presentation-chef

A tool that turns text, Markdown, or structured data into a single self-contained HTML slide presentation styled like an Apple Keynote deck.

In plain words
What is it for?
Use it to build presentations from notes, documents, descriptions, or data, with slide navigation, visual themes, and animated effects.
Why use it?
It removes the need to design each slide and assemble separate files or dependencies by hand.

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/sacredvoid/skillkit/presentation-chef
Any agent
npx skills add sacredvoid/skillkit --skill presentation-chef
Clone the repo
git clone --depth 1 https://github.com/sacredvoid/skillkit

Made for: Claude Code, Codex.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 12,690 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 $0.00052 $0.12690
Opus 5 $0.00026 $0.06345
Sonnet 5 $0.00010 $0.02538
Haiku 4.5 $0.00005 $0.01269

Measured yesterday against content hash 65ca86de08ae, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

presentation-chef 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 yesterday.

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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

skills/presentation-chef/SKILL.md · 1,261 lines

How it starts

The opening of the file, as written. The whole thing — 1,261 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Presentation Chef

Generate cinematic, Apple Keynote-style HTML presentations from any content. Single self-contained .html file with zero dependencies.

Process

Follow these steps exactly:

Pre-Step: Initialize Task Pipeline

Before starting Step 1, create tasks to give the user visibility into the full workflow:

TaskCreate:
  subject: "Gather content source"
  description: "Ask the user for their presentation content — paste, file, or topic"
  activeForm: "Gathering content source"

TaskCreate:
  subject: "Select theme & customize design"
  description: "Analyze content, recommend a theme, and gather design customization preferences"
  activeForm: "Selecting theme and design preferences"

TaskCreate:
  subject: "Plan slide structure"
  description: "Map content to slide types and confirm the structure with user"
  activeForm: "Planning slide structure"

TaskCreate:
  subject: "Build presentation"
  description: "Generate the complete HTML presentation with slides, navigation, and effects"
  activeForm: "Building presentation"

Update each task to in_progress when starting that phase, and completed when done:

  • "Gather content source" → covers Step 1
  • "Select theme & customize design" → covers Steps 2-3
  • "Plan slide structure" → covers Step 4
  • "Build presentation" → covers Steps 5-6

Step 1: Gather Content

TaskUpdate: Mark "Gather content source" → in_progress

Ask the user for their content source using AskUserQuestion:

AskUserQuestion:
  question: "What content should I turn into a presentation?"
  header: "Content"
  options:
    - label: "Paste or describe it"
      description: "I'll type/paste content or describe what I want in the presentation"
    - label: "Read from a file"
      description: "I have a markdown file, text file, or other document to convert"
    - label: "Generate from topic"
      description: "Give me a topic and I'll create both content and design"
  multiSelect: false

Read the full file on GitHub · 1,261 lines

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. yesterday First seen · 1,261 lines · 52 tokens per session scan A 65ca86de08ae

Subscribe to this mod's changes

presentation-chef is a skill published in the GitHub repository sacredvoid/skillkit (10 stars, last pushed 5mo ago), licensed MIT. It adds 52 tokens to every session and 12,690 once invoked, about $0.0003 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

ios-swiftui

Expert SwiftUI development skill for building iOS apps. Covers layout system (VStack/HStack/ZStack/Grid/LazyStacks), state management (@State/@Binding/@Observable/@Environment), navigation (NavigationStack/NavigationSplitView), animations (springs/transitions/matchedGeometryEffect/PhaseAnimator/KeyframeAnimator)…

koshkinvv/ios-agent-skills · 203 tokens

image-fetcher

Fetch relevant, high-quality, free-to-use images from the web. Accepts a description/query, or scans the current directory for context. Sources from Unsplash, Pexels, and Pixabay APIs (if keys configured) with a zero-config WebSearch fallback.

sacredvoid/image-fetcher · 57 tokens

vercel-react-view-transitions

Guide for implementing smooth, native-feeling animations using React's View Transition API ( component, addTransitionType, and CSS view transition pseudo-elements). Use this skill whenever the user wants to add page transitions, animate route changes, create shared element animations, animate enter/exit of components…

zhukunpenglinyutong/desktop-cc-gui · 127 tokens

animation-system

Use when implementing animations — AnimationPlayer, AnimationTree, blend trees, state machines, sprite animation, and code-driven animation.

jame581/GodotPrompter · 27 tokens

assets-pipeline

Use when importing and managing assets — image compression, 3D scene import, audio formats, resource formats, and import configuration.

jame581/GodotPrompter · 29 tokens

dedicated-server

Use when building dedicated servers — headless export, server architecture, lobby management, and deployment.

jame581/GodotPrompter · 22 tokens