Ready to supercharge your AI agents?

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

Higgsfield Seedance VFX — Footage Transformation · osidemedia | DecimalAI

Design & Mediaby osidemedia

Higgsfield Seedance VFX — Footage Transformation

Writes, improves, or rewrites Seedance 2.0 prompts that TRANSFORM footage the user already has (video-to-video), rather than building a scene from scratch.

Never made a case worseMaintained

SkillScore

SkillScore100/100

Test results 100

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

36%100%of test cases passed +64 pts

Without skill9 of 25

With skill25 of 25

16 fixed9 passed either way0 still failing0 broke

Measured on gemini-3.6-flash9/24/2026v1 · latest is v2

This benchmark measured an earlier version of the skill.

A newer attempt on gemini-3.6-flash on 10/3/2026 did not produce a publishable comparison (graded differently). The snapshot above is the previously measured run.

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWhat is the maximum single generation duration supported for a video transformation shot in Seedance 2.0?

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 osidemedia-higgsfield-seedance-vfx
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("osidemedia-higgsfield-seedance-vfx")
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 osidemedia-higgsfield-seedance-vfx

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/osidemedia-higgsfield-seedance-vfx/SKILL.md https://app.decimal.ai/s/osidemedia-higgsfield-seedance-vfx/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/osidemedia-higgsfield-seedance-vfx/SKILL.md

This gets SKILL.md only. The skill's 2 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 osidemedia-higgsfield-seedance-vfx

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("osidemedia-higgsfield-seedance-vfx")
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/osidemedia-higgsfield-seedance-vfx/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/osidemedia-higgsfield-seedance-vfx/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 2 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 osidemedia-higgsfield-seedance-vfx

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("osidemedia-higgsfield-seedance-vfx")
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/osidemedia-higgsfield-seedance-vfx/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/osidemedia-higgsfield-seedance-vfx/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 2 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 osidemedia-higgsfield-seedance-vfx

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("osidemedia-higgsfield-seedance-vfx")
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/osidemedia-higgsfield-seedance-vfx/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/osidemedia-higgsfield-seedance-vfx/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 2 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 osidemedia-higgsfield-seedance-vfx

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("osidemedia-higgsfield-seedance-vfx")
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/osidemedia-higgsfield-seedance-vfx/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/osidemedia-higgsfield-seedance-vfx/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 2 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 osidemedia-higgsfield-seedance-vfx

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("osidemedia-higgsfield-seedance-vfx")
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/osidemedia-higgsfield-seedance-vfx/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/osidemedia-higgsfield-seedance-vfx/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 2 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 osidemedia-higgsfield-seedance-vfx

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("osidemedia-higgsfield-seedance-vfx")
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/osidemedia-higgsfield-seedance-vfx/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/osidemedia-higgsfield-seedance-vfx/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 2 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 osidemedia-higgsfield-seedance-vfx

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("osidemedia-higgsfield-seedance-vfx")
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/osidemedia-higgsfield-seedance-vfx/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 2 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 osidemedia-higgsfield-seedance-vfx

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("osidemedia-higgsfield-seedance-vfx")
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/osidemedia-higgsfield-seedance-vfx/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/osidemedia-higgsfield-seedance-vfx/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 2 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 osidemedia-higgsfield-seedance-vfx

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("osidemedia-higgsfield-seedance-vfx")
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/osidemedia-higgsfield-seedance-vfx/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/osidemedia-higgsfield-seedance-vfx/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 2 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 osidemedia-higgsfield-seedance-vfx

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("osidemedia-higgsfield-seedance-vfx")
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/osidemedia-higgsfield-seedance-vfx/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/osidemedia-higgsfield-seedance-vfx/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 2 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 osidemedia-higgsfield-seedance-vfx

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("osidemedia-higgsfield-seedance-vfx")
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/osidemedia-higgsfield-seedance-vfx/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/osidemedia-higgsfield-seedance-vfx/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 2 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 osidemedia-higgsfield-seedance-vfx

