nano-banana
Skill486 starsChanged 47 days agoApache-2.0View on GitHub
Generate professional presentation slides and high-quality illustrations using Gemini image generation API (Nano Banana 2), with interactive browser-based review and iterative editing. Full workflow: content planning conversation → slides_plan.json → batch image generation → review with feedback → targeted slide editing → PPTX packaging. Use when: user wants to create a presentation, make slides, generate a PPT/PPTX, prepare a talk deck, design visual slide content, or generate high-quality figures/illustrations for papers and documents. Do NOT use for: writing academic papers (use paper-writing) or planning academic conference talk narrative structure (use academic-slides).
- Reads credentials
- Installs packages
40 other projects use a version of this.
Adopted by
Most recently taken up by
- okou-ai/okou-skillstheir own version, first seen Nov 11, 2026
- runapi-ai/nano-bananatheir own version, first seen Nov 8, 2026
- frontdesk-alhouse/alto-ostheir own version, first seen Nov 8, 2026
- hwangx/claude-skill-nano-bananatheir own version, first seen Nov 6, 2026
- agentrix-ai/skillstheir own version, first seen Oct 20, 2026
- Samueladewole/claude-skillstheir own version, first seen Oct 13, 2026
Used with
Projects with it also use agency-docs-updater, brand-agency and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
KISHOR403Skillagency-docs-updater
End-to-end pipeline for publishing Claude Code lab meetings. Automatically finds/creates Fathom transcript, downloads video, uploads to YouTube, generates fact-checked Russian summary, creates MDX documentation, and pushes to agency-docs for Vercel deployment. Single invocation replaces 5+ manual steps.
Also in 3 projects that use this
KISHOR403Skillbrand-agency
Applies Agency brand colors and typography to artifacts including presentations, SVG graphics, documents, and web interfaces. This skill should be used when brand colors, visual formatting, neobrutalism style, or Agency design standards apply. Keywords - branding, corporate identity, visual identity, styling, brand colors, typography, visual formatting, visual design, neobrutalism.
Also in 3 projects that use this
jechearteSkillelevenlabs-tts
Generate realistic audio from text using ElevenLabs Text-to-Speech API. Use when the user needs to convert text to speech, create voiceovers, generate narration, or produce audio content. Triggers include "generate audio", "text to speech", "TTS", "voiceover", "narration", "ElevenLabs", "audio from text", "read this text aloud
Also in 5 projects that use this
- +9 more from KISHOR403
Other versions40 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 40
- OpenMinis/MinisSkills★ 612same name
- glebis/claude-skills★ 414same name
- kkoppenhaver/cc-nano-banana★ 368same name
- mikeOnBreeze/cc-crossbeam★ 297same name
- ruizrica/agent-pi★ 274same name
- LichAmnesia/lich-skills★ 233same name
- refly-ai/refly-skills★ 204same name
- okou-ai/okou-skills★ 81same name
- vm0-ai/vm0-skills★ 81same name
- mycelium-hq/ai-brain-starter★ 50same name
30 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- academic-slidesSkill
- evomath-taoSkill
- evo-memorySkill
- experiment-craftSkill
- experiment-iterative-coderSkill
- experiment-pipelineSkill
- paper-figuresSkill
- paper-graphSkill
- paper-navigatorSkill
- paper-planningSkill
- paper-rebuttalSkill
- paper-reviewSkill
- paper-writingSkill
- research-ideationSkill
- research-surveySkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. 0 are common, 9 are distinctive, and 6 are very specific to this project.
0
Common
Most of the 36 edited versions we read keep these.
9
Distinctive
This author's own choices. Worth a look.
6
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 33
Before proceeding with any slide generation, verify these prerequisites.
- Distinctive: line 41
If empty, ask the user to provide one.
- Very specific: line 44
If the user provides the key in conversation, pass it to scripts with --api-key
- Very specific: line 48
Language: Ask the user what language the slide content should be in.
- Distinctive: line 64
Follow these phases in order.
- Distinctive: line 87
Ensure logical flow between pages
- Very specific: line 104
Create a slides_plan.json file in the workspace root with this schema:
- Distinctive: line 136
DO write descriptive titles and bullet points
- Distinctive: line 139
DO NOT: put the same sentence in both the title area and the bottom of the content — it causes duplication
- Distinctive: line 235
Start the interactive review server so the user can review slides and write feedback:
- Distinctive: line 250
Wait for the user to confirm they have saved their feedback before proceeding.
