Ready to supercharge your AI agents?

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

Cancer Cell Line Profiling and Selection · mims-harvard | DecimalAI

Scienceby mims-harvard

Cancer Cell Line Profiling and Selection

Cancer cell-line selection and profiling for experimental model choice. Cross-references DepMap, Cellosaurus, COSMIC, PharmacoDB to deliver identity verification, mutation/CNV profile, gene dependencies, drug sensitivities, and druggable targets. Use to answer 'which cell line should I use for studying gene X?' or 'is this cell line a good model for cancer Y?'. Outputs ranked recommendations with rationale, growth characteristics, and known pitfalls.

Maintained

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

70%43%of test cases passed -26 pts

Without skill16 of 23

With skill10 of 23

2 fixed8 passed either way5 still failing8 broke

Measured on gemini-3.6-flash9/7/2026v2 · latest is v311 comparable

This benchmark measured an earlier version of the skill.

Track record

Agent runs: 0; All time

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 tooluniverse-cell-line-profiling
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("tooluniverse-cell-line-profiling")
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 tooluniverse-cell-line-profiling

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/tooluniverse-cell-line-profiling/SKILL.md https://app.decimal.ai/s/tooluniverse-cell-line-profiling/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/tooluniverse-cell-line-profiling/SKILL.md

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

Other ways to add it

Claude Code docs

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

Install

pip install "decimalai[claude-agent-sdk]"
decimalai skills add tooluniverse-cell-line-profiling

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("tooluniverse-cell-line-profiling")
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/tooluniverse-cell-line-profiling/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/tooluniverse-cell-line-profiling/SKILL.md").read_text()
options = ClaudeAgentOptions(system_prompt=f"You are a helpful agent.\n\n{skill}", max_turns=6)

async def main():
    async for message in query(prompt="Hello!", options=options):
        print(message)

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

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

Other ways to add it

Claude Agent SDK docs

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

Install

pip install "decimalai[openai-agents]"
decimalai skills add tooluniverse-cell-line-profiling

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("tooluniverse-cell-line-profiling")
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/tooluniverse-cell-line-profiling/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/tooluniverse-cell-line-profiling/SKILL.md").read_text()
agent = Agent(name="support", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")

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

Other ways to add it

OpenAI Agents docs

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

Install

pip install "decimalai[openai]"
decimalai skills add tooluniverse-cell-line-profiling

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("tooluniverse-cell-line-profiling")
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/tooluniverse-cell-line-profiling/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/tooluniverse-cell-line-profiling/SKILL.md").read_text()
reply = client.chat.completions.create(
    model="gpt-5.4-mini",
    messages=[
        {"role": "system", "content": f"You are a helpful agent.\n\n{skill}"},
        {"role": "user", "content": "Hello!"},
    ],
).choices[0].message

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

Other ways to add it

OpenAI SDK docs

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

Install

pip install "decimalai[anthropic]"
decimalai skills add tooluniverse-cell-line-profiling

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("tooluniverse-cell-line-profiling")
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/tooluniverse-cell-line-profiling/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/tooluniverse-cell-line-profiling/SKILL.md").read_text()
reply = client.messages.create(
    model="claude-haiku-5-5",
    max_tokens=4096,
    system=f"You are a helpful agent.\n\n{skill}",
    messages=[{"role": "user", "content": "Hello!"}],
)

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

Other ways to add it

Anthropic docs

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

Install

pip install "decimalai[google-genai]"
decimalai skills add tooluniverse-cell-line-profiling

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("tooluniverse-cell-line-profiling")
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/tooluniverse-cell-line-profiling/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/tooluniverse-cell-line-profiling/SKILL.md").read_text()
response = client.models.generate_content(
    model="gemini-3.5-flash",
    contents="Hello!",
    config=types.GenerateContentConfig(system_instruction=f"You are a helpful agent.\n\n{skill}"),
)

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

Other ways to add it

Gemini API docs

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

Install

pip install "decimalai[langchain]" langchain-openai
decimalai skills add tooluniverse-cell-line-profiling