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("osidemedia-higgsfield-seedance-vfx")
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/osidemedia-higgsfield-seedance-vfx/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/osidemedia-higgsfield-seedance-vfx/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 2 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 osidemedia-higgsfield-seedance-vfx

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/osidemedia-higgsfield-seedance-vfx/SKILL.md https://app.decimal.ai/s/osidemedia-higgsfield-seedance-vfx/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/osidemedia-higgsfield-seedance-vfx/SKILL.md

This gets SKILL.md only. The skill's 2 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/osidemedia-higgsfield-seedance-vfx/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/osidemedia-higgsfield-seedance-vfx.json

This gets SKILL.md only. The skill's 2 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v2 (v1 tested 9/24/2026)
Source: osidemedia/higgsfield-ai-prompt-skill ↗
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

Higgsfield Seedance VFX — Footage Transformation

This skill is for editing a clip the user already has: keep a real subject and the real camera move, change only what they ask for. It is the video-to-video sibling of ../higgsfield-seedance/SKILL.md (the general Seedance director). It reuses that skill's grammar verbatim — the six-slot formula, the Prompt-Craft Laws, the preflight linter — and adds the transformation layer below. Do not contradict the parent skill; when a shot needs filter-safety, mode selection, or engine rules, defer to it.

This file is the Seedance 2.0 v2v lane. It stays the right choice when the job needs 4K, mode=std, or a genre hint. If the plate job is running on Seedance 2.5 — up to 1080p, up to 30 s, many references, platform start/end frames in omni_reference — the lane is omni_reference with the clip attached as a video reference, and its production doctrine (source ≥ 4 s, duration = source, the four-batch rule, the performance-inheritance clause) lives in ../higgsfield-seedance-2-5/VFX-PIPELINE.md.

This skill is a video-to-video layer on top of ../higgsfield-seedance/SKILL.md. Every VFX transform is still a Seedance prompt. This skill only changes the starting point: a real source clip whose subject, performance, and camera move must survive the edit. higgsfield-seedance § Seedance 2.0 Prompt Modes / Transformation covers the in-clip morph (a character visibly becoming something else in one take); this skill covers preservation-VFX — lock the real plate, layer the effect in.

QUICK FACTS

Routing aids — read the linked sections for the actual rules.

The one job: preserve everything that makes the source recognizable, change only the named element; repeat the fragile guardrail ("face and identity unchanged") at the end →
Run it in Seedance 2.0, mode std, 4K — faces, lip-sync and fine detail hold at 4K where they warp at 1080p (fast can't do 4K; Cinema Studio caps at 1080p) →
@source declares the clip as the base (not a style ref); add @creature/@element only when a real texture keeps getting faked →
Three levels of difficulty: L1 swap the world · L2 change an element in-frame · L3 full handheld cinematic →
Two modes: add an element to the plate, or replace the environment around a preserved subject →
Color matching alone looks pasted-in — match key direction, bounce, optics/haze, edges/grounding →
Photoreal creatures need biological accuracy (wrinkled, cracked, asymmetric, matte — never smooth/glossy/inflated) + a real contact shadow; a reference image beats a description →
Timed zoom synced to a line: anchor it twice — semantic (On the line "…") + numeric (At about Ts); see references/dialogue-timing.md →
Prepended-intro budget: total − intro = surviving window for the source performance; recompute on every change →
Generate the transformed start frame first to lock the look before spending video credits; see references/first-frame.md →
Output is plain-text English, no markdown inside the prompt, easy to copy →

The core idea: preserve, then change one thing

A transformation prompt has two jobs that pull against each other: lock everything that makes the source recognizable (the person's identity, face, wardrobe, performance, framing, lens, and camera motion), and change only the named element. If you under-specify the lock, Seedance re-rolls the face or the camera and the edit stops matching the original. So every prompt states both halves explicitly, and repeats the most fragile guardrail — usually "face and identity unchanged" — at the end of the action.