- Very specific: line 256
Read slides_plan.json and find all slides with a non-empty feedback field.
- Very specific: line 288
After editing all slides with feedback, clear the feedback fields from slides_plan.json and tell the user to refresh the browser to see …
- Distinctive: line 290
If the user has more feedback, repeat Phase 4-5.
- Very specific: line 315
Ask the user if they want to keep ppt_output/ directory or clean it up
“Common” is measured: kept by at least 6 in 10 of the 36 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Nano Banana
Generate high-quality presentation slides as images using Gemini's image generation API, review them interactively in a browser, and iteratively edit based on feedback.
When to Use This Skill
- User asks to create a presentation, slide deck, or PPT
- User wants to generate visual slides for a talk or lecture
- User has a document or outline and wants slides based on it
- User says "make me a PPT", "generate slides", "create a presentation"
- User wants to edit or refine existing generated slides
- User needs high-quality figures, diagrams, or illustrations for papers or documents
- User asks to generate research figures, architecture diagrams, or concept illustrations
Do NOT use for:
- Writing academic papers → use
paper-writing - Planning academic conference talk narrative structure → use
academic-slides
Before You Start: Prerequisites
Before proceeding with any slide generation, verify these prerequisites. Script and style paths in this document are relative to this skill's directory.
- Dependencies:
pip install pillow google-genai python-pptx python-dotenv(also listed inrequirements.txtat the skill root). Install into the environment the user is working in. Atlas Cloud uses the same dependencies and does not require an additional SDK. Provider and API Key: Gemini is the default provider. Check that its API key is available:
echo $GOOGLE_API_KEYIf empty, ask the user to provide one. They can either:
- Set it via config:
EvoSci config set google_api_key <key> - Provide it directly (pass via
--api-keyargument) - If the user provides the key in conversation, pass it to scripts with
--api-key
To use Atlas Cloud instead, set
ATLASCLOUD_API_KEYand pass--provider atlas. Atlas Cloud is opt-in and does not change the default Gemini workflow.- Set it via config:
- Language: Ask the user what language the slide content should be in. This affects the content you write in
slides_plan.json, not the style template.
Core Workflow
Phase 1: Content Planning Conversation ← most important phase
Phase 2: Generate slides_plan.json
Phase 3: Select Style & Generate Slides
Phase 4: Launch Review Server
Phase 5: Apply Feedback Edits ← repeat Phase 4-5 until satisfied
Phase 6: Package as PPTX
Phase 7: CleanupFollow these phases in order. Do NOT skip Phase 1 — the quality of generated slides depends directly on planning depth.
Phase 1: Content Planning Conversation
This is the most critical phase. Rushing to generation without proper planning produces mediocre slides. Engage the user in a structured conversation:
Step 1 — Understand the context:
- What is the topic of the presentation?
- Who is the audience? (technical peers, executives, students, general public)
- How long is the talk? (this determines page count)
- What is the occasion? (conference, internal talk, lecture, pitch)
Step 2 — Define the storyline:
- What is the opening hook? (a surprising fact, a question, a trend)
- What are the 3-5 main sections or arguments?
- What is the key takeaway the audience should remember?
- What is the closing message?
Step 3 — Outline per-page content:
- For each slide, agree on: title + 2-4 key points + visual description
- Identify which slides are cover, content, or data type
- Ensure logical flow between pages
Duration-to-page-count guidance:
| Duration | Pages | Structure |
| 5 min | 5 | Cover + 3 content + closing |
| 10-15 min | 8-12 | Cover + intro + 3-4 sections + summary + closing |
| 20-30 min | 15-20 | Cover + intro + 5-6 sections + summary + closing |
| 45-60 min | 25-30 | Cover + intro + 7-9 sections (2-3 pages each) + summary + closing |
If the user provides a document or outline, read it thoroughly, then propose a slide breakdown for approval before proceeding.
Phase 2: Generate slides_plan.json
Create a slides_plan.json file in the workspace root with this schema:
{
"title": "Presentation Title",
"total_slides": 10,
"slides": [
{
"slide_number": 1,
"page_type": "cover",
"content": "Title: My Presentation\nSubtitle: A subtitle here\nLabel: 2026 Edition"
},
{
"slide_number": 2,
"page_type": "content",
"content": "Title: First Topic\nKey points:\n- Point one\n- Point two\n- Point three"
},
{
"slide_number": 3,
"page_type": "data",
"content": "Title: Key Metrics\nMetric 1: 95% accuracy\nMetric 2: 3x faster\nMetric 3: 10k users"
}
]
}page_type values: cover, content, data
Critical Content Field Rules
The content field is what gets passed to the image generation model. Follow these rules strictly:
- DO write descriptive titles and bullet points
- DO describe the visual layout you want (e.g., "left-right comparison", "4 icon cards")
- DO NOT prefix lines with "Slogan:", "Visual:", "Points:", or any meta-labels — the model will render these as visible text on the slide
- DO NOT put the same sentence in both the title area and the bottom of the content — it causes duplication
- DO NOT include footer text, page numbers, or watermark instructions
Bad example (meta-labels leak as visible text):
Title: Why AI Matters
Visual: left-right comparison chart
Points:
- Point one
- Point two
Slogan: AI changes everythingGood example (clean, no meta-labels):
Title: Why AI Matters
Visual layout: left-right comparison chart showing traditional vs AI approach
Key points:
- Point one with brief explanation
- Point two with brief explanation
Bottom tagline: AI changes everythingPhase 3: Select Style & Generate Slides
Available Styles
| Style | File | Visual Characteristics | Best For |
| Lineal Color | styles/lineal-color.md | White background, teal accents, flat 2D icons, info cards | Technical talks, lectures, educational |
| Gradient Glass | styles/gradient-glass.md | Light pastel background, frosted glass cards, Apple Keynote feel | Product launches, pitches, SaaS |
| Vector Illustration | styles/vector-illustration.md | Cream background, black outlines, retro colors, toy-model charm | Educational, children's content, brand stories |
Present the styles to the user and let them choose. If unsure, recommend Lineal Color as the default.
Available Models
| Model | Speed | Quality | When to Use |
gemini-3-pro-image-preview | Moderate | Best | Final version, important presentations |
gemini-3.1-flash-image-preview | Fast | Good | Drafts, rapid iteration, large decks |
gemini-2.5-flash-image | Fastest | Basic | Quick prototypes, bulk generation |
google/nano-banana-2-lite/text-to-image | Fast | Good | Atlas Cloud slide generation at 1K |
google/nano-banana-2-lite/edit | Fast | Good | Atlas Cloud slide editing at 1K |
For first-time generation, recommend gemini-3.1-flash-image-preview (fast iteration). Switch to gemini-3-pro-image-preview for the final version.
Generate Command
python scripts/generate_ppt.py \
--plan slides_plan.json \
--style styles/lineal-color.md \
--model gemini-3.1-flash-image-preview \
--output ppt_outputAtlas Cloud is available as an optional provider:
python scripts/generate_ppt.py \
--plan slides_plan.json \
--style styles/lineal-color.md \
--provider atlas \
--output ppt_outputArguments:
--plan(required): Path to slides_plan.json--style(required): Path to style template--provider:gemini(default) oratlas--model: Image generation model (defaultgemini-3-pro-image-preview; Atlas accepts onlygoogle/nano-banana-2-lite/text-to-image)--resolution: Gemini supports2K(default) or4K; Atlas uses1K--output: Output directory (default:ppt_output/TIMESTAMP)--api-key: Provider API key (if not in the provider environment variable)--workers: Number of parallel workers (default: 1, recommended: 3-5 for large decks)
Output structure:
ppt_output/
├── images/
│ ├── slide-01.png
│ ├── slide-02.png
│ └── ...
├── prompts.json # All prompts used (for debugging)
└── index.html # Browser viewerExit code. 0 means every slide was generated. 2 means a partial deck was written: the last line on stderr lists the missing slide numbers (Failed slides: 3, 7), and each failure is printed as [n/total] FAIL: <reason>. Re-running the command regenerates the whole deck, so when the failures share one reason (quota, key, model name) fix that first. 1 means no slide was generated (or the API key / library is missing); there is nothing to review yet.
Phase 4: Launch Review Server
Start the interactive review server so the user can review slides and write feedback:
python scripts/serve_viewer.py \
--dir ppt_output \
--plan slides_plan.json \
--port 8080 \
--pid-file .viewer.pidTell the user:
Review server is running at http://localhost:8080. Open it in your browser to review each slide. Write feedback in the text box below any slide that needs changes, then click "Save Feedback". Tell me when you're done.
The server saves feedback directly into slides_plan.json as a feedback field on each slide.
Wait for the user to confirm they have saved their feedback before proceeding.
Phase 5: Apply Feedback Edits
Read slides_plan.json and find all slides with a non-empty feedback field. For each one, run the edit script:
python scripts/edit_slide.py \
--input ppt_output/images/slide-{NUMBER}.png \
--instruction "{FEEDBACK_TEXT}" \
--output ppt_output/images/slide-{NUMBER}.png \
--model gemini-3.1-flash-image-previewTo edit through Atlas Cloud, the script uploads the local source image for temporary generation use before submitting the edit task:
python scripts/edit_slide.py \
--input ppt_output/images/slide-01.png \
--instruction "Remove the footer text at the bottom" \
--output ppt_output/images/slide-01.png \
--provider atlasArguments:
--input(required): Path to the original slide image--instruction(required): The edit instruction (from feedback field)--output: Output path (default: overwrite input)--provider:gemini(default) oratlas--model: Image editing model (defaultgemini-3-pro-image-preview; Atlas accepts onlygoogle/nano-banana-2-lite/edit)--api-key: Provider API key (if not in the provider environment variable)
edit_slide.py prints OK: <path> and exits 0 on success, or FAIL: <reason> and exits 1. Both scripts exit 1 before any request when a required Python package is missing.
Atlas generation POST requests are submitted once and are never retried. Only prediction GET requests use bounded polling.
After editing all slides with feedback, clear the feedback fields from slides_plan.json and tell the user to refresh the browser to see updated slides.
If the user has more feedback, repeat Phase 4-5. This review-edit cycle continues until the user is satisfied.
Phase 6: Package as PPTX
Once the user approves all slides, ask for the desired filename and package them:
python scripts/package_pptx.py \
--dir ppt_output/images \
--output presentation.pptx \
--kill-server .viewer.pidArguments:
--dir(required): Directory containing slide-XX.png images--output(required): Output .pptx file path--kill-server: PID file from serve_viewer.py — automatically stops the review server after packaging
Phase 7: Cleanup
- The review server is automatically stopped by
package_pptx.py --kill-server - Ask the user if they want to keep
ppt_output/directory or clean it up - The
slides_plan.jsoncan be kept for future re-generation
Counterintuitive Rules
- Never include meta-labels in content — Words like "Slogan:", "Visual:", "Points:" will be rendered as visible text on the slide. Describe what you want without prefixes.
- Content describes WHAT, not HOW — The style template handles visual layout. The content field should focus on text and logical structure, not colors or positioning.
- More planning = better slides — Spending 10 minutes on Phase 1 conversation saves hours of re-generation. Do not rush to Phase 3.
- Edit, don't regenerate — When a slide needs minor changes (text fix, color change, remove footer), use
edit_slide.pyinstead of regenerating from scratch. Editing preserves visual consistency. - Use flash model for drafts —
gemini-3.1-flash-image-previewis fast enough for iteration. Only switch togemini-3-pro-image-previewfor the final version after all feedback is addressed. - Never read generated images yourself — Not all models support multimodal input. Do NOT use
read_fileon generated PNG images to check quality. Always launch the review server and let the user inspect slides visually in the browser. The user's feedback is your only quality signal. - One idea per slide — Do not pack multiple concepts into a single slide. If a slide has more than 4 bullet points, split it into two slides.
- Bottom taglines should not repeat the title — If the title says "Why AI Matters", the bottom tagline should add new insight, not restate the title.
Scripts Reference
| Script | Purpose | Key Arguments |
scripts/generate_ppt.py | Batch generate all slides from plan | --plan, --style, --provider, --model, --output, --resolution, --api-key, --workers |
scripts/edit_slide.py | Edit a single slide based on instruction | --input, --instruction, --output, --provider, --model, --api-key |
scripts/atlas_image.py | Submit and poll optional Atlas Cloud image tasks | Used by generation and editing scripts |
scripts/serve_viewer.py | Local review server with feedback | --dir, --plan, --port, --no-open, --pid-file |
scripts/package_pptx.py | Package slide images into .pptx | --dir, --output, --kill-server |
Style Template Format
Style templates are markdown files in styles/ with a fixed structure that generate_ppt.py parses:
| Section | Purpose | Parsed by Code |
## Base Prompt | Visual specifications shared by all slides | Yes — injected into every prompt |
## Page Templates | Layout descriptions per page type | Fallback only |
## Examples | Actual prompt templates with {Base Prompt} and [Content] placeholders | Yes — primary templates |
| Other sections | Documentation only | No |
To create a new style: copy an existing .md file, modify the ## Base Prompt and ## Examples sections. The code extracts ### Cover, ### Content, and ### Data code blocks from ## Examples.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