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("tooluniverse-cell-line-profiling")
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/tooluniverse-cell-line-profiling/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/tooluniverse-cell-line-profiling/SKILL.md").read_text()
agent = create_agent("openai:gpt-5.4-mini", tools=[], system_prompt=f"You are a helpful agent.\n\n{skill}")
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

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

Other ways to add it

LangChain docs

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

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add tooluniverse-cell-line-profiling

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("tooluniverse-cell-line-profiling")
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/tooluniverse-cell-line-profiling/SKILL.md

Give it to your agent

from pathlib import Path
from crewai import Agent, Crew, Task

agent = Agent(
    role="Support", goal="Help the customer", backstory="A support agent.",
    llm=llm,                         # your own CrewAI LLM
    skills=[Path(".agents/skills")],
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()

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

Other ways to add it

CrewAI docs

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

Install

pip install "decimalai[adk]"
decimalai skills add tooluniverse-cell-line-profiling

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("tooluniverse-cell-line-profiling")
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/tooluniverse-cell-line-profiling/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/tooluniverse-cell-line-profiling/SKILL.md").read_text()
agent = LlmAgent(
    name="support",
    model="gemini-3.5-flash",
    instruction=lambda context: f"You are a helpful agent.\n\n{skill}",
)

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

Other ways to add it

Google ADK docs

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

Install

pip install "decimalai[pydantic-ai]"
decimalai skills add tooluniverse-cell-line-profiling

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("tooluniverse-cell-line-profiling")
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/tooluniverse-cell-line-profiling/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/tooluniverse-cell-line-profiling/SKILL.md").read_text()
agent = Agent("openai:gpt-4o-mini", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")

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

Other ways to add it

Pydantic AI docs

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

Install

pip install "decimalai>=0.16" deepagents
decimalai skills add tooluniverse-cell-line-profiling

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("tooluniverse-cell-line-profiling")
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/tooluniverse-cell-line-profiling/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/tooluniverse-cell-line-profiling/SKILL.md").read_text()
agent = create_deep_agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})

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

Other ways to add it

Deep Agents docs

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

Install

pip install "decimalai>=0.16" agent-framework
decimalai skills add tooluniverse-cell-line-profiling

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("tooluniverse-cell-line-profiling")
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/tooluniverse-cell-line-profiling/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/tooluniverse-cell-line-profiling/SKILL.md").read_text()
agent = Agent(client=client, instructions=f"You are a helpful agent.\n\n{skill}")
asyncio.run(agent.run("Hello!"))

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

Other ways to add it

Microsoft Agent Framework docs

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

Install

pip install "decimalai>=0.16" strands-agents
decimalai skills add tooluniverse-cell-line-profiling

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("tooluniverse-cell-line-profiling")
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/tooluniverse-cell-line-profiling/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/tooluniverse-cell-line-profiling/SKILL.md").read_text()
agent = Agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent("Hello!")

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

Other ways to add it

Strands docs

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

pip install "decimalai>=0.15"
decimalai skills add tooluniverse-cell-line-profiling

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/tooluniverse-cell-line-profiling/SKILL.md https://app.decimal.ai/s/tooluniverse-cell-line-profiling/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/tooluniverse-cell-line-profiling/SKILL.md

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

Other ways to add it

Cursor and other editors docs

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

Get the file

curl -fsSL https://app.decimal.ai/s/tooluniverse-cell-line-profiling/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/tooluniverse-cell-line-profiling.json

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

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v3 (v2 tested 9/7/2026)
Source: mims-harvard/ToolUniverse ↗
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

Cancer Cell Line Profiling and Selection

Comprehensive profiling of cancer cell lines for experimental model selection. Transforms a query (cancer type, gene, or cell line name) into an actionable report covering identity verification, molecular features, gene dependencies, drug sensitivities, and druggable targets.

KEY PRINCIPLES:

Decision-first - Answer "which cell line should I use?" not "here is all the data"
Multi-source validation - Cross-reference DepMap, Cellosaurus, COSMIC, PharmacoDB
Actionable output - Ranked cell line recommendations with rationale
Practical focus - Include availability, growth characteristics, common pitfalls
Gene-aware - When a gene of interest is given, prioritize lines with relevant mutations/dependencies
Source-referenced - Cite database sources for every claim
English-first queries - Always use English terms in tool calls, even if the user writes in another language

LOOK UP, DON'T GUESS

When uncertain about any scientific fact, SEARCH databases first rather than reasoning from memory. A database-verified answer is always more reliable than a guess.

COMPUTE, DON'T DESCRIBE

When analysis requires computation (statistics, data processing, scoring, enrichment), write and run Python code via Bash. Don't describe what you would do — execute it and report actual results. Use ToolUniverse tools to retrieve data, then Python (pandas, scipy, statsmodels, matplotlib) to analyze it.

When to Use

Apply for: cell line selection by cancer type/gene, cell line profiling, gene dependencies, drug sensitivity queries, cell line comparisons, mutation checks.

Phase 0: Tool Parameter Reference (CRITICAL)

BEFORE calling ANY tool, verify parameters against this table.

Tool	Key Parameters	Notes
`DepMap_search_cell_lines`	`query` (required)	Search by name, e.g., "A549", "MCF"
`DepMap_get_cell_line`	`model_name` OR `model_id`	Name: "A549"; ID: "SIDM00001"
`DepMap_get_cell_lines`	`tissue`, `cancer_type`, `page_size`	Filter by tissue (e.g., "Lung")
`DepMap_get_gene_dependencies`	`gene_symbol` (required), `model_id`	Gene effect scores; negative = essential
`DepMap_search_genes`	`query` (required)	Validate gene symbol in DepMap first
`cellosaurus_search_cell_lines`	`q` (required), `size`	Solr syntax: `id:HeLa`, `ox:9606 AND char:cancer`
`cellosaurus_get_cell_line_info`	`accession` (required, CVCL_ format)	Full cell line record
`cellosaurus_query_converter`	`query` (required)	Natural language to Solr syntax
`COSMIC_search_mutations`	`terms` OR `query`, `max_results`	Search "BRAF V600E" or gene name
`COSMIC_get_mutations_by_gene`	`gene` OR `gene_name`, `max_results`	All mutations for a gene
`PharmacoDB_get_cell_line`	`operation="get_cell_line"`, `cell_name`	Cell line metadata + datasets
`PharmacoDB_get_experiments`	`operation="get_experiments"`, `compound_name`, `cell_line_name`, `dataset_name`, `per_page`	Drug response data (IC50, AAC, EC50)
`PharmacoDB_get_biomarker_assoc`	`operation="get_biomarker_associations"`, `compound_name`, `tissue_name`, `mdata_type`, `per_page`	Gene-drug sensitivity correlations
`PharmacoDB_search`	`operation="search"`, `query`	Find PharmacoDB IDs
`CellMarker_search_cancer_markers`	`operation="search_cancer_markers"`, `cancer_type`, `gene_symbol`, `cell_type`	Cancer cell markers
`CellMarker_search_by_gene`	`operation="search_by_gene"`, `gene_symbol` (required), `species`	Cell types expressing a gene
`HPA_get_comparative_expression_by_gene_and_cellline`	`gene_name` (required), `cell_line` (required)	Supported lines: ishikawa, hela, mcf7, a549, hepg2, jurkat, pc3, rh30, siha, u251
`SYNERGxDB_search_combos`	`drug_name_1`, `drug_name_2`, `sample` (tissue or cell ID)	Drug combination synergy (ZIP, Bliss, Loewe)
`SYNERGxDB_list_cell_lines`	-	All cell lines in SYNERGxDB
`DGIdb_get_drug_gene_interactions`	`genes: list[str]`	Druggable gene interactions
`OpenTargets_get_associated_drugs_by_target_ensemblID`	`ensemblId`, `size`	Drugs targeting a gene
`STRING_get_network`	`protein_ids: list[str]`, `species: int` (9606)	PPI network for gene context
`MyGene_query_genes`	`query` (NOT `q`)	Resolve gene symbol to Ensembl ID
`cBioPortal_get_mutations`	`study_id`, `gene_list` (STRING, not array)	Cell line mutations from CCLE

