Agent skill

Nano Banana Imagegen

by BlackBeltTechnology in BlackBeltTechnology/pi-agent-dashboard

Generate and edit images using Google Gemini image models via the nano-banana CLI.

MITAuto-check: notesMedia & Creative

Install Nano Banana Imagegen

skills CLI
$ npx skills add BlackBeltTechnology/pi-agent-dashboard --skill nano-banana-imagegen -a claude-code

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

GitHub CLI
$ gh skill install BlackBeltTechnology/pi-agent-dashboard nano-banana-imagegen --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/BlackBeltTechnology/pi-agent-dashboard.git skills-src && mkdir -p .claude/skills && cp -r skills-src/packages/nano-banana/.pi/skills/nano-banana-imagegen .claude/skills/nano-banana-imagegen && 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-imagegen
GitHub stars
315
Token cost
~1.6k tokens
SKILL.md length
619 words
Files
7 (incl. references)
Skills in repo
70
Repo updated
First seen
Licence
MIT

At a glance

Generate and edit images using Google Gemini image models via the nano-banana CLI.

  • Works in 4 steps: Understand the Request → Craft an Effective Prompt → Generate the Image → …
  • The user asks to create
  • SKILL.md covers Prerequisites, Quick Reference, Workflow and Commands, plus 3 more sections
  • Calls npx; needs GEMINI_API_KEY and OPENROUTER_API_KEY

What it does

Nano Banana Imagegen is an agent skill from BlackBeltTechnology/pi-agent-dashboard. Generate and edit images using Google Gemini image models via the nano-banana CLI. Use when the user asks to create, generate, make, or edit images with AI. Supports text-to-image, image editing, style transfer, and multi-image composition. Trigger on requests like "create an image", "generate a picture", "make me a logo", "edit this photo", "add X to this image".

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including reference files (for example `references/headers-and-heroes.md`, `references/icons-and-logos.md` and `references/illustrations.md`).

It sits in Media & Creative, covering Image generation and Image editing. It works with Google Gemini. The repository describes itself as: Real-time web dashboard for pi coding-agent sessions. Multi-session view, live chat mirroring, integrated terminal, diff viewer, pi-flows execution, and mobile-first remote… The licence is MIT.

When your agent uses it

  • The user asks to create
  • Edit images with AI
  • Requests like create an image
  • Generate a picture

Example prompts

  • “create an image”
  • “generate a picture”
  • “make me a logo”
  • “/nano-banana-imagegen”

Requirements

  • Node.js
  • A credential in GEMINI_API_KEY
  • A credential in OPENROUTER_API_KEY

Workflow steps

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

  1. Understand the Request
  2. Craft an Effective Prompt
  3. Generate the Image
  4. Iterate

What it can do on your machine

Read from SKILL.md and the folder at commit 7a2d171. 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

    Shell commands in SKILL.md call:

    • npx

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

  • Network

    No URLs in SKILL.md. Its commands use npx, which can reach the network depending on how they are called.

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

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • GEMINI_API_KEY
    • OPENROUTER_API_KEY

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

Context cost

Nano Banana Imagegen loads about 1.6k tokens when it runs, and up to ~7.4k if it reads all its reference files. Until then it costs about 97 tokens; SKILL.md has 619 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~97
When it runs · the whole SKILL.md, loaded when a task matches
~1.6k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~7.4k

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: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

  • NoteMentions a .env fileSKILL.md:14
    set via the environment or a gitignored `.env` in the project
  • NoteMentions a .env fileSKILL.md:166
    Or create a `.env` file in your project:

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 BlackBeltTechnology/pi-agent-dashboard at commit 7a2d171, republished under its MIT licence (© BlackBeltTechnology). 619 words, ~1,644 tokens.

Download SKILL.mdSave it as .claude/skills/nano-banana-imagegen/SKILL.md (or your agent's skills folder). This skill also uses 6 other files; get the full folder from GitHub.
name
nano-banana-imagegen
description
Generate and edit images using Google Gemini image models via the nano-banana CLI. Use when the user asks to create, generate, make, or edit images with AI. Supports text-to-image, image editing, style transfer, and multi-image composition. Trigger on requests like "create an image", "generate a picture", "make me a logo", "edit this photo", "add X to this image".

Nano Banana Image Generation

Generate and edit images using Google's Gemini image models. This skill ships the pi-nano-banana CLI (a TypeScript wrapper — no Python) that resolves the GEMINI_API_KEY for you and delegates to @the-focus-ai/nano-banana.

Prerequisites

  • GEMINI_API_KEY set via the environment or a gitignored .env in the project or package directory (the CLI resolves it automatically).
  • Network access — the underlying @the-focus-ai/nano-banana CLI is fetched via npx.

Quick Reference

Prefer the bundled pi-nano-banana bin (auto key resolution, output-dir creation):

bash
# Generate a new image
pi-nano-banana "a serene mountain landscape at sunset"

# Edit an existing image
pi-nano-banana "add a hot air balloon to the sky" --file photo.jpg

# Specify output path
pi-nano-banana "a minimalist logo" --output logo.png

# Use a specific model / faster flash model
pi-nano-banana "detailed illustration" --model gemini-2.0-flash-exp
pi-nano-banana "a quick sketch" --flash

The raw CLI still works if you prefer it (npx @the-focus-ai/nano-banana "…"). For batch generation from code, import batchGenerate from @blackbelt-technology/pi-dashboard-nano-banana/nano-banana.js.

Workflow

Step 1: Understand the Request

Before generating, clarify:

  • Subject: What should be in the image?
  • Style: Photorealistic, illustration, cartoon, abstract?
  • Mood: Bright, dark, moody, cheerful?
  • Composition: Close-up, wide shot, specific aspect ratio?
  • Use case: Hero image, icon, social media, print?
Step 2: Craft an Effective Prompt

Read references/prompting-guide.md for comprehensive guidance.

Key principles:

  1. Be specific and descriptive
  2. Include style references
  3. Specify what you DON'T want
  4. Describe composition and framing

Example — Weak prompt:

"a cat"

Example — Strong prompt:

"A fluffy orange tabby cat curled up on a velvet armchair, soft afternoon sunlight streaming through a window, warm cozy interior, photorealistic style, shallow depth of field"
Step 3: Generate the Image
bash
npx @the-focus-ai/nano-banana "your detailed prompt here"

Default output: output/generated-<timestamp>.png

Step 4: Iterate

If the result isn't right:

  1. Refine the prompt — Add more detail or constraints
  2. Edit the image — Use --file to modify the generated image
  3. Try a different model — Some models handle certain styles better

Commands

Text-to-Image Generation
bash
npx @the-focus-ai/nano-banana "<prompt>"
Image Editing
bash
npx @the-focus-ai/nano-banana "<edit instruction>" --file <input-image>

Edit instructions should describe the change:

  • "Remove the background and replace with a gradient"
  • "Add sunglasses to the person"
  • "Change the sky to sunset colors"
  • "Make it look like a watercolor painting"
Options
OptionDescription
--file <image>Input image for editing
--output <path>Custom output path
--model <name>Specific Gemini model
--flashUse gemini-2.0-flash (faster, simpler images)
--prompt-file <path>Read prompt from file
--list-modelsShow available models
--api-key <key>Explicit Gemini key
--backend gemini|piBackend (default gemini; pi is opt-in, see below)
Show full SKILL.md (308 more words)Show less
pi backend (opt-in, OpenRouter)

--backend pi (or NANO_BANANA_BACKEND=pi) generates through pi's own model runtime instead of the Gemini CLI — no GEMINI_API_KEY needed.

  • Credential: sign in to OpenRouter in pi (/login openrouter) or set OPENROUTER_API_KEY.
  • Requires @earendil-works/pi-coding-agent >= 1.0.0 resolvable next to this package.
  • Opt-in only: a missing Gemini key never falls back to pi; library callers (e.g. the video-production storyboard) stay on Gemini unless they pass backend: "pi".
  • Models are OpenRouter image ids. Bare Gemini ids get google/ in front (--model gemini-3-pro-image → google/gemini-3-pro-image); non-Google models need the full vendor/model id (black-forest-labs/flux.2-pro). Default google/gemini-2.5-flash-image; --flash maps to google/gemini-3.1-flash-lite-image. gemini-2.0-flash-exp does not exist there — an unknown id lists the known ones.
  • Cost: the success line prints (pi · <model>) · ~$<cost> est. — an estimate computed from token usage, not the billed amount.
bash
pi-nano-banana "a red fox in the snow, watercolor" -o fox.png --backend pi
pi-nano-banana "make it night" --file fox.png -o fox-night.png --backend pi

Best Practices

For Better Results
  1. Start with composition: Describe the layout first, then details
  2. Use artistic references: "in the style of Studio Ghibli", "like a National Geographic photo"
  3. Specify lighting: "golden hour lighting", "dramatic chiaroscuro", "soft diffused light"
  4. Include negative guidance: Describe what to avoid in the prompt itself
  5. Consider aspect ratio: The model generates square by default; describe wide/tall if needed
For Editing
  1. Be specific about changes: "Add a blue butterfly to the top-left corner"
  2. Preserve what works: "Keep the background unchanged, only modify the foreground"
  3. Iterative refinement: Make one change at a time for better control

Environment Setup

Ensure GEMINI_API_KEY is set:

bash
export GEMINI_API_KEY="your-api-key-here"

Or create a .env file in your project:

GEMINI_API_KEY=your-api-key-here

Troubleshooting

ProblemSolution
"No image in response"Prompt may have triggered safety filters — rephrase
Poor quality resultsAdd more specific style guidance, use gemini-2.0-flash-exp
--backend pi: "Provider is not configured"Run /login openrouter in pi or set OPENROUTER_API_KEY
--backend pi: "needs @earendil-works/pi-coding-agent >= 1.0.0"Install/update pi next to the package
Image doesn't match descriptionBe more explicit about composition, add negative constraints

© BlackBeltTechnology, MIT. 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 6 other files (references) in packages/nano-banana/.pi/skills/nano-banana-imagegen of BlackBeltTechnology/pi-agent-dashboard.

  • SKILL.md
  • references/headers-and-heroes.md
  • references/icons-and-logos.md
  • references/illustrations.md
  • references/photography-and-editing.md
  • references/prompting-guide.agent.md
  • references/prompting-guide.md

Open the folder on GitHubat commit 7a2d171

Compare with similar skills

Nano Banana Imagegen 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 Imagegen compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Nano Banana Imagegen this skillBlackBeltTechnology/pi-agent-dashboard315—~1.6kAutomated safety check: NotesMIT
AI Image Generation and Editingzhayujie/CowAgent47k—~1.3kAutomated safety check: PassMIT
BlockRun Image GenerationBlockRunAI/ClawRouter6.6k—~2.1kAutomated safety check: PassMIT
Antigravity Gemini ImageuluckyXH/OpenMOSS1.3k—~730Automated safety check: NotesMIT
FigureMuuuun/luxas1.2k—~1.2kAutomated safety check: PassMIT
Gemini Image Generatordair-ai/dair-academy-plugins6142 repos~3.5kAutomated safety check: NotesMIT

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
  • 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
  • Figure

    Muuuun/luxas

    Hybrid figure pipeline (Nano Banana raster + rembg background removal + TikZ vector assembly).

    1.2k GitHub stars~1.2k tokensUpdated 1 mo ago
    Media & CreativeAuto-check passed
  • Gemini Image Generator

    dair-ai/dair-academy-plugins

    Generates and edits images with Google's Gemini Nano Banana Pro model through the Gemini API, including photo edits and multi-image composition.

    614 GitHub starsUsed in 2 repos~3.5k tokens
    Media & CreativeAuto-check: notes
  • Nanobanana

    ReScienceLab/opc-skills

    Generate and edit images using Google Gemini 3 Pro Image (Nano Banana Pro).

    1.8k GitHub stars~1.3k tokensUpdated yesterday
    Media & CreativeAuto-check passed

More from BlackBeltTechnology/pi-agent-dashboard

All 70 skills in this repo
  • Browser

    BlackBeltTechnology/pi-agent-dashboard

    Browser automation via the agent-browser CLI. An agent skill from BlackBeltTechnology/pi-agent-dashboard.

    316 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • CI Troubleshoot

    BlackBeltTechnology/pi-agent-dashboard

    Diagnose failed GitHub Actions runs for pi-agent-dashboard: the 11-file workflow taxonomy, affected-test selection, the release pipeline, known failure modes, and how to read gh run logs and…

    316 GitHub stars~3.5k tokensUpdated today
    Auto-check passed
  • Debug Dashboard

    BlackBeltTechnology/pi-agent-dashboard

    Diagnose problems in the running pi-agent-dashboard system: server.log, /api/health, bridge WebSocket connectivity, vitest triage, known-issue FAQ entries.

    316 GitHub stars~1.6k tokensUpdated today
    Auto-check passed
  • Implement

    BlackBeltTechnology/pi-agent-dashboard

    Disciplined implementation in pi-agent-dashboard: the rebuild matrix (extension→reload, server→restart, client→build+restart, openspec-apply→full rebuild) plus the project's code discipline rules.

    316 GitHub stars~2k tokensUpdated today
    Auto-check passed
  • Pi Dashboard

    BlackBeltTechnology/pi-agent-dashboard

    Monitor and control the pi-dashboard server. An agent skill from BlackBeltTechnology/pi-agent-dashboard.

    316 GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Session To Guideline

    BlackBeltTechnology/pi-agent-dashboard

    Turn a pi session into a Markdown "how-we-did-it" collaboration guideline: reads the session's JSONL transcript and synthesizes a reusable playbook of which prompts worked, what had to be steered…

    316 GitHub stars~3.2k tokensUpdated today
    Auto-check passed

Works with

Questions about Nano Banana Imagegen

What does Nano Banana Imagegen do?

Generate and edit images using Google Gemini image models via the nano-banana CLI. Nano Banana Imagegen is an agent skill from BlackBeltTechnology/pi-agent-dashboard. Generate and edit images using Google Gemini image models via the nano-banana CLI.

When should I use Nano Banana Imagegen?

Nano Banana Imagegen fits situations like: the user asks to create; edit images with AI; requests like create an image; generate a picture.

How do I install Nano Banana Imagegen in Claude Code?

Run `npx skills add BlackBeltTechnology/pi-agent-dashboard --skill nano-banana-imagegen -a claude-code`. Or copy the skill folder (packages/nano-banana/.pi/skills/nano-banana-imagegen in BlackBeltTechnology/pi-agent-dashboard) into .claude/skills/nano-banana-imagegen in your project. Claude Code loads it when a task matches its description.

How do I install Nano Banana Imagegen in Codex?

Run `npx skills add BlackBeltTechnology/pi-agent-dashboard --skill nano-banana-imagegen -a codex`. Or copy the skill folder (packages/nano-banana/.pi/skills/nano-banana-imagegen in BlackBeltTechnology/pi-agent-dashboard) into .agents/skills/nano-banana-imagegen in your project. Codex loads it when a task matches its description.

Can I use Nano Banana Imagegen 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 BlackBeltTechnology/pi-agent-dashboard --skill nano-banana-imagegen -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-imagegen, .gemini/skills/nano-banana-imagegen, .github/skills/nano-banana-imagegen and .opencode/skills/nano-banana-imagegen in your project.

What does Nano Banana Imagegen need to run?

Going by SKILL.md and its folder, Nano Banana Imagegen needs the command-line tools its instructions call (npx) and credentials named GEMINI_API_KEY and OPENROUTER_API_KEY. Our summary lists: Node.js; A credential in GEMINI_API_KEY; A credential in OPENROUTER_API_KEY.

Does Nano Banana Imagegen access the network?

SKILL.md contains no URLs. Its commands use npx, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Nano Banana Imagegen safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Nano Banana Imagegen use?

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

How many tokens does Nano Banana Imagegen use?

About 1.6k tokens (SKILL.md is roughly 6.6k 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 5.8k tokens, read only when the agent opens those files.

What are the alternatives to Nano Banana Imagegen?

Skills that share tags, products or a category with Nano Banana Imagegen: AI Image Generation and Editing (zhayujie/CowAgent, 47k stars), BlockRun Image Generation (BlockRunAI/ClawRouter, 6.6k stars), Antigravity Gemini Image (uluckyXH/OpenMOSS, 1.3k stars) and Figure (Muuuun/luxas, 1.2k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Nano Banana Imagegen?

BlackBeltTechnology (a GitHub organization) maintains it in BlackBeltTechnology/pi-agent-dashboard, which has 315 GitHub stars. The repository holds 70 skills in this directory. The repository was last updated on October 10, 2026.

Source: BlackBeltTechnology/pi-agent-dashboard on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.