Ready to supercharge your AI agents?

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

Data Wrangling: Universal Access Patterns · mims-harvard | DecimalAI

Scienceby mims-harvard

Data Wrangling: Universal Access Patterns

Universal data access patterns for downloading and parsing scientific data when ToolUniverse tools don't cover the source, only return metadata, or you need bulk records.

Maintained

SkillScore

SkillScore17/100

Test results 17

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

9%17%of test cases passed +9 pts

Without skill2 of 23

With skill4 of 23

2 fixed2 passed either way19 still failing0 broke

Measured on gemini-3.6-flash7/27/2026v1 · latest is v218 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-data-wrangling
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-data-wrangling")
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-data-wrangling

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-data-wrangling/SKILL.md https://app.decimal.ai/s/tooluniverse-data-wrangling/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/tooluniverse-data-wrangling/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-data-wrangling

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-data-wrangling")
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-data-wrangling/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-data-wrangling/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-data-wrangling

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-data-wrangling")
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-data-wrangling/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/tooluniverse-data-wrangling/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-data-wrangling

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-data-wrangling")
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-data-wrangling/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/tooluniverse-data-wrangling/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-data-wrangling

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-data-wrangling")
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-data-wrangling/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/tooluniverse-data-wrangling/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-data-wrangling

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-data-wrangling")
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-data-wrangling/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-data-wrangling/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-data-wrangling

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-data-wrangling")
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-data-wrangling/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/tooluniverse-data-wrangling/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-data-wrangling

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-data-wrangling")
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-data-wrangling/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-data-wrangling

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-data-wrangling")
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-data-wrangling/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/tooluniverse-data-wrangling/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-data-wrangling

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-data-wrangling")
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-data-wrangling/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/tooluniverse-data-wrangling/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-data-wrangling

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-data-wrangling")
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-data-wrangling/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/tooluniverse-data-wrangling/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-data-wrangling

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-data-wrangling")
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-data-wrangling/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/tooluniverse-data-wrangling/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-data-wrangling

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-data-wrangling")
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-data-wrangling/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/tooluniverse-data-wrangling/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-data-wrangling

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-data-wrangling/SKILL.md https://app.decimal.ai/s/tooluniverse-data-wrangling/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/tooluniverse-data-wrangling/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-data-wrangling/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/tooluniverse-data-wrangling.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: v2 (v1 tested 7/27/2026)
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

Data Wrangling: Universal Access Patterns

Reference for downloading and parsing scientific data from any source. Write and run Python code via Bash for every step.

When to Use

ToolUniverse tool returned metadata/search results but you need raw or bulk data
Data is in a format tools don't parse (VCF, h5ad, BAM, SDF, GCT)
You need a multi-step API workflow (search -> filter -> download -> parse)
The data source has no ToolUniverse tool at all
You need thousands of records, not the 10-100 a tool returns

Decision: Tool vs Code

Situation	Use
Single record lookup, simple search, <100 results	ToolUniverse tool (`execute_tool`)
Bulk download, custom filtering, format conversion	Write Python code
Tool exists but returns truncated results	Write code using the same API the tool wraps
No tool exists for this source	Write code directly

Section A: Format Cookbook

Tabular

import pandas as pd, io

df = pd.read_csv("data.csv")                                # CSV
df = pd.read_csv("data.tsv", sep="\t")                      # TSV
df = pd.read_sas(io.BytesIO(content), format="xport")       # SAS Transport (XPT) — NHANES, CDC
df = pd.read_sas("data.sas7bdat", format="sas7bdat")        # SAS native
df = pd.read_stata("data.dta")                               # Stata — ICPSR, HRS
df = pd.read_parquet("data.parquet")                         # Parquet — MIMIC-IV
df = pd.read_excel("data.xlsx")                              # Excel
df = pd.read_spss("data.sav")                                # SPSS
df = pd.read_fwf("data.dat")                                 # Fixed-width — legacy surveys

Genomics

from Bio import SeqIO
records = list(SeqIO.parse("seqs.fasta", "fasta"))           # FASTA
records = list(SeqIO.parse("reads.fastq", "fastq"))          # FASTQ

# VCF (no cyvcf2 needed)
vcf_lines = [l for l in open("vars.vcf") if not l.startswith("##")]
df = pd.read_csv(io.StringIO("".join(vcf_lines)), sep="\t")

df = pd.read_csv("genes.gff3", sep="\t", comment="#",        # GFF/GTF
     names=["seqid","source","type","start","end","score","strand","phase","attrs"])
df = pd.read_csv("regions.bed", sep="\t", header=None,       # BED
     names=["chrom","start","end","name","score","strand"])

import pysam                                                  # BAM (requires pysam)
bam = pysam.AlignmentFile("aligned.bam", "rb")
for read in bam.fetch("chr1", 1000, 2000): print(read.query_name)

Structural

from Bio.PDB import PDBParser, MMCIFParser
parser = PDBParser(QUIET=True)
structure = parser.get_structure("prot", "structure.pdb")     # PDB

parser = MMCIFParser(QUIET=True)
structure = parser.get_structure("prot", "structure.cif")     # mmCIF

from rdkit import Chem                                        # SDF/MOL (requires rdkit)
supplier = Chem.SDMolSupplier("compounds.sdf")
mols = [m for m in supplier if m is not None]

Omics Matrices

import anndata
adata = anndata.read_h5ad("expression.h5ad")                 # AnnData (scRNA-seq, spatial)

import scipy.io
mat = scipy.io.mmread("matrix.mtx")                          # 10X Genomics MTX
barcodes = pd.read_csv("barcodes.tsv", header=None)[0].tolist()
features = pd.read_csv("features.tsv", sep="\t", header=None)[1].tolist()

df = pd.read_csv("expression.gct", sep="\t", skiprows=2)     # GCT (gene expression)

import loompy                                                 # Loom (legacy single-cell)
ds = loompy.connect("data.loom")

Mass Spectrometry & Flow Cytometry

from pyteomics import mzml                                    # mzML (proteomics, requires pyteomics)
spectra = list(mzml.read("spectra.mzML"))

import fcsparser                                              # FCS (flow cytometry, requires fcsparser)
meta, data = fcsparser.parse("sample.fcs", reformat_meta=True)

Neuroimaging

import nibabel as nib                                         # NIfTI (requires nibabel)
img = nib.load("brain.nii.gz")
data = img.get_fdata()  # 3D/4D numpy array

# DICOM (requires pydicom)
import pydicom
dcm = pydicom.dcmread("scan.dcm")
pixel_data = dcm.pixel_array

Phylogenetics & Systems Biology

from Bio import Phylo                                         # Newick/Nexus (BioPython)
tree = Phylo.read("tree.nwk", "newick")
tree = Phylo.read("tree.nex", "nexus")

import libsbml                                                # SBML (systems biology, requires python-libsbml)
reader = libsbml.SBMLReader()
doc = reader.readSBML("model.xml")
model = doc.getModel()

Serialized

import json, xml.etree.ElementTree as ET, h5py

data = json.load(open("data.json"))                           # JSON
df = pd.read_json("records.json")                             # JSON -> DataFrame
tree = ET.parse("data.xml"); root = tree.getroot()            # XML
f = h5py.File("data.h5", "r"); dataset = f["group/data"][:]   # HDF5

Compressed

df = pd.read_csv("data.csv.gz")                              # gzip (pandas auto-detects)
df = pd.read_csv("data.tsv.gz", sep="\t")                    # gzip TSV

import zipfile
with zipfile.ZipFile(io.BytesIO(content)) as z:               # ZIP
    df = pd.read_csv(z.open(z.namelist()[0]))

import tarfile
with tarfile.open("archive.tar.gz") as t:                     # tar.gz
    f = t.extractfile(t.getnames()[0])
    df = pd.read_csv(f)

Section B: API Patterns by Domain

Each category shows: which ToolUniverse tools exist, and how to go beyond them with direct API calls.

1. NCBI E-utilities (Gene, Nucleotide, Protein, SRA, GEO)

Tools: NCBIGene_search, NCBI_search_nucleotide, SRA_search_experiments, geo_search_datasets

import requests
base = "https://eutils.ncbi.nlm.nih.gov/entrez/eutils"
# Search -> get IDs -> fetch records in batches
ids = requests.get(f"{base}/esearch.fcgi?db=gene&term=BRCA1+AND+human&retmax=500&retmode=json").json()
id_list = ids["esearchresult"]["idlist"]
# Fetch in batches of 500
for i in range(0, len(id_list), 500):
    batch = ",".join(id_list[i:i+500])
    data = requests.get(f"{base}/efetch.fcgi?db=gene&id={batch}&retmode=xml").text

2. EBI APIs (UniProt, PDBe, ChEMBL, Ensembl, InterPro)

Tools: UniProt_search, PDBe_*, ChEMBL_*, Ensembl_*, InterPro_*

# UniProt bulk TSV download with cursor pagination
url = "https://rest.uniprot.org/uniprotkb/search?query=organism_id:9606+AND+keyword:kinase&format=tsv&size=500"
all_rows = []
while url:
    resp = requests.get(url)
    all_rows.append(resp.text)
    url = resp.headers.get("Link", "").split(";")[0].strip("<>") if "Link" in resp.headers else None

3. NCI GDC (TCGA/TARGET Cancer Data)

Tools: GDC_search_cases, GDC_list_files, GDC_get_clinical_data

# Bulk clinical data with filters
filters = {"op":"and","content":[
    {"op":"=","content":{"field":"project.project_id","value":"TCGA-BRCA"}},
    {"op":"=","content":{"field":"demographic.vital_status","value":"Dead"}}
]}
cases = requests.post("https://api.gdc.cancer.gov/cases", json={
    "filters": filters, "fields": "demographic.vital_status,diagnoses.days_to_death",
    "size": 1000, "from": 0
}).json()["data"]["hits"]

4. CDC Health Surveys (NHANES, BRFSS, WONDER)

Tools: NHANES_download_and_parse, cdc_data_search_datasets

# Direct NHANES XPT download (any cycle, any component)
cycle, component = "2017-2018", "DEMO_J"
url = f"https://wwwn.cdc.gov/Nchs/Data/Nhanes/Public/2017/DataFiles/{component}.XPT"
df = pd.read_sas(io.BytesIO(requests.get(url).content), format="xport")

5. GWAS & Genetics (GWAS Catalog, gnomAD, ClinVar)

Tools: gwas_search_associations, gnomAD_*, ClinVar_*

# GWAS Catalog full download (37MB TSV, all associations)
url = "https://www.ebi.ac.uk/gwas/api/search/downloads/alternative"
df = pd.read_csv(url, sep="\t")
# Filter locally
hits = df[df["DISEASE/TRAIT"].str.contains("diabetes", case=False, na=False)]

6. Chemical (PubChem, ChEMBL, KEGG)

Tools: PubChem_*, ChEMBL_*, KEGG_*

# PubChem batch property retrieval (up to 100 CIDs at once)
cids = "2244,5988,3672"  # aspirin, sucrose, ibuprofen
url = f"https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/cid/{cids}/property/MolecularWeight,XLogP,TPSA/JSON"
props = requests.get(url).json()["PropertyTable"]["Properties"]

7. Expression (GEO, ArrayExpress, GTEx)

Tools: geo_search_datasets, arrayexpress_search_experiments

# GEO series matrix direct download
geo_id = "GSE12345"
url = f"https://ftp.ncbi.nlm.nih.gov/geo/series/{geo_id[:5]}nnn/{geo_id}/matrix/{geo_id}_series_matrix.txt.gz"
df = pd.read_csv(url, sep="\t", comment="!", index_col=0)

# GTEx bulk expression (median TPM per tissue)
url = "https://storage.googleapis.com/adult-gtex/bulk-gex/v8/rna-seq/GTEx_Analysis_2017-06-05_v8_RNASeQCv1.1.9_gene_median_tpm.gct.gz"
df = pd.read_csv(url, sep="\t", skiprows=2)

8. Clinical (ClinicalTrials.gov, FDA/OpenFDA, FAERS)

Tools: search_clinical_trials, OpenFDA_*

# ClinicalTrials.gov v2 API with pagination
all_studies = []
token = None
while True:
    params = {"query.cond": "lung cancer", "query.intr": "immunotherapy", "pageSize": 100}
    if token: params["pageToken"] = token
    resp = requests.get("https://clinicaltrials.gov/api/v2/studies", params=params).json()
    all_studies.extend(resp.get("studies", []))
    token = resp.get("nextPageToken")
    if not token: break

9. Literature (PubMed, PMC, EuropePMC)

Tools: PubMed_search_articles, EuropePMC_search_articles

# EuropePMC full-text search with cursor
cursor = "*"
all_results = []
while cursor:
    resp = requests.get("https://www.ebi.ac.uk/europepmc/webservices/rest/search",
        params={"query": "BRCA1 AND resistance", "format": "json", "pageSize": 100, "cursorMark": cursor}).json()
    all_results.extend(resp.get("resultList", {}).get("result", []))
    cursor = resp.get("nextCursorMark") if len(all_results) < resp.get("hitCount", 0) else None

10. Data Repositories (Zenodo, Figshare, Dryad, DataCite)

Tools: DataCite_search_dois, Zenodo_search_records, Dryad_search_datasets

# Zenodo: search + download files
record = requests.get("https://zenodo.org/api/records", params={"q": "proteomics cancer", "size": 5}).json()["hits"]["hits"][0]
for f in record["files"]:
    content = requests.get(f["links"]["self"]).content  # download each file

11-24. Specialized Domains

For these 14 additional domains, read references/specialized-domains.md when you need the specific API pattern:

#	Domain	Key APIs/Tools	When to Read
11	Proteomics	PRIDE, MassIVE, ProteomeXchange	Mass spec data download
12	Metabolomics	MetaboLights, Metabolomics Workbench, HMDB	Metabolite/spectra data
13	Microbiome	MGnify, GMREPO	Metagenome profiles
14	Ecology	GBIF, iNaturalist, OBIS	Species occurrence data
15	Model Organisms	FlyBase, WormBase, ZFIN, RGD	Gene data for non-human species
16	Pathways & Networks	Reactome, STRING, BioGRID	Network/pathway export
17	Ontologies	OLS, GO, HPO	Term hierarchy traversal
18	Immunology	IEDB, VDJdb, ImmPort	Epitope/receptor data
19	Drug & Pharma	PharmGKB, DGIdb, SIDER	Drug-gene interactions
20	Imaging & Atlases	TCIA, HPA, Allen Brain Atlas	Imaging collections
21	Protein Structure	RCSB PDB, AlphaFold	PDB/CIF file download
22	Clinical Genomics	ClinVar, ClinGen, CIViC	Variant interpretation bulk
23	Single-Cell	cellxgene, ARCHS4	scRNA-seq data portals
24	Toxicology	CTD, EPA CompTox	Chemical-gene-disease

Section C: Restricted/Uncovered Data Sources

These sources require registration or have no ToolUniverse tool. For each, the table shows access requirements and how to get data programmatically once credentialed.

Note: ToolUniverse has 2,700+ tools — use find_tools("your topic") to discover tools not listed above. Section B covers the most common API patterns; many more databases use the same patterns (e.g., all EBI databases follow the EBI REST pattern in #2).

Source	Access	Wait Time	Format	Contents
UK Biobank	Restricted (institutional)	2-6 months	CSV/Bulk	500K participants, genetics + imaging + health records
dbGaP	Controlled (PI application)	1-3 months	SRA/VCF/phenotype	GWAS genotypes + phenotypes from thousands of studies
MIMIC-IV	Credentialed (PhysioNet)	1-2 weeks	CSV/Parquet	ICU clinical data, 300K+ admissions
ICPSR	Registration	1-3 days	Stata/CSV	Social/health science archives (10K+ studies)
HRS	Registration	1-3 days	Stata	Health & Retirement Study, 20K+ older Americans, biennial
ELSA	Registration	1-3 days	Stata/SPSS	English Longitudinal Study of Ageing
SHARE	Registration	1-2 weeks	Stata	Survey of Health, Ageing, Retirement in Europe (28 countries)
Materials Project	Free API key	Instant	JSON	150K+ computed materials properties
Human Cell Atlas	Open	Instant	h5ad/loom	Single-cell atlas across human tissues
ADNI	Application	1-2 months	DICOM/CSV	Alzheimer's neuroimaging + biomarkers + cognition
OpenNeuro	Open	Instant	NIfTI/BIDS	800+ neuroimaging datasets
CIBERSORTx	Free registration	Instant	GCT/TSV	Cell type deconvolution from bulk expression
FlowRepository	Open	Instant	FCS	Flow cytometry experiments
SynBioHub	Open	Instant	SBOL/GenBank	Synthetic biology parts and designs

For restricted sources: search literature (PubMed) for published analyses using that dataset. Papers cite their data source and often deposit derived data in public repositories (GEO, SRA, Zenodo).

Section D: Universal Patterns

Pagination

# Pattern 1: offset + limit (most REST APIs)
all_records = []
offset = 0
while True:
    resp = requests.get(f"{api_url}?offset={offset}&limit=500", timeout=30).json()
    batch = resp.get("data", resp.get("results", resp.get("hits", [])))
    if not batch: break
    all_records.extend(batch)
    offset += len(batch)

# Pattern 2: cursor/token (EuropePMC, ClinicalTrials.gov, UniProt)
token = None
while True:
    params = {"pageSize": 100}
    if token: params["pageToken"] = token
    resp = requests.get(api_url, params=params).json()
    all_records.extend(resp["results"])
    token = resp.get("nextPageToken")
    if not token: break

Rate Limiting & Retries

import time
def fetch_with_retry(url, max_retries=3, **kwargs):
    for attempt in range(max_retries):
        resp = requests.get(url, timeout=30, **kwargs)
        if resp.status_code == 200: return resp
        if resp.status_code == 429:  # rate limited
            wait = int(resp.headers.get("Retry-After", 2 ** attempt))
            time.sleep(wait)
        else:
            time.sleep(2 ** attempt)
    raise RuntimeError(f"Failed after {max_retries} retries: {url}")

Authentication

import os
# API key in header (most common)
headers = {"Authorization": f"Bearer {os.environ.get('API_KEY', '')}"}
# API key as query param
params = {"api_key": os.environ.get("API_KEY", "")}
# No auth needed for most scientific APIs (NCBI, EBI, PubChem, GDC, CDC)

Bulk Download with Streaming

def download_large_file(url, output_path):
    with requests.get(url, stream=True, timeout=300) as r:
        r.raise_for_status()
        with open(output_path, "wb") as f:
            for chunk in r.iter_content(chunk_size=8192):
                f.write(chunk)

Error Handling

resp = requests.get(url, timeout=30)
if resp.status_code != 200:
    raise ValueError(f"HTTP {resp.status_code}: {resp.text[:200]}")
# Guard against HTML error pages (CDC, NCBI return 200 with HTML for missing files)
if resp.content[:5] in (b"<!DOC", b"<html"):
    raise ValueError(f"Server returned HTML error page for {url}")
data = resp.json()  # raises JSONDecodeError if not valid JSON

When it activates

Only when you call it by name. Your agent never loads it on its own. Use for VCF/h5ad/BAM/SDF/GCT parsing, multi-step API workflows (search to filter to download to parse), thousands of records at once, or sources with no dedicated tool. Write Python code via Bash for every step.

About this skill

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

Data Engineer pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v8 — 11/6/2026

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-data-wrangling/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 11/6/2026Version v2Bundled 1 file

Illustrative Want to see what tooluniverse-data-wrangling 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-data-wranglingUniversal data access patterns for downloading and parsing scientific data when ToolUniverse tools don't cover the source, only return metadata, or you need bulk records. Use for VCF/h5ad/BAM/SDF/GCT parsing, multi-step API workflows (search to filter to download to parse), thousands of records at once, or sources with no dedicated tool. Write Python code via Bash for every step.Near-identical description-9 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?

SkillScore

Safety

What it changes

Track record

Use this skill

Data Wrangling: Universal Access Patterns

When to Use

Decision: Tool vs Code

Section A: Format Cookbook

Tabular

Genomics

Structural

Omics Matrices

Mass Spectrometry & Flow Cytometry

Neuroimaging

Phylogenetics & Systems Biology

Serialized

Compressed

Section B: API Patterns by Domain

1. NCBI E-utilities (Gene, Nucleotide, Protein, SRA, GEO)

2. EBI APIs (UniProt, PDBe, ChEMBL, Ensembl, InterPro)

3. NCI GDC (TCGA/TARGET Cancer Data)

4. CDC Health Surveys (NHANES, BRFSS, WONDER)

5. GWAS & Genetics (GWAS Catalog, gnomAD, ClinVar)

6. Chemical (PubChem, ChEMBL, KEGG)

7. Expression (GEO, ArrayExpress, GTEx)

8. Clinical (ClinicalTrials.gov, FDA/OpenFDA, FAERS)

9. Literature (PubMed, PMC, EuropePMC)

10. Data Repositories (Zenodo, Figshare, Dryad, DataCite)

11-24. Specialized Domains

Section C: Restricted/Uncovered Data Sources

Section D: Universal Patterns

Pagination

Rate Limiting & Retries

Authentication

Bulk Download with Streaming

Error Handling

When it activates

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry