Ready to supercharge your AI agents?

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

Get Started Free →

Imaging Data Commons · foryourhealth111-pixel | DecimalAI

Scienceby foryourhealth111-pixel

Imaging Data Commons

Query and download public cancer imaging data from NCI Imaging Data Commons using idc-index.

Never made a case worse

SkillScore

SkillScore88/100

Test results 100 · Live runs 75

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

41%100%of test cases passed +59 pts

Without skill9 of 22

With skill22 of 22

13 fixed9 passed either way0 still failing0 broke

Measured on gemini-3.6-flash8/13/2026v1

Track record

Agent runs: 14; All time
Forks: 1

See one task, with and without the skill

One test taskIf an imaging study references DICOM series from older release versions of NCI Imaging Data Commons that are no longer in the active index, which table contains metadata for these deprecated series?

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 foryourhealth111-pixel-imaging-data-commons
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("foryourhealth111-pixel-imaging-data-commons")
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 foryourhealth111-pixel-imaging-data-commons

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/foryourhealth111-pixel-imaging-data-commons/SKILL.md https://app.decimal.ai/s/foryourhealth111-pixel-imaging-data-commons/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/foryourhealth111-pixel-imaging-data-commons/SKILL.md

This gets SKILL.md only. The skill's 9 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 foryourhealth111-pixel-imaging-data-commons

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("foryourhealth111-pixel-imaging-data-commons")
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/foryourhealth111-pixel-imaging-data-commons/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/foryourhealth111-pixel-imaging-data-commons/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 9 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 foryourhealth111-pixel-imaging-data-commons

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("foryourhealth111-pixel-imaging-data-commons")
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/foryourhealth111-pixel-imaging-data-commons/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/foryourhealth111-pixel-imaging-data-commons/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 9 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 foryourhealth111-pixel-imaging-data-commons

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("foryourhealth111-pixel-imaging-data-commons")
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/foryourhealth111-pixel-imaging-data-commons/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/foryourhealth111-pixel-imaging-data-commons/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 9 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 foryourhealth111-pixel-imaging-data-commons

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("foryourhealth111-pixel-imaging-data-commons")
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/foryourhealth111-pixel-imaging-data-commons/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/foryourhealth111-pixel-imaging-data-commons/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 9 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 foryourhealth111-pixel-imaging-data-commons

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("foryourhealth111-pixel-imaging-data-commons")
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/foryourhealth111-pixel-imaging-data-commons/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/foryourhealth111-pixel-imaging-data-commons/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 9 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 foryourhealth111-pixel-imaging-data-commons

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("foryourhealth111-pixel-imaging-data-commons")
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/foryourhealth111-pixel-imaging-data-commons/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/foryourhealth111-pixel-imaging-data-commons/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 9 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 foryourhealth111-pixel-imaging-data-commons

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("foryourhealth111-pixel-imaging-data-commons")
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/foryourhealth111-pixel-imaging-data-commons/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 9 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 foryourhealth111-pixel-imaging-data-commons

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("foryourhealth111-pixel-imaging-data-commons")
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/foryourhealth111-pixel-imaging-data-commons/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/foryourhealth111-pixel-imaging-data-commons/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 9 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 foryourhealth111-pixel-imaging-data-commons

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("foryourhealth111-pixel-imaging-data-commons")
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/foryourhealth111-pixel-imaging-data-commons/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/foryourhealth111-pixel-imaging-data-commons/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 9 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 foryourhealth111-pixel-imaging-data-commons

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("foryourhealth111-pixel-imaging-data-commons")
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/foryourhealth111-pixel-imaging-data-commons/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/foryourhealth111-pixel-imaging-data-commons/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 9 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 foryourhealth111-pixel-imaging-data-commons

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("foryourhealth111-pixel-imaging-data-commons")
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/foryourhealth111-pixel-imaging-data-commons/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/foryourhealth111-pixel-imaging-data-commons/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 9 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 foryourhealth111-pixel-imaging-data-commons

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("foryourhealth111-pixel-imaging-data-commons")
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/foryourhealth111-pixel-imaging-data-commons/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/foryourhealth111-pixel-imaging-data-commons/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 9 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 foryourhealth111-pixel-imaging-data-commons

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/foryourhealth111-pixel-imaging-data-commons/SKILL.md https://app.decimal.ai/s/foryourhealth111-pixel-imaging-data-commons/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/foryourhealth111-pixel-imaging-data-commons/SKILL.md

This gets SKILL.md only. The skill's 9 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/foryourhealth111-pixel-imaging-data-commons/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/foryourhealth111-pixel-imaging-data-commons.json

This gets SKILL.md only. The skill's 9 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/13/2026
Source: foryourhealth111-pixel/vibe-skills ↗
License: Apache-2.0

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

Imaging Data Commons

Overview

Use the idc-index Python package to query and download public cancer imaging data from the National Cancer Institute Imaging Data Commons (IDC). No authentication required for data access.

Routing Boundary

Use this skill for NCI Imaging Data Commons, IDC, TCIA cancer imaging cohorts, DICOMWeb, public cancer imaging data, radiology datasets, and DICOM imaging cohort retrieval. This is not generic Data Commons, public statistical data, population indicators, statistical variables, DCIDs, PubMed, ClinicalTrials.gov, or generic public dataset search.

Current IDC Data Version: v23 (always verify with IDCClient().get_idc_version())

Primary tool: idc-index (GitHub)

CRITICAL - Check package version and upgrade if needed (run this FIRST):

import idc_index

REQUIRED_VERSION = "0.11.9"  # Must match metadata.idc-index in this file
installed = idc_index.__version__

if installed < REQUIRED_VERSION:
    print(f"Upgrading idc-index from {installed} to {REQUIRED_VERSION}...")
    import subprocess
    subprocess.run(["pip3", "install", "--upgrade", "--break-system-packages", "idc-index"], check=True)
    print("Upgrade complete. Restart Python to use new version.")
else:
    print(f"idc-index {installed} meets requirement ({REQUIRED_VERSION})")

Verify IDC data version and check current data scale:

from idc_index import IDCClient
client = IDCClient()

# Verify IDC data version (should be "v23")
print(f"IDC data version: {client.get_idc_version()}")

# Get collection count and total series
stats = client.sql_query("""
    SELECT
        COUNT(DISTINCT collection_id) as collections,
        COUNT(DISTINCT analysis_result_id) as analysis_results,
        COUNT(DISTINCT PatientID) as patients,
        COUNT(DISTINCT StudyInstanceUID) as studies,
        COUNT(DISTINCT SeriesInstanceUID) as series,
        SUM(instanceCount) as instances,
        SUM(series_size_MB)/1000000 as size_TB
    FROM index
""")
print(stats)

Core workflow:

Query metadata → client.sql_query()
Download DICOM files → client.download_from_selection()
Visualize in browser → client.get_viewer_URL(seriesInstanceUID=...)

When to Use This Skill

Finding publicly available radiology (CT, MR, PET) or pathology (slide microscopy) images
Selecting image subsets by cancer type, modality, anatomical site, or other metadata
Downloading DICOM data from IDC
Checking data licenses before use in research or commercial applications
Visualizing medical images in a browser without local DICOM viewer software

Quick Navigation

Core Sections (inline):

IDC Data Model - Collection and analysis result hierarchy
Index Tables - Available tables and joining patterns
Installation - Package setup and version verification
Core Capabilities - Essential API patterns (query, download, visualize, license, citations, batch)
Best Practices - Usage guidelines
Troubleshooting - Common issues and solutions

Reference Guides (load on demand):

Guide	When to Load
`index_tables_guide.md`	Complex JOINs, schema discovery, DataFrame access
`use_cases.md`	End-to-end workflow examples (training datasets, batch downloads)
`sql_patterns.md`	Quick SQL patterns for filter discovery, annotations, size estimation
`clinical_data_guide.md`	Clinical/tabular data, imaging+clinical joins, value mapping
`cloud_storage_guide.md`	Direct S3/GCS access, versioning, UUID mapping
`dicomweb_guide.md`	DICOMweb endpoints, PACS integration
`digital_pathology_guide.md`	Slide microscopy (SM), annotations (ANN), pathology workflows
`bigquery_guide.md`	Full DICOM metadata, private elements (requires GCP)
`cli_guide.md`	Command-line tools (`idc download`, manifest files)

IDC Data Model

IDC adds two grouping levels above the standard DICOM hierarchy (Patient → Study → Series → Instance):

collection_id: Groups patients by disease, modality, or research focus (e.g., tcga_luad, nlst). A patient belongs to exactly one collection.
analysis_result_id: Identifies derived objects (segmentations, annotations, radiomics features) across one or more original collections.

Use collection_id to find original imaging data, may include annotations deposited along with the images; use analysis_result_id to find AI-generated or expert annotations.

Key identifiers for queries:

Identifier	Scope	Use for
`collection_id`	Dataset grouping	Filtering by project/study
`PatientID`	Patient	Grouping images by patient
`StudyInstanceUID`	DICOM study	Grouping of related series, visualization
`SeriesInstanceUID`	DICOM series	Grouping of related series, visualization

Index Tables

The idc-index package provides multiple metadata index tables, accessible via SQL or as pandas DataFrames.

Complete index table documentation: Use https://idc-index.readthedocs.io/en/latest/indices_reference.html for quick check of available tables and columns without executing any code.

