Ready to supercharge your AI agents?

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

oiiotool Skill · leoyeai | DecimalAI

Design & Mediaby leoyeai

oiiotool Skill

Image processing with oiiotool CLI — format conversion (EXR, TIFF, DPX, PNG, JPEG, HDR), OCIO/ACES color management and display transforms, exposure adjustment, resize/crop, compositing, EXR sequence to video, texture baking, image comparison, and batch/sequence operations.

Never made a case worse

SkillScore

SkillScore100/100

Test results 100

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

67%100%of test cases passed +33 pts

Without skill16 of 24

With skill24 of 24

8 fixed16 passed either way0 still failing0 broke

Measured on gemini-3.6-flash8/9/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskA batch of JPEG camera photos photo.jpg has orientation flags stored in EXIF metadata. What oiiotool flag automatically rotates the image pixels to match the EXIF orientation tag before outputting oriented.jpg?

Without the skillMissed

With the skillPassed

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

Use this skill

Your agent runs on

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

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

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

Install

pip install "decimalai>=0.15"

Add the skill

from decimalai import skillpkg

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

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

Start Claude Code with it

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

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

Add the DecimalAI plugin, once

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

Install this skill

/decimalai:install leoyeai-oiiotool

The plugin needs python3 and curl on your machine.

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

Save it into your project

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

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-oiiotool/SKILL.md

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Claude Code docs

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

Install

pip install "decimalai[claude-agent-sdk]"
decimalai skills add leoyeai-oiiotool

Add it to your agent

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

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

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

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

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

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

Install

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

Add it to your agent

from decimalai import skillpkg

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

import asyncio

from claude_agent_sdk import ClaudeAgentOptions
from decimalai.claude_agent_sdk import agent_config

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

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

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-oiiotool/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-oiiotool/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 5 other files are not included.

Other ways to add it

Claude Agent SDK docs

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

Install

pip install "decimalai[openai-agents]"
decimalai skills add leoyeai-oiiotool

Add it to your agent

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

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

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

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

Install

pip install "decimalai[openai-agents]"

Add it to your agent

from decimalai import skillpkg

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

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

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

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-oiiotool/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-oiiotool/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 5 other files are not included.

Other ways to add it

OpenAI Agents docs

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

Install

pip install "decimalai[openai]"
decimalai skills add leoyeai-oiiotool

Add it to your agent

import json

from openai import OpenAI
from decimalai.openai import agent_config

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


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


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

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

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

Install

pip install "decimalai[openai]"

Add it to your agent

from decimalai import skillpkg

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

import json

from openai import OpenAI
from decimalai.openai import agent_config

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


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


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

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-oiiotool/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-oiiotool/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 5 other files are not included.

Other ways to add it

OpenAI SDK docs

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

Install

pip install "decimalai[anthropic]"
decimalai skills add leoyeai-oiiotool

Add it to your agent

import anthropic
from decimalai.anthropic import agent_config

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

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

Install

pip install "decimalai[anthropic]"

Add it to your agent

from decimalai import skillpkg

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

import anthropic
from decimalai.anthropic import agent_config

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-oiiotool/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-oiiotool/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 5 other files are not included.

Other ways to add it

Anthropic docs

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

Install

pip install "decimalai[google-genai]"
decimalai skills add leoyeai-oiiotool

Add it to your agent

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

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


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


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

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

Install

pip install "decimalai[google-genai]"

Add it to your agent

from decimalai import skillpkg

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

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

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


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


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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-oiiotool/SKILL.md

Give it to your agent

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

client = genai.Client()
skill = Path(".agents/skills/leoyeai-oiiotool/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 5 other files are not included.

Other ways to add it

Gemini API docs

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

Install

pip install "decimalai[langchain]" langchain-openai
decimalai skills add leoyeai-oiiotool

Add it to your agent

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

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

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

Install

pip install "decimalai[langchain]" langchain-openai

Add it to your agent

from decimalai import skillpkg

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

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

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-oiiotool/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-oiiotool/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 5 other files are not included.