This is the whole blueprint: real footage goes in, the exact same shot comes back — same subject, same movement — with only the one requested change applied.

Resolution: run it in 4K

Run everything in Seedance 2.0, mode=std, 4K. The 4K matters: faces, lip-sync and fine detail hold at 4K where they warp and fall apart at 1080p — and a footage transform lives or dies on the preserved face reading as the same face. The 4k resolution enum is model-verified (../../specs/model-specs.json → seedance_2_0); the "detail holds at 4K" observation is a practitioner claim, strong but not a spec guarantee.

Two model constraints to respect (from ../higgsfield-seedance/SKILL.md § Pre-flight Linter): native 4K is available in mode=std only — mode=fast (Seedance 2.0 Fast) caps at 480p/720p, and inside Cinema Studio the model is still capped at 1080p. So a 4K footage transform must run in std mode, on the standard Seedance 2.0 surface. If the user is on fast mode or in Cinema Studio and asks for 4K, flag the cap before they generate.

Prompt anatomy (transform variant)

1. The `@source` declaration

The source clip is the base, not a style reference. One line:

@source: Original <clip name> — <who/what is in it: subject, wardrobe, setting, action>. Preserve
<identity, face, wardrobe, performance, framing, camera and motion> exactly; <what to change —
e.g. enhance only the environment / add the creature on the tower / transform only the right arm>.

If a transformation needs a real texture the model keeps faking (an animal's fur, a specific face), add a second input as a texture reference and declare it:

@creature: Reference photo of a real <animal> — <fur / face / anatomy notes>. Appearance and
fur/skin texture reference only; ignore the photo's background and lighting, do not use it for the
environment.

The user supplies their own descriptions of what is in their files — use the tags correctly, don't invent what the clip contains. But before writing @source for a clip you can open, inspect it: read its duration / fps / aspect and extract a few frames. Build @source and the specs runtime from what the footage actually shows — subject, wardrobe, framing, camera move, time of day, key direction — not from the user's one-line summary. Set the specs duration to the probed runtime by default. If no source clip is described, ask what footage they're starting from before writing.

Seedance reads an uploaded video as a set of frames, not as a watched clip — so the frame content (subject, walk, light) is the context it has. Same principle as the screenshot → Claude workflow in ../higgsfield-seedance/SKILL.md § Load-Bearing Rule.

2. Specs line

One compact line. Always include the source-matching constraints:

Photoreal. <aspect, default 16:9>. <duration — match the source clip>s. 4K. <look / grade>.
NON-IP — generic <creature/design>, not based on any brand or character. <SFX only | SFX and
source dialogue only>.

Match the source runtime by default. If the clip is 6s, the prompt is 6s. Extend only when a payoff needs room (a slow creature turning to camera), and say why.
NON-IP guardrail belongs in the specs line whenever a creature, armor, vehicle, or character design is added — generic, never a branded character. Keeps outputs clean and tends to generate more reliably than a trademarked design. (Same filter logic as ../higgsfield-seedance/SKILL.md § The Rewrite Playbook / Brand · IP.)
Audio: SFX only for added effects; SFX and source dialogue only when the source talk track must survive (e.g. a zoom synced to a spoken line — see references/dialogue-timing.md).

3. Scene action — one continuous shot

The source is a single take, so describe continuous camera movement, not cuts. Lead with the shot/lens and "same framing as the source," then the preserved performance, then the transformation, then any timed camera move. Close with the lock-down clause.

4. SFX line

End with a specific, ordered SFX note, exactly as the parent grammar requires. For added effects be behavioral: not "fire" but "a soft whoomph as it catches, then a low steady flame roar and crackle, occasional ember pop." Sync every effect (footsteps, impacts, wind, creature calls, servo whirs) to the visible action.

Three levels

The workflow scales in difficulty. The steps are identical at every level — inspect the clip, name the one change, lock the rest — but the harder the camera moves, the harder the effect has to track:

Level 1 — swap the world around you. Keep the subject exactly as shot; replace the environment. Easiest on slow/steady moves; a driving shot raises the bar because the new world has to stream past at the right speed and relight the subject as it goes (§ Two transformation modes / B).
Level 2 — change an element in the frame. Add or morph one specific thing: set a head of hair on fire, morph a hand into something unexpected, add a creature climbing a building. The plate stays; the effect is layered in and lit into it (§ Two transformation modes / A).
Level 3 — full handheld cinematic. The camera is in-hand and moving the whole time — angle, parallax and shake all changing — and the effect (creature, environment, weather) must track to all of it without falling apart. This is the hardest case; preserve the handheld move frame-for-frame and lean on § Photoreal creature / element integration and § Lighting integration hardest here.

Locked-off shots are easy — the frame barely changes, so the model just paints the effect in. The difficulty is entirely in how much the camera moves.

Two transformation modes

A. Add an element to the footage

Set a head on fire, transform a hand, make a limb invisible, perch a creature on a landmark. Keep the whole plate; layer the effect in.

Describe the effect's physics and behavior over time, not just its presence: where it starts, how it spreads, how it moves, what light it throws. Use directional "creep" for transformations ("starts at the tattoo, fine seams split one at a time and peel back, a servo seats, a cable plugs in, the next plate locks…") and ignition-then-build for fire.
Make the effect interact with the plate: firelight flickering on a face and spilling onto a car's paint; a glassy invisible arm refracting the background; a giant creature casting a real soft-edged contact shadow on the structure it grips. (The model spills an added fire's orange glow onto skin, shirt and car on its own — but naming the interaction makes it reliable.)
Scale must be explicit for giant creatures, or the model renders them life-size. Say "enormous, its massive body dwarfing the structure, clearly colossal relative to the mast."
The subject usually stays oblivious / unfazed, mid-delivery — that contrast is the joke. State it.

B. Replace the environment around a preserved subject

Keep the person, their vehicle, the seatbelt, the camera rig and its move; swap the whole world.

The new world must stream past with parallax consistent with the original motion. If the car was driving, the replacement must give it a surface to drive on and things that rush past at speed. On a fast move the environment can't just sit behind the subject — it has to move with the subject at the right speed and change the lighting as it goes.
The bigger the move, the longer the lock list: it's not just the face anymore — it's the car, the seatbelt, the rig framing, the whole driving motion, all held while only the environment changes.
Warm, directional daylight worlds are safer for face/identity consistency than night or neon — those force a full relight of the subject and raise drift risk. Flag this tradeoff and bake the relight instruction in when the user wants night/neon anyway. (Seedance will pull light from the generated world and bounce it onto the subject — neon sliding across a car, lava glowing under a chin — without being asked; naming it makes it dependable.)

Lighting integration (the part that makes or breaks it)

First decide the fork with the user — it changes everything:

Preserve the subject's lighting, grade only the new elements. Lock the subject's original light; light and grade the added creature/environment to match the existing key on the subject so they integrate. Lowest identity risk.
Relight the whole frame under one look. Subject included. Use this for a unified cinematic / commercial grade. Higher risk to the face, so keep identity/expression/wardrobe explicitly locked while only lighting and grade change.

Color matching alone is not enough to make a preserved subject sit in a new world — that's the most common "looks pasted in" failure. When integrating a subject (or a creature) into a plate, go beyond color with this recipe:

Light: same key direction (name it — screen-left or screen-right), same softness, same shadow density and direction across the subject. ("Keep the sun as the key from screen-left exactly as before so the face and the light on it barely change.")
Environmental bounce: let the world spill onto the subject — cool skylight from above, a warm bounce from sunlit ground/foliage, subtle ambient occlusion where forms meet.
Optics & atmosphere: match lens character and micro-contrast; add a touch of the scene's atmospheric haze and aerial perspective over the subject so they aren't unnaturally crisp against a hazy background; match depth of field, focus falloff and film grain to the rest of the frame.
Edges & grounding: remove hard cut-out edges, halos and mismatched rims; ground the subject with believable depth so they occupy the same space.

State the time of day and key direction concretely ("soft, diffused midday daylight with the key coming from screen-right"). "Softer" means a larger, more diffuse source: gentle soft-edged shadows, low contrast, smooth highlight rolloff, light haze. Full cinematic-lighting vocabulary is in ../../vocab.md § Lighting.

Photoreal creature / element integration

When a creature or hard-surface element is added and must read as real:

Demand wildlife-documentary / practical realism explicitly: "fully photoreal, real fur with depth and individual strands (or true scale detail / brushed metal), true anatomy, never CG, plastic or cartoonish."
Biological accuracy is what separates a living thing from a cheap render. Specify real anatomical detail — "pebbled scaly skin, long claws, heavy tail, true reptile anatomy" — and demand imperfection: deeply wrinkled, cracked, sagging, asymmetric, mud-caked and matte. Avoid smooth, glossy or inflated surfaces; real animals are uneven. Match behavior to the species (a sloth shifts slow heavy weight; a chimp is alert and twitchy; a snake's coils tighten and a forked tongue tastes the air — and snakes don't blink, so use an unblinking stare, not a blink, for a reptile payoff).
Sell the scale. Use on-screen reference objects (trees, buildings, crew, the subject) to establish true size, and use a telephoto-lens illusion with shallow depth of field to veil a giant creature partly behind foreground elements — plus a little motion blur and handheld softness so it integrates rather than floats.
Tie it into the plate: same sun direction and color temperature as the subject, a real soft-edged contact shadow on what it touches, the same hazy atmosphere and depth as the far background.
If it still reads as CG after a take, the reliable fix is a second input — a reference photo of the real animal/material, declared as a texture-only reference (see @creature above). When you already know exactly what you want, it's better to show the model than to describe it; generate the reference in ../higgsfield-gpt-image-2/SKILL.md (GPT Image 2) or Nano Banana Pro, then point the prompt at it.

Timed camera moves synced to dialogue

A crash zoom or smooth push-in landing on a beat is a recurring payoff. Anchor it two ways at once so it lands even if Seedance's internal timing drifts: a semantic cue and a numeric cue. The full measurement procedure — how to read T off the source audio and convert a timecode — is in references/dialogue-timing.md.

Semantic: On the line "<exact words>," the camera <snaps into a hard crash zoom | begins a smooth, steady push-in> …. Requires SFX and source dialogue only in the specs so the talk track survives.
Numeric: At about <T> seconds … the camera …. Get T from the source audio (or a visible action beat — "at about 2.2s, on his finger snap").
Crash zoom = fast hard punch-in; smooth push-in = slow steady glide, no snap. Match the user's word.
If a landmark or subject must stay visible through the move, say so explicitly ("the tower stays in frame throughout, never cropped").
Leave enough tail after the trigger for the payoff to play (a creature slowly turning to camera needs ~2–3s). If the clip is short, fire the zoom on the first word of the line rather than after it.

Reveal pull-back (the outward move)

The mirror of the push-in: open tight on the added element in isolation — a long-telephoto, compressed framing of the creature/effect with the subject out of frame — then move outward to land on the real plate. Two flavors, match the user's word:

Hard / snap zoom-out = a fast punch outward, abrupt.
Smooth pull-back = a slow steady decompression, no snap.

Anchor the landing the same two ways as a timed zoom, and demand a 100% match of the source composition at the landing: name the matched attributes — same angle, headroom, horizon, lens character — or the model lands on a near-miss framing that no longer cuts against the original. After the landing, hand off to the preserved take and keep the source's own camera motion running.

Preserving lip-sync to a known line

When the payoff is the subject's mouth matching a specific line, quote it verbatim and anchor it twice: once inside the action ("…lips matching the source exactly, saying clearly: ''…") and once in the SFX/dialogue line. Require SFX and source dialogue only in the specs so the talk track survives, and add "lips matching the source exactly" to the lock-down clause. Then check the line against the surviving dialogue window (see § Duration discipline / Prepended-intro budget) — a line that runs ~6s cannot sit in a 5s tail. If it doesn't fit, resolve the runtime before delivering; don't ship a prompt that can't lip-sync. Dialogue + [AUDIO: Xs] mechanics live in ../higgsfield-audio/SKILL.md.

Duration discipline

Default to the source clip's exact runtime. When the user changes the runtime, recompute any numeric zoom timing and tell them the new mark. When a long hold lands on a static creature, add small "living" micro-movements (a slow blink, jaw shift, steady breath) so it doesn't look frozen.

Prepended-intro budget: intro + remaining = total

When you prepend a beat (a reveal, a telephoto hold, an establishing creature shot) to footage you must preserve, the preserved take does not get longer — it gets pushed back. State the arithmetic every time and flag what falls off:

total runtime − intro length = surviving window for the source performance

If the source take is longer than that surviving window, some of it cannot play. Say so explicitly and offer the three resolutions, in order of fidelity:

Extend the total so the full source fits (intro + full source). Highest fidelity, longest clip.
Start the source earlier — sacrifice the clip's own quiet lead-in so the dialogue still lands in the window. Keeps total fixed, keeps the words, loses pre-roll.
Accept truncation — the first N seconds of the source won't appear. Only safe if the dropped head has no dialogue.

Never promise "100% lip-sync" and a prepended intro on a fixed total without doing this subtraction first. Recompute and re-flag it on every change to either number.

First / start-frame workflow

Before spending video credits, it's often worth generating the transformed opening still as an image, locking the look, then animating from it. See references/first-frame.md for the full procedure (model, settings, inputs, upload mechanics, and how to hand the still back to Seedance as a start_image). This pairs with ../higgsfield-seedance/SKILL.md § Drafts Validate the Prompt — pin the frame, not the roll.

Iterating

The user iterates fast and in small steps ("softer light," "from the right," "bigger snowier mountains," "make the chimp huge," "a beat before the zoom," "keep the original runtime"). Change only the named thing and keep the rest of the prompt stable — re-rolling the whole prompt loses what already worked. When refining a generated still, edit the chosen result (pass it back as the base) and fix only what's off rather than starting over. This is the footage-transform case of ../higgsfield-prompt/SKILL.md § The Iteration Rule.

Output format

Output in English first, plain text — no bold, no headers, no bullets inside the prompt, not in a code block. Easy to copy as-is. Chinese translation only if asked, after the English, same format.

A short label above each prompt (e.g. Hook_2 · Variant 1 — Through the clouds) is fine and helps when you deliver several variants; the prompt body itself stays plain text.

Skeleton:

@source: ...
@creature: ...            (only if a texture reference is used)

Photoreal. 16:9. <N>s. 4K. <look/grade>. NON-IP — generic <X>. SFX [and source dialogue] only.

<Continuous shot, same framing as source. Preserved performance. The transformation, with physics
and plate interaction. Any timed camera move with semantic + numeric anchor. Lock-down clause: face
and identity unchanged; everything else identical to the source.>

SFX [and source dialogue] only: <specific, ordered sounds>.

Voice (match the user)

Terse and kinetic; physically precise (exact materials, behaviors, scale); director-minded (lenses, angles, moves); non-generic (no "beautiful / stunning / amazing" — texture words instead); emotionally controlled. Don't inflate, don't soften, don't explain what things "represent." Same anti-slop discipline as ../higgsfield-seedance/SKILL.md § Voice Rewrite.

Seedance 2.0 input limits (reference)

Images ≤ 9; videos ≤ 3 items, total ≤ 15s; audio ≤ 3 MP3s, total ≤ 15s; total mixed inputs ≤ 12; generation duration 4–15s. A source clip plus a texture-reference photo fits easily. If a request needs more inputs than allowed, flag it and say what to prioritize. (Verified against ../../specs/model-specs.json → seedance_2_0: media_roles include video, image, audio, start_image, end_image; 4k is a legal resolution in mode=std.)

Structure patterns to internalize (style reference only — do not reproduce)

Add-element: @source (preserve all, add effect) → specs + 4K + NON-IP + SFX only → continuous shot, preserved performance, effect igniting/creeping with plate interaction, subject unfazed → lock-down clause → SFX.
Environment-swap: @source (preserve subject + vehicle + rig + motion, replace world) → specs + 4K + grade for the new world → continuous shot from the same rig, new world streaming past with parallax, relight to match or relight-all → lock-down → SFX.
Creature-on-landmark with timed zoom: @source + @creature (texture ref) → specs + 4K + NON-IP + SFX and source dialogue only → continuous locked shot, giant photoreal creature integrated on the landmark, subject delivering to camera → at ~T / on the line "…", smooth push-in keeping the landmark in frame, creature turns to camera → lock-down → SFX and dialogue.
Prepended reveal intro (transform + outward move + preserved performance): @source (preserve subject + performance + lip-sync + framing, add element, prepend a telephoto intro) + @creature (texture ref) → specs + 4K + NON-IP + SFX and source dialogue only → open tight/telephoto on the added element in isolation for the intro beat, hard or smooth zoom-out at ~T landing on a 100% match of the source composition, then the preserved take plays with exact lip-sync to the quoted line while the added element continues behind → budget check (intro + remaining = total) → lock-down → SFX and dialogue.

A ready-to-fill skeleton plus worked variants live in ../../templates/seedance/footage-vfx-transform.md.

Related Skills

../higgsfield-seedance/SKILL.md — the parent Seedance director: six-slot formula, Prompt-Craft Laws, engine rules, content-filter preflight linter, and the in-clip Transformation prompt mode
../higgsfield-audio/SKILL.md — audio-as-conditioning, [AUDIO: Xs] dialogue/SFX, lip-sync (the timed-zoom-to-dialogue and source-dialogue-preservation cases)
../higgsfield-camera/SKILL.md — video reference, the Load-Bearing Rule, camera-move vocabulary (handheld preservation + moves you never filmed)
../higgsfield-gpt-image-2/SKILL.md — generate the creature/texture reference image and the transformed start frame
../higgsfield-facs/SKILL.md — muscle-level facial control when a dialogue-preserving transform also needs an exact expression
references/dialogue-timing.md · references/first-frame.md — the two procedures this skill leans on

When it activates

Automatically, when a task matches. Use whenever a real clip is the starting point and they want to: add a VFX element (set a head or hair on fire, transform a hand, make a limb invisible), swap the environment around a preserved subject (desert, clouds, lava, a neon city), drop a giant photoreal creature behind or onto a subject/landmark, relight or regrade so subject and adde

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 v5 — 10/3/2026

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

osidemedia / higgsfield-ai-prompt-skill

skills/higgsfield-seedance-vfx/SKILL.md

View on GitHub ↗

License MITImported 10/3/2026Version v2Bundled 2 files

Illustrative Want to see what osidemedia/higgsfield-seedance-vfx would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

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

Higgsfield Seedance VFX — Footage Transformation

QUICK FACTS

The core idea: preserve, then change one thing

Resolution: run it in 4K

Prompt anatomy (transform variant)

1. The @source declaration

2. Specs line

3. Scene action — one continuous shot

4. SFX line

Three levels

Two transformation modes

A. Add an element to the footage

B. Replace the environment around a preserved subject

Lighting integration (the part that makes or breaks it)

Photoreal creature / element integration

Timed camera moves synced to dialogue

Reveal pull-back (the outward move)

Preserving lip-sync to a known line

Duration discipline

Prepended-intro budget: intro + remaining = total

First / start-frame workflow

Iterating

Output format

Voice (match the user)

Seedance 2.0 input limits (reference)

Structure patterns to internalize (style reference only — do not reproduce)

Related Skills

When it activates

SkillSafety

Source

Related skills

More in the registry

1. The `@source` declaration