Ready to supercharge your AI agents?

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

Bona Movie Production · leoyeai | DecimalAI

Design & Mediaby leoyeai

Bona Movie Production

Bona Movie Production is Bona Group's film-grade production skill. It covers image generation, image editing, and video generation, using Nano Banana 2 and Nano Banana Pro for images, and Seedance plus generate_video_kling_v3 for videos.

SkillScore

SkillScore91/100

Test results 91

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

22%91%of test cases passed +70 pts

Without skill5 of 23

With skill21 of 23

17 fixed4 passed either way1 still failing1 broke

Measured on gemini-3.6-flash8/6/2026v122 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskI have a background music track at `https://cdn.test/beat.mp3`. I want to generate a 5-second vertical 9:16 dance clip synchronized to the rhythm of this audio track. Provide the CLI command.

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-bona-movie-production
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-bona-movie-production")
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-bona-movie-production

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-bona-movie-production/SKILL.md https://app.decimal.ai/s/leoyeai-bona-movie-production/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-bona-movie-production/SKILL.md

This gets SKILL.md only. The skill's 1 other file is 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-bona-movie-production

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-bona-movie-production")
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-bona-movie-production/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-bona-movie-production/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 1 other file is 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-bona-movie-production

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-bona-movie-production")
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-bona-movie-production/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-bona-movie-production/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 1 other file is 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-bona-movie-production

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-bona-movie-production")
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-bona-movie-production/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-bona-movie-production/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 1 other file is 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-bona-movie-production

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-bona-movie-production")
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-bona-movie-production/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-bona-movie-production/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 1 other file is 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-bona-movie-production

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-bona-movie-production")
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-bona-movie-production/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-bona-movie-production/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 1 other file is 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-bona-movie-production

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-bona-movie-production")
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-bona-movie-production/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-bona-movie-production/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 1 other file is 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-bona-movie-production

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-bona-movie-production")
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-bona-movie-production/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 1 other file is 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-bona-movie-production

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-bona-movie-production")
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-bona-movie-production/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-bona-movie-production/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 1 other file is 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-bona-movie-production

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-bona-movie-production")
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-bona-movie-production/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-bona-movie-production/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 1 other file is 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-bona-movie-production

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-bona-movie-production")
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-bona-movie-production/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-bona-movie-production/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 1 other file is 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-bona-movie-production

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-bona-movie-production")
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-bona-movie-production/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-bona-movie-production/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 1 other file is 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-bona-movie-production

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-bona-movie-production")
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-bona-movie-production/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-bona-movie-production/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 1 other file is 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-bona-movie-production

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-bona-movie-production/SKILL.md https://app.decimal.ai/s/leoyeai-bona-movie-production/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-bona-movie-production/SKILL.md

This gets SKILL.md only. The skill's 1 other file is 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-bona-movie-production/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-bona-movie-production.json

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/6/2026
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

Bona Movie Production

这是博纳集团电影级的制作 Skill，包含：

图片生成
图片编辑
视频生成

流程：

创建任务后，持续轮询查询任务结果
轮询状态为 9 说明生成完毕
-1 为生成失败
1 是正在生成中
图片大概 1min
视频大概 3-5min

当前 Skill 只使用四个模型：

图片：generate_image_nano_banana_2、generate_image_nano_banana_pro
视频：generate_video_seedance、generate_video_kling_v3

使用前先配置环境变量：

export BONA_API_KEY="your_api_key"

一、图片生成

Nano Banana 2 更偏理解能力。适合复杂指令、参考图理解、换视角、文本渲染、多图关系理解。
Nano Banana Pro 更偏最终质量。适合高质量成片、商业视觉、海报、封面、九宫格或 5x5 宫格输出。

1. `generate_image_nano_banana_2`

适合：

指令复杂
要求理解更强
文字内容多
多元素关系清晰

参数规则：

分辨率：0.5K、1K、2K、4K
比例：1:1、1:4、1:8、2:3、3:2、3:4、4:1、4:3、4:5、5:4、8:1、9:16、16:9、21:9

Prompt 写法：

必须用英文
用户需求清晰时，尽量保持原意
不清晰时，按主体 + 场景 + 风格 + 光线 + 细节来写
如果要文字渲染，直接把文字内容写进 prompt

示例：

python skills/bona-movie-production/scripts/bona_movie_production.py create-image \
  --tool-name generate_image_nano_banana_2 \
  --image-name "hero-character-design" \
  --prompt "A modern bookstore cafe interior with warm wood shelves, soft afternoon sunlight, a handwritten chalkboard menu, calm and inviting atmosphere, editorial interior photography" \
  --task-type TEXT_TO_IMAGE \
  --resolution 2K \
  --aspect-ratio 4:3