Important: Use client.indices_overview to get current table descriptions and column schemas. This is the authoritative source for available columns and their types — always query it when writing SQL or exploring data structure.

Available Tables

Table	Row Granularity	Loaded	Description
`index`	1 row = 1 DICOM series	Auto	Primary metadata for all current IDC data
`prior_versions_index`	1 row = 1 DICOM series	Auto	Series from previous IDC releases; for downloading deprecated data
`collections_index`	1 row = 1 collection	fetch_index()	Collection-level metadata and descriptions
`analysis_results_index`	1 row = 1 analysis result collection	fetch_index()	Metadata about derived datasets (annotations, segmentations)
`clinical_index`	1 row = 1 clinical data column	fetch_index()	Dictionary mapping clinical table columns to collections
`sm_index`	1 row = 1 slide microscopy series	fetch_index()	Slide Microscopy (pathology) series metadata
`sm_instance_index`	1 row = 1 slide microscopy instance	fetch_index()	Instance-level (SOPInstanceUID) metadata for slide microscopy
`seg_index`	1 row = 1 DICOM Segmentation series	fetch_index()	Segmentation metadata: algorithm, segment count, reference to source image series
`ann_index`	1 row = 1 DICOM ANN series	fetch_index()	Microscopy Bulk Simple Annotations series metadata; references annotated image series
`ann_group_index`	1 row = 1 annotation group	fetch_index()	Detailed annotation group metadata: graphic type, annotation count, property codes, algorithm
`contrast_index`	1 row = 1 series with contrast info	fetch_index()	Contrast agent metadata: agent name, ingredient, administration route (CT, MR, PT, XA, RF)

Auto = loaded automatically when IDCClient() is instantiated fetch_index() = requires client.fetch_index("table_name") to load

Joining Tables

Key columns are not explicitly labeled, the following is a subset that can be used in joins.

Join Column	Tables	Use Case
`collection_id`	index, prior_versions_index, collections_index, clinical_index	Link series to collection metadata or clinical data
`SeriesInstanceUID`	index, prior_versions_index, sm_index, sm_instance_index	Link series across tables; connect to slide microscopy details
`StudyInstanceUID`	index, prior_versions_index	Link studies across current and historical data
`PatientID`	index, prior_versions_index	Link patients across current and historical data
`analysis_result_id`	index, analysis_results_index	Link series to analysis result metadata (annotations, segmentations)
`source_DOI`	index, analysis_results_index	Link by publication DOI
`crdc_series_uuid`	index, prior_versions_index	Link by CRDC unique identifier
`Modality`	index, prior_versions_index	Filter by imaging modality
`SeriesInstanceUID`	index, seg_index, ann_index, ann_group_index, contrast_index	Link segmentation/annotation/contrast series to its index metadata
`segmented_SeriesInstanceUID`	seg_index → index	Link segmentation to its source image series (join seg_index.segmented_SeriesInstanceUID = index.SeriesInstanceUID)
`referenced_SeriesInstanceUID`	ann_index → index	Link annotation to its source image series (join ann_index.referenced_SeriesInstanceUID = index.SeriesInstanceUID)

Note: Subjects, Updated, and Description appear in multiple tables but have different meanings (counts vs identifiers, different update contexts).

For detailed join examples, schema discovery patterns, key columns reference, and DataFrame access, see references/index_tables_guide.md.

Clinical Data Access

# Fetch clinical index (also downloads clinical data tables)
client.fetch_index("clinical_index")

# Query clinical index to find available tables and their columns
tables = client.sql_query("SELECT DISTINCT table_name, column_label FROM clinical_index")

# Load a specific clinical table as DataFrame
clinical_df = client.get_clinical_table("table_name")

See references/clinical_data_guide.md for detailed workflows including value mapping patterns and joining clinical data with imaging.

Data Access Options

Method	Auth Required	Best For
`idc-index`	No	Key queries and downloads (recommended)
IDC Portal	No	Interactive exploration, manual selection, browser-based download
BigQuery	Yes (GCP account)	Complex queries, full DICOM metadata
DICOMweb proxy	No	Tool integration via DICOMweb API
Cloud storage (S3/GCS)	No	Direct file access, bulk downloads, custom pipelines

Cloud storage organization

IDC maintains all DICOM files in public cloud storage buckets mirrored between AWS S3 and Google Cloud Storage. Files are organized by CRDC UUIDs (not DICOM UIDs) to support versioning.

Bucket (AWS / GCS)	License	Content
`idc-open-data` / `idc-open-data`	No commercial restriction	>90% of IDC data
`idc-open-data-two` / `idc-open-idc1`	No commercial restriction	Collections with potential head scans
`idc-open-data-cr` / `idc-open-cr`	Commercial use restricted (CC BY-NC)	~4% of data

Files are stored as <crdc_series_uuid>/<crdc_instance_uuid>.dcm. Access is free (no egress fees) via AWS CLI, gsutil, or s5cmd with anonymous access. Use series_aws_url column from the index for S3 URLs; GCS uses the same path structure.

See references/cloud_storage_guide.md for bucket details, access commands, UUID mapping, and versioning.

DICOMweb access

IDC data is available via DICOMweb interface (Google Cloud Healthcare API implementation) for integration with PACS systems and DICOMweb-compatible tools.

Endpoint	Auth	Use Case
Public proxy	No	Testing, moderate queries, daily quota
Google Healthcare	Yes (GCP)	Production use, higher quotas

See references/dicomweb_guide.md for endpoint URLs, code examples, supported operations, and implementation details.

Installation and Setup

Required (for basic access):

pip install --upgrade idc-index

Important: New IDC data release will always trigger a new version of idc-index. Always use --upgrade flag while installing, unless an older version is needed for reproducibility.

IMPORTANT: IDC data version v23 is current. Always verify your version:

print(client.get_idc_version())  # Should return "v23"

If you see an older version, upgrade with: pip install --upgrade idc-index

Tested with: idc-index 0.11.9 (IDC data version v23)

Optional (for data analysis):

pip install pandas numpy pydicom

Core Capabilities

1. Data Discovery and Exploration

Discover what imaging collections and data are available in IDC:

from idc_index import IDCClient

client = IDCClient()

# Get summary statistics from primary index
query = """
SELECT
  collection_id,
  COUNT(DISTINCT PatientID) as patients,
  COUNT(DISTINCT SeriesInstanceUID) as series,
  SUM(series_size_MB) as size_mb
FROM index
GROUP BY collection_id
ORDER BY patients DESC
"""
collections_summary = client.sql_query(query)

# For richer collection metadata, use collections_index
client.fetch_index("collections_index")
collections_info = client.sql_query("""
    SELECT collection_id, CancerTypes, TumorLocations, Species, Subjects, SupportingData
    FROM collections_index
""")

# For analysis results (annotations, segmentations), use analysis_results_index
client.fetch_index("analysis_results_index")
analysis_info = client.sql_query("""
    SELECT analysis_result_id, analysis_result_title, Subjects, Collections, Modalities
    FROM analysis_results_index
""")

collections_index provides curated metadata per collection: cancer types, tumor locations, species, subject counts, and supporting data types — without needing to aggregate from the primary index.

analysis_results_index lists derived datasets (AI segmentations, expert annotations, radiomics features) with their source collections and modalities.

2. Querying Metadata with SQL

Query the IDC mini-index using SQL to find specific datasets.

First, explore available values for filter columns:

from idc_index import IDCClient

client = IDCClient()

# Check what Modality values exist
modalities = client.sql_query("""
    SELECT DISTINCT Modality, COUNT(*) as series_count
    FROM index
    GROUP BY Modality
    ORDER BY series_count DESC
""")
print(modalities)

# Check what BodyPartExamined values exist for MR modality
body_parts = client.sql_query("""
    SELECT DISTINCT BodyPartExamined, COUNT(*) as series_count
    FROM index
    WHERE Modality = 'MR' AND BodyPartExamined IS NOT NULL
    GROUP BY BodyPartExamined
    ORDER BY series_count DESC
    LIMIT 20
""")
print(body_parts)

Then query with validated filter values:

# Find breast MRI scans (use actual values from exploration above)
results = client.sql_query("""
    SELECT
      collection_id,
      PatientID,
      SeriesInstanceUID,
      Modality,
      SeriesDescription,
      license_short_name
    FROM index
    WHERE Modality = 'MR'
      AND BodyPartExamined = 'BREAST'
    LIMIT 20
""")

# Access results as pandas DataFrame
for idx, row in results.iterrows():
    print(f"Patient: {row['PatientID']}, Series: {row['SeriesInstanceUID']}")

To filter by cancer type, join with collections_index:

client.fetch_index("collections_index")
results = client.sql_query("""
    SELECT i.collection_id, i.PatientID, i.SeriesInstanceUID, i.Modality
    FROM index i
    JOIN collections_index c ON i.collection_id = c.collection_id
    WHERE c.CancerTypes LIKE '%Breast%'
      AND i.Modality = 'MR'
    LIMIT 20
""")

Available metadata fields (use client.indices_overview for complete list):

Identifiers: collection_id, PatientID, StudyInstanceUID, SeriesInstanceUID
Imaging: Modality, BodyPartExamined, Manufacturer, ManufacturerModelName
Clinical: PatientAge, PatientSex, StudyDate
Descriptions: StudyDescription, SeriesDescription
Licensing: license_short_name

Note: Cancer type is in collections_index.CancerTypes, not in the primary index table.

3. Downloading DICOM Files

Download imaging data efficiently from IDC's cloud storage:

Download entire collection:

from idc_index import IDCClient

client = IDCClient()

# Download small collection (RIDER Pilot ~1GB)
client.download_from_selection(
    collection_id="rider_pilot",
    downloadDir="./data/rider"
)

Download specific series:

# First, query for series UIDs
series_df = client.sql_query("""
    SELECT SeriesInstanceUID
    FROM index
    WHERE Modality = 'CT'
      AND BodyPartExamined = 'CHEST'
      AND collection_id = 'nlst'
    LIMIT 5
""")

# Download only those series
client.download_from_selection(
    seriesInstanceUID=list(series_df['SeriesInstanceUID'].values),
    downloadDir="./data/lung_ct"
)

Custom directory structure:

Default dirTemplate: %collection_id/%PatientID/%StudyInstanceUID/%Modality_%SeriesInstanceUID

# Simplified hierarchy (omit StudyInstanceUID level)
client.download_from_selection(
    collection_id="tcga_luad",
    downloadDir="./data",
    dirTemplate="%collection_id/%PatientID/%Modality"
)
# Results in: ./data/tcga_luad/TCGA-05-4244/CT/

# Flat structure (all files in one directory)
client.download_from_selection(
    seriesInstanceUID=list(series_df['SeriesInstanceUID'].values),
    downloadDir="./data/flat",
    dirTemplate=""
)
# Results in: ./data/flat/*.dcm

Downloaded file names:

Individual DICOM files are named using their CRDC instance UUID: <crdc_instance_uuid>.dcm (e.g., 0d73f84e-70ae-4eeb-96a0-1c613b5d9229.dcm). This UUID-based naming:

Enables version tracking (UUIDs change when file content changes)
Matches cloud storage organization (s3://idc-open-data/<crdc_series_uuid>/<crdc_instance_uuid>.dcm)
Differs from DICOM UIDs (SOPInstanceUID) which are preserved inside the file metadata

To identify files, use the crdc_instance_uuid column in queries or read DICOM metadata (SOPInstanceUID) from the files.

Command-Line Download

The idc download command provides command-line access to download functionality without writing Python code. Available after installing idc-index.

Auto-detects input type: manifest file path, or identifiers (collection_id, PatientID, StudyInstanceUID, SeriesInstanceUID, crdc_series_uuid).

# Download entire collection
idc download rider_pilot --download-dir ./data

# Download specific series by UID
idc download "1.3.6.1.4.1.9328.50.1.69736" --download-dir ./data

# Download multiple items (comma-separated)
idc download "tcga_luad,tcga_lusc" --download-dir ./data

# Download from manifest file (auto-detected)
idc download manifest.txt --download-dir ./data

Options:

Option	Description
`--download-dir`	Output directory (default: current directory)
`--dir-template`	Directory hierarchy template (default: `%collection_id/%PatientID/%StudyInstanceUID/%Modality_%SeriesInstanceUID`)
`--log-level`	Verbosity: debug, info, warning, error, critical

Manifest files:

Manifest files contain S3 URLs (one per line) and can be:

Exported from the IDC Portal after cohort selection
Shared by collaborators for reproducible data access
Generated programmatically from query results

Format (one S3 URL per line):

s3://idc-open-data/cb09464a-c5cc-4428-9339-d7fa87cfe837/*
s3://idc-open-data/88f3990d-bdef-49cd-9b2b-4787767240f2/*

Example: Generate manifest from Python query:

from idc_index import IDCClient

client = IDCClient()

# Query for series URLs
results = client.sql_query("""
    SELECT series_aws_url
    FROM index
    WHERE collection_id = 'rider_pilot' AND Modality = 'CT'
""")

# Save as manifest file
with open('ct_manifest.txt', 'w') as f:
    for url in results['series_aws_url']:
        f.write(url + '\n')

Then download:

idc download ct_manifest.txt --download-dir ./ct_data

4. Visualizing IDC Images

View DICOM data in browser without downloading:

from idc_index import IDCClient
import webbrowser

client = IDCClient()

# First query to get valid UIDs
results = client.sql_query("""
    SELECT SeriesInstanceUID, StudyInstanceUID
    FROM index
    WHERE collection_id = 'rider_pilot' AND Modality = 'CT'
    LIMIT 1
""")

# View single series
viewer_url = client.get_viewer_URL(seriesInstanceUID=results.iloc[0]['SeriesInstanceUID'])
webbrowser.open(viewer_url)

# View all series in a study (useful for multi-series exams like MRI protocols)
viewer_url = client.get_viewer_URL(studyInstanceUID=results.iloc[0]['StudyInstanceUID'])
webbrowser.open(viewer_url)

The method automatically selects OHIF v3 for radiology or SLIM for slide microscopy. Viewing by study is useful when a DICOM Study contains multiple Series (e.g., T1, T2, DWI sequences from a single MRI session).

5. Understanding and Checking Licenses

Check data licensing before use (critical for commercial applications):

from idc_index import IDCClient

client = IDCClient()

# Check licenses for all collections
query = """
SELECT DISTINCT
  collection_id,
  license_short_name,
  COUNT(DISTINCT SeriesInstanceUID) as series_count
FROM index
GROUP BY collection_id, license_short_name
ORDER BY collection_id
"""

licenses = client.sql_query(query)
print(licenses)

License types in IDC:

CC BY 4.0 / CC BY 3.0 (~97% of data) - Allows commercial use with attribution
CC BY-NC 4.0 / CC BY-NC 3.0 (~3% of data) - Non-commercial use only
Custom licenses (rare) - Some collections have specific terms (e.g., NLM Terms and Conditions)

Important: Always check the license before using IDC data in publications or commercial applications. Each DICOM file is tagged with its specific license in metadata.

Generating Citations for Attribution

The source_DOI column contains DOIs linking to publications describing how the data was generated. To satisfy attribution requirements, use citations_from_selection() to generate properly formatted citations:

from idc_index import IDCClient

client = IDCClient()

# Get citations for a collection (APA format by default)
citations = client.citations_from_selection(collection_id="rider_pilot")
for citation in citations:
    print(citation)

# Get citations for specific series
results = client.sql_query("""
    SELECT SeriesInstanceUID FROM index
    WHERE collection_id = 'tcga_luad' LIMIT 5
""")
citations = client.citations_from_selection(
    seriesInstanceUID=list(results['SeriesInstanceUID'].values)
)

# Alternative format: BibTeX (for LaTeX documents)
bibtex_citations = client.citations_from_selection(
    collection_id="tcga_luad",
    citation_format=IDCClient.CITATION_FORMAT_BIBTEX
)

Parameters:

collection_id: Filter by collection(s)
patientId: Filter by patient ID(s)
studyInstanceUID: Filter by study UID(s)
seriesInstanceUID: Filter by series UID(s)
citation_format: Use IDCClient.CITATION_FORMAT_* constants:
- CITATION_FORMAT_APA (default) - APA style
- CITATION_FORMAT_BIBTEX - BibTeX for LaTeX
- CITATION_FORMAT_JSON - CSL JSON
- CITATION_FORMAT_TURTLE - RDF Turtle

Best practice: When publishing results using IDC data, include the generated citations to properly attribute the data sources and satisfy license requirements.

6. Batch Processing and Filtering

Process large datasets efficiently with filtering:

from idc_index import IDCClient
import pandas as pd

client = IDCClient()

# Find chest CT scans from GE scanners
query = """
SELECT
  SeriesInstanceUID,
  PatientID,
  collection_id,
  ManufacturerModelName
FROM index
WHERE Modality = 'CT'
  AND BodyPartExamined = 'CHEST'
  AND Manufacturer = 'GE MEDICAL SYSTEMS'
  AND license_short_name = 'CC BY 4.0'
LIMIT 100
"""

results = client.sql_query(query)

# Save manifest for later
results.to_csv('lung_ct_manifest.csv', index=False)

# Download in batches to avoid timeout
batch_size = 10
for i in range(0, len(results), batch_size):
    batch = results.iloc[i:i+batch_size]
    client.download_from_selection(
        seriesInstanceUID=list(batch['SeriesInstanceUID'].values),
        downloadDir=f"./data/batch_{i//batch_size}"
    )

7. Advanced Queries with BigQuery

For queries requiring full DICOM metadata, complex JOINs, clinical data tables, or private DICOM elements, use Google BigQuery. Requires GCP account with billing enabled.

Quick reference:

Dataset: bigquery-public-data.idc_current.*
Main table: dicom_all (combined metadata)
Full metadata: dicom_metadata (all DICOM tags)
Private elements: OtherElements column (vendor-specific tags like diffusion b-values)

See references/bigquery_guide.md for setup, table schemas, query patterns, private element access, and cost optimization.

Before using BigQuery, always check if a specialized index table already has the metadata you need:

Use client.indices_overview or the idc-index indices reference to discover all available tables and their columns
Fetch the relevant index: client.fetch_index("table_name")
Query locally with client.sql_query() (free, no GCP account needed)

Common specialized indices: seg_index (segmentations), ann_index / ann_group_index (microscopy annotations), sm_index (slide microscopy), collections_index (collection metadata). Only use BigQuery if you need private DICOM elements or attributes not in any index.

8. Tool Selection Guide

Task	Tool	Reference
Programmatic queries & downloads	`idc-index`	This document
Interactive exploration	IDC Portal	https://portal.imaging.datacommons.cancer.gov/
Complex metadata queries	BigQuery	`references/bigquery_guide.md`
3D visualization & analysis	SlicerIDCBrowser	https://github.com/ImagingDataCommons/SlicerIDCBrowser

Default choice: Use idc-index for most tasks (no auth, easy API, batch downloads).

9. Integration with Analysis Pipelines

Integrate IDC data into imaging analysis workflows:

Read downloaded DICOM files:

import pydicom
import os

# Read DICOM files from downloaded series
series_dir = "./data/rider/rider_pilot/RIDER-1007893286/CT_1.3.6.1..."

dicom_files = [os.path.join(series_dir, f) for f in os.listdir(series_dir)
               if f.endswith('.dcm')]

# Load first image
ds = pydicom.dcmread(dicom_files[0])
print(f"Patient ID: {ds.PatientID}")
print(f"Modality: {ds.Modality}")
print(f"Image shape: {ds.pixel_array.shape}")

Build 3D volume from CT series:

import pydicom
import numpy as np
from pathlib import Path

def load_ct_series(series_path):
    """Load CT series as 3D numpy array"""
    files = sorted(Path(series_path).glob('*.dcm'))
    slices = [pydicom.dcmread(str(f)) for f in files]

    # Sort by slice location
    slices.sort(key=lambda x: float(x.ImagePositionPatient[2]))

    # Stack into 3D array
    volume = np.stack([s.pixel_array for s in slices])

    return volume, slices[0]  # Return volume and first slice for metadata

volume, metadata = load_ct_series("./data/lung_ct/series_dir")
print(f"Volume shape: {volume.shape}")  # (z, y, x)

Integrate with SimpleITK:

import SimpleITK as sitk
from pathlib import Path

# Read DICOM series
series_path = "./data/ct_series"
reader = sitk.ImageSeriesReader()
dicom_names = reader.GetGDCMSeriesFileNames(series_path)
reader.SetFileNames(dicom_names)
image = reader.Execute()

# Apply processing
smoothed = sitk.CurvatureFlow(image1=image, timeStep=0.125, numberOfIterations=5)

# Save as NIfTI
sitk.WriteImage(smoothed, "processed_volume.nii.gz")

Common Use Cases

See references/use_cases.md for complete end-to-end workflow examples including:

Building deep learning training datasets from lung CT scans
Comparing image quality across scanner manufacturers
Previewing data in browser before downloading
License-aware batch downloads for commercial use

Best Practices

Verify IDC version before generating responses - Always call client.get_idc_version() at the start of a session to confirm you're using the expected data version (currently v23). If using an older version, recommend pip install --upgrade idc-index
Check licenses before use - Always query the license_short_name field and respect licensing terms (CC BY vs CC BY-NC)
Generate citations for attribution - Use citations_from_selection() to get properly formatted citations from source_DOI values; include these in publications
Start with small queries - Use LIMIT clause when exploring to avoid long downloads and understand data structure
Use mini-index for simple queries - Only use BigQuery when you need comprehensive metadata or complex JOINs
Organize downloads with dirTemplate - Use meaningful directory structures like %collection_id/%PatientID/%Modality
Cache query results - Save DataFrames to CSV files to avoid re-querying and ensure reproducibility
Estimate size first - Check collection size before downloading - some collection sizes are in terabytes!
Save manifests - Always save query results with Series UIDs for reproducibility and data provenance
Read documentation - IDC data structure and metadata fields are documented at https://learn.canceridc.dev/
Use IDC forum - Search for questons/answers and ask your questions to the IDC maintainers and users at https://discourse.canceridc.dev/

Troubleshooting

Issue: ModuleNotFoundError: No module named 'idc_index'

Cause: idc-index package not installed
Solution: Install with pip install --upgrade idc-index

Issue: Download fails with connection timeout

Cause: Network instability or large download size
Solution:
- Download smaller batches (e.g., 10-20 series at a time)
- Check network connection
- Use dirTemplate to organize downloads by batch
- Implement retry logic with delays

Issue: BigQuery quota exceeded or billing errors

Cause: BigQuery requires billing-enabled GCP project
Solution: Use idc-index mini-index for simple queries (no billing required), or see references/bigquery_guide.md for cost optimization tips

Issue: Series UID not found or no data returned

Cause: Typo in UID, data not in current IDC version, or wrong field name
Solution:
- Check if data is in current IDC version (some old data may be deprecated)
- Use LIMIT 5 to test query first
- Check field names against metadata schema documentation