Other ways to add it

LangChain docs

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

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add leoyeai-oiiotool

Add it to your agent

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

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

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

Install

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

Add it to your agent

from decimalai import skillpkg

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

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-oiiotool/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 5 other files are not included.

Other ways to add it

CrewAI docs

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

Install

pip install "decimalai[adk]"
decimalai skills add leoyeai-oiiotool

Add it to your agent

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

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

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

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

Install

pip install "decimalai[adk]"

Add it to your agent

from decimalai import skillpkg

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

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

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

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-oiiotool/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-oiiotool/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 5 other files are not included.

Other ways to add it

Google ADK docs

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

Install

pip install "decimalai[pydantic-ai]"
decimalai skills add leoyeai-oiiotool

Add it to your agent

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

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

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

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

Install

pip install "decimalai[pydantic-ai]"

Add it to your agent

from decimalai import skillpkg

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

from pydantic_ai import Agent
from decimalai.pydantic_ai import agent_config

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

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-oiiotool/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-oiiotool/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 5 other files are not included.

Other ways to add it

Pydantic AI docs

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

Install

pip install "decimalai>=0.16" deepagents
decimalai skills add leoyeai-oiiotool

Add it to your agent

import decimalai.deepagents
from deepagents import create_deep_agent

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

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

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

Install

pip install "decimalai>=0.16" deepagents

Add it to your agent

from decimalai import skillpkg

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

import decimalai.deepagents
from deepagents import create_deep_agent

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-oiiotool/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-oiiotool/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 5 other files are not included.

Other ways to add it

Deep Agents docs

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

Install

pip install "decimalai>=0.16" agent-framework
decimalai skills add leoyeai-oiiotool

Add it to your agent

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

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

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

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

Install

pip install "decimalai>=0.16" agent-framework

Add it to your agent

from decimalai import skillpkg

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

import asyncio

from agent_framework import Agent
from decimalai.agent_framework import skills

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-oiiotool/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-oiiotool/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 5 other files are not included.

Other ways to add it

Microsoft Agent Framework docs

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

Install

pip install "decimalai>=0.16" strands-agents
decimalai skills add leoyeai-oiiotool

Add it to your agent

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

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

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

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

Install

pip install "decimalai>=0.16" strands-agents

Add it to your agent

from decimalai import skillpkg

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

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

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

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

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

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-oiiotool/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-oiiotool/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 5 other files are not included.

Other ways to add it

Strands docs

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

pip install "decimalai>=0.15"
decimalai skills add leoyeai-oiiotool

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

Save it into your project

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

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-oiiotool/SKILL.md

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Cursor and other editors docs

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

Get the file

curl -fsSL https://app.decimal.ai/s/leoyeai-oiiotool/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-oiiotool.json

This gets SKILL.md only. The skill's 5 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/9/2026
Source: LeoYeAI/openclaw-master-skills ↗
License: MIT

Manage it in DecimalAI

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Use this skill

SKILL.md

oiiotool Skill

Command-line image processing with OpenImageIO's oiiotool. Industry-standard tool used across VFX, CGI, game dev, and photography for format conversion, color management, compositing, and batch image operations.

Setup

pip install openimageio

This installs both the oiiotool CLI and the OpenImageIO Python module.

Verify:

oiiotool --version
oiiotool --list-formats

OCIO / ACES Configuration

oiiotool uses OpenColorIO for color management. Since OCIO 2.2+, built-in ACES configs are available — no file download needed:

# Use built-in ACES CG config (recommended for most users)
export OCIO=ocio://cg-config-latest

# Or specify per-command
oiiotool --colorconfig ocio://cg-config-latest input.exr ...

Available built-in configs:

ocio://cg-config-latest — CG-focused config (no camera color spaces, lean). Recommended.
ocio://studio-config-latest — Full studio config (includes camera color spaces).
ocio://cg-config-v4.0.0_aces-v2.0_ocio-v2.5 — Pin to a specific version.

For production studios with a custom config:

export OCIO=/path/to/studio_config.ocio

Check what's available:

oiiotool --colorconfiginfo

Core Concept: Stack-Based Processing

oiiotool processes commands left to right on a stack:

Naming a file pushes it onto the stack
Commands pop inputs, process, and push results
-o writes the top of stack to a file

# Read -> process -> write
oiiotool input.exr --resize 1920x1080 -o output.png

# Two images -> composite -> write
oiiotool fg.exr bg.exr --over -o comp.exr

File Info & Metadata

# Basic info (resolution, channels, format)
oiiotool --info input.exr

# Verbose info (all metadata)
oiiotool --info -v input.exr

# Pixel statistics (min, max, mean, stddev per channel)
oiiotool --stats input.exr

# Filter metadata with regex
oiiotool --info -v --metamatch "camera|lens" input.exr

Format Conversion

Supported formats: EXR, TIFF, PNG, JPEG, DPX, HDR (Radiance), BMP, TGA, GIF, WebP, JPEG2000, PSD, ICO, FITS, and more.

# Simple conversion (format inferred from extension)
oiiotool input.exr -o output.png
oiiotool input.dpx -o output.tiff
oiiotool input.hdr -o output.exr

# Control output bit depth
oiiotool input.exr -d uint8 -o output.png       # 8-bit
oiiotool input.exr -d uint16 -o output.png       # 16-bit
oiiotool input.exr -d half -o output.exr         # 16-bit float (half)
oiiotool input.exr -d float -o output.tiff       # 32-bit float

# JPEG quality
oiiotool input.exr -d uint8 --compression jpeg:95 -o output.jpg

# EXR compression types
oiiotool input.exr --compression zip -o output.exr        # lossless, good general
oiiotool input.exr --compression piz -o output.exr        # lossless, best for noisy/CG
oiiotool input.exr --compression zips -o output.exr       # lossless, scanline
oiiotool input.exr --compression dwaa:45 -o output.exr    # lossy, very small files

# Tiled vs scanline EXR
oiiotool input.exr --tile 64 64 -o output.exr
oiiotool input.exr --scanline -o output.exr

# Add dither when going from high bit depth to 8-bit (reduces banding)
oiiotool input.exr -d uint8 --dither -o output.png

Production Tip: Selective Channel Reading

For large multichannel EXRs (beauty + depth + normals + crypto), read only what you need to save memory and time:

# Read only R,G,B channels (skip depth, normals, cryptomatte, etc.)
oiiotool -i:ch=R,G,B input.exr -o output.png

# Combined with conversion and color management
oiiotool -i:ch=R,G,B input.exr --resize 1024x0 --colorconvert "ACES2065-1" "Rec.1886 Rec.709 - Display" --compression "jpeg:90" -o output.jpg

This is critical in production where EXRs can have 50+ channels and be hundreds of MB each.

Color Management (OCIO)

Color Space Conversion

# Convert between named color spaces
oiiotool input.exr --colorconvert ACEScg "sRGB - Texture" -o output.png
oiiotool input.exr --colorconvert linear srgb -o output.png
oiiotool input.exr --tocolorspace "sRGB - Texture" -o output.png

# Set the assumed input color space (without changing pixels)
oiiotool input.png --iscolorspace srgb --tocolorspace linear -o linear.exr

ACES Display Transforms (Tone Mapping)

The proper way to view HDR content. Applies the ACES Reference Rendering Transform (RRT) + Output Device Transform (ODT) for correct highlight rolloff:

# sRGB monitor (most common for web/review)
oiiotool input.exr --ociodisplay "sRGB - Display" "ACES 1.0 - SDR Video" -d uint8 -o output.png

# Rec.709 broadcast
oiiotool input.exr --ociodisplay "Rec.1886 Rec.709 - Display" "ACES 1.0 - SDR Video" -d uint8 -o output.png

# DCI-P3 cinema
oiiotool input.exr --ociodisplay "P3-D65 - Display" "ACES 1.0 - SDR Cinema" -d uint8 -o output.png

# HDR (1000 nits, PQ)
oiiotool input.exr --ociodisplay "Rec.2100-PQ - Display" "ACES 1.1 - HDR Video (1000 nits & Rec.2020 lim)" -d uint16 -o output.png

# Un-tone-mapped (linear to display, no RRT — useful for comparing raw values)
oiiotool input.exr --ociodisplay "sRGB - Display" "Un-tone-mapped" -d uint8 -o output.png

When to use display transforms vs colorconvert: Use --ociodisplay when converting HDR scene-referred data to a display for viewing (applies tone mapping). Use --colorconvert when converting between working color spaces (no tone mapping, preserves linearity).

OCIO Looks & File Transforms

# Apply an OCIO look (e.g., ACES gamut compression)
oiiotool input.exr --ociolook "ACES 1.3 Reference Gamut Compression" -o output.exr

# Apply a file-based transform (3D LUT, CDL, CLF)
oiiotool input.exr --ociofiletransform my_grade.cube -o output.exr

# Inverse
oiiotool input.exr --ociofiletransform:inverse=1 my_grade.cube -o output.exr

Manual Matrix Color Conversion

When you don't have OCIO or need a specific 3x3 matrix:

# ACEScg to linear sRGB (comma-separated, row-major)
oiiotool input.exr --ccmatrix "1.70505,-0.62179,-0.08326,-0.13026,1.14080,-0.01055,-0.02400,-0.12897,1.15297" -o output.exr

Exposure Adjustment

EXR stores linear light values. Exposure in stops is powers of 2:

# Lower exposure (darken) — reveal HDR highlights
oiiotool input.exr --mulc 0.0625 -o output.exr        # -4 stops
oiiotool input.exr --mulc 0.0078125 -o output.exr      # -7 stops

# Raise exposure (brighten) — reveal shadow detail
oiiotool input.exr --mulc 4 -o output.exr              # +2 stops
oiiotool input.exr --mulc 16 -o output.exr             # +4 stops

# Fractional stops
oiiotool input.exr --mulc 0.00407 -o output.exr        # -7.6 stops

Exposure + ACES display transform (most useful combo for HDR review):

oiiotool input.exr --mulc 0.0078125 --ociodisplay "sRGB - Display" "ACES 1.0 - SDR Video" -d uint8 -o output_exp-7.png

Exposure Reference Table

Stops	Multiplier	Formula	Use Case
+8	256	2^8	Deep shadow recovery
+6	64	2^6	Dark shadow detail
+4	16	2^4	Shadow detail
+2	4	2^2	Slight brighten
0	1	2^0	Native exposure
-2	0.25	2^-2	Slight darken
-4	0.0625	2^-4	Highlight recovery
-6	0.015625	2^-6	Bright highlight detail
-8	0.00390625	2^-8	Extreme highlight recovery

Ready-Made Scripts

Exposure Sweep

Generate a composite contact sheet of multiple exposures from an HDR EXR:

python scripts/exposure_sweep.py input.exr
python scripts/exposure_sweep.py input.exr --stops -8,-6,-4,-2,0,2,4,6,8
python scripts/exposure_sweep.py input.exr --display "sRGB - Display" --view "ACES 1.0 - SDR Video"
python scripts/exposure_sweep.py input.exr --cols 4 --output sweep.jpg

EXR Sequence to Video

Convert an EXR image sequence to MP4:

python scripts/seq_to_video.py /path/to/sequence/
python scripts/seq_to_video.py /path/to/sequence/ --fps 24 --crf 18
python scripts/seq_to_video.py /path/to/sequence/ --display "sRGB - Display" --view "ACES 1.0 - SDR Video"
python scripts/seq_to_video.py /path/to/sequence/ --exposure -4 --output comp.mp4

Requires ffmpeg in PATH.

Image Operations

Resize & Fit

# Resize to exact dimensions
oiiotool input.exr --resize 1920x1080 -o output.exr

# Resize by percentage
oiiotool input.exr --resize 50% -o output.exr

# Resize width only, preserve aspect (height=0 means auto)
oiiotool input.exr --resize 1024x0 -o output.exr

# Fit within dimensions (preserves aspect ratio, no stretching)
oiiotool input.exr --fit 1920x1080 -o output.exr

# Fit and pad to exact dimensions
oiiotool input.exr --fit:pad=1 1920x1080 -o output.exr

# Choose resize filter
oiiotool input.exr --resize:filter=lanczos3 1920x1080 -o output.exr

# Fix pixel aspect ratio
oiiotool input.exr --pixelaspect 2.0 -o output.exr

Available filters: box, triangle, gaussian, catmull-rom, blackman-harris, sinc, lanczos3, mitchell, bspline, cubic. Default lanczos3 is good for most uses.

