Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →An orbiting camera follows an ice logo as it breaks apart, reforms into two text moments, and fades. HyperFrames block, 1920×1080, 22.5s, 216 variables.
SkillScore100/100
Test results 100
3/3 safety checks passed
14%100%of test cases passed +86 pts
Passed 22 of 22 test cases with the skill, and 3 of 22 without it.
19 fixed3 passed either way0 still failing0 broke
One test taskIn the frost-sequence-camera-orbit composition, we want headline1 to display 'Cold Winter' on line one and 'Ahead' on line two. Should we pass `\n`, `<br/>`, or another character delimiter in the headline1 variable?
Adds every file the skill has, pinned so you can update it. No account needed.
pip install "decimalai>=0.15"
decimalai skills add heygen-com-frost-sequence-camera-orbit
claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"The same install from Python, for a notebook or a setup script.
pip install "decimalai>=0.15"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("heygen-com-frost-sequence-camera-orbit")
if result.exit_code:
raise SystemExit(result.problems)
print("Added. Start Claude Code with the command below.")claude --plugin-dir "$(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.
/plugin marketplace add decimal-labs/decimalai-claude-plugins
/plugin install decimalai@decimalai/decimalai:install heygen-com-frost-sequence-camera-orbitThe plugin needs python3 and curl on your machine.
No Python or account. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/heygen-com-frost-sequence-camera-orbit/SKILL.md https://app.decimal.ai/s/heygen-com-frost-sequence-camera-orbit/SKILL.md.claude/skills/heygen-com-frost-sequence-camera-orbit/SKILL.mdThis gets SKILL.md only. The skill's 6 other files are not included.
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.
pip install "decimalai[claude-agent-sdk]"
decimalai skills add heygen-com-frost-sequence-camera-orbitimport 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.
pip install "decimalai[claude-agent-sdk]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("heygen-com-frost-sequence-camera-orbit")
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.
.agents/skills/heygen-com-frost-sequence-camera-orbit/SKILL.mdimport asyncio
from pathlib import Path
from claude_agent_sdk import ClaudeAgentOptions, query
skill = Path(".agents/skills/heygen-com-frost-sequence-camera-orbit/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 6 other files are not included.
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.
pip install "decimalai[openai-agents]"
decimalai skills add heygen-com-frost-sequence-camera-orbitfrom 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.
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.
pip install "decimalai[openai-agents]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("heygen-com-frost-sequence-camera-orbit")
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.
.agents/skills/heygen-com-frost-sequence-camera-orbit/SKILL.mdfrom pathlib import Path
from agents import Agent, Runner
skill = Path(".agents/skills/heygen-com-frost-sequence-camera-orbit/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 6 other files are not included.
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.
pip install "decimalai[openai]"
decimalai skills add heygen-com-frost-sequence-camera-orbitimport 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.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.
pip install "decimalai[openai]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("heygen-com-frost-sequence-camera-orbit")
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.
.agents/skills/heygen-com-frost-sequence-camera-orbit/SKILL.mdfrom pathlib import Path
from openai import OpenAI
client = OpenAI()
skill = Path(".agents/skills/heygen-com-frost-sequence-camera-orbit/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].messageThis gets SKILL.md only. The skill's 6 other files are not included.
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.
pip install "decimalai[anthropic]"
decimalai skills add heygen-com-frost-sequence-camera-orbitimport 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()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.
pip install "decimalai[anthropic]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("heygen-com-frost-sequence-camera-orbit")
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.
.agents/skills/heygen-com-frost-sequence-camera-orbit/SKILL.mdfrom pathlib import Path
import anthropic
client = anthropic.Anthropic()
skill = Path(".agents/skills/heygen-com-frost-sequence-camera-orbit/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 6 other files are not included.
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.
pip install "decimalai[google-genai]"
decimalai skills add heygen-com-frost-sequence-camera-orbitfrom 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)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.
pip install "decimalai[google-genai]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("heygen-com-frost-sequence-camera-orbit")
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.