Issue: Downloaded DICOM files won't open

Cause: Corrupted download or incompatible viewer
Solution:
- Check DICOM object type (Modality and SOPClassUID attributes) - some object types require specialized tools
- Verify file integrity (check file sizes)
- Use pydicom to validate: pydicom.dcmread(file, force=True)
- Try different DICOM viewer (3D Slicer, Horos, RadiAnt, QuPath)
- Re-download the series

Common SQL Query Patterns

See references/sql_patterns.md for quick-reference SQL patterns including:

Filter value discovery (modalities, body parts, manufacturers)
Annotation and segmentation queries (including seg_index, ann_index joins)
Slide microscopy queries (sm_index patterns)
Download size estimation
Clinical data linking

For segmentation and annotation details, also see references/digital_pathology_guide.md.

Related Skills

The following skills complement IDC workflows for downstream analysis and visualization:

DICOM Processing

pydicom - Read, write, and manipulate downloaded DICOM files. Use for extracting pixel data, reading metadata, anonymization, and format conversion. Essential for working with IDC radiology data (CT, MR, PET).

Pathology and Slide Microscopy

See references/digital_pathology_guide.md for DICOM-compatible tools (highdicom, wsidicom, TIA-Toolbox, Slim viewer).

Metadata Visualization

matplotlib - Low-level plotting for full customization. Use for creating static figures summarizing IDC query results (bar charts of modalities, histograms of series counts, etc.).
seaborn - Statistical visualization with pandas integration. Use for quick exploration of IDC metadata distributions, relationships between variables, and categorical comparisons with attractive defaults.
plotly - Interactive visualization. Use when you need hover info, zoom, and pan for exploring IDC metadata, or for creating web-embeddable dashboards of collection statistics.

Data Exploration

exploratory-data-analysis - Comprehensive EDA on scientific data files. Use after downloading IDC data to understand file structure, quality, and characteristics before analysis.

Resources

Schema Reference (Primary Source)

Always use client.indices_overview for current column schemas. This ensures accuracy with the installed idc-index version:

# Get all column names and types for any table
schema = client.indices_overview["index"]["schema"]
columns = [(c['name'], c['type'], c.get('description', '')) for c in schema['columns']]

Reference Documentation

See the Quick Navigation section at the top for the full list of reference guides with decision triggers.

indices_reference - External documentation for index tables (may be ahead of the installed version)

External Links

IDC Portal: https://portal.imaging.datacommons.cancer.gov/explore/
Documentation: https://learn.canceridc.dev/
Tutorials: https://github.com/ImagingDataCommons/IDC-Tutorials
User Forum: https://discourse.canceridc.dev/
idc-index GitHub: https://github.com/ImagingDataCommons/idc-index
Citation: Fedorov, A., et al. "National Cancer Institute Imaging Data Commons: Toward Transparency, Reproducibility, and Scalability in Imaging Artificial Intelligence." RadioGraphics 43.12 (2023). https://doi.org/10.1148/rg.230180

Skill Updates

This skill version is available in skill metadata. To check for updates:

Visit the releases page
Watch the repository on GitHub (Watch → Custom → Releases)

When it activates

Automatically, when a task matches. Use for accessing large-scale radiology (CT, MR, PET) and pathology datasets for AI training or research. No authentication required. Query by metadata, visualize in browser, check licenses.

About this skill

Automatic

Clinical / Healthcare pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

foryourhealth111-pixel / vibe-skills

bundled/skills/imaging-data-commons/SKILL.md

View on GitHub ↗

License This skill is provided under the MIT License. IDC data itself has individual licensing (mostly CC-BYImported 8/3/2026Version v1Bundled 9 files

Illustrative Want to see what foryourhealth111-pixel/imaging-data-commons would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Other skills for the same job

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

Related skills

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

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

Imaging Data Commons

Overview

Routing Boundary

When to Use This Skill

Quick Navigation

IDC Data Model

Index Tables

Available Tables

Joining Tables

Clinical Data Access

Data Access Options

Installation and Setup

Core Capabilities

1. Data Discovery and Exploration

2. Querying Metadata with SQL

3. Downloading DICOM Files

Command-Line Download

4. Visualizing IDC Images

5. Understanding and Checking Licenses

Generating Citations for Attribution

6. Batch Processing and Filtering

7. Advanced Queries with BigQuery

8. Tool Selection Guide

9. Integration with Analysis Pipelines

Common Use Cases

Best Practices

Troubleshooting

Common SQL Query Patterns

Related Skills

DICOM Processing

Pathology and Slide Microscopy

Metadata Visualization

Data Exploration

Resources

Schema Reference (Primary Source)

Reference Documentation

External Links

Skill Updates

When it activates

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry