New: 98,000+ skills indexed from GitHub repos with 100+ stars · every skill safety-checkedBrowse top skillsTop skills
Esc to closeBrowse all skills
Submit a skillBrowse skills
Submit a skillBrowse skills

Agent skill

Nano Banana Image Ad

by krusemediallc in krusemediallc/arcads-claude-code

Generate one or more standalone Meta image-ad creatives via Nano Banana 2 / Nano Banana Pro (Gemini Flash Image family) through the Arcads external API.

MITAuto-check: notesMedia & Creative

Install Nano Banana Image Ad

skills CLI
$ npx skills add krusemediallc/arcads-claude-code --skill nano-banana-image-ad -a claude-code

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

GitHub CLI
$ gh skill install krusemediallc/arcads-claude-code nano-banana-image-ad --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/krusemediallc/arcads-claude-code.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/nano-banana-image-ad .claude/skills/nano-banana-image-ad && 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-image-ad
GitHub stars
1.6k
Token cost
~2.5k tokens
SKILL.md length
936 words
Files
2 (incl. scripts)
Skills in repo
8
Repo updated
First seen
Licence
MIT

At a glance

Generate one or more standalone Meta image-ad creatives via Nano Banana 2 / Nano Banana Pro (Gemini Flash Image family) through the Arcads external API.

  • Works in 7 steps: Preflight → Gather inputs → Prompt rewrite → …
  • The user asks for a Nano Banana ad
  • SKILL.md covers Read order, Hard rules — never relax, Prerequisites and Configuration, plus 8 more sections
  • Runs Python scripts from its folder; calls curl; reaches external-api.arcads.ai; needs ARCADS_API_KEY

What it does

Nano Banana Image Ad is an agent skill from krusemediallc/arcads-claude-code. Generate one or more standalone Meta image-ad creatives via Nano Banana 2 / Nano Banana Pro (Gemini Flash Image family) through the Arcads external API. Locks the model family, auto-strips platform chrome, enforces edge-safe layouts. Use when the user asks for a "Nano Banana ad", "Gemini image ad", "nano-banana-2 ad creative", "make a static image ad with Gemini", or anchors on a need for photoreal / lifestyle / multi-reference / handheld-object / clay-texture ad creatives (sticky-note flatlays, held-whiteboard…

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including scripts (for example `scripts/generate_image.py`).

It sits in Media & Creative, covering Image generation and Paid advertising. It works with Google Gemini and OpenAI. The repository describes itself as: Arcads external API: agent skills, prompting library, and Cursor/Claude workspace. The licence is MIT.

When your agent uses it

  • The user asks for a Nano Banana ad
  • Gemini image ad
  • Nano-banana-2 ad creative
  • Make a static image ad with Gemini

Example prompts

  • “Nano Banana ad”
  • “Gemini image ad”
  • “nano-banana-2 ad creative”
  • “/nano-banana-image-ad”

Requirements

  • Python 3
  • A credential in ARCADS_API_KEY

Workflow steps

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

  1. Preflight
  2. Gather inputs
  3. Prompt rewrite
  4. Credit cost confirmation (MANDATORY)
  5. Generate
  6. Visual QA (MANDATORY)
  7. Confirm and hand off

What it can do on your machine

Read from SKILL.md and the folder at commit 1263501. 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

    Ships 1 file in scripts/ (Python), which the agent can run.

    Shell commands in SKILL.md call:

    • curl

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

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • external-api.arcads.ai

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

  • Credentials

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

    • ARCADS_API_KEY

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

Context cost

Nano Banana Image Ad loads about 2.5k tokens when it runs. Until then it costs about 169 tokens; SKILL.md has 936 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~169
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

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:30
    - `.env` containing `ARCADS_BASIC_AUTH` (preferred) OR `ARCADS_API_KEY`
  • NoteMentions a .env fileSKILL.md:31
    Optional: `PRODUCT_ID`, `PROJECT_ID` in `.env` for session-folder organization
  • NoteMentions a .env fileSKILL.md:65
    1. `.env` exists with credentials.
  • NoteMentions a .env fileSKILL.md:96
    --env-file .env
  • NoteMentions a .env fileSKILL.md:106
    --env-file .env
  • NoteMentions a .env fileSKILL.md:117
    --env-file .env
  • NoteMentions a .env fileSKILL.md:152
    - **401/403** → fix `.env`.