Crop & Cut

# Crop to region (WxH+X+Y — adjusts data window, keeps display window)
oiiotool input.exr --crop 1920x1080+100+50 -o output.exr

# Cut (crop + reposition to origin)
oiiotool input.exr --cut 1920x1080+100+50 -o output.exr

# Crop to full/display window
oiiotool input.exr --croptofull -o output.exr

# Auto-trim black borders
oiiotool input.exr --trim -o output.exr

Rotate & Flip

oiiotool input.exr --rotate90 -o output.exr      # 90 CW
oiiotool input.exr --rotate180 -o output.exr
oiiotool input.exr --rotate270 -o output.exr      # 90 CCW
oiiotool input.exr --flip -o output.exr           # vertical mirror
oiiotool input.exr --flop -o output.exr           # horizontal mirror
oiiotool input.exr --transpose -o output.exr
oiiotool input.exr --rotate 45 -o output.exr      # arbitrary angle

# Auto-orient based on EXIF
oiiotool --autoorient input.jpg -o output.jpg

Blur & Sharpen

# Gaussian blur
oiiotool input.exr --blur 5x5 -o output.exr
oiiotool input.exr --blur:kernel=gaussian 10x10 -o output.exr

# Median filter (salt-and-pepper noise removal)
oiiotool input.exr --median 3x3 -o output.exr

# Unsharp mask (sharpen)
oiiotool input.exr --unsharp:kernel=gaussian:width=3:contrast=1.5 -o output.exr

# Morphological ops
oiiotool input.exr --dilate 3x3 -o output.exr
oiiotool input.exr --erode 3x3 -o output.exr

Channel Operations

# Select/reorder channels
oiiotool input.exr --ch R,G,B -o output.exr         # drop alpha
oiiotool input.exr --ch B,G,R -o output.exr         # BGR swap
oiiotool input.exr --ch R,G,B,A=1.0 -o output.exr   # add solid alpha
oiiotool input.exr --ch 0 -o output.exr             # first channel only

# Rename channels
oiiotool input.exr --chnames R,G,B -o output.exr

# Combine channels from multiple files
oiiotool rgb.exr alpha.exr --chappend -o rgba.exr

# Luminance (sum weighted channels)
oiiotool input.exr --chsum:weight=0.2126,0.7152,0.0722 -o luminance.exr

# Split layer-named channels into separate images
oiiotool multilayer.exr --layersplit -o layer.exr

Compositing

# Alpha-over composite
oiiotool fg.exr bg.exr --over -o comp.exr

# Paste fg at position
oiiotool bg.exr fg.exr --paste +100+50 -o comp.exr

# Depth-based composite (Z channel)
oiiotool a.exr b.exr --zover -o comp.exr

# Mosaic/contact sheet
oiiotool img1.exr img2.exr img3.exr img4.exr --mosaic 2x2 -o grid.exr
oiiotool img*.exr --mosaic:pad=4 3x3 -o contact.exr

# Math operations between two images
oiiotool a.exr b.exr --add -o sum.exr
oiiotool a.exr b.exr --mul -o product.exr
oiiotool a.exr b.exr --absdiff -o diff.exr
oiiotool a.exr b.exr --max -o max.exr
oiiotool a.exr b.exr --min -o min.exr

Color & Value Adjustments

# Multiply (exposure, tint)
oiiotool input.exr --mulc 2.0 -o output.exr              # all channels
oiiotool input.exr --mulc 1.1,1.0,0.9 -o output.exr      # per-channel warm tint

