agentmods.dev

illustrated-slides-with-nano-banana

illustrated-slides-with-nano-banana is a skill for Claude Code, Codex from deancourse/user-dot-agents. It costs 71 tokens per session (2,705 once invoked), scanned A, original, MIT.

A presentation-making skill that creates PowerPoint or PDF slides as complete AI-generated images, with the words and illustrations built into each image. It supports several visual styles, such as corporate, minimalist, creative, and playful.

In plain words
What is it for?
Use it to create fully illustrated presentation decks, visual-first talks, and slides whose diagrams, titles, and artwork are embedded in the slide image.
Why use it?
It is for cases where the visual design of each slide matters more than having separately editable text and shapes.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

not rated 7repo 3mo ago A scan 71 tokens original MIT

Good fit Use it to create fully illustrated presentation decks, visual-first talks, and slides whose diagrams, titles, and artwork are embedded in the slide image.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/deancourse/user-dot-agents/illustrated-slides-with-nano-banana
View source ↗ deancourse/user-dot-agents
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.

Any agent
npx skills add deancourse/user-dot-agents --skill illustrated-slides-with-nano-banana
Clone the repo
git clone --depth 1 https://github.com/deancourse/user-dot-agents

Made for: Claude Code, Codex.

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 illustrated-slides-with-nano-banana

README.md
[![agentmods](https://agentmods.dev/badge/skills/deancourse/user-dot-agents/illustrated-slides-with-nano-banana/github.svg)](https://agentmods.dev/skills/deancourse/user-dot-agents/illustrated-slides-with-nano-banana)
Your own site
<a href="https://agentmods.dev/skills/deancourse/user-dot-agents/illustrated-slides-with-nano-banana"><img src="https://agentmods.dev/badge/skills/deancourse/user-dot-agents/illustrated-slides-with-nano-banana/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for illustrated-slides-with-nano-banana

Your own site · 80×15
<a href="https://agentmods.dev/skills/deancourse/user-dot-agents/illustrated-slides-with-nano-banana"><img src="https://agentmods.dev/badge/skills/deancourse/user-dot-agents/illustrated-slides-with-nano-banana.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,705 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 $0.00071 $0.02705
Opus 5 $0.00036 $0.01352
Sonnet 5 $0.00014 $0.00541
Haiku 4.5 $0.00007 $0.00270

Measured 12d ago against content hash a362028d9ae0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

illustrated-slides-with-nano-banana 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 12d ago.

The scan reads SKILL.md. This mod also ships 2 executable files (fluxa-wallet/scripts/fluxa-cli.bundle.js, scripts/build-image-pptx.js), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/illustrated-slides-with-nano-banana/SKILL.md · 405 lines

How it starts

The opening of the file, as written. The whole thing — 405 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Illustrated Slides with Nano Banana

Create presentations where each slide is a complete AI-generated image with all text and content embedded directly in the image. No separate text layers — the presentation file is simply a container for full-page illustrated slides. Supports multiple visual styles from corporate to creative.

Key Principle

All content is embedded in the images.

Unlike traditional presentations with text overlays, this skill generates complete slide images where titles, bullet points, diagrams, and illustrations are all part of the generated image itself - like pages in a children's picture book.

Behavior

When this skill is triggered:

1. Get Presentation Topic

Ask the user for their presentation topic if not specified.

2. Ask for Visual Style

Always ask the user to choose a style:

🎨 What visual style would you like?

1️⃣ **Kawaii / Children's Book**
   Warm pastels, cream background, cute characters with faces
   Best for: Kids content, educational, playful topics

2️⃣ **Professional / Corporate**  
   Clean blues & grays, white background, modern icons
   Best for: Business, finance, tech presentations

3️⃣ **Bold / Creative**
   Vibrant colors, dynamic compositions, artistic flair
   Best for: Marketing, startups, creative pitches

4️⃣ **Minimalist / Elegant**
   Black & white with one accent, lots of whitespace
   Best for: Luxury brands, design, architecture

5️⃣ **Custom**
   Describe your own style preference

Which style would you like? (1-5)

3. Plan Slide Structure

Based on topic, plan ~8-12 slides:

  • Title slide
  • Introduction/Chapter slides
  • Content slides (with embedded text & illustrations)
  • Diagram/flow slides
  • Summary/statistics slides
  • Closing slide

4. Estimate Budget & Request Approval

  • Each image: 0.1 USDC
  • Recommend 1.5x buffer
  • Tell user: "To create this presentation with X slides, I need a budget of Y USDC."

5. Generate Slide Images

For each slide:

  1. Get x402 payment signature
  2. Generate image with ALL content embedded (title, text, illustrations)
  3. Download and save image
  4. Repeat for all slides

Read the full file on GitHub · 405 lines

Files

What ships with it

6 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. 12d ago First seen · 405 lines · 71 tokens per session scan A a362028d9ae0

Subscribe to this mod's changes

illustrated-slides-with-nano-banana is a skill published in the GitHub repository deancourse/user-dot-agents (7 stars, last pushed 3mo ago), licensed MIT. It adds 71 tokens to every session and 2,705 once invoked, about $0.0004 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.

Claude CodeCreative and mediaDocumentsPDFagent-skillsai-agentsanthropicclaudecli
Related

Other skills, from other repositories

hushdrop

Publish/share an artifact (HTML, Markdown, PDF, file, or whole site) as a private, branded, password-protected link on your own domain. Use when the user says 'publish this', 'share this page', 'drop this', 'send them a link', or whenever you've generated an HTML artifact they'll want to open in a browser.…

maxtechera/hushdrop · 105 tokens

nano-pdf

Extract text and metadata from PDF files using pdftotext and poppler-utils. Supports full extraction, page ranges, and structured output.

profclaw/profclaw · 32 tokens

pdf

Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…

opencue/cuecards · 92 tokens

ocr-and-documents

Extract text from PDFs/scans (pymupdf, marker-pdf).

StarryCod/cogitum · 21 tokens

nano-pdf

Edit PDF text/typos/titles via nano-pdf CLI (NL prompts).

StarryCod/cogitum · 21 tokens

hushdrop

Publish/share an artifact (HTML, Markdown, PDF, file, or whole site) as a private, branded, password-protected link on your own domain. Use when the user says 'publish this', 'share this page', 'drop this', 'send them a link', or whenever you've generated an HTML artifact they'll want to open in a browser.…

maxtechera/hushdrop · 105 tokens