nano-banana-prompting

nano-banana-prompting is a skill for Claude Code from NikiforovAll/claude-code-rules. It costs 51 tokens per session (1,257 once invoked), scanned A, original, Apache-2.0.

A guided prompt-writing skill for Nano Banana Pro, an image-generation model from Google Gemini.

In plain words
What is it for?
Use it to write or improve image prompts, including prompts based on reference images, existing prompts, or examples of the desired result.
Why use it?
It helps turn an unclear image idea into a prompt with enough subject, style, composition, and reference details to guide image generation.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: names the AskUserQuestion tool.

Part of the handbook-nano-banana plugin — 2 skills shipped together

Good fit Use it to write or improve image prompts, including prompts based on reference images, existing prompts, or examples of the desired result.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/nikiforovall/claude-code-rules/nano-banana-prompting
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 NikiforovAll/claude-code-rules --skill nano-banana-prompting
Clone the repo
git clone --depth 1 https://github.com/NikiforovAll/claude-code-rules

Made for: Claude Code.

Or install handbook-nano-banana, the plugin that ships this one along with the rest of its 2 skills.

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 nano-banana-prompting

README.md
[![agentmods](https://agentmods.dev/badge/skills/nikiforovall/claude-code-rules/nano-banana-prompting/github.svg)](https://agentmods.dev/skills/nikiforovall/claude-code-rules/nano-banana-prompting)
Your own site
<a href="https://agentmods.dev/skills/nikiforovall/claude-code-rules/nano-banana-prompting"><img src="https://agentmods.dev/badge/skills/nikiforovall/claude-code-rules/nano-banana-prompting/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 nano-banana-prompting

Your own site · 80×15
<a href="https://agentmods.dev/skills/nikiforovall/claude-code-rules/nano-banana-prompting"><img src="https://agentmods.dev/badge/skills/nikiforovall/claude-code-rules/nano-banana-prompting.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,257 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00051 $0.01257
Opus 5 $0.00026 $0.00629
Sonnet 5 $0.00010 $0.00251
Haiku 4.5 $0.00005 $0.00126

Measured 11d ago against content hash 41324b12b25d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

nano-banana-prompting 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 11d ago.

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.

plugins/handbook-nano-banana/skills/nano-banana-prompting/SKILL.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

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

Read the full file on GitHub · 146 lines

Files

What ships with it

1 file 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. 11d ago First seen · 146 lines · 51 tokens per session scan A 41324b12b25d

Subscribe to this mod's changes

nano-banana-prompting is a skill published in the GitHub repository NikiforovAll/claude-code-rules (141 stars, last pushed 12d ago), licensed Apache-2.0. It adds 51 tokens to every session and 1,257 once invoked, about $0.0003 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 2026-08-30.

Related

Other skills, from other repositories

seedance-prompter

Expert prompt engineering for Seedance 2.0. Use when the user wants to generate a video with multimodal assets (images, videos, audio) and needs the best possible prompt.

wells1137/media-skills · 44 tokens

cloudflare-workers-ai

Cloudflare Workers AI for serverless GPU inference. Use for LLMs, text/image generation, embeddings, or encountering AIERROR, rate limits, token exceeded errors.

secondsky/claude-skills · 39 tokens

structured-output

This skill should be used when the user mentions "structured output", "json mode", "tool schema", "function calling", "json parse error", "responseformat", "pydantic ai", "invalid json from the model", or "the model's JSON keeps breaking". It provides a methodology for getting reliably valid, schema-conformant…

sigistry/marketplace · 89 tokens

prompt-versioning-hygiene

This skill should be used when the user mentions "prompt engineering", "prompt versioning", "prompt management", "system prompt", "prompt template", "manage prompts", or "prompts scattered in code". It provides a methodology for treating prompts as versioned, reviewable, testable code rather than magic strings buried…

sigistry/marketplace · 75 tokens

mkprompt-goal

A goal-focused prompt builder that creates a short instruction around the desired outcome, how to check it, and when the work is objectively finished. It can also prepare prompts for work that continues across multiple sessions.

smk-labs/claude-plugins · 87 tokens

fal-prompt

Reçeteleri hedef modelin konuştuğu dile çevirme — model şemasından ve resmi örneklerinden prompt lehçesi çıkarma, negatif prompt ve parametre ayarı. fal-promptsmith agent'ı bunu okur. Use for writing prompts for a specific fal model, prompt format detection, negative prompts, seed and parameter tuning.

mertagralii/fal.ai-butler · 77 tokens