# Add offset
oiiotool input.exr --addc 0.1 -o output.exr

# Power/gamma
oiiotool input.exr --powc 2.2 -o output.exr              # apply gamma
oiiotool input.exr --powc 0.4545 -o output.exr            # remove gamma

# Invert colors
oiiotool input.exr --invert -o output.exr

# Clamp values
oiiotool input.exr --clamp:min=0:max=1 -o output.exr

# Contrast (S-curve)
oiiotool input.exr --contrast:black=0.1:white=0.9:scontrast=2.0 -o output.exr

# Saturation
oiiotool input.exr --saturate 1.5 -o output.exr          # boost
oiiotool input.exr --saturate 0 -o output.exr             # desaturate

# Range compress (HDR -> log preview)
oiiotool input.exr --rangecompress -o output.exr

# Fix NaN/Inf values
oiiotool input.exr --fixnan black -o output.exr
oiiotool input.exr --fixnan box3 -o output.exr            # interpolate neighbors

# False color visualization
oiiotool depth.exr --colormap inferno -o heatmap.png
oiiotool depth.exr --colormap viridis -o heatmap.png
oiiotool depth.exr --colormap turbo -o heatmap.png

Drawing & Annotation

# Text overlay
oiiotool input.exr --text:x=20:y=40:size=24:color=1,1,1 "Frame 001" -o output.exr

# Draw box outline
oiiotool input.exr --box:color=1,0,0 100,100,500,400 -o output.exr

# Draw lines
oiiotool input.exr --line:color=0,1,0 0,0,100,100 -o output.exr

# Fill region with solid color
oiiotool input.exr --fill:color=0,0,1 100x100+50+50 -o output.exr

# Create solid color image from scratch
oiiotool --create 1920x1080 3 --fill:color=0.18,0.18,0.18 1920x1080+0+0 -o gray18.exr

Sequence Processing

oiiotool supports frame number wildcards for batch operations:

# '#' expands to frame numbers (padded to match # count)
oiiotool --frames 1001-1100 input.####.exr --resize 50% -o output.####.exr

# printf-style patterns
oiiotool --frames 1001-1100 input.%04d.exr -o output.%04d.png

# Frame step (every other frame)
oiiotool --frames 1-100x2 input.####.exr -o output.####.exr

# Skip missing frames
oiiotool --frames 1001-1100 --skip-bad-frames input.####.exr -o output.####.png

# Parallel frame processing (use all cores)
oiiotool --frames 1001-1100 --parallel-frames input.####.exr --resize 1920x1080 -o output.####.exr

# ACES display transform on entire sequence
oiiotool --frames 1001-1100 input.####.exr --ociodisplay "sRGB - Display" "ACES 1.0 - SDR Video" -d uint8 -o output.####.png

# Exposure + display transform on sequence
oiiotool --frames 1001-1100 input.####.exr --mulc 0.0625 --ociodisplay "sRGB - Display" "ACES 1.0 - SDR Video" -d uint8 -o output.####.png

# Read only RGB channels for efficiency on multichannel sequences
oiiotool --frames 1001-1100 -i:ch=R,G,B input.####.exr --ociodisplay "sRGB - Display" "ACES 1.0 - SDR Video" -d uint8 -o output.####.png

Sequence to Video (with ffmpeg)

Two-step process:

# Step 1: Convert EXR sequence to PNG
oiiotool --frames 1001-1100 --parallel-frames input.####.exr --ociodisplay "sRGB - Display" "ACES 1.0 - SDR Video" -d uint8 -o _tmp/output.####.png

# Step 2: Encode with ffmpeg
ffmpeg -framerate 24 -start_number 1001 -i _tmp/output.%04d.png -c:v libx264 -pix_fmt yuv420p -crf 18 output.mp4

Or use the helper script: python scripts/seq_to_video.py /path/to/sequence/

Texture Baking

# Tiled, mipmapped texture for rendering engines
oiiotool input.exr -otex output.tx

# Environment map (lat-long to cube)
oiiotool latlong.hdr -oenv environment.tx

# Bump map processing
oiiotool bump.exr -obump normals.tx

Image Comparison

# Difference report
oiiotool a.exr b.exr --diff

# Perceptual difference
oiiotool a.exr b.exr --pdiff

# With thresholds
oiiotool a.exr b.exr --fail 0.001 --failpercent 1 --diff

# Visual difference (amplified)
oiiotool a.exr b.exr --absdiff --mulc 10 -o diff_amplified.exr

# Count pixels matching a color
oiiotool input.exr --colorcount "0,0,0"

# Count pixels outside a range
oiiotool input.exr --rangecheck 0,0,0 1,1,1

Patterns & Test Images

# Black
oiiotool --create 1920x1080 3 -o black.exr

# Constant color
oiiotool --pattern constant:color=0.5,0.5,0.5 1920x1080 3 -o gray50.exr

# Checker
oiiotool --pattern checker:color1=0.2,0.2,0.2:color2=0.8,0.8,0.8:width=64:height=64 1920x1080 3 -o checker.exr

# Noise
oiiotool --pattern noise:type=gaussian:mean=0.5:stddev=0.1 1920x1080 3 -o noise.exr

Metadata Manipulation

# Set metadata
oiiotool input.exr --attrib "Artist" "John Doe" -o output.exr
oiiotool input.exr --attrib:type=float "exposure" 1.5 -o output.exr

# Remove metadata by pattern
oiiotool input.exr --eraseattrib "camera.*" -o output.exr

# Copy metadata from one image to another
oiiotool source.exr target.exr --pastemeta -o output.exr

# Set caption
oiiotool input.exr --caption "Final comp v3" -o output.exr

Deep Image Operations

# Flatten deep image to regular 2D
oiiotool deep.exr --flatten -o flat.exr

# Convert regular image to deep
oiiotool input.exr --deepen -o deep.exr

# Merge two deep images
oiiotool a_deep.exr b_deep.exr --deepmerge -o merged.exr

# Deep holdout
oiiotool fg_deep.exr holdout_deep.exr --deepholdout -o result.exr

Cryptomatte Visualization

# Built-in cryptomatte to color matte
oiiotool input.exr --cryptomatte-colors crypto_material -o material_colors.exr

For advanced cryptomatte extraction with custom palettes and batch processing, see the exr skill.

Performance Tips

--threads N — control parallelism (default: all cores)
--parallel-frames — parallelize sequence processing
-i:ch=R,G,B — read only needed channels from multichannel EXRs
--cache MB — increase image cache for large files
--native — bypass cache for one-shot operations
--autotile 64 — better cache performance with large scanline images
-u — update mode: skip outputs newer than inputs

Related Skills

exr — Python-level EXR internals: channel inspection, cryptomatte extraction with custom palettes, beauty pass extraction with ACEScg matrix. Use when you need fine-grained channel access or cryptomatte decoding beyond what --cryptomatte-colors provides.

When it activates

Automatically, when a task matches. Use when working with image files, EXR sequences, color spaces, or HDR content.

About this skill

Automatic

Coding pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

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

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

LeoYeAI / openclaw-master-skills

skills/oiiotool/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 5 files · scripts

Illustrative Want to see what leoyeai/oiiotool 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

oiiotool Skill

Setup

OCIO / ACES Configuration

Core Concept: Stack-Based Processing

File Info & Metadata

Format Conversion

Production Tip: Selective Channel Reading

Color Management (OCIO)

Color Space Conversion

ACES Display Transforms (Tone Mapping)

OCIO Looks & File Transforms

Manual Matrix Color Conversion

Exposure Adjustment

Exposure Reference Table

Ready-Made Scripts

Exposure Sweep

EXR Sequence to Video

Image Operations

Resize & Fit

Crop & Cut

Rotate & Flip

Blur & Sharpen

Channel Operations

Compositing

Color & Value Adjustments

Drawing & Annotation

Sequence Processing

Sequence to Video (with ffmpeg)

Texture Baking

Image Comparison

Patterns & Test Images

Metadata Manipulation

Deep Image Operations

Cryptomatte Visualization

Performance Tips

Related Skills

When it activates

SkillSafety

Source

Related skills

More in the registry