Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Nanobanana Image Generation · leoyeai | DecimalAI

Design & Mediaby leoyeai

Nanobanana Image Generation

Use when the user wants to generate or edit images with Google's Nanobanana/Gemini image models using the official Gemini API shape, or when they need publication-style scientific figures rendered exactly from data with the bundled Python plotting tool. Prefer this skill for text-to-image, image-to-image editing, multi-image reference workflows, attachment-based recreations, exact bar/trend/heatmap/scatter plots, or when the user wants publication-style figures such as materials-science paper sc

Never made a case worse

SkillScore

SkillScore83/100

Test results 83

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

35%83%of test cases passed +48 pts

Without skill8 of 23

With skill19 of 23

11 fixed8 passed either way4 still failing0 broke

Measured on gemini-3.6-flash8/8/2026v121 comparable

Track record

Agent runs: 0; All time
Forks: 1

See one task, with and without the skill

One test taskWhen building raw HTTP requests for Gemini image generation against the Google endpoint, what exact REST route path and HTTP method must be targeted for model gemini-3.1-flash-image-preview?

Without the skillMissed

With the skillPassed

Same model, same task. Answers are capped and redacted.

Use this skill

Your agent runs on

Adds every file the skill has, pinned so you can update it. No account needed.

pip install "decimalai>=0.15"
decimalai skills add leoyeai-nanobanana-image-generation
claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

The same install from Python, for a notebook or a setup script.

Install

pip install "decimalai>=0.15"

Add the skill

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nanobanana-image-generation")
if result.exit_code:
    raise SystemExit(result.problems)

print("Added. Start Claude Code with the command below.")

Start Claude Code with it

claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"

Type these in a Claude Code session. No account or API key. It writes the skill and any files it bundles, and asks first when its safety rating isn't Passed.

Add the DecimalAI plugin, once

/plugin marketplace add decimal-labs/decimalai-claude-plugins
/plugin install decimalai@decimalai

Install this skill

/decimalai:install leoyeai-nanobanana-image-generation

The plugin needs python3 and curl on your machine.

No Python or account. Claude Code picks it up in its next session.

Save it into your project

curl -fsSL --create-dirs -o .claude/skills/leoyeai-nanobanana-image-generation/SKILL.md https://app.decimal.ai/s/leoyeai-nanobanana-image-generation/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-nanobanana-image-generation/SKILL.md

This gets SKILL.md only. The skill's 13 other files are not included.

Other ways to add it

Claude Code docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"
decimalai skills add leoyeai-nanobanana-image-generation

Add it to your agent

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

The same install from Python, for a notebook or a setup script. agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[claude-agent-sdk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nanobanana-image-generation")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

async def main():
    question = "Hello!"
    async with support.run(question) as run:  # one user message, one run
        async for message in run.query(options=ClaudeAgentOptions(max_turns=6)):
            print(message)

# In a notebook or async code: await main()
asyncio.run(main())

Prefer its own loader? ClaudeAgentOptions(plugins=[skills_plugin()], skills="all") reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nanobanana-image-generation/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from claude_agent_sdk import ClaudeAgentOptions, query

skill = Path(".agents/skills/leoyeai-nanobanana-image-generation/SKILL.md").read_text()
options = ClaudeAgentOptions(system_prompt=f"You are a helpful agent.\n\n{skill}", max_turns=6)

async def main():
    async for message in query(prompt="Hello!", options=options):
        print(message)

# In a notebook or async code: await main()
asyncio.run(main())

This gets SKILL.md only. The skill's 13 other files are not included.

Other ways to add it

Claude Agent SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai-agents]"
decimalai skills add leoyeai-nanobanana-image-generation

Add it to your agent

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

Install

pip install "decimalai[openai-agents]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nanobanana-image-generation")
if result.exit_code:
    raise SystemExit(result.problems)

from agents import Agent, Runner
from decimalai.openai_agents import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    name=support.name,
    instructions=support.instructions,  # your prompt, then the skill list
    tools=[*support.tools],             # your tools, then load_skill
)
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

Using SandboxAgent? capabilities=[Shell(), decimalai.openai_agents.sandbox_skills()] points its own loader at the same folder.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nanobanana-image-generation/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-nanobanana-image-generation/SKILL.md").read_text()
agent = Agent(name="support", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

This gets SKILL.md only. The skill's 13 other files are not included.

Other ways to add it

OpenAI Agents docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[openai]"
decimalai skills add leoyeai-nanobanana-image-generation

Add it to your agent

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

Install

pip install "decimalai[openai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nanobanana-image-generation")
if result.exit_code:
    raise SystemExit(result.problems)

import json

from openai import OpenAI
from decimalai.openai import agent_config

client = OpenAI()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your tools, as Chat Completions takes them, and what answers each.
TOOLS = [{"type": "function", "function": {
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters": {"type": "object", "properties": {"order_id": {"type": "string"}},
                   "required": ["order_id"]},
}}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    # run.system is your prompt, then the skill list.
    messages = [{"role": "system", "content": run.system}, run.message]
    while True:
        reply = client.chat.completions.create(
            model="gpt-5.4-mini",
            messages=messages,
            tools=[*TOOLS, *run.tools],  # your tools, then load_skill
        ).choices[0].message
        messages.append(reply)
        if not reply.tool_calls:
            break
        for call in reply.tool_calls:
            # load_skill is answered by the run; your own tools by FUNCTIONS.
            function = FUNCTIONS.get(call.function.name)
            messages.append(run.tool_result(call) or {
                "role": "tool", "tool_call_id": call.id,
                "content": function(**json.loads(call.function.arguments)) if function
                else f"There is no tool named {call.function.name!r}.",
            })
print(reply.content)

# The Responses API takes run.response_tools instead of run.tools.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nanobanana-image-generation/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-nanobanana-image-generation/SKILL.md").read_text()
reply = client.chat.completions.create(
    model="gpt-5.4-mini",
    messages=[
        {"role": "system", "content": f"You are a helpful agent.\n\n{skill}"},
        {"role": "user", "content": "Hello!"},
    ],
).choices[0].message

This gets SKILL.md only. The skill's 13 other files are not included.

Other ways to add it

OpenAI SDK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[anthropic]"
decimalai skills add leoyeai-nanobanana-image-generation

Add it to your agent

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

Install

pip install "decimalai[anthropic]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nanobanana-image-generation")
if result.exit_code:
    raise SystemExit(result.problems)

import anthropic
from decimalai.anthropic import agent_config

client = anthropic.Anthropic()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

question = "Hello!"
with support.run(question) as run:  # one user message, one run
    answer = client.beta.messages.tool_runner(
        model="claude-haiku-5-5",
        max_tokens=4096,
        system=run.system,     # your prompt, then the skill list
        tools=[*run.tools],    # your tools, then load_skill
        messages=[{"role": "user", "content": question}],
    ).until_done()

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nanobanana-image-generation/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-nanobanana-image-generation/SKILL.md").read_text()
reply = client.messages.create(
    model="claude-haiku-5-5",
    max_tokens=4096,
    system=f"You are a helpful agent.\n\n{skill}",
    messages=[{"role": "user", "content": "Hello!"}],
)

This gets SKILL.md only. The skill's 13 other files are not included.

Other ways to add it

Anthropic docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[google-genai]"
decimalai skills add leoyeai-nanobanana-image-generation

Add it to your agent

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

Install

pip install "decimalai[google-genai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nanobanana-image-generation")
if result.exit_code:
    raise SystemExit(result.problems)

from google import genai
from google.genai import types
from decimalai.google_genai import agent_config

client = genai.Client()
# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")


def lookup_order(order_id: str) -> str:
    return f"Order {order_id} shipped yesterday."


