an editable .pptx, build HTML slides → PDF, or use a slides/Express/Canva path. Keep text as real editable text. State which method and why.
  5. Self-review against knowledge/05-quality/review-checklist.md and the deck-mistakes table (no text walls, no tiny fonts, no label-titles, consistent everything).

Ask only if a blocking decision is missing (audience, length, brand). Otherwise apply sensible defaults and state assumptions. Deliver the deck plus a slide outline and the production method.

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. 5d ago First seen · 17 lines · 34 tokens per session scan A 17d5373d592c

Subscribe to this mod's changes

make-deck is a command published in the GitHub repository ca-who-codes/ultimate.UIUX.design.skills (3 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 451 once invoked, about $0.0002 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.