.agents/skills/heygen-com-frost-sequence-camera-orbit/SKILL.mdfrom pathlib import Path
from google import genai
from google.genai import types
client = genai.Client()
skill = Path(".agents/skills/heygen-com-frost-sequence-camera-orbit/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 6 other files are not included.
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.
pip install "decimalai[langchain]" langchain-openai
decimalai skills add heygen-com-frost-sequence-camera-orbitfrom 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!"}]})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.
pip install "decimalai[langchain]" langchain-openaifrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("heygen-com-frost-sequence-camera-orbit")
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.
.agents/skills/heygen-com-frost-sequence-camera-orbit/SKILL.mdfrom pathlib import Path
from langchain.agents import create_agent
skill = Path(".agents/skills/heygen-com-frost-sequence-camera-orbit/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 6 other files are not included.
CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add heygen-com-frost-sequence-camera-orbitimport 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.
pip install "decimalai>=0.16" "crewai>=1.15.27"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("heygen-com-frost-sequence-camera-orbit")
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.
.agents/skills/heygen-com-frost-sequence-camera-orbit/SKILL.mdfrom 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 6 other files are not included.
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.
pip install "decimalai[adk]"
decimalai skills add heygen-com-frost-sequence-camera-orbitfrom 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.
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.
pip install "decimalai[adk]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("heygen-com-frost-sequence-camera-orbit")
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.
.agents/skills/heygen-com-frost-sequence-camera-orbit/SKILL.mdfrom pathlib import Path
from google.adk.agents import LlmAgent
skill = Path(".agents/skills/heygen-com-frost-sequence-camera-orbit/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 6 other files are not included.
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.
pip install "decimalai[pydantic-ai]"
decimalai skills add heygen-com-frost-sequence-camera-orbitfrom 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.
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.
pip install "decimalai[pydantic-ai]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("heygen-com-frost-sequence-camera-orbit")
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.
.agents/skills/heygen-com-frost-sequence-camera-orbit/SKILL.mdfrom pathlib import Path
from pydantic_ai import Agent
skill = Path(".agents/skills/heygen-com-frost-sequence-camera-orbit/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 6 other files are not included.
Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" deepagents
decimalai skills add heygen-com-frost-sequence-camera-orbitimport 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.
pip install "decimalai>=0.16" deepagentsfrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("heygen-com-frost-sequence-camera-orbit")
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.
.agents/skills/heygen-com-frost-sequence-camera-orbit/SKILL.mdfrom pathlib import Path
from deepagents import create_deep_agent
skill = Path(".agents/skills/heygen-com-frost-sequence-camera-orbit/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 6 other files are not included.
Its own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" agent-framework
decimalai skills add heygen-com-frost-sequence-camera-orbitimport 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.
pip install "decimalai>=0.16" agent-frameworkfrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("heygen-com-frost-sequence-camera-orbit")
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.
.agents/skills/heygen-com-frost-sequence-camera-orbit/SKILL.mdimport asyncio
from pathlib import Path
from agent_framework import Agent
skill = Path(".agents/skills/heygen-com-frost-sequence-camera-orbit/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 6 other files are not included.
Strands' own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" strands-agents
decimalai skills add heygen-com-frost-sequence-camera-orbitfrom 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.
pip install "decimalai>=0.16" strands-agentsfrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("heygen-com-frost-sequence-camera-orbit")
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.
.agents/skills/heygen-com-frost-sequence-camera-orbit/SKILL.mdfrom pathlib import Path
from strands import Agent
skill = Path(".agents/skills/heygen-com-frost-sequence-camera-orbit/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 6 other files are not included.
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 heygen-com-frost-sequence-camera-orbitNo Python or account. Cursor, Copilot, Cline and Warp read this folder by themselves.
curl -fsSL --create-dirs -o .agents/skills/heygen-com-frost-sequence-camera-orbit/SKILL.md https://app.decimal.ai/s/heygen-com-frost-sequence-camera-orbit/SKILL.md.agents/skills/heygen-com-frost-sequence-camera-orbit/SKILL.mdThis gets SKILL.md only. The skill's 6 other files are not included.
Give its text to your model as instructions. No account or package needed.
This gets SKILL.md only. The skill's 6 other files are not included.
Raw files: /s/heygen-com-frost-sequence-camera-orbit/SKILL.md · /s/heygen-com-frost-sequence-camera-orbit.json
Fetch the file and give its text to your model as instructions. No account or package needed.
curl -fsSL https://app.decimal.ai/s/heygen-com-frost-sequence-camera-orbit/SKILL.mdcurl -fsSL https://app.decimal.ai/s/heygen-com-frost-sequence-camera-orbit.jsonThis gets SKILL.md only. The skill's 6 other files are not included.
You don't need a DecimalAI account.
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.
A complete 22.5-second ice sequence: logo, first text, second text, breakup, and fade. The camera orbits the fixed objects with slower front-facing passes for reading. The same particle field carries each transition. Customize the two text moments and SVG logo; the source includes editable camera and assembly timing.
Composition id: frost-sequence-rig. Duration 22.5 s at 30 fps, 1920×1080.
frost-sequence-camera-orbit.html (131 KB)assets/example-logo.svg (1 KB)assets/fonts/Geist-Bold.ttf (65 KB)assets/fonts/Geist-OFL.txt (4 KB)assets/fonts/Geist-Regular.ttf (65 KB)assets/fonts/Geist-SemiBold.ttf (65 KB)assets/frost.js (1.5 MB)assets/Three-LICENSE.txt (1 KB)assets/ThreeMeshBVH-LICENSE.txt (1 KB)assets/OpentypeJS-LICENSE.txt (1 KB)assets/Clipper-LICENSE.txt (3 KB)assets/gsap-3.14.2.min.js (128 KB)assets/GSAP-NOTICE.txt (1 KB)assets/logo.svg (1 KB)assets/shards-atlas.png (fetched from the CDN at install)assets/test-mark.svg (1 KB)assets/textures/bluenoise64.png (12 KB)assets/textures/ice-inclusions-generated.png (fetched from the CDN at install)Install with npx hyperframes add frost-sequence-camera-orbit; by default the files above land under compositions/frost-sequence-camera-orbit/. Then mount the block from the host index.html:
<div
data-composition-id="frost-sequence-rig"
data-composition-src="compositions/frost-sequence-camera-orbit/frost-sequence-camera-orbit.html"
data-start="0"
data-duration="22.5"
data-track-index="1"
data-width="1920"
data-height="1080"
></div>
Render with custom values by targeting the composition file directly:
npx --yes [email protected] render 'compositions/frost-sequence-camera-orbit/frost-sequence-camera-orbit.html' --variables '{"headline1":"Hard to|break.","headline2":"Easy to|remember."}'
Read at runtime via window.__hyperframes.getVariables(); declared on the composition root as data-composition-variables (single-quoted attribute, plain JSON).
| id | type | default | label / range |
| --------------------------- | ------- | ------------------- | --------------------------------------------------------------------------------------------- | ------------- | -------------------------- | ------- | ------- |
| headline1 | string | "Hard to | break." | First text ( | = line break) max 60 chars |
| headline2 | string | "Easy to | remember." | Second text ( | = line break) max 60 chars |
| logoUrl | string | "assets/logo.svg" | Logo SVG asset path (upload in Assets, then paste path) max 200 chars |
| assemblyMode | enum | "hybrid" | Assembly response (physical | directed | hybrid) |
| materialBaseColor | color | "#ffffff" | Base color |
| baseRoughness | number | 0.31 | Base roughness 0–0.5 step 0.005 |