Workflow Overview

Input: Cancer type AND/OR Gene of interest AND/OR Cell line name(s)

Phase 1: Cell Line Identification
  - Search and verify cell line identity (Cellosaurus)
  - Get metadata: species, disease, STR profile, cross-references
  - If cancer type given without cell line: find candidate lines (DepMap)

Phase 2: Molecular Profiling
  - Mutation landscape (COSMIC, cBioPortal CCLE)
  - Gene expression (HPA, DepMap)
  - Cancer markers (CellMarker)

Phase 3: Gene Dependencies (CRISPR Screens)
  - Gene essentiality scores from DepMap
  - Identify selectively essential genes
  - Compare across cell lines if multiple candidates

Phase 4: Drug Sensitivity
  - IC50/AAC from PharmacoDB (GDSC, CCLE, CTRPv2, PRISM)
  - Biomarker associations for drug response
  - Drug combination synergy (SYNERGxDB)

Phase 5: Target Druggability & Recommendations
  - Druggable targets (DGIdb, OpenTargets)
  - Final ranked recommendation with rationale

Phase 1: Cell Line Identification

Goal: Verify cell line identity and find candidates.

If specific cell line given: (1) cellosaurus_search_cell_lines(q="id:<NAME>") → get CVCL accession, species, disease, contamination flags. (2) cellosaurus_get_cell_line_info(accession="CVCL_XXXX") for STR profile. (3) DepMap_get_cell_line(model_name="...") for tissue, cancer_type, MSI, ploidy. (4) PharmacoDB_get_cell_line(operation="get_cell_line", cell_name="...") for datasets.

If cancer type only: (1) DepMap_get_cell_lines(tissue="Lung", page_size=20). (2) Narrow by gene mutations/dependencies in Phases 2-3. (3) CellMarker_search_cancer_markers(operation="search_cancer_markers", cancer_type="Lung").

OUTPUT: Table of candidate cell lines with: name, tissue, cancer type, key identifiers.

Phase 2: Molecular Profiling

Goal: Characterize mutational and expression landscape.

2A Mutations: COSMIC_get_mutations_by_gene(gene="EGFR") + cBioPortal_get_mutations(study_id="ccle_broad_2019", gene_list="EGFR,KRAS,TP53"). Note: gene_list is a comma-separated STRING. CCLE study ID: ccle_broad_2019.

2B Expression: HPA_get_comparative_expression_by_gene_and_cellline(gene_name="EGFR", cell_line="a549"). Only 10 lines supported: hela, mcf7, a549, hepg2, jurkat, pc3, rh30, siha, u251, ishikawa.

2C Cancer markers: CellMarker_search_by_gene(operation="search_by_gene", gene_symbol="EGFR", species="Human")

OUTPUT: Mutation table (gene, AA change, type) + expression summary per cell line.

Phase 3: Gene Dependencies (CRISPR Screens)

Goal: Determine which genes are essential in candidate cell lines.

LIMITATION: DepMap_get_gene_dependencies returns gene metadata (HGNC ID, Ensembl ID) but NOT per-cell-line CRISPR scores. Full Chronos scores require depmap.org download.

Available tools: (1) DepMap_search_genes(query="EGFR") — validate gene exists. (2) DepMap_get_gene_dependencies(gene_symbol="EGFR") — metadata only. (3) Alternatives: cBioPortal CCLE for mutation data, PubMed for published screens, or direct user to depmap.org/portal.

Interpreting Chronos scores (from DepMap portal): <-0.5 = essential; ~0 = not essential; ~-1.0 = strongly essential. Selective dependency (essential in some lineages only) indicates therapeutic window.

OUTPUT: Gene validation + mutation status per cell line.

Per-cell-line Chronos scores (what the API can't give you): use the bundled script scripts/depmap_gene_dependency.py. It pulls the current DepMap Public release (CRISPRGeneEffect.csv + Model.csv) once via the public download index, caches it, and answers the dependency question directly: NOTE (2026-09-21): DepMap's download index now answers with a bot-check page instead of the file list; the script reports that (exit 2) rather than bypassing it. Download CRISPRGeneEffect.csv and Model.csv from https://depmap.org/portal/download/all/ in a browser and put them in the cache directory ($DEPMAP_CACHE_DIR, default <tmp>/depmap_cache); cached files are used without contacting DepMap.

# Cell lines most dependent on a gene (optionally within a lineage)
python scripts/depmap_gene_dependency.py gene KRAS --lineage Pancreas --top 20
# Genes a given cell line is most dependent on
python scripts/depmap_gene_dependency.py cell-line A375 --top 25

Output: cell line, lineage, primary disease, Chronos score (most negative = most dependent; < -0.5 ≈ dependency). For selective-dependency reasoning, compare a gene's scores across lineages.

If DepMap data is unavailable: Use cBioPortal_get_mutations(study_id="ccle_broad_2019", gene_list="KRAS") for mutation data, and the Quick Reference table below for common recommendations.

Phase 4: Drug Sensitivity

Goal: Profile drug response data.

4A PharmacoDB: PharmacoDB_get_experiments(operation="get_experiments", compound_name="Erlotinib", cell_line_name="A549", per_page=20) for dose-response (IC50, AAC, EC50). Omit compound_name to get all drugs for a cell line. Use PharmacoDB_get_biomarker_assoc(compound_name="...", tissue_name="...", mdata_type="mutation") for sensitivity biomarkers.

4B SYNERGxDB: SYNERGxDB_search_combos(drug_name_1="gemcitabine", drug_name_2="erlotinib", sample="lung"). Positive ZIP = synergy. Covers cytotoxic agents only (not targeted therapies/biologics).

OUTPUT: Drug sensitivity table (drug, IC50, AAC, dataset) + synergy data if available.

Phase 5: Target Druggability and Recommendations

5A Druggability: DGIdb_get_drug_gene_interactions(genes=["EGFR", "KRAS"]) + MyGene_query_genes(query="EGFR") → OpenTargets_get_associated_drugs_by_target_ensemblID(ensemblId="...", size=10) + STRING_get_network(protein_ids=["EGFR"], species=9606).

5B Final Recommendation: Synthesize all phases. Explain WHY one line is better for this specific use case.

Decision Criteria with Concrete Thresholds

Criterion	Weight	Score 3 (Best)	Score 2 (Acceptable)	Score 1 (Poor)
Mutation match	x3	Exact mutation (e.g., KRAS G12D)	Same gene, different mutation	No mutation in gene of interest
Co-mutation simplicity	x2	Few co-mutations (cleaner background)	Moderate co-mutations	Complex background (3+ driver mutations)
Gene dependency	x2	DepMap score < -0.5 (essential)	Score -0.5 to -0.2 (moderately essential)	Score > -0.2 (not essential)
Drug sensitivity data	x1	In GDSC + CCLE + PRISM (3+ datasets)	In 1-2 datasets	No drug response data
Practical factors	x1	Adherent, well-characterized, widely used	Suspension or less common	Hard to culture, contamination-prone

Total score = sum of (criterion score × weight). Max = 27. Rank cell lines by total score.

Use-Case-Specific Guidance

The best cell line depends on what you're doing with it:

Use Case	Key Requirements	Extra Considerations
CRISPR knockout screen	Adherent growth, good lentiviral transduction, pre-existing Cas9 clones (check Cellosaurus for "-Cas9" derivatives)	Doubling time matters for library coverage; <72h ideal
Drug sensitivity testing	In PharmacoDB/GDSC, known IC50 for reference compounds	Check SYNERGxDB for combo data
Xenograft model	Known tumorigenicity in mice, available PDX data	Check if line forms tumors in nude/NSG mice (Cellosaurus often notes this)
Mechanism of action	Clean genetic background, gene dependency confirmed	Fewer co-mutations = easier to attribute phenotypes
Biomarker discovery	Isogenic pairs available, well-characterized omics	Check if isogenic knockouts exist (Cellosaurus)
Drug combination	In SYNERGxDB with combo data, known single-agent responses	ZIP score available for synergy assessment

Cellosaurus Derivative Lines

Check for pre-made derivatives — this can save months of lab work:

cellosaurus_search_cell_lines(q="ca:<PARENT_LINE>", size=20) — finds all derivatives
Look for: Cas9-expressing clones, drug-resistant derivatives, knockout lines, fluorescent reporter lines
Example: PANC-1-Cas9-554 through PANC-1-Cas9-559 (CVCL_WL48-WL53) are pre-validated Cas9 clones

DepMap API Fallbacks

If DepMap_get_gene_dependencies fails (common for some genes):

The Sanger Cell Model Passports API may not index all genes. Note this limitation.
Recommend the user check DepMap portal (depmap.org) directly for CRISPR dependency data.
Use cBioPortal_get_mutations(study_id="ccle_broad_2019", gene_list="<GENE>") as an alternative source for cell line mutation data.

OUTPUT: Ranked cell line table with total scores, per-criterion breakdown, and a text recommendation explaining the top pick and runner-up with biological reasoning.

Common Use Patterns

Pattern	Question Type	Key Tools (in order)
1	"Which cell line for [cancer] + [gene]?"	DepMap_get_cell_lines → DepMap_get_gene_dependencies → COSMIC_get_mutations_by_gene → cBioPortal_get_mutations (ccle_broad_2019) → PharmacoDB_get_experiments → rank by mutation + dependency + drug sensitivity
2	"Profile cell line X"	cellosaurus_search → DepMap_get_cell_line → PharmacoDB_get_cell_line → cBioPortal_get_mutations → HPA expression (if supported) → PharmacoDB_get_experiments
3	"Which lines are sensitive to [drug]?"	DepMap_get_cell_lines (tissue filter) → PharmacoDB_get_experiments (compound) → PharmacoDB_get_biomarker_assoc → rank by AAC (higher=sensitive) or IC50 (lower=sensitive)
4	"Compare A vs B"	Run Pattern 2 for both in parallel → side-by-side comparison table
5	"Drug combos for [cell line]?"	SYNERGxDB_search_combos → PharmacoDB_get_experiments (single-agent baseline) → report synergistic pairs with ZIP scores

Quick Reference: Common Cancer Cell Lines by Type

Cancer Type	Key Cell Lines	Common Mutations
NSCLC	A549 (KRAS G12S), H1975 (EGFR L858R/T790M), PC-9 (EGFR del19), HCC827 (EGFR del19/amp), H460 (KRAS Q61H), H1299 (NRAS Q61K, TP53-null)	KRAS, EGFR, TP53, STK11
Breast	MCF7 (ER+/PR+), MDA-MB-231 (TNBC, KRAS G13D), T-47D (ER+), BT-474 (HER2+), SK-BR-3 (HER2+)	PIK3CA, TP53, BRCA1/2
Colorectal	HCT116 (KRAS G13D, MSI-H), SW480 (KRAS G12V), HT-29 (BRAF V600E), Caco-2 (APC), LoVo (KRAS G13D, MSI-H)	APC, KRAS, TP53, BRAF
Melanoma	A375 (BRAF V600E), SK-MEL-28 (BRAF V600E), WM266-4 (BRAF V600D), MeWo (WT BRAF)	BRAF, NRAS, TP53
Pancreatic	PANC-1 (KRAS G12D), MIA PaCa-2 (KRAS G12C), AsPC-1 (KRAS G12D), Capan-1 (BRCA2 mut)	KRAS, TP53, CDKN2A, SMAD4
Prostate	PC-3 (AR-negative), LNCaP (AR+, PTEN-null), DU145 (AR-negative), VCaP (AR amp, TMPRSS2-ERG)	AR, PTEN, TP53, RB1
Ovarian	SKOV3 (HER2+, TP53 mut), OVCAR3 (TP53 mut), A2780 (sensitive), A2780cis (cisplatin-resistant)	TP53, BRCA1/2
Leukemia	K562 (CML, BCR-ABL), Jurkat (T-ALL), HL-60 (AML), THP-1 (AML, monocytic)	BCR-ABL, FLT3, NPM1
Glioblastoma	U251 (TP53 mut), U87MG (PTEN-null), T98G (TP53/PTEN mut), LN229 (TP53 mut, PTEN WT)	TP53, PTEN, EGFR, IDH1
Liver	HepG2 (hepatoblastoma, WT TP53), Hep3B (HBV+, TP53-null), Huh7 (HCC, TP53 Y220C)	TP53, CTNNB1, AXIN1

Cross-Referencing Cell Line IDs

Use cell line NAME as common key across databases. IDs: DepMap=SIDM, Cellosaurus=CVCL, cBioPortal=sample (e.g. A549_LUNG), PharmacoDB/SYNERGxDB=name string. When names differ ("HCT 116" vs "HCT116"), check Cellosaurus synonyms first.

Mutation-based filtering: cBioPortal_get_mutations(study_id="ccle_broad_2019", gene_list="KRAS") → filter by amino_acid_change → extract cell line names → query other databases.

Error Handling

Issue	Resolution
DepMap returns no results for cell line name	Try alternative names: check Cellosaurus synonyms first
cBioPortal CCLE study ID unknown	Use `ccle_broad_2019` as default CCLE study
PharmacoDB cell line name mismatch	Use `PharmacoDB_search(operation="search", query="<name>")` to find the canonical name
HPA cell line not supported	Only 10 lines supported (hela, mcf7, a549, hepg2, jurkat, pc3, rh30, siha, u251, ishikawa). Skip HPA for other lines
Gene symbol not found in DepMap	Use `DepMap_search_genes(query="<symbol>")` to check aliases
Cellosaurus accession pattern	Must be CVCL_XXXX format; search first if you only have a name
SYNERGxDB no results for drug combo	Drug may not be in database; SYNERGxDB covers cytotoxic agents, not most targeted therapies

Completeness Checklist

Before finalizing the report, verify:

Cell line identity verified (Cellosaurus or DepMap)
Species confirmed as human (unless otherwise specified)
Key mutations documented (COSMIC or cBioPortal)
Gene dependency assessed (DepMap CRISPR, if gene of interest provided)
Drug sensitivity data included (PharmacoDB, at least one dataset)
Druggability of key targets checked (DGIdb or OpenTargets)
Practical recommendation provided (not just raw data)
All claims cite their source database
Known limitations noted (missing data, unsupported lines)

About this skill

On-demandOn-demand: invoked explicitly — never occupies your agent's context until called.

Research pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v8 — 10/29/2026

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

mims-harvard / ToolUniverse

skills/tooluniverse-cell-line-profiling/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 10/29/2026Version v3Bundled 1 file · scripts

Illustrative Want to see what tooluniverse-cell-line-profiling 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.

mims-harvard/tooluniverse-cell-line-profilingCancer cell-line selection and profiling for experimental model choice. Cross-references DepMap, Cellosaurus, COSMIC, PharmacoDB to deliver identity verification, mutation/CNV profile, gene dependencies, drug sensitivities, and druggable targets. Use to answer 'which cell line should I use for studying gene X?' or 'is this cell line a good model for cancer Y?'. Outputs ranked recommendations with rationale, growth characteristics, and known pitfalls.Near-identical description+26 pts pass-rate lift

Related skills

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

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

Safety

What it changes

Track record

Use this skill

Cancer Cell Line Profiling and Selection

LOOK UP, DON'T GUESS

COMPUTE, DON'T DESCRIBE

When to Use

Phase 0: Tool Parameter Reference (CRITICAL)

Workflow Overview

Phase 1: Cell Line Identification

Phase 2: Molecular Profiling

Phase 3: Gene Dependencies (CRISPR Screens)

Phase 4: Drug Sensitivity

Phase 5: Target Druggability and Recommendations

Decision Criteria with Concrete Thresholds

Use-Case-Specific Guidance

Cellosaurus Derivative Lines

DepMap API Fallbacks

Common Use Patterns

Quick Reference: Common Cancer Cell Lines by Type

Cross-Referencing Cell Line IDs

Error Handling

Completeness Checklist

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry