slides-style-prompt-studio
```markdown
What this skill does
```markdown
---
name: slides-style-prompt-studio
description: Generate multi-style PPT slide prompts for AI image generation via nanobanana2/Gemini
triggers:
- generate slide prompts
- create PPT style prompts
- make presentation slides with AI
- generate retro pop art slide
- create cyberpunk presentation
- slides style prompt studio
- generate nanobanana2 prompts
- create multi-style slides
---
# Slides Style Prompt Studio
> Skill by [ara.so](https://ara.so) — Daily 2026 Skills collection.
A prompt library and generator for creating styled PPT slides using AI image generation (nanobanana2 / Gemini). No code required — copy prompts, customize text, and generate 2K slides.
---
## What It Does
- Provides **11 pre-built style prompts** for AI-generated PPT slides
- Targets `gemini-3.1-flash-image-preview` via nanobanana2
- Outputs `2048×1152` (2K 16:9) presentation slides
- Covers styles from Retro Pop Art to Cyberpunk, Swiss International, Y2K Pixel Retro, and more
---
## Project Structure
```
slides/
├── README.md # Overview and style gallery
├── PROMPTS.md # All 11 style prompts (primary resource)
├── skill.json # OpenClaw skill config
├── CLAUDE.md # Skill context
└── demos/yc-intro/images/ # 22 generated sample images
```
---
## Installation / Setup
No Python package to install — this is a prompt library. Clone the repo:
```bash
git clone https://github.com/AAAAAAAJ/slides.git
cd slides
```
To use the prompts programmatically with the Gemini API:
```bash
pip install google-generativeai pillow
export GEMINI_API_KEY="your_api_key_here"
```
---
## Recommended Generation Settings
| Setting | Value |
|---------------|------------------------------------|
| Model | `gemini-3.1-flash-image-preview` |
| Resolution | `2048×1152` |
| Aspect Ratio | `16:9` |
| Platform | nanobanana2 / APImart |
---
## The 11 Style Prompts
Reference `PROMPTS.md` for the full list. Key styles:
### 1. Retro Pop Art
```
Retro pop art style PPT slide, 1970s magazine aesthetic, flat design with thick black outlines,
cream beige background, bold title text, subtitle below, key statistics displayed as cards,
Salmon pink #FF6B6B, sky blue #4ECDC4, mustard yellow #FFD93D, mint green #6BCB77 accents,
Geometric decorations: quarter circles, concentric rings, star bursts,
Bold sans-serif typography, Professional presentation design, 16:9
```
### 2. Minimalist Clean
```
Minimalist clean design PPT slide, White background, generous whitespace, centered title text,
subtitle below, key stats in simple cards, Subtle gray and blue accents, Thin elegant lines,
Inter Helvetica font, Professional corporate presentation, Simple elegant layout, 16:9
```
### 3. Cyberpunk Neon
```
Cyberpunk neon style PPT slide, Dark charcoal background, title text with neon glow effect,
subtitle below, Neon colors: magenta #FF00FF, cyan #00FFFF, yellow #FFFF00,
Tech grid patterns, circuit decorations, Holographic data panels, glow effects,
Futuristic UI elements, Digital presentation, 16:9
```
### 4. Neo-Brutalism
```
Neo-brutalism style PPT slide, raw design, Cream background, bold title text, subtitle below,
key stats displayed, Bold primary colors: red #FF4D4D, blue #4D94FF, yellow #FFD93D,
Thick 4px black outlines, hard shadows, Brutalist frames, bold typography, Stark contrast, 16:9
```
### 5. Acid Graphics Y2K
```
Acid graphics Y2K style PPT slide, Light gray background, title text, subtitle below,
key stats in stylized cards, Metallic chrome elements, holographic accents,
Colors: purple #B185FF, pink #FF6EC7, mint #7BFFCB, gold #FFD700,
Liquid shapes, star sparkles, mesh gradients, Y2K aesthetic, futuristic design, 16:9
```
### 6. Modern Minimal Pop
```
Modern minimal pop art PPT slide, Instagram aesthetic, Pastel background, title text,
subtitle below, key stats displayed, Pastel colors: mint #A8E6C8, cream #FFF4BD,
coral #FF8B7A, purple #8B7AFF, Star burst graphics, thin line circles,
Tilted color blocks, small arrows, Clean sans-serif typography, Swiss design influence, 16:9
```
### 7. Swiss International
```
Swiss international style PPT slide, brutalist graphic design, Light gray background,
bold title text, subtitle with diagonal layout, key stats in geometric blocks,
High saturation colors: blue #007AFF, green #00994D, yellow #FFF066,
purple #9966FF, pink #FF3399, orange #FF8800, Helvetica font, Asymmetric composition, 16:9
```
### 8. Dark Editorial
```
Dark editorial PPT slide, New York Times Sunday Review style,
Black background with white dot grid pattern, title text in white, subtitle below,
white text, orange accent #E85D2A, Minimalist wireframe illustrations,
Serif typography, Dramatic negative space, Newspaper aesthetic, 16:9
```
### 9. Design Blueprint
```
Design blueprint PPT slide, Figma documentation style, White background with cyan grid lines
#66B8CC, title text, subtitle below, Figma selection boxes with control points,
Annotation lines, numbered labels, Technical UI mockup aesthetic,
Clean sans-serif Inter font, 16:9
```
### 10. Neo-Brutalist UI
```
Neo-brutalist UI PPT slide, dashboard interface design, Cream background, title text,
subtitle below, stats in cards, Pastel panels: mint #A8E4CF, yellow #FFD93D, lavender #E5B3FF,
Thick 3px black outlines, Card-based layout, flat colors,
Bold typography, Contemporary SaaS dashboard aesthetic, 16:9
```
### 11. Y2K Pixel Retro
```
Y2K pixel retro PPT slide, 1990s aesthetic, Dark background with noise texture,
title text in pixel font, subtitle below, Bright colors: yellow #FFD700, orange #FF8C00,
green #4A7C4E, Pixel art computer icons, CRT monitor graphics,
Isometric tech illustrations, VT323 pixel font style, Vintage 1990s design, 16:9
```
---
## Programmatic Usage (Python)
### Generate a slide via Gemini API
```python
import google.generativeai as genai
import os
from PIL import Image
import io
import base64
genai.configure(api_key=os.environ["GEMINI_API_KEY"])
def generate_slide(style_prompt: str, title: str, subtitle: str, stats: list[str]) -> bytes:
"""
Generate a styled PPT slide image using Gemini.
Args:
style_prompt: Base style prompt from PROMPTS.md
title: Slide title (≤8 words recommended)
subtitle: Slide subtitle (≤12 words recommended)
stats: List of 3-5 key data points
Returns:
Image bytes (PNG)
"""
stats_text = ", ".join(stats)
full_prompt = f"{style_prompt}\nTitle: {title}\nSubtitle: {subtitle}\nKey stats: {stats_text}"
model = genai.GenerativeModel("gemini-3.1-flash-image-preview")
response = model.generate_content(
full_prompt,
generation_config=genai.GenerationConfig(
response_modalities=["image"],
)
)
for part in response.candidates[0].content.parts:
if part.inline_data and part.inline_data.mime_type.startswith("image/"):
return base64.b64decode(part.inline_data.data)
raise ValueError("No image returned in response")
# Example: Retro Pop Art slide
RETRO_POP_PROMPT = """Retro pop art style PPT slide, 1970s magazine aesthetic,
flat design with thick black outlines, cream beige background, bold title text,
subtitle below, key statistics displayed as cards,
Salmon pink #FF6B6B, sky blue #4ECDC4, mustard yellow #FFD93D, mint green #6BCB77 accents,
Geometric decorations: quarter circles, concentric rings, star bursts,
Bold sans-serif typography, Professional presentation design, 16:9"""
image_bytes = generate_slide(
style_prompt=RETRO_POP_PROMPT,
title="What is Y Combinator",
subtitle="The World's Most Famous Startup Accelerator",
stats=["Founded 2005", "4000+ companies", "$600B combined value"]
)
with open("slide_output.png", "wb") as f:
f.write(image_bytes)
print("Slide saved to slide_output.png")
```
### Batch Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.