| materialTransmission | boolean | true | Transmission |
| materialBacklight | number | 0.27 | Backlight through ice 0–2 step 0.01 |
| ior | number | 1.675 | Index of refraction 1–2 step 0.005 |
| thicknessScale | number | 2.04 | Thickness scale 0.1–3 step 0.01 |
| materialAbsorption | boolean | true | Absorption / tint |
| attenuationColor | color | "#d5f4ff" | Attenuation colour (white = no absorption, clear glass) |
| attenuationDistance | number | 6.54 | Attenuation distance 0.05–12 step 0.01 |
| materialDispersion | boolean | false | Dispersion |
| dispersion | number | 0.12 | Dispersion (0 = off; on/off reloads) 0–0.3 step 0.005 |
| materialReflections | boolean | true | Reflections |
| envIntensity | number | 2.04 | Environment intensity 0–3 step 0.01 |
| specularIntensity | number | 1.44 | Specular intensity 0–2 step 0.01 |
| materialFrost | boolean | true | Frost |
| materialInteriorFrost | number | 0 | Uniform frost 0–1 step 0.01 |
| frostScale | number | 0.7 | Scale 0.2–6 step 0.05 |
| frostThreshold | number | 0.62 | Threshold (1 = no frost, clear glass) 0–1 step 0.01 |
| frostSoftness | number | 0.24 | Softness 0.01–1 step 0.01 |
| frostRoughness | number | 0.73 | Roughness 0–1 step 0.01 |
| frostDiffuse | number | 0.11 | Diffuse (how much light frosted areas catch) 0–1 step 0.01 |
| materialSurfaceBumps | boolean | false | Object surface bumps / crack notches |
| materialCrystals | boolean | true | Crystal bumps |
| crystalBump | number | 0.01 | Crystal bump 0–1 step 0.01 |
| crystalScale | number | 4 | Crystal scale 4–80 step 1 |
| materialGrain | boolean | true | Grain bumps |
| materialGrainAmount | number | 0.47 | Grain strength 0–2 step 0.01 |
| materialGrainScale | number | 150 | Grain scale 1–150 step 1 |
| materialCutNormals | boolean | true | Fracture normals |
| materialMicro | boolean | true | Micro bumps |
| microBump | number | 0.445 | Micro bump 0–1 step 0.005 |
| microScale | number | 10 | Micro scale 10–200 step 1 |
| microCoverage | number | 0.25 | Micro coverage 0–1 step 0.01 |
| bumpMaskScale | number | 1.45 | Mask scale 0.1–6 step 0.05 |
| materialRipples | boolean | true | Ripples |
| rippleBump | number | 0.22 | Ripple bump 0–1 step 0.01 |
| rippleScale | number | 23 | Ripple scale 2–30 step 0.5 |
| materialSmudges | boolean | true | Smudges |
| smudgeAmount | number | 0.78 | Amount 0–1 step 0.01 |
| smudgeCoverage | number | 0.58 | Coverage 0–1 step 0.01 |
| smudgeMaskScale | number | 1.85 | Mask scale 0.1–6 step 0.05 |
| smudgeAnisotropy | number | 16.5 | Anisotropy 1–20 step 0.5 |
| smudgeRoughness | number | 0.75 | Roughness 0–1 step 0.01 |
| smudgeWhiteness | number | 0.035 | Whiteness 0–0.5 step 0.005 |
| smudgeScale | number | 1.3 | Scale 0.5–10 step 0.1 |
| materialCracks | boolean | true | Cracks |
| crackLargeScale | number | 2.45 | Large scale 0.3–8 step 0.05 |
| crackWarp | number | 0.22 | Warp 0–1.5 step 0.01 |
| crackCoverage | number | 0.19 | Coverage 0–1 step 0.01 |
| crackRegionScale | number | 1.8 | Region scale 0.1–4 step 0.05 |
| crackRegionCoverage | number | 0.6 | Region coverage 0–1 step 0.01 |
| veinScale | number | 8 | Vein scale 1–20 step 0.25 |
| veinContrast | number | 0.55 | Vein contrast 0–1 step 0.01 |
| crackWidth | number | 0.0025 | Width 0.0005–0.02 step 0.0005 |
| crackBrightness | number | 0.65 | Brightness 0–3 step 0.01 |
| crackDarkness | number | 0.69 | Darkness 0–1 step 0.01 |
| crackRefraction | number | 0.076 | Refraction 0–0.1 step 0.001 |
| crackSurfaceStrength | number | 0.16 | Surface strength 0–1 step 0.01 |
| fineScale | number | 18.4 | Fine scale 2–20 step 0.1 |
| fineAmount | number | 0.52 | Fine amount 0–1 step 0.01 |
| fineCoverage | number | 1 | Fine coverage 0–1 step 0.01 |
| materialScatter | boolean | true | Internal scattering |
| materialInclusionScale | number | 0.05 | Inclusion scale 0.05–3 step 0.01 |
| materialInclusionAmount | number | 2 | Photographic inclusions 0–2 step 0.01 |
| interiorScatter | number | 0.09 | Interior scatter 0–1 step 0.01 |
| materialClearcoat | boolean | true | Clearcoat |
| clearcoat | number | 0 | Clearcoat 0–1 step 0.01 |
| clearcoatRoughness | number | 0 | Clearcoat roughness 0–1 step 0.005 |
| materialShardNormals | boolean | true | Shard normals |
| spriteNormal | number | 0.15 | Sprite normal strength 0–2.5 step 0.05 |
| materialShardFrost | boolean | true | Shard frost |
| materialShardTransmission | boolean | true | Shard transparency |
| spriteSeeThrough | number | 1 | See-through (0 = off; on/off reloads) 0–1 step 0.01 |
| materialShardReflections | boolean | true | Shard reflections |
| minPixelSize | number | 0.25 | Minimum pixel size 0–4 step 0.05 |
| grainSizeMultiplier | number | 1.05 | Grain size multiplier 0.2–4 step 0.05 |
| spriteSize | number | 1.9 | Sprite size 0.3–4 step 0.05 |
| spriteTilt | number | 12 | Sprite tilt 0–70 step 1 |
| spriteAlphaCut | number | 0.6 | Alpha cut 0.05–0.6 step 0.01 |
| fontWeight | enum | "600" | Type · Weight (Geist) (400 | 600 | 700) |
| letterSpacing | number | 0.01 | Type · Letter spacing -0.1–0.4 step 0.005 |
| shardAmount | number | 0.44 | Shards · Visible fraction of the broken volume (Powder amount) 0.02–1 step 0.01 |
| strayDust | number | 24 | Shards · Ambient dust motes around the object (the experiment had 40) 0–200 step 1 |
| sliceRadius | number | 0.6 | Break · First (diagonal) slice radius 0.05–1.5 step 0.01 |
| sliceStrength | number | 21.5 | Break · First slice strength 1–40 step 0.5 |
| finalEjectBoost | number | 2.5 | Break · Last break: eject speed and speed cap multiplier 1–6 step 0.1 |
| shatterRadius | number | 0.45 | Break · Follow-up slice radius (sets their spacing too) 0.1–1.5 step 0.01 |
| shatterStrength | number | 32.5 | Break · Follow-up slice strength 1–40 step 0.5 |
| cutThreshold | number | 0.3 | Tune break · Cut threshold (surface gone above this erosion) 0.3–0.98 step 0.01 |
| cutSoftness | number | 0.19 | Tune break · Cut softness 0.005–0.3 step 0.005 |
| edgeWidth | number | 0.19 | Tune break · Crumbly edge band width 0.05–0.8 step 0.01 |
| edgeInset | number | 0 | Tune break · Edge inset 0–0.3 step 0.005 |
| brushSoftness | number | 0.15 | Tune break · Brush softness (edge falloff of a slice) 0.02–1 step 0.01 |
| brushNoise | number | 0.4 | Tune break · Brush noise (ragged boundary) 0–1 step 0.01 |
| crumbleRate | number | 4.3 | Tune break · Crumble rate along cracks (high = the whole shape goes at once) 0–6 step 0.05 |
| crumbleCrackBias | number | 5.1 | Tune break · Crumble crack bias 0–6 step 0.05 |
| crumbleDuration | number | 0.35 | Tune break · Crumble duration after a stroke 0–2 step 0.01 |
| ejectSpeed | number | 0.91 | Flight · Eject speed 0–4 step 0.01 |
| ejectSpread | number | 0.48 | Flight · Eject spread along the normal 0–3 step 0.01 |
| ejectTurbulence | number | 4 | Flight · Eject turbulence 0–4 step 0.01 |
| drag | number | 0 | Flight · Drag (speed decays by this per second) 0–8 step 0.01 |
| gravity | number | 0 | Flight · Gravity (0 = shards never fall) 0–2 step 0.005 |
| turbulence | number | 4 | Flight · Turbulence strength (curl noise) 0–4 step 0.01 |
| turbulenceScale | number | 2.65 | Flight · Turbulence scale 0.2–8 step 0.05 |
| turbulenceDecay | number | 3.65 | Flight · Turbulence decay with age (low = keeps swirling) 0.05–4 step 0.01 |
| clumpCohesion | number | 0.9 | Flight · Clump cohesion (shards orbit a leader; 0 = none) 0–10 step 0.05 |
| followObject | number | 30 | Flight · Shards follow the object motion for (s; 30 = whole flight) 0–30 step 0.5 |
| settleTime | number | 2.2 | Flight · Settle time (velocity is killed after this; 12 = never) 0.3–12 step 0.05 |
| settledDrift | number | 1 | Flight · Organic drift once settled (curl noise) 0–1 step 0.005 |
| maxSpeed | number | 26.3 | Flight · Speed cap 1–40 step 0.1 |
| repelStrength | number | 30 | Flight · Push out of the solid shape while it breaks 0–30 step 0.1 |
| repelRange | number | 0.97 | Flight · Push range outside the surface 0.02–2 step 0.01 |
| repelRadial | number | 17.5 | Flight · Push away from the shape centre (clears pockets and the hole) 0–60 step 0.5 |
| repelRadialRange | number | 3.3 | Flight · Radial push range (object radii) 1–4 step 0.05 |
| tumble | number | 1.05 | Flight · Tumble rate 0–12 step 0.05 |
| returnGroupStagger | number | 1.35 | Assembly · Regional delay (seconds) 0–1.5 step 0.05 |
| returnGroupScale | number | 2.55 | Assembly · Region / noise size 0.1–3 step 0.05 |
| returnGroupSeed | number | 60765 | Return · Group timing seed 0–65535 step 1 |
| formSpread | number | 0 | Return · Wave spread (nearest shards leave first, seconds) 0–4 step 0.05 |
| waveReach | number | 10 | Return · Distance over which the wave spreads 0.2–10 step 0.1 |
| formJitter | number | 2.8 | Return · Per-shard stagger (random delay up to this) 0–3 step 0.05 |
| formFill | number | 3 | Return · Fill-in rate for voxels no shard returns to 0.05–3 step 0.05 |
| returnSpring | number | 29.9 | Return · Spring stiffness 0.5–40 step 0.1 |
| returnDamping | number | 1.34 | Return · Spring damping 0.2–2 step 0.01 |
| returnRamp | number | 0.45 | Return · Spring ramp-in (seconds until it pulls at full strength) 0–3 step 0.05 |
| returnMaxSpeed | number | 60 | Return · Speed cap on the way home 1–60 step 0.5 |
| alignToSurface | number | 1 | Return · Shards turn to lie on the surface (0 = keep tumbling) 0–1 step 0.01 |
| alignCurve | number | 3.75 | Return · Alignment curve over the flight home (1 linear, higher = later) 0.2–4 step 0.05 |
| healRate | number | 3 | Return · Neighbour heal rate 0.02–3 step 0.01 |
| cellRestore | number | 60 | Return · Cell restore rate 0–60 step 0.5 |
| landedFade | number | 1.65 | Return · Landed shard fade 0–2 step 0.01 |
| refrostTime | number | 10.6 | Return · Refrost time 0.2–12 step 0.1 |
| keyColor | color | "#f0f7ff" | Light · Key colour |
| keyIntensity | number | 5.05 | Light · Key intensity 0–12 step 0.05 |
| keyElevation | number | 42 | Light · Key elevation 10–89 step 0.5 |
| keyAzimuth | number | -38 | Light · Key azimuth -90–90 step 0.5 |
| keySize | number | 1.25 | Light · Key size (softbox) 0.2–3 step 0.01 |
| fill | number | 0.18 | Light · Fill intensity (hemisphere, diffuse only: barely shows on clear ice) 0–1.5 step 0.005 |
| fillColor | color | "#cadde9" | Light · Fill sky colour |
| fillGroundColor | color | "#172635" | Light · Fill ground colour |
| rim | number | 2.5 | Light · Rim spot intensity 0–5 step 0.01 |
| rimColor | color | "#d9f1ff" | Light · Rim colour |
| rimElevation | number | 20 | Light · Rim elevation (0 = straight behind) 0–89 step 0.5 |
| swayAmplitude | number | 0 | Light · Key sway amplitude 0–0.15 step 0.001 |
| swayPeriod | number | 35 | Light · Key sway period 2–40 step 0.5 |
| envSoftbox | number | 1.1 | Light · Environment softbox (the main light on glass) 0–3 step 0.01 |
| envRim | number | 1.4 | Light · Environment rim strip 0–3 step 0.01 |
| envFill | number | 0.22 | Light · Environment front fill 0–1 step 0.005 |
| backdropTop | color | "#050505" | Backdrop · Top colour |
| backdropMid | color | "#050505" | Backdrop · Mid colour |
| backdropBottom | color | "#050505" | Backdrop · Bottom colour |
| backdropCenterX | number | 0.73 | Backdrop · Bloom centre X 0–1 step 0.005 |
| backdropCenterY | number | 0.22 | Backdrop · Bloom centre Y 0–2 step 0.005 |
| backdropRadius | number | 0.8 | Backdrop · Bloom radius 0.1–2 step 0.005 |
| backdropFalloff | number | 0.85 | Backdrop · Bloom falloff 0.5–6 step 0.01 |
| backdropNoise | number | 0 | Backdrop · Dither noise 0–3 step 0.05 |
| bloomThreshold | number | 3 | Post · Bloom threshold 0–3 step 0.01 |
| bloomIntensity | number | 0.04 | Post · Bloom intensity 0–1.5 step 0.005 |
| bloomRadius | number | 1 | Post · Bloom radius 0–1 step 0.005 |
| monochrome | number | 0.04 | Post · Monochrome 0–1 step 0.01 |
| tonemap | enum | "aces" | Post · Tonemap (agx | aces | neutral | linear) |
| exposure | number | 1 | Post · Exposure 0.1–4 step 0.01 |
| contrast | number | 1.03 | Post · Contrast 0.6–1.6 step 0.005 |
| blackLift | number | 0 | Post · Black lift 0–0.1 step 0.001 |
| vignetteStrength | number | 0.14 | Post · Vignette strength 0–1 step 0.005 |
| vignetteSoftness | number | 1.2 | Post · Vignette softness 0.1–1.5 step 0.005 |
| vignetteRadius | number | 1.2 | Post · Vignette radius 0.2–1.6 step 0.005 |
| grainStrength | number | 0 | Post · Film grain 0–0.15 step 0.001 |
| quality | enum | "full" | Performance · Quality profile (full | lite) |
| upscaler | enum | "fsr1" | Performance · Upscaler (fsr1 | taau | bilinear | native) |
| renderScale | number | 1 | Performance · Scene resolution scale (upscaled to 1080p) 0.35–1 step 0.05 |
| shapeResolution | enum | "256" | Shape voxel resolution (128 | 256 | 384) |
| erosionResolution | enum | "96" | Performance · Erosion field resolution (voxels per axis) (64 | 96 | 128 | 192) |
| particleCount | enum | "100k" | Performance · Powder particles (100k | 250k | 500k | 1M) |
| logoMeshDetail | number | 2 | Shape · Logo mesh detail (1-4; higher = finer surface) 1–4 step 1 |
| deformStrength | number | 0 | Geometry · Ice deformation strength (0 = original) 0–0.08 step 0.001 |
| deformScale | number | 0.41 | Geometry · Noise feature size (larger = broader) 0.001–0.5 step 0.001 |
| deformSeed | number | 7 | Geometry · Deformation seed 0–65535 step 1 |
