Agent skill

Nano Banana Prompting

by NikiforovAll in NikiforovAll/claude-code-rules

This skill should be used when crafting prompts for Nano Banana Pro (Gemini image generation).

Apache-2.0Auto-check passedMedia & Creative

Install Nano Banana Prompting

skills CLI
$ npx skills add NikiforovAll/claude-code-rules --skill nano-banana-prompting -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install NikiforovAll/claude-code-rules nano-banana-prompting --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/NikiforovAll/claude-code-rules.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/handbook-nano-banana/skills/nano-banana-prompting .claude/skills/nano-banana-prompting && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
nano-banana-prompting
GitHub stars
141
Token cost
~1.4k tokens
SKILL.md length
538 words
Files
2 (incl. references)
Skills in repo
26
Repo updated
First seen
Licence
Apache-2.0

At a glance

This skill should be used when crafting prompts for Nano Banana Pro (Gemini image generation).

  • Works in 6 steps: Gather Reference Materials → Clarify Intent with Questions → Determine Prompt Style → …
  • Users want help writing image generation prompts
  • SKILL.md covers Workflow, Quick Reference: Technique… and Resources
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Nano Banana Prompting is an agent skill from NikiforovAll/claude-code-rules. This skill should be used when crafting prompts for Nano Banana Pro (Gemini image generation). Use when users want help writing image generation prompts, need guidance on prompt structure, or want to optimize their prompts for better results.

Its SKILL.md is about 1.4k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/guide.md`).

It sits in Media & Creative, covering Image generation. It works with Google Gemini. The repository describes itself as: Learn practical techniques to enhance your AI-assisted development workflow with Claude Code. The licence is Apache-2.0.

When your agent uses it

  • Users want help writing image generation prompts
  • Need guidance on prompt structure
  • Want to optimize their prompts for better results

Example prompts

  • “/nano-banana-prompting”

Workflow steps

6 steps, taken from the step headings in SKILL.md.

  1. Gather Reference Materials
  2. Clarify Intent with Questions
  3. Determine Prompt Style
  4. Generate the Prompt
  5. Present and Iterate
  6. Generate the Image

What it can do on your machine

Read from SKILL.md and the folder at commit 281c063. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    No scripts in the folder and no shell commands in SKILL.md.

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Nano Banana Prompting loads about 1.4k tokens when it runs, and up to ~4.1k if it reads all its reference files. Until then it costs about 66 tokens; SKILL.md has 538 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~66
When it runs · the whole SKILL.md, loaded when a task matches
~1.4k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from NikiforovAll/claude-code-rules at commit 281c063, republished under its Apache-2.0 licence (© NikiforovAll). 538 words, ~1,417 tokens.

Download SKILL.mdSave it as .claude/skills/nano-banana-prompting/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
nano-banana-prompting
description
This skill should be used when crafting prompts for Nano Banana Pro (Gemini image generation). Use when users want help writing image generation prompts, need guidance on prompt structure, or want to optimize their prompts for better results.

Nano Banana Prompting

Interactive prompt crafting for Nano Banana Pro image generation. This skill guides users through a structured process to create effective prompts by clarifying intent and applying proven techniques.

Workflow

Step 1: Gather Reference Materials

Before asking questions, check if the user has provided:

  • Reference images - Photos to use for character consistency, style, or composition
  • Existing prompts - Previous attempts to improve upon
  • Visual references - Screenshots or examples of desired output

If reference materials are available, this affects which techniques apply (e.g., Reference Role Assignment, Character Consistency).

Step 2: Clarify Intent with Questions

Use the AskUserQuestion tool to understand the user's goal. Ask questions in batches of 2-4, focusing on the most important aspects first.

Core Questions (always ask)
  1. Output Type - What kind of image?

    • Photo/realistic
    • Illustration/artistic
    • Infographic/educational
    • Product shot/commercial
    • UI mockup/design
  2. Subject - Who or what is the main focus?

    • Person (with or without reference)
    • Object/product
    • Scene/environment
    • Concept/abstract
Technique-Specific Questions (based on answers)

If Photo/Realistic:

  • What era or camera style? (modern DSLR, 1990s film, 2000s digital)
  • Specific lighting? (golden hour, studio, flash)
  • Aspect ratio needed? (16:9, 9:16, 1:1)

If Reference Images Provided:

  • What role for each image? (pose, style, color palette, background)
  • Should character identity be preserved?
  • Combine images or use as style reference?

If Text Needed:

  • What text should appear?
  • What font style? (serif, sans-serif, handwritten)
  • Where should text be placed?

If Educational/Infographic:

  • What concept to explain?
  • Target audience level?
  • Should it include labels, arrows, flow?
Step 3: Determine Prompt Style

Based on user responses, select the appropriate prompt format from references/guide.md:

User NeedRecommended Style
Simple, quick generationNarrative Prompt (Technique 1)
Precise control over detailsStructured Prompt (Technique 2)
Era-specific aestheticVibe Library + Photography Terms (Techniques 3-4)
Magazine/poster with textPhysical Object Framing (Technique 5)
Conceptual/interpretivePerspective Framing (Technique 6)
Diagram/infographicEducational Imagery (Technique 7)
Editing existing imageImage Transformation (Technique 8)
Multiple views/panelsMulti-Panel Output (Technique 9)
Multiple reference imagesReference Role Assignment (Technique 12)
Show full SKILL.md (216 more words)Show less
Step 4: Generate the Prompt

Construct the prompt by:

  1. Loading references/guide.md to access technique details
  2. Applying relevant techniques based on Step 3 selection
  3. Cross-checking against guide examples for proper formatting
  4. Including negative prompts if needed (Technique 10)
  5. Specifying aspect ratio/resolution if required (Technique 11)
Prompt Construction Checklist
  • Subject clearly defined
  • Action/pose specified (if applicable)
  • Location/background described
  • Style/aesthetic anchored
  • Technical specs included (aspect ratio, lighting, camera)
  • Text integration specified (if needed)
  • Negative prompts added (if needed)
  • Reference image roles assigned (if using references)
Step 5: Present and Iterate

Present the generated prompt to the user with:

  1. The prompt - Ready to use
  2. Technique explanation - Why this structure was chosen
  3. Variation suggestions - Alternative approaches to try

Offer to refine based on feedback.

Step 6: Generate the Image

After the user is satisfied with the prompt, recommend using the nano-banana skill to generate the actual image. Inform the user:

"Your prompt is ready! Would you like me to generate the image now? I can use the nano-banana skill to create it."

If the user agrees, invoke the nano-banana skill with the crafted prompt.

Quick Reference: Technique Selection

User wants...                    → Use Technique...
─────────────────────────────────────────────────────
Simple description               → 1 (Narrative)
Detailed control                 → 2 (Structured YAML/JSON)
Specific era look                → 3 (Vibe Library)
Professional photo style         → 4 (Photography Terms)
Magazine/poster                  → 5 (Physical Object Framing)
"How X sees Y"                   → 6 (Perspective Framing)
Educational diagram              → 7 (Educational Imagery)
Edit existing image              → 8 (Image Transformation)
Multiple panels in one           → 9 (Multi-Panel)
Exclude something                → 10 (Negative Prompts)
Specific dimensions              → 11 (Aspect Ratio)
Multiple reference images        → 12 (Reference Roles)
Same character across images     → 13 (Character Consistency)
Merge multiple images            → 14 (Image Blending)
Enhance/restore image            → 15 (Upscaling)
Translate text in image          → 16 (Translation)

Resources

references/
  • guide.md - Complete prompting guide with 16 techniques, examples, and patterns. Load this file when constructing prompts to access specific technique details and examples.

© NikiforovAll, Apache-2.0. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in plugins/handbook-nano-banana/skills/nano-banana-prompting of NikiforovAll/claude-code-rules.

  • SKILL.md
  • references/guide.md

Open the folder on GitHubat commit 281c063

Compare with similar skills

Nano Banana Prompting next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Nano Banana Prompting compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Nano Banana Prompting this skillNikiforovAll/claude-code-rules141—~1.4kAutomated safety check: PassApache-2.0
AI Image Generation and Editingzhayujie/CowAgent47k—~1.3kAutomated safety check: PassMIT
Logo Generatorop7418/logo-generator-skill2.2k—~1.8kAutomated safety check: NotesNone
Gemini Web Reverse-Engineered ClientJimLiu/baoyu-skills27k5 repos~1.6kAutomated safety check: PassMIT
SEO Image GeneratorAgriciDaniel/claude-seo19k2 repos~2.1kAutomated safety check: PassMIT
BlockRun Image GenerationBlockRunAI/ClawRouter6.6k—~2.1kAutomated safety check: PassMIT

Similar skills

  • Generates or edits images from text prompts through a Python script that picks an image backend based on which API keys are configured.

    47k GitHub stars~1.3k tokensUpdated yesterday
    Media & CreativeAuto-check passed
  • Logo Generator

    op7418/logo-generator-skill

    Generate professional SVG logos and high-end showcase images.

    2.2k GitHub stars~1.8k tokensUpdated 5 mo ago
    Media & CreativeAuto-check: notes
  • Generates text and images through an unofficial, reverse-engineered Gemini Web API, supporting reference images and multi-turn conversations.

    27k GitHub starsUsed in 5 repos~1.6k tokens
    Media & CreativeAuto-check passed
  • SEO Image Generator

    AgriciDaniel/claude-seo

    Generates Open Graph previews, blog hero images, product photos and infographics for SEO use through Gemini image tools and the banana extension.

    19k GitHub starsUsed in 2 repos~2.1k tokens
    Media & CreativeAuto-check passed
  • BlockRun Image Generation

    BlockRunAI/ClawRouter

    Generates or edits images through ClawRouter's local image API, with a choice of models and sizes and payment handled automatically through x402.

    6.6k GitHub stars~2.1k tokensUpdated 5 days ago
    Media & CreativeAuto-check passed
  • Antigravity Gemini Image

    uluckyXH/OpenMOSS

    Generate or edit images using the Antigravity-hosted Gemini image model via the local gateway.

    1.3k GitHub stars~730 tokensUpdated 3 mo ago
    Media & CreativeAuto-check: notes

More from NikiforovAll/claude-code-rules

All 26 skills in this repo
  • Reflect Solution

    NikiforovAll/claude-code-rules

    Summarize WHAT WAS SHIPPED in a Claude Code session as a self-contained HTML slide deck — the elevator pitch (problem, solution, decisions, artifacts, verification, gaps), not a play-by-play of tool…

    141 GitHub stars~3.8k tokensUpdated 9 days ago
    Auto-check passed
  • Dotnet Analyzers

    NikiforovAll/claude-code-rules

    Run dotnet format to fix code style and analyzer diagnostics (IDE0005, CA, SA).

    141 GitHub stars~1.9k tokensUpdated 9 days ago
    Auto-check passed
  • Ilspy Decompile

    NikiforovAll/claude-code-rules

    Understand implementation details of .NET code by decompiling assemblies.

    141 GitHub starsUsed in 2 repos~760 tokens
    Auto-check passed
  • Reflect Tree

    NikiforovAll/claude-code-rules

    Visualize a Claude Code session as a quest/skill tree — a navigable SVG graph where nodes are turns and edges show flow, with distinct visual encoding for normal flow, dead-ends, corrections…

    141 GitHub stars~2.8k tokensUpdated 9 days ago
    Auto-check passed
  • Structured Plan Mode

    NikiforovAll/claude-code-rules

    This skill should be used when planning and tracking complex feature implementations that require systematic task decomposition.

    141 GitHub stars~4.2k tokensUpdated 9 days ago
    Auto-check passed
  • Glab

    NikiforovAll/claude-code-rules

    Expert guidance for using the GitLab CLI (glab) to manage GitLab issues, merge requests, CI/CD pipelines, repositories, and other GitLab operations from the command line.

    141 GitHub starsUsed in 1 repo~2.2k tokens
    Auto-check passed

Works with

Questions about Nano Banana Prompting

What does Nano Banana Prompting do?

This skill should be used when crafting prompts for Nano Banana Pro (Gemini image generation). Nano Banana Prompting is an agent skill from NikiforovAll/claude-code-rules. This skill should be used when crafting prompts for Nano Banana Pro (Gemini image generation).

When should I use Nano Banana Prompting?

Nano Banana Prompting fits situations like: users want help writing image generation prompts; need guidance on prompt structure; want to optimize their prompts for better results.

How do I install Nano Banana Prompting in Claude Code?

Run `npx skills add NikiforovAll/claude-code-rules --skill nano-banana-prompting -a claude-code`. Or copy the skill folder (plugins/handbook-nano-banana/skills/nano-banana-prompting in NikiforovAll/claude-code-rules) into .claude/skills/nano-banana-prompting in your project. Claude Code loads it when a task matches its description.

How do I install Nano Banana Prompting in Codex?

Run `npx skills add NikiforovAll/claude-code-rules --skill nano-banana-prompting -a codex`. Or copy the skill folder (plugins/handbook-nano-banana/skills/nano-banana-prompting in NikiforovAll/claude-code-rules) into .agents/skills/nano-banana-prompting in your project. Codex loads it when a task matches its description.

Can I use Nano Banana Prompting in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add NikiforovAll/claude-code-rules --skill nano-banana-prompting -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/nano-banana-prompting, .gemini/skills/nano-banana-prompting, .github/skills/nano-banana-prompting and .opencode/skills/nano-banana-prompting in your project.

What does Nano Banana Prompting need to run?

SKILL.md names no scripts, command-line tools or credentials: Nano Banana Prompting is instructions for the agent only.

Does Nano Banana Prompting access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Nano Banana Prompting safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Nano Banana Prompting use?

Nano Banana Prompting is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Nano Banana Prompting use?

About 1.4k tokens (SKILL.md is roughly 5.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.7k tokens, read only when the agent opens those files.

What are the alternatives to Nano Banana Prompting?

Skills that share tags, products or a category with Nano Banana Prompting: AI Image Generation and Editing (zhayujie/CowAgent, 47k stars), Logo Generator (op7418/logo-generator-skill, 2.2k stars), Gemini Web Reverse-Engineered Client (JimLiu/baoyu-skills, 27k stars) and SEO Image Generator (AgriciDaniel/claude-seo, 19k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Nano Banana Prompting?

NikiforovAll (a GitHub user) maintains it in NikiforovAll/claude-code-rules, which has 141 GitHub stars. The repository holds 26 skills in this directory. The repository was last updated on October 2, 2026.

Source: NikiforovAll/claude-code-rules on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.