Automated summary

Generates images using Google's Nano Banana model via x402 micropayments on Base network, no API keys required.

Strengths

Pay-per-request with no subscription or API keys needed.
Private key never leaves your machine thanks to local EIP-712 signing.
Multiple models available (Nano Banana, DALL-E 3) with different resolutions.

Limitations

Requires owning USDC on the Base network.
Cost per image may be prohibitive for high-volume use.
Initial setup (bridge, wallet) can be complex for non-crypto users.

When to use it

Best for occasional image generation without commitment, especially in decentralized setups or when micropayments are preferred.

When not to use it

Avoid if you need to generate a large number of images (cumulative costs) or prefer a traditional subscription model.

Security analysis

Caution

Quality score85/100

The skill involves handling a crypto wallet private key for micropayments. While the key is intended to stay local, the risk of exposure through environment variables or a malicious package exists.

Findings

•Instructs user to set a cryptocurrency wallet private key in environment variables, which if mishandled could lead to loss of funds.
•Relies on external package `blockrun-llm` which could potentially have access to the private key if malicious.

How this analysis is made

Examples

Generate a cute cat

Generate an image of a cute cat wearing a space helmet using Nano Banana.

Use pro model

Create a high-resolution image of a futuristic cityscape at 4K using google/nano-banana-pro.

Save to folder

Generate an image of a serene mountain lake and save it to /home/user/images.

name: nano-banana-blockrun description: "Nano Banana by BlockRun - Generate images using Google's Nano Banana via x402 micropayments. Use when the user asks to generate, create, draw, or make images. Pay-per-request via USDC on Base, no API keys needed." allowed-tools: Read, Bash(python:), Bash(python3:), Bash(pip:), Bash(pip3:)

Nano Banana by BlockRun

Name: Nano Banana by BlockRun - Image Generation
Author: Skills Guide Bot

Generate images using Google's Nano Banana model via BlockRun's x402 API. Pay-per-request with USDC on Base - no API keys needed.

Setup (one-time)

Install the SDK:
```
pip install blockrun-llm
```
Get USDC on Base network:
- Bridge from Ethereum: https://bridge.base.org
- Or buy directly on Coinbase and withdraw to Base
- You need ~$1-5 USDC to start generating images

Set your wallet private key:

# Copy .env.example to .env and add your key
cp .env.example .env

# Or export directly
export BLOCKRUN_WALLET_KEY=0x...

Network: Base (Chain ID: 8453) Payment: USDC only

Generate an Image

from blockrun_llm import ImageClient

client = ImageClient()
result = client.generate("a cute cat wearing a space helmet")
print(result.data[0].url)

Or use the script:

python scripts/generate.py "a cute cat wearing a space helmet"

# Save to a specific directory
python scripts/generate.py "a cute cat" "google/nano-banana" "/path/to/save"

# Or use OUTPUT_DIR environment variable
OUTPUT_DIR=/path/to/save python scripts/generate.py "a cute cat"

Available Models

| Model | Price | Resolution | |-------|-------|------------| | google/nano-banana | ~$0.05 | 1024x1024 | | google/nano-banana-pro | ~$0.10 | up to 4K | | openai/dall-e-3 | ~$0.04-0.12 | 1024x1024 to 1792x1024 |

How It Works

Your request goes to BlockRun API (https://blockrun.ai)
BlockRun returns HTTP 402 Payment Required
SDK signs USDC payment locally (key never leaves your machine)
Only the signature is sent to server
Image is generated and returned

No API keys, no subscriptions - just crypto micropayments.

Security

Your private key NEVER leaves your machine.

The SDK uses EIP-712 typed data signing locally. Only the signature is transmitted. Same security as signing any MetaMask transaction.

From the file to a first result

The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.

View the source and supporting files

This download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.

1. Download the file

Download SKILL.md

From the root of a test project, save the file as .skill-downloads/nano-banana-by-blockrun-image-generation-mrwakat3/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.

Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.

mkdir -p '.skill-downloads/nano-banana-by-blockrun-image-generation-mrwakat3' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/nano-banana-by-blockrun-image-generation-mrwakat3/download' --output '.skill-downloads/nano-banana-by-blockrun-image-generation-mrwakat3/SKILL.md.part' && mv '.skill-downloads/nano-banana-by-blockrun-image-generation-mrwakat3/SKILL.md.part' '.skill-downloads/nano-banana-by-blockrun-image-generation-mrwakat3/SKILL.md'

2. Check prerequisites

Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.

Tools declared by the author (check availability in your agent): Read, Bash(python:*), Bash(python3:*), Bash(pip:*), Bash(pip3:*)

No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.

The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.

3. Load the skill

After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.

Claude Code

test -f '.skill-downloads/nano-banana-by-blockrun-image-generation-mrwakat3/SKILL.md' && test -s '.skill-downloads/nano-banana-by-blockrun-image-generation-mrwakat3/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/nano-banana-blockrun' && cp -R '.skill-downloads/nano-banana-by-blockrun-image-generation-mrwakat3' '.claude/skills/nano-banana-blockrun'

Cursor

test -f '.skill-downloads/nano-banana-by-blockrun-image-generation-mrwakat3/SKILL.md' && test -s '.skill-downloads/nano-banana-by-blockrun-image-generation-mrwakat3/SKILL.md' && mkdir -p '.cursor/skills' && test ! -e '.cursor/skills/nano-banana-blockrun' && cp -R '.skill-downloads/nano-banana-by-blockrun-image-generation-mrwakat3' '.cursor/skills/nano-banana-blockrun'

Codex

test -f '.skill-downloads/nano-banana-by-blockrun-image-generation-mrwakat3/SKILL.md' && test -s '.skill-downloads/nano-banana-by-blockrun-image-generation-mrwakat3/SKILL.md' && mkdir -p '.agents/skills' && test ! -e '.agents/skills/nano-banana-blockrun' && cp -R '.skill-downloads/nano-banana-by-blockrun-image-generation-mrwakat3' '.agents/skills/nano-banana-blockrun'

OpenSkills

OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.

Official OpenSkills installation

openskills install './.skill-downloads/nano-banana-by-blockrun-image-generation-mrwakat3'

openskills read 'nano-banana-by-blockrun-image-generation-mrwakat3'

Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.

For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.

openskills sync

Manual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.

4. Try a first task

Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:

Read .skill-downloads/nano-banana-by-blockrun-image-generation-mrwakat3/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.

Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.

Related skills

Create Interactive Maps with kepler.gl

Data & AI

Create interactive map visualizations and export standalone HTML using the keplergl Python package. Use to plot geospatial data from DataFrames, GeoJSON, or CSV.

Claude CodeCursorCodexintermediateSafe 11,995

Skills Guide Bot