Ready to supercharge your AI agents?

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

GWAS Catalog Database · FreedomIntelligence | DecimalAI

Scienceby FreedomIntelligence

GWAS Catalog Database

Query NHGRI-EBI GWAS Catalog for SNP-trait associations. Search variants by rs ID, disease/trait, gene, retrieve p-values and summary statistics, for genetic epidemiology and polygenic risk scores.

Never made a case worse

SkillScore

SkillScore30/100

Test results 30

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

13%30%of test cases passed +17 pts

Without skill3 of 23

With skill7 of 23

4 fixed3 passed either way16 still failing0 broke

Measured on gemini-3.6-flash7/26/2026v1

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 gwas-database
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("gwas-database")
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 gwas-database

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/gwas-database/SKILL.md https://app.decimal.ai/s/gwas-database/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/gwas-database/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 gwas-database

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("gwas-database")
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/gwas-database/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/gwas-database/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 gwas-database

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("gwas-database")
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/gwas-database/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/gwas-database/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 gwas-database

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("gwas-database")
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/gwas-database/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/gwas-database/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 gwas-database

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("gwas-database")
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/gwas-database/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/gwas-database/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 gwas-database

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("gwas-database")
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/gwas-database/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/gwas-database/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 gwas-database

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("gwas-database")
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/gwas-database/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/gwas-database/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 gwas-database

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("gwas-database")
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/gwas-database/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 gwas-database

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("gwas-database")
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/gwas-database/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/gwas-database/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 gwas-database

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("gwas-database")
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/gwas-database/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/gwas-database/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 gwas-database

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("gwas-database")
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/gwas-database/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/gwas-database/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 gwas-database

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("gwas-database")
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/gwas-database/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/gwas-database/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 gwas-database

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("gwas-database")
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/gwas-database/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/gwas-database/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 gwas-database

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/gwas-database/SKILL.md https://app.decimal.ai/s/gwas-database/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/gwas-database/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/gwas-database/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/gwas-database.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: v1, tested 7/26/2026
Source: FreedomIntelligence/OpenClaw-Medical-Skills ↗
License: Not recorded

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

GWAS Catalog Database

Overview

The GWAS Catalog is a comprehensive repository of published genome-wide association studies maintained by the National Human Genome Research Institute (NHGRI) and the European Bioinformatics Institute (EBI). The catalog contains curated SNP-trait associations from thousands of GWAS publications, including genetic variants, associated traits and diseases, p-values, effect sizes, and full summary statistics for many studies.

When to Use This Skill

This skill should be used when queries involve:

Genetic variant associations: Finding SNPs associated with diseases or traits
SNP lookups: Retrieving information about specific genetic variants (rs IDs)
Trait/disease searches: Discovering genetic associations for phenotypes
Gene associations: Finding variants in or near specific genes
GWAS summary statistics: Accessing complete genome-wide association data
Study metadata: Retrieving publication and cohort information
Population genetics: Exploring ancestry-specific associations
Polygenic risk scores: Identifying variants for risk prediction models
Functional genomics: Understanding variant effects and genomic context
Systematic reviews: Comprehensive literature synthesis of genetic associations

Core Capabilities

1. Understanding GWAS Catalog Data Structure

The GWAS Catalog is organized around four core entities:

Studies: GWAS publications with metadata (PMID, author, cohort details)
Associations: SNP-trait associations with statistical evidence (p ≤ 5×10⁻⁸)
Variants: Genetic markers (SNPs) with genomic coordinates and alleles
Traits: Phenotypes and diseases (mapped to EFO ontology terms)

Key Identifiers:

Study accessions: GCST IDs (e.g., GCST001234)
Variant IDs: rs numbers (e.g., rs7903146) or variant_id format
Trait IDs: EFO terms (e.g., EFO_0001360 for type 2 diabetes)
Gene symbols: HGNC approved names (e.g., TCF7L2)

2. Web Interface Searches

The web interface at https://www.ebi.ac.uk/gwas/ supports multiple search modes:

By Variant (rs ID):

rs7903146

Returns all trait associations for this SNP.

By Disease/Trait:

type 2 diabetes
Parkinson disease
body mass index

Returns all associated genetic variants.

By Gene:

APOE
TCF7L2

Returns variants in or near the gene region.

By Chromosomal Region:

10:114000000-115000000

Returns variants in the specified genomic interval.

By Publication:

PMID:20581827
Author: McCarthy MI
GCST001234

Returns study details and all reported associations.

3. REST API Access

The GWAS Catalog provides two REST APIs for programmatic access:

Base URLs:

GWAS Catalog API: https://www.ebi.ac.uk/gwas/rest/api
Summary Statistics API: https://www.ebi.ac.uk/gwas/summary-statistics/api

API Documentation:

Main API docs: https://www.ebi.ac.uk/gwas/rest/docs/api
Summary stats docs: https://www.ebi.ac.uk/gwas/summary-statistics/docs/

Core Endpoints:

Studies endpoint - /studies/{accessionID}

import requests

# Get a specific study
url = "https://www.ebi.ac.uk/gwas/rest/api/studies/GCST001795"
response = requests.get(url, headers={"Content-Type": "application/json"})
study = response.json()

Associations endpoint - /associations

# Find associations for a variant
variant = "rs7903146"
url = f"https://www.ebi.ac.uk/gwas/rest/api/singleNucleotidePolymorphisms/{variant}/associations"
params = {"projection": "associationBySnp"}
response = requests.get(url, params=params, headers={"Content-Type": "application/json"})
associations = response.json()

Variants endpoint - /singleNucleotidePolymorphisms/{rsID}

# Get variant details
url = "https://www.ebi.ac.uk/gwas/rest/api/singleNucleotidePolymorphisms/rs7903146"
response = requests.get(url, headers={"Content-Type": "application/json"})
variant_info = response.json()

Traits endpoint - /efoTraits/{efoID}

# Get trait information
url = "https://www.ebi.ac.uk/gwas/rest/api/efoTraits/EFO_0001360"
response = requests.get(url, headers={"Content-Type": "application/json"})
trait_info = response.json()

4. Query Examples and Patterns

Example 1: Find all associations for a disease

import requests

trait = "EFO_0001360"  # Type 2 diabetes
base_url = "https://www.ebi.ac.uk/gwas/rest/api"

# Query associations for this trait
url = f"{base_url}/efoTraits/{trait}/associations"
response = requests.get(url, headers={"Content-Type": "application/json"})
associations = response.json()

# Process results
for assoc in associations.get('_embedded', {}).get('associations', []):
    variant = assoc.get('rsId')
    pvalue = assoc.get('pvalue')
    risk_allele = assoc.get('strongestAllele')
    print(f"{variant}: p={pvalue}, risk allele={risk_allele}")

Example 2: Get variant information and all trait associations

import requests

variant = "rs7903146"
base_url = "https://www.ebi.ac.uk/gwas/rest/api"

# Get variant details
url = f"{base_url}/singleNucleotidePolymorphisms/{variant}"
response = requests.get(url, headers={"Content-Type": "application/json"})
variant_data = response.json()

# Get all associations for this variant
url = f"{base_url}/singleNucleotidePolymorphisms/{variant}/associations"
params = {"projection": "associationBySnp"}
response = requests.get(url, params=params, headers={"Content-Type": "application/json"})
associations = response.json()

# Extract trait names and p-values
for assoc in associations.get('_embedded', {}).get('associations', []):
    trait = assoc.get('efoTrait')
    pvalue = assoc.get('pvalue')
    print(f"Trait: {trait}, p-value: {pvalue}")

Example 3: Access summary statistics

import requests

# Query summary statistics API
base_url = "https://www.ebi.ac.uk/gwas/summary-statistics/api"

# Find associations by trait with p-value threshold
trait = "EFO_0001360"  # Type 2 diabetes
p_upper = "0.000000001"  # p < 1e-9
url = f"{base_url}/traits/{trait}/associations"
params = {
    "p_upper": p_upper,
    "size": 100  # Number of results
}
response = requests.get(url, params=params)
results = response.json()

# Process genome-wide significant hits
for hit in results.get('_embedded', {}).get('associations', []):
    variant_id = hit.get('variant_id')
    chromosome = hit.get('chromosome')
    position = hit.get('base_pair_location')
    pvalue = hit.get('p_value')
    print(f"{chromosome}:{position} ({variant_id}): p={pvalue}")

Example 4: Query by chromosomal region

import requests

# Find variants in a specific genomic region
chromosome = "10"
start_pos = 114000000
end_pos = 115000000

base_url = "https://www.ebi.ac.uk/gwas/rest/api"
url = f"{base_url}/singleNucleotidePolymorphisms/search/findByChromBpLocationRange"
params = {
    "chrom": chromosome,
    "bpStart": start_pos,
    "bpEnd": end_pos
}
response = requests.get(url, params=params, headers={"Content-Type": "application/json"})
variants_in_region = response.json()

5. Working with Summary Statistics

The GWAS Catalog hosts full summary statistics for many studies, providing access to all tested variants (not just genome-wide significant hits).

Access Methods:

FTP download: http://ftp.ebi.ac.uk/pub/databases/gwas/summary_statistics/
REST API: Query-based access to summary statistics
Web interface: Browse and download via the website

Summary Statistics API Features:

Filter by chromosome, position, p-value
Query specific variants across studies
Retrieve effect sizes and allele frequencies
Access harmonized and standardized data

Example: Download summary statistics for a study

import requests
import gzip

# Get available summary statistics
base_url = "https://www.ebi.ac.uk/gwas/summary-statistics/api"
url = f"{base_url}/studies/GCST001234"
response = requests.get(url)
study_info = response.json()

# Download link is provided in the response
# Alternatively, use FTP:
# ftp://ftp.ebi.ac.uk/pub/databases/gwas/summary_statistics/GCSTXXXXXX/

6. Data Integration and Cross-referencing

The GWAS Catalog provides links to external resources:

Genomic Databases:

Ensembl: Gene annotations and variant consequences
dbSNP: Variant identifiers and population frequencies
gnomAD: Population allele frequencies

Functional Resources:

Open Targets: Target-disease associations
PGS Catalog: Polygenic risk scores
UCSC Genome Browser: Genomic context

Phenotype Resources:

EFO (Experimental Factor Ontology): Standardized trait terms
OMIM: Disease gene relationships
Disease Ontology: Disease hierarchies

Following Links in API Responses:

import requests

# API responses include _links for related resources
response = requests.get("https://www.ebi.ac.uk/gwas/rest/api/studies/GCST001234")
study = response.json()

# Follow link to associations
associations_url = study['_links']['associations']['href']
associations_response = requests.get(associations_url)

Query Workflows

Workflow 1: Exploring Genetic Associations for a Disease

Identify the trait using EFO terms or free text:
- Search web interface for disease name
- Note the EFO ID (e.g., EFO_0001360 for type 2 diabetes)

Query associations via API:

url = f"https://www.ebi.ac.uk/gwas/rest/api/efoTraits/{efo_id}/associations"

Filter by significance and population:
- Check p-values (genome-wide significant: p ≤ 5×10⁻⁸)
- Review ancestry information in study metadata
- Filter by sample size or discovery/replication status
Extract variant details:
- rs IDs for each association
- Effect alleles and directions
- Effect sizes (odds ratios, beta coefficients)
- Population allele frequencies
Cross-reference with other databases:
- Look up variant consequences in Ensembl
- Check population frequencies in gnomAD
- Explore gene function and pathways

Workflow 2: Investigating a Specific Genetic Variant

Query the variant:

url = f"https://www.ebi.ac.uk/gwas/rest/api/singleNucleotidePolymorphisms/{rs_id}"

Retrieve all trait associations:

url = f"https://www.ebi.ac.uk/gwas/rest/api/singleNucleotidePolymorphisms/{rs_id}/associations"

Analyze pleiotropy:
- Identify all traits associated with this variant
- Review effect directions across traits
- Look for shared biological pathways
Check genomic context:
- Determine nearby genes
- Identify if variant is in coding/regulatory regions
- Review linkage disequilibrium with other variants

Workflow 3: Gene-Centric Association Analysis

Search by gene symbol in web interface or:

url = f"https://www.ebi.ac.uk/gwas/rest/api/singleNucleotidePolymorphisms/search/findByGene"
params = {"geneName": gene_symbol}

Retrieve variants in gene region:
- Get chromosomal coordinates for gene
- Query variants in region
- Include promoter and regulatory regions (extend boundaries)
Analyze association patterns:
- Identify traits associated with variants in this gene
- Look for consistent associations across studies
- Review effect sizes and directions
Functional interpretation:
- Determine variant consequences (missense, regulatory, etc.)
- Check expression QTL (eQTL) data
- Review pathway and network context

Workflow 4: Systematic Review of Genetic Evidence

Define research question:
- Specific trait or disease of interest
- Population considerations
- Study design requirements
Comprehensive variant extraction:
- Query all associations for trait
- Set significance threshold
- Note discovery and replication studies
Quality assessment:
- Review study sample sizes
- Check for population diversity
- Assess heterogeneity across studies
- Identify potential biases
Data synthesis:
- Aggregate associations across studies
- Perform meta-analysis if applicable
- Create summary tables
- Generate Manhattan or forest plots
Export and documentation:
- Download full association data
- Export summary statistics if needed
- Document search strategy and date
- Create reproducible analysis scripts

Workflow 5: Accessing and Analyzing Summary Statistics

Identify studies with summary statistics:
- Browse summary statistics portal
- Check FTP directory listings
- Query API for available studies

Download summary statistics:

# Via FTP
wget ftp://ftp.ebi.ac.uk/pub/databases/gwas/summary_statistics/GCSTXXXXXX/harmonised/GCSTXXXXXX-harmonised.tsv.gz

Query via API for specific variants:

url = f"https://www.ebi.ac.uk/gwas/summary-statistics/api/chromosomes/{chrom}/associations"
params = {"start": start_pos, "end": end_pos}

Process and analyze:
- Filter by p-value thresholds
- Extract effect sizes and confidence intervals
- Perform downstream analyses (fine-mapping, colocalization, etc.)

Response Formats and Data Fields

Key Fields in Association Records:

rsId: Variant identifier (rs number)
strongestAllele: Risk allele for the association
pvalue: Association p-value
pvalueText: P-value as text (may include inequality)
orPerCopyNum: Odds ratio or beta coefficient
betaNum: Effect size (for quantitative traits)
betaUnit: Unit of measurement for beta
range: Confidence interval
efoTrait: Associated trait name
mappedLabel: EFO-mapped trait term

Study Metadata Fields:

accessionId: GCST study identifier
pubmedId: PubMed ID
author: First author
publicationDate: Publication date
ancestryInitial: Discovery population ancestry
ancestryReplication: Replication population ancestry
sampleSize: Total sample size

Pagination: Results are paginated (default 20 items per page). Navigate using:

size parameter: Number of results per page
page parameter: Page number (0-indexed)
_links in response: URLs for next/previous pages

Best Practices

Query Strategy

Start with web interface to identify relevant EFO terms and study accessions
Use API for bulk data extraction and automated analyses
Implement pagination handling for large result sets
Cache API responses to minimize redundant requests

Data Interpretation

Always check p-value thresholds (genome-wide: 5×10⁻⁸)
Review ancestry information for population applicability
Consider sample size when assessing evidence strength
Check for replication across independent studies
Be aware of winner's curse in effect size estimates

Rate Limiting and Ethics

Respect API usage guidelines (no excessive requests)
Use summary statistics downloads for genome-wide analyses
Implement appropriate delays between API calls
Cache results locally when performing iterative analyses
Cite the GWAS Catalog in publications

Data Quality Considerations

GWAS Catalog curates published associations (may contain inconsistencies)
Effect sizes reported as published (may need harmonization)
Some studies report conditional or joint associations
Check for study overlap when combining results
Be aware of ascertainment and selection biases

Python Integration Example

Complete workflow for querying and analyzing GWAS data:

import requests
import pandas as pd
from time import sleep

def query_gwas_catalog(trait_id, p_threshold=5e-8):
    """
    Query GWAS Catalog for trait associations

    Args:
        trait_id: EFO trait identifier (e.g., 'EFO_0001360')
        p_threshold: P-value threshold for filtering

    Returns:
        pandas DataFrame with association results
    """
    base_url = "https://www.ebi.ac.uk/gwas/rest/api"
    url = f"{base_url}/efoTraits/{trait_id}/associations"

    headers = {"Content-Type": "application/json"}
    results = []
    page = 0

    while True:
        params = {"page": page, "size": 100}
        response = requests.get(url, params=params, headers=headers)

        if response.status_code != 200:
            break

        data = response.json()
        associations = data.get('_embedded', {}).get('associations', [])

        if not associations:
            break

        for assoc in associations:
            pvalue = assoc.get('pvalue')
            if pvalue and float(pvalue) <= p_threshold:
                results.append({
                    'variant': assoc.get('rsId'),
                    'pvalue': pvalue,
                    'risk_allele': assoc.get('strongestAllele'),
                    'or_beta': assoc.get('orPerCopyNum') or assoc.get('betaNum'),
                    'trait': assoc.get('efoTrait'),
                    'pubmed_id': assoc.get('pubmedId')
                })

        page += 1
        sleep(0.1)  # Rate limiting

    return pd.DataFrame(results)

# Example usage
df = query_gwas_catalog('EFO_0001360')  # Type 2 diabetes
print(df.head())
print(f"\nTotal associations: {len(df)}")
print(f"Unique variants: {df['variant'].nunique()}")

Resources

references/api_reference.md

Comprehensive API documentation including:

Detailed endpoint specifications for both APIs
Complete list of query parameters and filters
Response format specifications and field descriptions
Advanced query examples and patterns
Error handling and troubleshooting
Integration with external databases

Consult this reference when:

Constructing complex API queries
Understanding response structures
Implementing pagination or batch operations
Troubleshooting API errors
Exploring advanced filtering options

Training Materials

The GWAS Catalog team provides workshop materials:

GitHub repository: https://github.com/EBISPOT/GWAS_Catalog-workshop
Jupyter notebooks with example queries
Google Colab integration for cloud execution

Important Notes

Data Updates

The GWAS Catalog is updated regularly with new publications
Re-run queries periodically for comprehensive coverage
Summary statistics are added as studies release data
EFO mappings may be updated over time

Citation Requirements

When using GWAS Catalog data, cite:

Sollis E, et al. (2023) The NHGRI-EBI GWAS Catalog: knowledgebase and deposition resource. Nucleic Acids Research. PMID: 37953337
Include access date and version when available
Cite original studies when discussing specific findings

Limitations

Not all GWAS publications are included (curation criteria apply)
Full summary statistics available for subset of studies
Effect sizes may require harmonization across studies
Population diversity is growing but historically limited
Some associations represent conditional or joint effects

Data Access

Web interface: Free, no registration required
REST APIs: Free, no API key needed
FTP downloads: Open access
Rate limiting applies to API (be respectful)

Additional Resources

GWAS Catalog website: https://www.ebi.ac.uk/gwas/
Documentation: https://www.ebi.ac.uk/gwas/docs
API documentation: https://www.ebi.ac.uk/gwas/rest/docs/api
Summary Statistics API: https://www.ebi.ac.uk/gwas/summary-statistics/docs/
FTP site: http://ftp.ebi.ac.uk/pub/databases/gwas/
Training materials: https://github.com/EBISPOT/GWAS_Catalog-workshop
PGS Catalog (polygenic scores): https://www.pgscatalog.org/
Help and support: [email protected]

About this skill

Automatic

Research pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 7/30/2026

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

FreedomIntelligence / OpenClaw-Medical-Skills

skills/gwas-database/SKILL.md

View on GitHub ↗

Imported 8/1/2026Version v1Bundled 1 file

Illustrative Want to see what gwas-database would put in front of your model? Preview the rendered body and check its trigger phrases — no LLM call, no signup.

Other skills for the same job

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

Related skills

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

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

GWAS Catalog Database

Overview

When to Use This Skill

Core Capabilities

1. Understanding GWAS Catalog Data Structure

2. Web Interface Searches

3. REST API Access

4. Query Examples and Patterns

5. Working with Summary Statistics

6. Data Integration and Cross-referencing

Query Workflows

Workflow 1: Exploring Genetic Associations for a Disease

Workflow 2: Investigating a Specific Genetic Variant

Workflow 3: Gene-Centric Association Analysis

Workflow 4: Systematic Review of Genetic Evidence

Workflow 5: Accessing and Analyzing Summary Statistics

Response Formats and Data Fields

Best Practices

Query Strategy

Data Interpretation

Rate Limiting and Ethics

Data Quality Considerations

Python Integration Example

Resources

references/api_reference.md

Training Materials

Important Notes

Data Updates

Citation Requirements

Limitations

Data Access

Additional Resources

SkillSafety

Source

Other skills for the same job

Related skills

More in the registry