agentleFS
EvoScientistEvoScientist/EvoSkills/skills/nano-banana/SKILL.md

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

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.
  • KISHOR403Skill

    agency-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

  • KISHOR403Skill

    brand-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

  • jechearteSkill

    elevenlabs-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

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
  1. Distinctive:

    Before proceeding with any slide generation, verify these prerequisites.

    line 33
  2. Distinctive:

    If empty, ask the user to provide one.

    line 41
  3. Very specific:

    If the user provides the key in conversation, pass it to scripts with --api-key

    line 44
  4. Very specific:

    Language: Ask the user what language the slide content should be in.

    line 48
  5. Distinctive:

    Follow these phases in order.

    line 64
  6. Distinctive:

    Ensure logical flow between pages

    line 87
  7. Very specific:

    Create a slides_plan.json file in the workspace root with this schema:

    line 104
  8. Distinctive:

    DO write descriptive titles and bullet points

    line 136
  9. Distinctive:

    DO NOT: put the same sentence in both the title area and the bottom of the content — it causes duplication

    line 139
  10. Distinctive:

    Start the interactive review server so the user can review slides and write feedback:

    line 235
  11. Distinctive:

    Wait for the user to confirm they have saved their feedback before proceeding.

    line 250
  12. Very specific:

    Read slides_plan.json and find all slides with a non-empty feedback field.

    line 256
  13. Very specific:

    After editing all slides with feedback, clear the feedback fields from slides_plan.json and tell the user to refresh the browser to see …

    line 288
  14. Distinctive:

    If the user has more feedback, repeat Phase 4-5.

    line 290
  15. Very specific:

    Ask the user if they want to keep ppt_output/ directory or clean it up

    line 315

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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.

  1. Dependencies: pip install pillow google-genai python-pptx python-dotenv (also listed in requirements.txt at 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.
  2. Provider and API Key: Gemini is the default provider. Check that its API key is available:

    echo $GOOGLE_API_KEY

    If 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-key argument)
    • If the user provides the key in conversation, pass it to scripts with --api-key

    To use Atlas Cloud instead, set ATLASCLOUD_API_KEY and pass --provider atlas. Atlas Cloud is opt-in and does not change the default Gemini workflow.

  3. 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: Cleanup

Follow 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:

DurationPagesStructure
5 min5Cover + 3 content + closing
10-15 min8-12Cover + intro + 3-4 sections + summary + closing
20-30 min15-20Cover + intro + 5-6 sections + summary + closing
45-60 min25-30Cover + 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:

  1. DO write descriptive titles and bullet points
  2. DO describe the visual layout you want (e.g., "left-right comparison", "4 icon cards")
  3. DO NOT prefix lines with "Slogan:", "Visual:", "Points:", or any meta-labels — the model will render these as visible text on the slide
  4. DO NOT put the same sentence in both the title area and the bottom of the content — it causes duplication
  5. 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 everything

Good 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 everything

Phase 3: Select Style & Generate Slides

Available Styles

StyleFileVisual CharacteristicsBest For
Lineal Colorstyles/lineal-color.mdWhite background, teal accents, flat 2D icons, info cardsTechnical talks, lectures, educational
Gradient Glassstyles/gradient-glass.mdLight pastel background, frosted glass cards, Apple Keynote feelProduct launches, pitches, SaaS
Vector Illustrationstyles/vector-illustration.mdCream background, black outlines, retro colors, toy-model charmEducational, 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

ModelSpeedQualityWhen to Use
gemini-3-pro-image-previewModerateBestFinal version, important presentations
gemini-3.1-flash-image-previewFastGoodDrafts, rapid iteration, large decks
gemini-2.5-flash-imageFastestBasicQuick prototypes, bulk generation
google/nano-banana-2-lite/text-to-imageFastGoodAtlas Cloud slide generation at 1K
google/nano-banana-2-lite/editFastGoodAtlas 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_output

Atlas 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_output

Arguments:

  • --plan (required): Path to slides_plan.json
  • --style (required): Path to style template
  • --provider: gemini (default) or atlas
  • --model: Image generation model (default gemini-3-pro-image-preview; Atlas accepts only google/nano-banana-2-lite/text-to-image)
  • --resolution: Gemini supports 2K (default) or 4K; Atlas uses 1K
  • --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 viewer

Exit 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.pid

Tell 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-preview

To 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 atlas

Arguments:

  • --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) or atlas
  • --model: Image editing model (default gemini-3-pro-image-preview; Atlas accepts only google/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.pid

Arguments:

  • --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.json can be kept for future re-generation

Counterintuitive Rules

  1. 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.
  2. 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.
  3. More planning = better slides — Spending 10 minutes on Phase 1 conversation saves hours of re-generation. Do not rush to Phase 3.
  4. Edit, don't regenerate — When a slide needs minor changes (text fix, color change, remove footer), use edit_slide.py instead of regenerating from scratch. Editing preserves visual consistency.
  5. Use flash model for drafts — gemini-3.1-flash-image-preview is fast enough for iteration. Only switch to gemini-3-pro-image-preview for the final version after all feedback is addressed.
  6. Never read generated images yourself — Not all models support multimodal input. Do NOT use read_file on 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.
  7. 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.
  8. 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

ScriptPurposeKey Arguments
scripts/generate_ppt.pyBatch generate all slides from plan--plan, --style, --provider, --model, --output, --resolution, --api-key, --workers
scripts/edit_slide.pyEdit a single slide based on instruction--input, --instruction, --output, --provider, --model, --api-key
scripts/atlas_image.pySubmit and poll optional Atlas Cloud image tasksUsed by generation and editing scripts
scripts/serve_viewer.pyLocal review server with feedback--dir, --plan, --port, --no-open, --pid-file
scripts/package_pptx.pyPackage 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:

SectionPurposeParsed by Code
## Base PromptVisual specifications shared by all slidesYes — injected into every prompt
## Page TemplatesLayout descriptions per page typeFallback only
## ExamplesActual prompt templates with {Base Prompt} and [Content] placeholdersYes — primary templates
Other sectionsDocumentation onlyNo

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.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.