2. `generate_image_nano_banana_pro`

适合：

成片质量优先
广告图
质感、细节、商业感更重要

参数规则：

分辨率：1K、2K、4K
比例：21:9、16:9、4:3、3:2、1:1、9:16、3:4、2:3、5:4、4:5

Prompt 写法：

必须用英文
适合写高质量商业表达
强调材质、光线、构图、品牌感

示例：

python skills/bona-movie-production/scripts/bona_movie_production.py create-image \
  --tool-name generate_image_nano_banana_pro \
  --image-name "premium-key-visual" \
  --prompt "A premium skincare bottle on polished black stone, controlled studio side lighting, luxury beauty advertising, sharp reflections, elegant minimal composition" \
  --task-type TEXT_TO_IMAGE \
  --resolution 4K \
  --aspect-ratio 4:5

二、图片编辑

1. `generate_image_nano_banana_2`

适合：

精确编辑
改一处、保留其余不变
对指令理解要求高

Prompt 写法：

必须用英文
明确要保留什么
明确只改什么
常用句式： change only X to Y add/remove X while keeping everything else unchanged

示例：

python skills/bona-movie-production/scripts/bona_movie_production.py create-image \
  --tool-name generate_image_nano_banana_2 \
  --image-name "character-bg-edit" \
  --prompt "Change only the wall color to muted olive green while keeping the furniture, layout, lighting, and camera angle unchanged" \
  --image-url https://example.com/room.png \
  --task-type EDIT_SINGLE_IMAGE \
  --aspect-ratio 4:3 \
  --resolution 1K

2. `generate_image_nano_banana_pro`

适合：

成片质感优先的编辑
海报、封面、商业人像精修

示例：

python skills/bona-movie-production/scripts/bona_movie_production.py create-image \
  --tool-name generate_image_nano_banana_pro \
  --image-name "fashion-campaign-edit" \
  --prompt "Change only the background to a luxury hotel lobby, keeping the model pose, facial expression, clothing, and lighting direction unchanged, premium fashion campaign look" \
  --image-url https://example.com/model.png \
  --task-type EDIT_SINGLE_IMAGE \
  --aspect-ratio 3:4 \
  --resolution 2K

三、参考图生成

1. `generate_image_nano_banana_2`

适合：

参考图理解
角色一致性
多图语义关系清晰

Prompt 写法：

必须用英文
用 the first image、the second image
明确每张参考图负责什么
如果要角色一致，直接写 keep character consistent

示例：

python skills/bona-movie-production/scripts/bona_movie_production.py create-image \
  --tool-name generate_image_nano_banana_2 \
  --image-name "character-consistency-scene" \
  --prompt "Refer to the first image for the character appearance and the second image for the outfit details. Keep character consistent and place her in a futuristic subway station with cinematic lighting." \
  --image-url https://example.com/char.png \
  --image-url https://example.com/outfit.png \
  --task-type REFERENCE_TO_IMAGE \
  --aspect-ratio 9:16 \
  --resolution 2K

2. `generate_image_nano_banana_pro`

适合：

品牌 KV
人物、商品一致性但最终输出更重质量

示例：

python skills/bona-movie-production/scripts/bona_movie_production.py create-image \
  --tool-name generate_image_nano_banana_pro \
  --image-name "premium-reference-kv" \
  --prompt "Refer to the first image for the product shape and the second image for the lighting mood. Create a premium hero shot with clean reflections and luxury beauty campaign quality." \
  --image-url https://example.com/product.png \
  --image-url https://example.com/light.png \
  --task-type REFERENCE_TO_IMAGE \
  --aspect-ratio 1:1 \
  --resolution 4K

四、转视角

这个任务更推荐 Nano Banana 2。

原因：

它对结构理解更强
更适合“同一主体换角度、换视角、转三视图”

Prompt 写法：

必须用英文
明确是同一主体
明确要变成什么视角
保留哪些元素不变

示例 1：单图转侧视角

python skills/bona-movie-production/scripts/bona_movie_production.py create-image \
  --tool-name generate_image_nano_banana_2 \
  --image-name "product-side-view" \
  --prompt "Use the first image as the same product reference. Change the camera view from front view to left side view, while keeping material, color, proportions, and design details unchanged." \
  --image-url https://example.com/product-front.png \
  --task-type REFERENCE_TO_IMAGE \
  --aspect-ratio 1:1 \
  --resolution 2K

示例 2：角色转背视角

python skills/bona-movie-production/scripts/bona_movie_production.py create-image \
  --tool-name generate_image_nano_banana_2 \
  --image-name "character-rear-view" \
  --prompt "Use the first image as the same character reference. Generate a clean rear view of the same character, keeping hairstyle, clothing, silhouette, and proportions consistent." \
  --image-url https://example.com/character-front.png \
  --task-type REFERENCE_TO_IMAGE \
  --aspect-ratio 3:4 \
  --resolution 2K

示例 3：角色三视图

python skills/bona-movie-production/scripts/bona_movie_production.py create-image \
  --tool-name generate_image_nano_banana_2 \
  --image-name "character-turnaround-sheet" \
  --prompt "Use the first image as the same character reference. Create a character turnaround sheet showing front view, side view, and back view, consistent design, clean white background, concept art presentation." \
  --image-url https://example.com/character.png \
  --task-type REFERENCE_TO_IMAGE \
  --aspect-ratio 16:9 \
  --resolution 4K

五、九宫格和 5x5 宫格

这种任务更推荐 Nano Banana Pro。

原因：

最终输出质量更好
适合整页构图
更适合海报、角色表、商品矩阵图

Prompt 写法：

必须用英文
明确是几宫格
明确每格内容是否一致风格
明确整体版式和背景
最好逐格指定构图，至少写清每一格的景别、角度或主体动作
推荐写法：panel 1 ... panel 2 ... panel 3 ...，不要只写“九个不同画面”

示例 1：九宫格人物造型板

python skills/bona-movie-production/scripts/bona_movie_production.py create-image \
  --tool-name generate_image_nano_banana_pro \
  --image-name "character-style-board-3x3" \
  --prompt "Create a 3x3 character style board for the same girl in one image, consistent character design, clean editorial layout, white background, fashion mood board quality. Panel 1 full-body front standing pose. Panel 2 full-body left side view. Panel 3 full-body back view. Panel 4 medium shot looking up with arms crossed. Panel 5 medium shot smiling toward camera. Panel 6 medium shot turning while hair moves. Panel 7 close-up calm expression. Panel 8 close-up laughing expression. Panel 9 seated three-quarter view with elegant pose." \
  --task-type TEXT_TO_IMAGE \
  --aspect-ratio 1:1 \
  --resolution 4K

示例 2：九宫格商品展示图

python skills/bona-movie-production/scripts/bona_movie_production.py create-image \
  --tool-name generate_image_nano_banana_pro \
  --image-name "product-grid-3x3" \
  --prompt "Create a 3x3 product grid in one image for the same sneaker, nine clean panels showing different angles and close-up details, premium e-commerce presentation, consistent lighting, white studio background." \
  --task-type TEXT_TO_IMAGE \
  --aspect-ratio 1:1 \
  --resolution 4K

示例 3：5x5 表情宫格

python skills/bona-movie-production/scripts/bona_movie_production.py create-image \
  --tool-name generate_image_nano_banana_pro \
  --image-name "expression-sheet-5x5" \
  --prompt "Create a 5x5 facial expression sheet in one image for the same anime girl, twenty-five panels, consistent character design, each panel with a different expression, clean character sheet layout, white background." \
  --task-type TEXT_TO_IMAGE \
  --aspect-ratio 1:1 \
  --resolution 4K

示例 4：5x5 icon / sticker sheet

python skills/bona-movie-production/scripts/bona_movie_production.py create-image \
  --tool-name generate_image_nano_banana_pro \
  --image-name "sticker-sheet-5x5" \
  --prompt "Create a 5x5 sticker sheet in one image, twenty-five cute food icons, consistent illustration style, balanced spacing, bright clean colors, packaging-ready quality." \
  --task-type TEXT_TO_IMAGE \
  --aspect-ratio 1:1 \
  --resolution 4K

六、文生视频

当用户只有文本描述，没有首帧、尾帧、参考图、参考视频、参考音频时，按文生视频处理。

1. `generate_video_kling_v3`

适合：

默认首选文生视频
要更强镜头感
想要音画表现更完整
短时长电影感镜头

参数规则：

比例：16:9、9:16、1:1
时长：推荐 5、10
模式：std、pro
声音：on、off
支持多镜头 shot_prompts

Prompt 写法：

清楚写主体、动作、镜头运动、场景、光线
单镜头直接写完整 prompt
多镜头时优先拆成 shot_prompts
如果要声音氛围，可直接写进 prompt

示例：

python skills/bona-movie-production/scripts/bona_movie_production.py create-video \
  --tool-name generate_video_kling_v3 \
  --video-name "teaser-shot-01" \
  --prompt "A young woman walking through a rainy neon street at night, reflections on the wet ground, camera slowly tracking forward, blue and pink neon lighting, cinematic atmosphere, realistic motion" \
  --duration 5 \
  --aspect-ratio 16:9 \
  --mode pro \
  --sound on

2. `generate_video_seedance`

适合：

文生视频
更强运动质量
后续可能扩展到参考素材模式

参数规则：

比例：21:9、16:9、4:3、1:1、3:4、9:16
时长：4-15
分辨率：480P、720P
文生模式下不要同时传首尾帧或参考素材

Prompt 写法：

清楚描述主体、动作、镜头、光线
优先写成单镜头
不要太抽象，尽量写清动作节奏

示例：

python skills/bona-movie-production/scripts/bona_movie_production.py create-video \
  --tool-name generate_video_seedance \
  --video-name "character-motion-shot" \
  --prompt "A fashion model turns slowly toward camera, fabric moves naturally, soft cinematic backlight, stable single-shot motion" \
  --duration 6 \
  --aspect-ratio 9:16 \
  --resolution 720P

七、首帧生视频

当用户提供一张起始图片，希望把静态图做成视频时，按首帧生视频处理。

1. `generate_video_kling_v3`

适合：

首帧图转视频默认首选
人物轻动作
海报起身
电影感人物镜头

参数规则：

起始帧可传 --start-frame
支持 16:9、9:16、1:1
时长推荐 5、10

示例：

python skills/bona-movie-production/scripts/bona_movie_production.py create-video \
  --tool-name generate_video_kling_v3 \
  --video-name "character-i2v" \
  --prompt "The character slowly turns her head, blinks naturally, and breathes subtly. Keep the framing stable and cinematic." \
  --start-frame https://example.com/character-first-frame.png \
  --duration 5 \
  --aspect-ratio 9:16 \
  --mode pro

2. `generate_video_seedance`

适合：

起始帧驱动动画
更重运动质量
人物、服装、动态保持自然

参数规则：

比例：21:9、16:9、4:3、1:1、3:4、9:16
时长：4-15
分辨率：480P、720P

Prompt 写法：

如果用了起始帧，重点写动作变化，不要重复描述外观
清楚写镜头和动作

示例：

python skills/bona-movie-production/scripts/bona_movie_production.py create-video \
  --tool-name generate_video_seedance \
  --video-name "seedance-first-frame" \
  --prompt "The subject smiles slightly and the camera pushes in gently, preserving identity and costume details." \
  --start-frame https://example.com/char.png \
  --duration 5 \
  --aspect-ratio 9:16 \
  --resolution 720P

八、首尾帧视频

当用户同时提供起始图和结束图，希望做中间插帧和过渡时，按首尾帧视频处理。

1. `generate_video_kling_v3`

适合：

默认首选
标准首尾帧过渡
电影感过渡镜头

参数规则：

传尾帧时必须同时传首帧
若不想生成声音，建议 --sound off

示例：

python skills/bona-movie-production/scripts/bona_movie_production.py create-video \
  --tool-name generate_video_kling_v3 \
  --video-name "start-end-transition" \
  --prompt "A smooth cinematic transition from the first frame to the final frame, with natural body movement and stable camera motion." \
  --start-frame https://example.com/start.png \
  --end-frame https://example.com/end.png \
  --duration 5 \
  --aspect-ratio 16:9 \
  --mode pro \
  --sound off

2. `generate_video_seedance`

适合：

首尾帧过渡
更强调动作质量
人物、产品从 A 状态平滑过渡到 B 状态

参数规则：

image_end_frame 存在时，必须有 image_start_frame
首尾帧模式和参考模式互斥

示例：

python skills/bona-movie-production/scripts/bona_movie_production.py create-video \
  --tool-name generate_video_seedance \
  --video-name "seedance-start-end" \
  --prompt "The character walks from the first pose into the final pose with continuous natural motion and matching costume dynamics." \
  --start-frame https://example.com/start-pose.png \
  --end-frame https://example.com/end-pose.png \
  --duration 6 \
  --aspect-ratio 3:4 \
  --resolution 720P