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); the scripts in this folder are not scanned.

SKILL.md

The full file from krusemediallc/arcads-claude-code at commit 1263501, republished under its MIT licence (© krusemediallc). 936 words, ~2,523 tokens.

Download SKILL.mdSave it as .claude/skills/nano-banana-image-ad/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
nano-banana-image-ad
description
Generate one or more standalone Meta image-ad creatives via Nano Banana 2 / Nano Banana Pro (Gemini Flash Image family) through the Arcads external API. Locks the model family, auto-strips platform chrome, enforces edge-safe layouts. Use when the user asks for a "Nano Banana ad", "Gemini image ad", "nano-banana-2 ad creative", "make a static image ad with Gemini", or anchors on a need for photoreal / lifestyle / multi-reference / handheld-object / clay-texture ad creatives (sticky-note flatlays, held-whiteboard signs, lifestyle portraits, ingredient collages, OOH photography). Does NOT trigger on ChatGPT Image cues — use chatgpt-image-ad for those.

nano-banana-image-ad (Arcads)

Generate one or more standalone Meta ad image creatives via Arcads' POST /v2/images/generate with the Nano Banana model family (default nano-banana-2). Hands the image paths off to your Meta-ad-builder skill — this skill does not upload to Meta itself.

Read order

  1. This file — Arcads-specific endpoint, auth, presigned upload flow, workflow phases.
  2. shared/skills/nano-banana-image-ad/prompting/guide.md — model-specific prompting (what Nano Banana is good/bad at, when to switch to gpt-image-2).
  3. shared/skills/image-ad-prompting/prompting/prompt-library.md — 30+ validated templates with per-model notes.
  4. shared/skills/image-ad-prompting/prompting/safety-suffixes.md — the 3 always-on guards.
  5. scripts/generate_image.py — the helper script (Python stdlib only).

Hard rules — never relax

  1. Model is in the Nano Banana family. The script accepts nano-banana-2 (default), nano-banana-pro (Gemini 3 Pro Image, higher cost / locked identity), nano-banana-edit (inpaint-focused), or nano-banana (legacy). Anything else is refused. If the user asks for gpt-image-2, point them at chatgpt-image-ad.
  2. No platform/screenshot chrome in output. NO_CHROME_SUFFIX is always on (override only with --allow-chrome).
  3. Edge-safe + glyph-safety suffixes always on unless --no-safe-zone is explicit.
  4. Max 14 reference images. Hard Arcads cap for Nano Banana. Script enforces.
  5. No Meta upload from this skill. Image generation only. The user has a separate ad-builder skill in their stack — hand off via filesystem paths.
  6. Always present a credit-cost estimate before generating. Each Nano Banana call is one image; multiply by --n. nano-banana-pro costs more than nano-banana-2 — surface the per-model rate from logs/arcads-api.jsonl.

Prerequisites

  • .env containing ARCADS_BASIC_AUTH (preferred) OR ARCADS_API_KEY
  • Optional: PRODUCT_ID, PROJECT_ID in .env for session-folder organization
  • Reference images on local disk. The script handles the Arcads presigned-upload flow internally.

Configuration

  • Base URL: https://external-api.arcads.ai (or ARCADS_BASE_URL).
  • Auth: HTTP Basic. The script prefers a pre-encoded ARCADS_BASIC_AUTH; falls back to encoding ARCADS_API_KEY.
  • Endpoint: POST /v2/images/generate; poll GET /v1/assets/{id} until status: generated.
  • Reference uploads: POST /v1/file-upload/get-presigned-url returns {presignedUrl, filePath}; PUT bytes to presignedUrl; pass the filePath in referenceImages. Single-use — re-uploaded fresh per variant by the script.

Generation modes

ModeWhen to useRequiredOptional
image (default)Brand-new ad image.--prompt, --aspect-ratio--image-ref (up to 14)
image_editModify a --source image.--prompt, --source--image-ref (up to 14)

Supported aspect ratios

1:1, 16:9, 9:16. Only these three are accepted by Arcads' /v2/images/generate endpoint (the same endpoint serves gpt-image-2 and Nano Banana — same ratio constraints). Templates in the shared library that use 2:3, 4:5, 3:2, etc. won't render at their native ratio on this backend — fall back to 1:1 and post-crop, or use the KIE nano-banana-image-ad sibling which supports the full Meta ratio set natively via the /jobs/createTask endpoint.

Model variants (--model)

  • nano-banana-2 (default) — Gemini 2.5 Flash Image. The standard. Use for most templates.
  • nano-banana-pro — Gemini 3 Pro Image. Use for hero stills, character continuity across runs, material-realism critical shots (claymation, Pixar, premium product photography). Costs more credits.
  • nano-banana-edit — inpaint-focused. Use only with --mode image_edit for tight masked edits (swap background, change object color).
  • nano-banana — legacy. Use only if the user explicitly asks; new work should use nano-banana-2.

Ask the user which variant they want before the first generation in a session if the value isn't already set in MASTER_CONTEXT.md. Default to nano-banana-2.

Workflow

Phase 1: Preflight
  1. .env exists with credentials.
  2. (Optional) arcads-external-api session folder set up.
  3. Health-check: curl -sf -H "$AUTH" "$BASE_URL/v1/products" returns 200.
Phase 2: Gather inputs

Collect: seed prompt, mode, source (if edit), reference paths (up to 14), variant count, aspect ratio, model variant.

Show full SKILL.md (388 more words)Show less
Phase 3: Prompt rewrite

Read shared/skills/image-ad-prompting/prompting/prompt-library.md. If the user's brief matches a template, check the Model notes block — only proceed if nano-banana is marked clean, preferred, or strong. If gpt-image-2 is preferred, suggest switching skills.

Fill {placeholders} and show the user the rewritten prompt. Ask for approval before generating.

For fresh prompts (no template match), follow the structure in shared/skills/nano-banana-image-ad/prompting/guide.md § Phase 3b — lean on Nano Banana strengths (named reference roles, lighting specifics, material specifics).

Phase 4: Credit cost confirmation (MANDATORY)

Present the estimated credit cost (read from logs/arcads-api.jsonl for matching past calls). Surface the model variant prominently: nano-banana-pro costs more than nano-banana-2. Wait for explicit confirmation.

Phase 5: Generate
bash
~/.claude/skills/nano-banana-image-ad/scripts/generate_image.py \
  --prompt "<rewritten>" \
  --aspect-ratio <ratio> \
  --n <N> \
  --image-ref <product.png> \
  [--image-ref <character.png>] \
  [--image-ref <style.png>] \
  --out ./generated \
  --env-file .env

# For higher-stakes hero shots:
~/.claude/skills/nano-banana-image-ad/scripts/generate_image.py \
  --model nano-banana-pro \
  --prompt "<rewritten>" \
  --aspect-ratio <ratio> \
  --n <N> \
  --image-ref <product.png> \
  --out ./generated \
  --env-file .env

# For an edit run (inpaint):
~/.claude/skills/nano-banana-image-ad/scripts/generate_image.py \
  --mode image_edit \
  --model nano-banana-edit \
  --prompt "<edit-instruction>" \
  --source <existing.png> \
  [--image-ref <guidance.png>] \
  --n <N> \
  --out ./generated \
  --env-file .env

Each line on stdout is one JSON variant (variant, path, asset_id, width, height, prompt, mode, aspect_ratio, model).

Log each call to logs/arcads-api.jsonl with the model variant, ref count, and returned asset_ids.

Phase 6: Visual QA (MANDATORY)

For each completed variant, read the image and inspect for:

  • Garbled small text (the main Nano Banana weakness)
  • Extra fingers / wrong limb count (common Gemini-family failure)
  • Wordmark drift (always pass brand wordmarks as --image-ref to mitigate)
  • Character identity drift across variants (use nano-banana-pro to lock identity if it matters)

If defects: regenerate with a revised prompt that explicitly corrects the issue (see shared/skills/nano-banana-image-ad/prompting/guide.md § Retry mode). Cap at 2 retries per variant.

Phase 7: Confirm and hand off

Show all paths to the user. Ask "Use all / use these specific ones / regenerate / cancel."

Selected variants are ready for your Meta-ad-builder skill. Print the paths.

Optionally, write the selected paths to ./generated/run-<ts>.jsonl for downstream consumption.

Out of scope — fail clearly

  • Meta upload — different skill in your stack.
  • ChatGPT Image 2 / gpt-image-2 generation — use chatgpt-image-ad.
  • Video, carousel, DCO ads — image only.
  • Ad copy writing — different skill.
  • Editing the shared prompt library — use image-ad-clone (asks which backend at Phase 1).

Common errors

  • 401/403 → fix .env.
  • 422 validation/moderation → tighten prompt; check aspectRatio is in supported set; check --n ≤ 5.
  • 500 UNKNOWN_ERROR → usually a stale presigned filePath. The script re-uploads per variant; if persistent, file an issue with the asset_id.

Files this skill owns

  • ~/.claude/skills/nano-banana-image-ad/SKILL.md — this file
  • ~/.claude/skills/nano-banana-image-ad/scripts/generate_image.py — Arcads Nano Banana caller

See also

© krusemediallc, 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 1 other file (scripts) in skills/nano-banana-image-ad of krusemediallc/arcads-claude-code.

  • SKILL.md
  • scripts/generate_image.py

Open the folder on GitHubat commit 1263501

Compare with similar skills

Nano Banana Image Ad 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 Image Ad compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Nano Banana Image Ad this skillkrusemediallc/arcads-claude-code1.6k—~2.5kAutomated safety check: NotesMIT
Nano Banana Pro Prompts Recommend SkillYouMind-OpenLab/nano-banana-pro-prompts-recommend-skill1.9k1 repos~4.1kAutomated safety check: PassNone
AI Image Creatorcentminmod/my-claude-code-setup2.7k—~8.1kAutomated safety check: NotesMIT
Zy Cinematic Realismpopopo-99/zy-cinematic-realism570—~4.6kAutomated safety check: PassCC-BY-NC-4.0
Image GenerationNegai-ai/AgentClaw330—~1.9kAutomated safety check: NotesApache-2.0
ImageNexus-JPF/note-companion8703 repos~3.9kAutomated safety check: PassMIT

Similar skills

  • Nano Banana Pro Prompts Recommend Skill

    YouMind-OpenLab/nano-banana-pro-prompts-recommend-skill

    Recommend suitable prompts from 10,000+ Nano Banana Pro image generation prompts based on user needs.

    1.9k GitHub starsUsed in 1 repo~4.1k tokens
    Media & CreativeAuto-check passed

  • AI Image Creator

    centminmod/my-claude-code-setup

    Generate, edit-from-reference, or analyze images with AI via OpenRouter (Gemini, GPT Image, Seedream, Qwen, MAI, Grok, FLUX.2, Recraft, Muse, Riverflow; Cloudflare AI Gateway BYOK).

    2.7k GitHub stars~8.1k tokensUpdated 3 days ago
    Media & CreativeAuto-check: notes

  • Zy Cinematic Realism

    popopo-99/zy-cinematic-realism

    Develop supplied scripts, short stories, or synopses into scene understanding, director-facing art concepts, and motivated narrative keyframes; compile scene ideas, visual references, or existing…

    570 GitHub stars~4.6k tokensUpdated 7 days ago
    Media & CreativeAuto-check passed

  • Image Generation

    Negai-ai/AgentClaw

    Generate, edit, and iterate raster images from text prompts or reference images with GPT Image, Nano Banana, or Seedream.

    330 GitHub stars~1.9k tokensUpdated 4 mo ago
    Media & CreativeAuto-check: notes

  • Image

    Nexus-JPF/note-companion

    When the user wants to create, generate, edit, or optimize images for marketing — blog heroes, social graphics, product mockups, profile banners, listing visuals, or brand assets.

    870 GitHub starsUsed in 3 repos~3.9k tokens
    Media & CreativeAuto-check passed

  • Nbcraft

    jieyefriic/nbcraft

    Multi-backend Image + Video Generation CLI (nb command). An agent skill from jieyefriic/nbcraft.

    155 GitHub stars~2.8k tokensUpdated 5 mo ago
    Media & CreativeAuto-check passed

More from krusemediallc/arcads-claude-code

All 8 skills in this repo

  • Analyze Video

    krusemediallc/arcads-claude-code

    Analyze a reference video and reverse-engineer its style into a reusable Seedance 2.0 prompting template.

    1.6k GitHub stars~4.2k tokensUpdated 18 days ago
    Auto-check passed

  • Chatgpt Image Ad

    krusemediallc/arcads-claude-code

    Generate one or more standalone Meta image-ad creatives via ChatGPT Image 2 (gpt-image-2) through the Arcads external API.

    1.6k GitHub stars~2.7k tokensUpdated 18 days ago
    Auto-check: notes

  • Generate Youtube Thumbnail

    krusemediallc/arcads-claude-code

    Generate high-CTR YouTube thumbnails using Nano Banana 2 via the Arcads external API.

    1.6k GitHub stars~2.4k tokensUpdated 18 days ago
    Auto-check: notes

  • Meta Ad Builder

    krusemediallc/arcads-claude-code

    Publish finished creatives as live Meta (Facebook/Instagram) ads via the Meta Marketing API, plus research and ad-copy support.

    1.6k GitHub stars~1.7k tokensUpdated 18 days ago
    Auto-check: notes

  • Image Ad Clone

    krusemediallc/arcads-claude-code

    A skill your agent uses when the user wants to reverse-engineer an existing image ad into a reusable prompt template.

    1.6k GitHub stars~2.4k tokensUpdated 18 days ago
    Auto-check: notes

  • Arcads External API

    krusemediallc/arcads-claude-code

    Creates and retrieves AI video and image-related assets via the Arcads external API (Seedance 2.0, Sora 2, Veo 3.1, Kling, Grok Video, Nano Banana, b-roll, scene, script/actor flows).

    1.6k GitHub stars~8.7k tokensUpdated 18 days ago
    Auto-check: notes

Works with

Categories

Questions about Nano Banana Image Ad

What does Nano Banana Image Ad do?

Generate one or more standalone Meta image-ad creatives via Nano Banana 2 / Nano Banana Pro (Gemini Flash Image family) through the Arcads external API. Nano Banana Image Ad is an agent skill from krusemediallc/arcads-claude-code. Generate one or more standalone Meta image-ad creatives via Nano Banana 2 / Nano Banana Pro (Gemini Flash Image family) through the Arcads external API.

When should I use Nano Banana Image Ad?

Nano Banana Image Ad fits situations like: the user asks for a Nano Banana ad; gemini image ad; nano-banana-2 ad creative; make a static image ad with Gemini.

How do I install Nano Banana Image Ad in Claude Code?

Run `npx skills add krusemediallc/arcads-claude-code --skill nano-banana-image-ad -a claude-code`. Or copy the skill folder (skills/nano-banana-image-ad in krusemediallc/arcads-claude-code) into .claude/skills/nano-banana-image-ad in your project. Claude Code loads it when a task matches its description.

How do I install Nano Banana Image Ad in Codex?

Run `npx skills add krusemediallc/arcads-claude-code --skill nano-banana-image-ad -a codex`. Or copy the skill folder (skills/nano-banana-image-ad in krusemediallc/arcads-claude-code) into .agents/skills/nano-banana-image-ad in your project. Codex loads it when a task matches its description.

Can I use Nano Banana Image Ad 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 krusemediallc/arcads-claude-code --skill nano-banana-image-ad -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-image-ad, .gemini/skills/nano-banana-image-ad, .github/skills/nano-banana-image-ad and .opencode/skills/nano-banana-image-ad in your project.

What does Nano Banana Image Ad need to run?

Going by SKILL.md and its folder, Nano Banana Image Ad needs Python for the scripts in its folder, the command-line tools its instructions call (curl) and credentials named ARCADS_API_KEY. Our summary lists: Python 3; A credential in ARCADS_API_KEY.

Does Nano Banana Image Ad access the network?

SKILL.md names 1 domain. In commands or code: external-api.arcads.ai; the agent is likely to contact it when it follows the instructions. This is read from the text; nothing was executed.

Is Nano Banana Image Ad 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. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Nano Banana Image Ad use?

Nano Banana Image Ad 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 Image Ad use?

About 2.5k tokens (SKILL.md is roughly 10k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Nano Banana Image Ad?

Skills that share tags, products or a category with Nano Banana Image Ad: Nano Banana Pro Prompts Recommend Skill (YouMind-OpenLab/nano-banana-pro-prompts-recommend-skill, 1.9k stars), AI Image Creator (centminmod/my-claude-code-setup, 2.7k stars), Zy Cinematic Realism (popopo-99/zy-cinematic-realism, 570 stars) and Image Generation (Negai-ai/AgentClaw, 330 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Nano Banana Image Ad?

krusemediallc (a GitHub user) maintains it in krusemediallc/arcads-claude-code, which has 1,585 GitHub stars. The repository holds 8 skills in this directory. The repository was last updated on September 22, 2026.

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