| rimAzimuth | number | -146 | Light · Rim azimuth -180–180 step 1 |
| rimAngle | number | 26 | Light · Rim beam angle 10–89 step 1 |
| rimSize | number | 0.45 | Light · Rim reflection size 0.1–3 step 0.05 |
| fillReflectionStrength | number | 0.3 | Light · Fill reflection strength 0–2 step 0.01 |
| accentCoolIntensity | number | 3.71 | Studio Cool accent · intensity 0–4 step 0.01 |
| accentCoolReflection | number | 2.31 | Studio Cool accent · reflection 0–3 step 0.01 |
| accentCoolElevation | number | 63 | Studio Cool accent · elevation -85–85 step 1 |
| accentCoolAzimuth | number | 22 | Studio Cool accent · azimuth -180–180 step 1 |
| accentCoolSize | number | 2.65 | Studio Cool accent · size 0.1–3 step 0.05 |
| accentCoolColor | color | "#ff5900" | Studio Cool accent · color |
| accentWarmIntensity | number | 2.99 | Studio Warm accent · intensity 0–4 step 0.01 |
| accentWarmReflection | number | 0.34 | Studio Warm accent · reflection 0–3 step 0.01 |
| accentWarmElevation | number | 30 | Studio Warm accent · elevation -85–85 step 1 |
| accentWarmAzimuth | number | -30 | Studio Warm accent · azimuth -180–180 step 1 |
| accentWarmSize | number | 1.2 | Studio Warm accent · size 0.1–3 step 0.05 |
| accentWarmColor | color | "#75aaff" | Studio Warm accent · color |
| returnNoiseAmount | enum | "2" | Assembly · Regional pattern (2 | 1 | 0) |
| assemblyFrontDuration | number | 3.2 | Assembly · Growth duration (seconds) 0–6 step 0.05 |
| assemblyOriginX | number | -0.65 | Assembly · Growth start X -1–1 step 0.01 |
| assemblyOriginY | number | 0.55 | Assembly · Growth start Y -1–1 step 0.01 |
| assemblyAngle | number | -35 | Assembly · Seam direction (degrees) -180–180 step 1 |
| assemblySpread | number | 0.65 | Assembly · Outward spread vs seam travel 0–1 step 0.01 |
| assemblyFrontNoise | number | 0.35 | Assembly · Growth edge irregularity 0–1 step 0.01 |
| assemblySpeedVariation | number | 0.65 | Assembly · Return speed variation 0–1 step 0.01 |
| assemblyBend | number | 1.2 | Assembly · Approach path bend 0–3 step 0.05 |
| assemblySwirl | number | 1.1 | Assembly · Approach twist 0–3 step 0.05 |
| assemblyLandingVariation | number | 0.8 | Assembly · Landing transition variation 0–1 step 0.01 |
| rendererProfile | enum | "studio" | Renderer experiment (reload required) (original | lookup | mesh | studio | matcap) |
| textWidth | number | 6.5 | Type · Headline block width (the mark is 2.6 wide) 1.2–9 step 0.05 |
| textLineHeight | number | 0.95 | Type · Line height 0.7–1.4 step 0.01 |
| textDepth | number | 0.16 | Type · Extrusion depth (fraction of the font size) 0.05–0.8 step 0.01 |
| textBevel | number | 0.04 | Type · Bevel (fraction of the font size) 0–0.12 step 0.005 |
| textCorner | number | 0.008 | Type · Corner rounding (fraction of the font size) 0–0.06 step 0.002 |
| textMeshDetail | number | 4 | Type · Text mesh detail (1-4; higher = smoother deformation) 1–4 step 1 |
window.__timelines["frost-sequence-rig"].hf-seek CustomEvent; every frame is a closed-form function of time (seeded PRNG only, no rAF loops, no Date.now).data-composition-variables a single-quoted attribute with plain " JSON. Never save it through Studio's Design panel.<canvas> in static markup; create it at runtime.Skills that do similar work, with their headline benchmark lift.
From the same source and nearby in the catalogue.