Skip to content
TrustedSkillsbeta
Back to all skills

Nano Banana Prompt

Checked
giulioco·vlatest·ai-ml·Apache-2.0

This skill generates highly focused, concise prompts for large language models, boosting efficiency and clarity in your requests.

Repository

Install on your platform

Showing Claude Code. One command installs this skill into any of the agents below.

  1. 1

    Run this in your project

    terminal
    $ npx skills add giulioco/skills --skill nano-banana-prompt -a claude-code

  2. Uses the open-source skills CLI and needs Node.js. Add -g to install it for your user instead of this project.

What we know about this skill

Publisher

giulioco

Taken from the source listing. We haven't verified who controls this account.

Install target

Live repository

Not pinned. Installing fetches whatever the repository holds at the time you run the command.

No human has reviewed this code. The checks below are a static scan of the files at one commit — nobody has run this skill or judged whether it works. A skill runs with whatever access you give your agent, so read the source before you install it.

Automated safety checks

scanned

This skill passed all 6 checks. We read its files at one commit and looked for the things that make a skill dangerous to run — not for whether it works.

  • Declares what it does: passed

    SKILL.md parses and declares a name and a description.

    SKILL.md exists, its frontmatter parses, and it declares a name and a description.

  • No undeclared network calls: passed

    Makes no network calls.

    Every host the skill dials — from its scripts, its config endpoints or the commands it tells the agent to run — is either well-known package and API infrastructure or declared in its own frontmatter. Links in documentation are not counted.

  • No obfuscated payloads: passed

    No encoded or obfuscated payloads.

    No base64, hex or compressed blob is decoded and then executed, and no encoded shell commands.

  • No credential access: passed

    Reads no keys, tokens, keychains or credential files.

    Neither the code nor the SKILL.md instructions read SSH keys, cloud credentials, keychains, token stores, browser cookie databases or dotfiles that hold secrets.

  • No pipe-to-shell installers: passed

    No pipe-to-shell or download-and-run installers.

    No `curl … | sh` pattern, in the code or in the instructions, that runs code fetched at run time.

  • Pinned to a commit: passed

    Scanned giulioco/skills at 2db17d19e5.

    The exact upstream commit SHA that was scanned is recorded, so the result refers to specific bytes.

Commit
2db17d19e5
Manifest
skills/nano-banana-prompt/SKILL.md
Scanned
6 files, 2,909 lines
This is a static scan, not a review. It reads the skill's files; it does not run them, and it cannot tell you whether the skill is any good or whether the code does what its description says. A skill runs with whatever access you give your agent.
What each check looks for →

About this skill

What it does

The Nano Banana Prompt skill helps you craft highly detailed and effective prompts for large language models, particularly when generating images. It specializes in creating prompts that achieve photorealistic rendering, maintain consistent facial features across transformations (identity preservation), handle complex compositions with multiple subjects, and incorporate precise technical specifications like camera settings and lighting setups. The skill provides structured approaches using both text-based and JSON prompt formats to maximize control over the output.

When to use it

  • Generating photorealistic images: When you need highly detailed and realistic visuals.
  • Maintaining facial consistency: When transforming an image while ensuring the person's face remains recognizable.
  • Creating complex scenes: For prompts involving multiple subjects, layered effects, or specific era aesthetics (like Y2K).
  • Requiring technical precision: When you need to control camera settings, lighting, and other photographic elements.

Key capabilities

  • Photorealistic rendering: Generates prompts for realistic textures, lighting, and materials.
  • Identity preservation: Maintains facial features across image transformations.
  • Complex composition handling: Supports multiple subjects and detailed environments.
  • Technical precision control: Allows specification of camera specs, lighting setups, and era aesthetics.
  • Text-based prompt generation: Provides a structured text format for simpler prompts.
  • JSON prompt generation: Enables precise control over complex scenes through JSON formatting.
  • Hybrid Prompting: Combines narrative descriptions with technical specifications.

Example prompts

  • "A professional, high-resolution profile photo, maintaining exact facial features of the uploaded image. Shot from chest up with ample headroom, looking directly at camera. Smart casual blazer in charcoal gray. Solid neutral studio background (#562226). Bright airy lighting with catchlights in eyes. 85mm f/1.8 lens, shallow depth of field, crisp focus on eyes, soft bokeh."
  • "Create a scene with multiple subjects: a cyberpunk hacker and a futuristic robot bartender. The hacker is wearing neon-lit clothing; the robot has intricate mechanical details. Use JSON to specify element placement and lighting conditions."
  • "Keep the facial features of the person in the uploaded image exactly consistent. Dress them in a professional navy blue business suit with..."

Tips & gotchas

  • Specificity is key: Detailed prompts yield significantly better results than brief ones.
  • Use technical language: Incorporate photography and cinematography terminology for greater precision.
  • JSON Structure Guide: Refer to the JSON Structure Guide for templates when constructing complex, structured prompts.