九、参考图视频

当用户希望人物、产品、IP 形象保持一致性，且提供了一张或多张参考图时，按参考图视频处理。

十、参考视频视频

当用户提供参考视频，希望做视频风格迁移、动作参考或节奏参考时，按参考视频视频处理。

十一、参考音频视频

当用户提供参考音频，希望根据节拍、对白节奏或音乐做视频时，按参考音频视频处理。

十二、多镜头视频

1. `generate_video_kling_v3`

适合：

分镜式短片
一条任务内多个 shot
预告片节奏剪辑

参数规则：

最多 6 个 shot
每个 shot 要有 index、prompt、duration
所有 shot 的时长总和必须等于外层 duration

Prompt 写法：

多镜头时优先用 shot_prompts
每个 shot 单独写清场景、动作、镜头

schema 示例：

{
  "tool_name": "generate_video_kling_v3",
  "video_name": "multi-shot-trailer",
  "prompt": "Trailer sequence",
  "aspect_ratio": "16:9",
  "duration": 5,
  "mode": "pro",
  "sound": "on",
  "shot_prompts": [
    {
      "index": 0,
      "prompt": "A dark cinema corridor, camera pushes forward, tense ambience",
      "duration": "2"
    },
    {
      "index": 1,
      "prompt": "The heroine turns back suddenly, dramatic backlight, cloth movement",
      "duration": "3"
    }
  ]
}

十三、查询任务

图片查询：

python skills/bona-movie-production/scripts/bona_movie_production.py query-image \
  --task-id your-task-id

视频查询：

python skills/bona-movie-production/scripts/bona_movie_production.py query-video \
  --task-id your-task-id

状态说明：

1：进行中
9：完成
-1：失败

查询判断规则：

先看 status，不要先看 result_url
status = 1 时，即使 result_url 为空，也只是任务还在跑，不能判断为失败
status = 9 时，才去读取 result_url
status = -1 时，才按失败处理，并查看 error_code、error_message
不要因为 result_url 暂时为空，就改判成“接口行为变了”或“需要重新生成”
只有确认 status = -1，或者长时间轮询后仍没有进入终态，才考虑进一步排查
status = 9 但 result_url 仍为空时，只能说明“任务已完成，但当前回包没有返回结果地址”

推荐理解方式：

status = 1：继续查询
status = 9：返回结果链接
status = -1：返回失败原因

和视频联动时的规则：

如果用户要求“先生成分镜图，再用分镜图生成视频”，这就是两段任务，不能混成一个纯文生视频任务
只有真正拿到分镜图 URL 或本地文件后，才能进入下一步视频生成
如果图片任务 status = 9 但没有可用图片地址，要停在这里如实汇报，而不是自动改成“直接文生视频”

十四、实用建议

默认普通文生图：先用 Nano Banana Pro
复杂理解、换视角、参考图关系、多图任务：优先 Nano Banana 2
九宫格、5x5 宫格、海报、成片质量：优先 Nano Banana Pro
默认普通文生视频：先用 generate_video_kling_v3
参考图、参考视频、参考音频、多素材一致性：优先 generate_video_seedance
如果只想先看参数，用 --print-payload

About this skill

Automatic

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/bona-movie-skill/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 1 file · scripts

Illustrative Want to see what leoyeai/bona-movie-production 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.

bona-movie-productionBona Movie Production is Bona Group's film-grade production skill. It covers image generation, image editing, and video generation, using Nano Banana 2 and Nano Banana Pro for images, and Seedance plus generate_video_kling_v3 for videos.Near-identical description+73 pts pass-rate 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

Bona Movie Production

一、图片生成

1. generate_image_nano_banana_2

2. generate_image_nano_banana_pro

二、图片编辑

1. generate_image_nano_banana_2

2. generate_image_nano_banana_pro

三、参考图生成

1. generate_image_nano_banana_2

2. generate_image_nano_banana_pro

四、转视角

五、九宫格和 5x5 宫格

六、文生视频

1. generate_video_kling_v3

2. generate_video_seedance

七、首帧生视频

1. generate_video_kling_v3

2. generate_video_seedance

八、首尾帧视频

1. generate_video_kling_v3

2. generate_video_seedance

九、参考图视频

推荐模型

1. generate_video_seedance

十、参考视频视频

推荐模型

1. generate_video_seedance

十一、参考音频视频

推荐模型

1. generate_video_seedance

十二、多镜头视频

1. generate_video_kling_v3

十三、查询任务

十四、实用建议

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry

1. `generate_image_nano_banana_2`

2. `generate_image_nano_banana_pro`

1. `generate_image_nano_banana_2`

2. `generate_image_nano_banana_pro`

1. `generate_image_nano_banana_2`

2. `generate_image_nano_banana_pro`

1. `generate_video_kling_v3`

2. `generate_video_seedance`

1. `generate_video_kling_v3`

2. `generate_video_seedance`

1. `generate_video_kling_v3`

2. `generate_video_seedance`

1. `generate_video_seedance`

1. `generate_video_seedance`

1. `generate_video_seedance`

1. `generate_video_kling_v3`