# Your functions, as declarations for the model, and what answers each.
TOOLS = [{"function_declarations": [{
    "name": "lookup_order",
    "description": "Look up the status of an order.",
    "parameters_json_schema": {"type": "object", "properties": {"order_id": {"type": "string"}},
                               "required": ["order_id"]},
}]}]
FUNCTIONS = {"lookup_order": lookup_order}

question = "Where is order A1001?"
with support.run(question) as run:  # one user message, one run
    config = types.GenerateContentConfig(
        system_instruction=run.system,     # your prompt, then the skill list
        tools=[*TOOLS, *run.tool_params],  # your functions, then load_skill
    )
    contents = [{"role": "user", "parts": [{"text": run.message}]}]
    while True:
        response = client.models.generate_content(
            model="gemini-3.5-flash", contents=contents, config=config,
        )
        if not response.function_calls:
            break
        contents.append(response.candidates[0].content)
        parts = []
        for call in response.function_calls:
            # load_skill is answered by the run; your own functions by FUNCTIONS.
            # A loop of your own rather than automatic function calling, which
            # raises KeyError when the model asks for a function you did not pass.
            function = FUNCTIONS.get(call.name)
            parts.append(run.tool_result(call) or {"function_response": {
                "name": call.name, "id": call.id,
                "response": {"result": function(**(call.args or {})) if function
                             else f"There is no function named {call.name!r}."},
            }})
        contents.append({"role": "user", "parts": parts})
print(response.text)

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nanobanana-image-generation/SKILL.md

Give it to your agent

from pathlib import Path
from google import genai
from google.genai import types

client = genai.Client()
skill = Path(".agents/skills/leoyeai-nanobanana-image-generation/SKILL.md").read_text()
response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="Hello!",
    config=types.GenerateContentConfig(system_instruction=f"You are a helpful agent.\n\n{skill}"),
)

This gets SKILL.md only. The skill's 13 other files are not included.

Other ways to add it

Gemini API docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[langchain]" langchain-openai
decimalai skills add leoyeai-nanobanana-image-generation

Add it to your agent

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

Install

pip install "decimalai[langchain]" langchain-openai

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nanobanana-image-generation")
if result.exit_code:
    raise SystemExit(result.problems)

from langchain.agents import create_agent
from decimalai.langchain import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = create_agent(
    "openai:gpt-5.4-mini",
    tools=[],                         # your tools; the middleware adds load_skill
    middleware=[support.middleware],  # your prompt, the skill list and load_skill
)
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nanobanana-image-generation/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-nanobanana-image-generation/SKILL.md").read_text()
agent = create_agent("openai:gpt-5.4-mini", tools=[], system_prompt=f"You are a helpful agent.\n\n{skill}")
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

This gets SKILL.md only. The skill's 13 other files are not included.

Other ways to add it

LangChain docs

CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add leoyeai-nanobanana-image-generation

Add it to your agent

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

The same install from Python, for a notebook or a setup script. CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nanobanana-image-generation")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.crewai
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                               # your own CrewAI LLM
    skills=decimalai.crewai.skills(),      # the installed folder
    tools=decimalai.crewai.skill_tools(),  # reads a skill's files, runs its scripts
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

No DecimalAI package. CrewAI's own loader reads the folder, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nanobanana-image-generation/SKILL.md

Give it to your agent

from pathlib import Path
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                         # your own CrewAI LLM
    skills=[Path(".agents/skills")],
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

This gets SKILL.md only. The skill's 13 other files are not included.

Other ways to add it

CrewAI docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[adk]"
decimalai skills add leoyeai-nanobanana-image-generation

Add it to your agent

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

Install

pip install "decimalai[adk]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nanobanana-image-generation")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.adk import DecimalAIPlugin, agent_config
from google.adk.agents import LlmAgent
from google.adk.apps import App

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = LlmAgent(
    name="support",          # ADK needs a Python identifier
    model="gemini-3.5-flash",
    instruction=support.instruction,  # your prompt, then the skill list
    tools=[*support.tools],           # your tools, then load_skill
)
# DecimalAIPlugin makes each invocation of runners built from this App one trace.
app = App(name="support", root_agent=agent, plugins=[DecimalAIPlugin()])

Prefer ADK's own loader? SkillToolset(skills=decimalai.adk.skills(), ...) reads the same folder. Use one or the other: a skill delivered both ways reaches the prompt twice.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nanobanana-image-generation/SKILL.md

Give it to your agent

from pathlib import Path
from google.adk.agents import LlmAgent

skill = Path(".agents/skills/leoyeai-nanobanana-image-generation/SKILL.md").read_text()
agent = LlmAgent(
    name="support",
    model="gemini-3.5-flash",
    instruction=lambda context: f"You are a helpful agent.\n\n{skill}",
)

This gets SKILL.md only. The skill's 13 other files are not included.

Other ways to add it

Google ADK docs

agent_config() hands your agent the skill. With no DecimalAI key it reads your project's files and sends nothing. Needs SDK 0.27 or newer.

Install

pip install "decimalai[pydantic-ai]"
decimalai skills add leoyeai-nanobanana-image-generation

Add it to your agent

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

Install

pip install "decimalai[pydantic-ai]"

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nanobanana-image-generation")
if result.exit_code:
    raise SystemExit(result.problems)

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

# With no DECIMAL_API_KEY this reads the skills your project lists, from disk.
support = agent_config("support", fallback="You are a helpful agent.")

agent = Agent(
    "openai:gpt-4o-mini",
    name=support.name,
    tools=[],                 # your tools; the capability adds load_skill
    capabilities=[support],   # your prompt, the skill list and load_skill
)
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

On the Pydantic AI harness, decimalai.pydantic_ai_harness.skills(project) uses its own loader instead.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nanobanana-image-generation/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-nanobanana-image-generation/SKILL.md").read_text()
agent = Agent("openai:gpt-4o-mini", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

This gets SKILL.md only. The skill's 13 other files are not included.

Other ways to add it

Pydantic AI docs

Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents
decimalai skills add leoyeai-nanobanana-image-generation

Add it to your agent

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

The same install from Python, for a notebook or a setup script. Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" deepagents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nanobanana-image-generation")
if result.exit_code:
    raise SystemExit(result.problems)

import decimalai.deepagents
from deepagents import create_deep_agent

agent = create_deep_agent(model=model, **decimalai.deepagents.skills())
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

The default backend reads files but has no shell. To run a skill's scripts, pass skills(backend=LocalShellBackend(...)).

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nanobanana-image-generation/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-nanobanana-image-generation/SKILL.md").read_text()
agent = create_deep_agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

This gets SKILL.md only. The skill's 13 other files are not included.

Other ways to add it

Deep Agents docs

Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework
decimalai skills add leoyeai-nanobanana-image-generation

Add it to your agent

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

The same install from Python, for a notebook or a setup script. Its own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" agent-framework

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nanobanana-image-generation")
if result.exit_code:
    raise SystemExit(result.problems)

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

agent = Agent(client=client, instructions="You are a helpful agent.", context_providers=[skills()])
asyncio.run(agent.run("Hello!"))

It caches skills by default, so restart the process after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nanobanana-image-generation/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-nanobanana-image-generation/SKILL.md").read_text()
agent = Agent(client=client, instructions=f"You are a helpful agent.\n\n{skill}")
asyncio.run(agent.run("Hello!"))

This gets SKILL.md only. The skill's 13 other files are not included.

Other ways to add it

Microsoft Agent Framework docs

Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents
decimalai skills add leoyeai-nanobanana-image-generation

Add it to your agent

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

The same install from Python, for a notebook or a setup script. Strands' own skill loader reads the installed folder. No DecimalAI account needed.

Install

pip install "decimalai>=0.16" strands-agents

Add it to your agent

from decimalai import skillpkg

# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("leoyeai-nanobanana-image-generation")
if result.exit_code:
    raise SystemExit(result.problems)

from decimalai.strands import skills
from strands import Agent
from strands.vended_tools import file_editor, shell

agent = Agent(
    model=model,                # always pass one: the default is Amazon Bedrock
    system_prompt="You are a helpful agent.",
    tools=[file_editor, shell],
    plugins=[skills()],
)
agent("Hello!")

Strands loads an agent's skills once, so build the agent again after decimalai skills update.

No DecimalAI package. The whole skill goes in every prompt, and nothing pins or updates it.

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nanobanana-image-generation/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-nanobanana-image-generation/SKILL.md").read_text()
agent = Agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent("Hello!")

This gets SKILL.md only. The skill's 13 other files are not included.

Other ways to add it

Strands docs

Adds every file the skill has, pinned so you can update it. Cursor, Copilot, Cline and Warp read this folder by themselves.

pip install "decimalai>=0.15"
decimalai skills add leoyeai-nanobanana-image-generation

No Python or account. Cursor, Copilot, Cline and Warp read this folder by themselves.

Save it into your project

curl -fsSL --create-dirs -o .agents/skills/leoyeai-nanobanana-image-generation/SKILL.md https://app.decimal.ai/s/leoyeai-nanobanana-image-generation/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-nanobanana-image-generation/SKILL.md

This gets SKILL.md only. The skill's 13 other files are not included.

Other ways to add it

Cursor and other editors docs

Fetch the file and give its text to your model as instructions. No account or package needed.

Get the file

curl -fsSL https://app.decimal.ai/s/leoyeai-nanobanana-image-generation/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-nanobanana-image-generation.json

This gets SKILL.md only. The skill's 13 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/8/2026
Source: LeoYeAI/openclaw-master-skills ↗
License: MIT

Manage it in DecimalAI

Saved prompts and skills, pinned versions, and traces of this skill in your runs. DecimalAI does not run your agent.

Claude Code reads files from your project, so DecimalAI config does not apply there.

On Claude Agent SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI Agents: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On OpenAI SDK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Anthropic: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Gemini API: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On LangChain: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On CrewAI: set DECIMAL_API_KEY and add decimalai.init(crewai=True) to record runs and skill use. The skill version stays in your repo.

On Google ADK: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Pydantic AI: save the skill to an agent here, set DECIMAL_API_KEY, and the same code uses it with no command to run. Changes you save reach the next run with no redeploy.

On Deep Agents: set DECIMAL_API_KEY and add decimalai.init(langchain=True) to record runs and skill use. The skill version stays in your repo.

On Microsoft Agent Framework: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

On Strands: set DECIMAL_API_KEY and add decimalai.init(otel=True, agent_name="support") to record runs and skill use. The skill version stays in your repo.

Editors read files from your project, so DecimalAI config does not apply there.

Anywhere else: record a use with decimalai.log_skill_activation() inside a trace.

Use this skill

SKILL.md

Nanobanana Image Generation

Overview

This skill now supports two modes:

image mode Gemini or Nanobanana generation and editing through the official generateContent flow
plot mode Exact Python or matplotlib rendering of publication-style figures from numeric data

Use image mode for mechanism figures, graphical abstracts, device schematics, style-matched redraws, and diagram-first work. Use plot mode for exact bar charts, trend curves, heatmaps, scatter plots, and multi-panel figures that must preserve numeric truth.

Runtime policy:

Python is the required runtime for this skill and the canonical path for both image and plot workflows.
scripts/generate_image.js is an optional parity CLI for environments that already use Node.js, not the required runtime baseline for registry gating.

When the user is working in Codex and describes a plot in natural language, do not require them to hand-write a JSON spec. Codex should translate the request into an internal plot request or spec and run the plotting scripts.

For image mode, follow Google's official examples and replace:

API key with the provider key
base URL with the chosen Google-compatible Gemini endpoint

Do not use OpenAI-style /images/generations or /images/edits routes for this skill.

Attachment-Only Inputs

If the image exists only as a chat attachment and the platform does not expose a local file path, do not claim the script can upload it directly.

Use this rule:

If the user needs an exact edit of the original uploaded pixels, ask for the local file path first.
If the user accepts a close recreation, analyze the attached image visually and generate a new image that preserves the original composition and style as closely as possible.

For requests like "replace the English text in this attached image with Chinese", the fallback recreation workflow is acceptable when exact pixel-preserving edit is impossible.

Quick Start

Preflight:

plot mode is local-only and does not require API credentials or outbound network access.
image mode sends prompt text, API credentials, and any --input-image files to the configured Gemini-compatible endpoint.
Prefer the official Google endpoint unless you intentionally trust another provider.
If you use a third-party endpoint, require --allow-third-party or NANOBANANA_ALLOW_THIRD_PARTY=1 and treat that as an explicit trust decision.

Set environment variables:

export NANOBANANA_API_KEY="your-provider-key"
export NANOBANANA_BASE_URL="https://generativelanguage.googleapis.com"
export NANOBANANA_MODEL="gemini-3.1-flash-image-preview"

Optional third-party provider:

export NANOBANANA_BASE_URL="https://api.zhizengzeng.com/google"
export NANOBANANA_ALLOW_THIRD_PARTY=1

If you do not want the API key to appear in the command line, store it in a file and use:

export NANOBANANA_API_KEY_FILE="$PWD/.secrets/nanobanana_api_key"

Generate an image:

python3 scripts/generate_image.py "Create a picture of a nano banana dish in a fancy restaurant with a Gemini theme"

Edit an image:

python3 scripts/generate_image.py "Using the provided image, change only the blue sofa to a vintage brown leather Chesterfield sofa. Keep everything else exactly the same." --input-image ./living-room.png

Recreate an attached diagram with translated labels:

python3 scripts/generate_image.py "Recreate the attached pastel technical diagram with the same layout, icons, arrows, and hand-drawn style. Replace all visible English labels with natural Simplified Chinese. Keep the composition unchanged." --aspect-ratio 16:9 --image-size 2K

Safety note:

scripts/build_materials_figure_prompt.py and --print-prompt are local-only and do not send data over the network.
Actual prompt text, API keys, and user-provided input images are sent only when you run the generation scripts against the configured provider.
Non-official Gemini-compatible endpoints require explicit confirmation via --allow-third-party or NANOBANANA_ALLOW_THIRD_PARTY=1.
Prefer NANOBANANA_API_KEY_FILE over inline --api-key when you do not want the key to appear in shell history.

Workflow

Choose a mode first:

If the user supplied numeric data and needs exact plotting, use plot mode. Read references/publication-plot-api.md and run scripts/plot_publication_figure.py. For natural-language requests, also read references/natural-language-plot-workflow.md.
If the user needs a schematic, graphical abstract, or image editing workflow, use image mode. Follow the Gemini generateContent flow below.

For image mode:

Keep the official Gemini request shape. Use POST /v1beta/models/{model}:generateContent with X-goog-api-key.
Put prompt text and image inputs into contents[].parts. Text-only generation uses one text part. Image editing appends one or more inline image parts.
Put image options in generationConfig.imageConfig. Prefer --aspect-ratio and --image-size, matching the official docs.
For materials-science figures, prefer building the final prompt first. Use python3 scripts/build_materials_figure_prompt.py --materials-figure ... when you want to inspect or refine the prompt before sending any API request.
For publication-style research figures, load the bundled design guides as needed. Read references/publication-figure-design.md for house style, palette semantics, typography, and panel logic.
If the figure contains chart-like panels, read references/publication-chart-patterns.md. Use those patterns to specify grouped bars, heatmaps, trend layouts, dedicated legends, and wide comparison panels.
Save image outputs from candidates[0].content.parts[].inlineData. Save text parts too when returned.
If the source image is attachment-only, choose between exact edit and recreation. Ask for a local path for exact editing. Use recreation if the user wants the result and accepts a visually matched redraw.

For plot mode:

Read references/publication-plot-api.md.
If the user is speaking naturally, infer the plotting intent and data structure. Do not ask the user to author the internal spec unless they explicitly want low-level control.
For concise internal translation, optionally create a request JSON and expand it with scripts/build_plot_spec.py.
Build or generate a JSON spec with top-level style, layout, and panels.
Use bar, trend, heatmap, scatter, legend, or empty panels.
Render with:

python3 skills/nanobanana-image-generation/scripts/plot_publication_figure.py spec.json

Export exact PNG, PDF, or SVG outputs.

Environment

Required:

NANOBANANA_API_KEY
NANOBANANA_BASE_URL Must be set explicitly. Official Google endpoint: https://generativelanguage.googleapis.com

Optional:

NANOBANANA_MODEL Default: gemini-3.1-flash-image-preview
NANOBANANA_TIMEOUT Default: 120
NANOBANANA_API_KEY_FILE Path to a file containing the API key. Prefer this when you do not want the key shown in command history or command logs.
NANOBANANA_ALLOW_THIRD_PARTY Set to 1 only when you intentionally want to send API keys and user-provided files to a non-official Gemini-compatible provider.

Scripts

scripts/generate_image.py Python CLI that follows the official Gemini generateContent request shape.
scripts/generate_image.js Node.js CLI with the same request format.
scripts/plot_publication_figure.py Python CLI for exact publication-style plotting from JSON specs.
scripts/build_plot_spec.py Python CLI that expands a concise request JSON into a full plotting spec.

Common options:

--input-image ./source.png
--prompt-file ./background.md
--aspect-ratio 16:9
--image-size 2K
--text-only
--thinking-level high
--include-thoughts
--materials-figure mechanism-figure
--lang zh
--style-note "Nature Energy style"
--print-prompt
--allow-third-party
--api-key-file ./.secrets/nanobanana_api_key

Default output location:

./output/nanobanana/ relative to the current Codex working directory
Override only when the user explicitly wants another folder

Deterministic plotting:

python3 skills/nanobanana-image-generation/scripts/plot_publication_figure.py ./spec.json \
  --out-path ./output/plots/result \
  --formats png pdf svg \
  --dpi 300

Natural-language-friendly internal workflow:

python3 skills/nanobanana-image-generation/scripts/build_plot_spec.py ./request.json --out ./spec.json
python3 skills/nanobanana-image-generation/scripts/plot_publication_figure.py ./spec.json

Official Mapping

Official Google examples:

api_key="GEMINI_API_KEY"
base_url="https://generativelanguage.googleapis.com"

Third-party provider replacements:

api_key="your_provider_api_key"
base_url="your_google_compatible_endpoint"
allow_third_party=true

Optional Zhizengzeng example:

api_key="your_zzz_api_key"
base_url="https://api.zhizengzeng.com/google"
allow_third_party=true

Everything else should stay aligned with the official Gemini documentation.

Prompting Rules

For generation, describe the scene instead of dumping keywords.
For editing, explicitly say what must stay unchanged.
For multi-image workflows, describe the role of each reference image.
Prefer English or zh-CN prompts when image fidelity matters.
For attachment-only translation tasks, list each label that must be rewritten so the regenerated image does not miss text.
If layout fidelity matters, explicitly say to preserve icon positions, arrows, spacing, hierarchy, and reading order.
For publication figures, specify semantic color roles, panel order, arrow logic, and which elements should stay neutral.
Keep figure text short. Prefer concise labels and legend entries over paragraph-like annotations baked into the image.
If the figure resembles a plot, say whether it is a conceptual chart, a style-matched redraw, or an exact quantitative reproduction.

Materials Science Figure Shortcut

If the user asks for a materials-science paper figure, journal-style scientific schematic, graphical abstract, mechanism diagram, synthesis workflow figure, microstructure-property diagram, device architecture figure, or characterization-plan figure, use the bundled materials-science templates instead of writing the prompt from scratch.

Workflow:

Read references/materials-science-figure-template.md.
Pick the closest subtype:
- graphical-abstract
- mechanism-figure
- device-architecture
- processing-workflow
Choose the output language:
- en
- zh
Insert the user's scientific content into the Scientific Background slot, or use the script shortcut directly.
Preserve the template's constraints about causality, palette, typography, layout, and avoiding unsupported claims.
If the user did not provide exact numbers, keep labels qualitative or explicitly use placeholders rather than fabricating data.
If the user wants a specific journal style, append that preference after the template rather than rewriting the template.
If the scientific background is long, put it in a markdown file and use --prompt-file or scripts/build_materials_figure_prompt.py --background-file ... instead of squeezing it into one shell argument.
For prompt refinement, consult:
- references/materials-science-figure-template.md
- references/publication-figure-design.md
- references/publication-chart-patterns.md

Research Figure Design Integration

This skill includes a distilled publication-figure playbook adapted from the figures4papers project. Use it to make Nanobanana outputs look like journal figures rather than generic AI art.

Read the reference files only as needed:

references/publication-figure-design.md Use for overall figure art direction: typography, palette semantics, panel hierarchy, white-background policy, legend handling, and print-safe simplification.
references/publication-chart-patterns.md Use when the figure contains bars, trend lines, heatmaps, comparison matrices, or dedicated legend panels.

Apply these rules when prompting:

Keep the overall composition minimal, high-contrast, and panel-driven.
Use blue for the primary mechanism or proposed method, green for improvements, red for contrasts, and neutral gray for scaffolds/background categories.
Ask for short professional labels, frameless legends, and uncluttered white backgrounds.
Preserve consistent visual encoding across panels so the same color always means the same phase, state, or method.
For chart-like figures, ask the model to mimic publication layout and styling, but do not imply exact quantitative correctness unless the figure is being recreated from provided source data or reference images.

Quantitative Boundary

This skill is strong for:

graphical abstracts
mechanism figures
device schematics
processing workflows
chart-like conceptual panels
style-matched redraws of existing paper figures

This skill is not a guarantee of exact quantitative plotting. If the user needs exact bar heights, exact heatmap values, or faithful axis tick math from raw numbers, treat Nanobanana as a layout or visual-direction tool unless the request is explicitly a redraw from a trusted reference image.

For exact plotting, switch to plot mode and use references/publication-plot-api.md plus scripts/plot_publication_figure.py.

Python shortcut:

python3 scripts/generate_image.py "paste the scientific background here" \
  --materials-figure mechanism-figure \
  --lang en \
  --style-note "Benchmark the figure against Nature Materials aesthetics." \
  --aspect-ratio 4:3 \
  --image-size 2K

JavaScript shortcut:

node scripts/generate_image.js "paste the scientific background here" \
  --materials-figure graphical-abstract \
  --lang zh \
  --aspect-ratio 4:3 \
  --image-size 2K

Prompt-only preflight:

python3 scripts/build_materials_figure_prompt.py \
  --materials-figure mechanism-figure \
  --lang en \
  --background-file ./background.md \
  --style-note "Nature Materials aesthetic with concise panel labels."

Failure Handling

If the API returns 401 or 403, verify NANOBANANA_API_KEY.
If the CLI says the base URL is missing, set NANOBANANA_BASE_URL or pass --base-url.
If the CLI refuses a non-official endpoint, add --allow-third-party or set NANOBANANA_ALLOW_THIRD_PARTY=1 only if that provider is intentional.
If the API returns 404, verify that the request is going to /v1beta/models/{model}:generateContent.
If the provider says the model does not exist, verify the exact model name in the official docs and the provider's supported model list.
If no image is returned, inspect candidates[0].content.parts and check whether the request asked for image output.
If the user supplied only a chat attachment and no file path, do not describe the result as an exact edit unless the platform actually exposed the attachment bytes.

References

Read references/api-reference.md for the official request shape.
Read references/prompt-templates.md for generation and editing prompt scaffolds.
Read references/materials-science-figure-template.md when generating materials-science paper figures.
Read references/publication-figure-design.md for publication-style research figure rules adapted from figures4papers.
Read references/publication-chart-patterns.md for chart and multi-panel layout patterns.
Read references/publication-plot-api.md for exact plotting from numeric data.
Read references/natural-language-plot-workflow.md when the user describes an exact plot in natural language and Codex needs to translate it into an internal plotting request.

About this skill

On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.

AI Engineer pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/2/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

LeoYeAI / openclaw-master-skills

skills/materials-science-figure-skill/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 13 files · scripts

Illustrative Want to see what leoyeai/nanobanana-image-generation would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Other skills for the same job

Published skills whose descriptions closely match this one, with their headline benchmark lift.

Related skills

Skills that do similar work, with their headline benchmark lift.

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

Nanobanana Image Generation

Overview

Attachment-Only Inputs

Quick Start

Workflow

Environment

Scripts

Official Mapping

Prompting Rules

Materials Science Figure Shortcut

Research Figure Design Integration

Quantitative Boundary

Failure Handling

References

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry