Ready to supercharge your AI agents?

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

OneKGPd: Individual-Level Queries over the 1000 Genomes Project · k-dense-ai | DecimalAI

Scienceby k-dense-ai

OneKGPd: Individual-Level Queries over the 1000 Genomes Project

Query the 1000 Genomes Project dataset (3,202 whole-genome-sequenced individuals, GRCh38) at the level of individual participants.

Never made a case worseMaintained

SkillScore

SkillScore74/100

Test results 74

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

17%74%of test cases passed +57 pts

Without skill4 of 23

With skill17 of 23

13 fixed4 passed either way6 still failing0 broke

Measured on gemini-3.6-flash8/11/2026v1 · latest is v218 comparable

This benchmark measured an earlier version of the skill.

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWe want to identify individuals who are heterozygous carriers (excluding homozygotes) for missense variants in region chr2:233000000-233100000. Which flag restricts the query to heterozygous state?

Without the skillMissed

With the skillPassed

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

Use this skill

Your agent runs on

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

pip install "decimalai>=0.15"
decimalai skills add k-dense-ai-onekgpd
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("k-dense-ai-onekgpd")
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 k-dense-ai-onekgpd

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/k-dense-ai-onekgpd/SKILL.md https://app.decimal.ai/s/k-dense-ai-onekgpd/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/k-dense-ai-onekgpd/SKILL.md

This gets SKILL.md only. The skill's 4 other files are not included.

Other ways to add it

Claude Code docs

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

Install

pip install "decimalai[claude-agent-sdk]"
decimalai skills add k-dense-ai-onekgpd

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("k-dense-ai-onekgpd")
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/k-dense-ai-onekgpd/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/k-dense-ai-onekgpd/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 4 other files are not included.

Other ways to add it

Claude Agent SDK docs

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

Install

pip install "decimalai[openai-agents]"
decimalai skills add k-dense-ai-onekgpd

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("k-dense-ai-onekgpd")
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/k-dense-ai-onekgpd/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/k-dense-ai-onekgpd/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 4 other files are not included.

Other ways to add it

OpenAI Agents docs

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

Install

pip install "decimalai[openai]"
decimalai skills add k-dense-ai-onekgpd

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("k-dense-ai-onekgpd")
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/k-dense-ai-onekgpd/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/k-dense-ai-onekgpd/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 4 other files are not included.

Other ways to add it

OpenAI SDK docs

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

Install

pip install "decimalai[anthropic]"
decimalai skills add k-dense-ai-onekgpd

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("k-dense-ai-onekgpd")
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/k-dense-ai-onekgpd/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/k-dense-ai-onekgpd/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 4 other files are not included.

Other ways to add it

Anthropic docs

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

Install

pip install "decimalai[google-genai]"
decimalai skills add k-dense-ai-onekgpd

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("k-dense-ai-onekgpd")
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/k-dense-ai-onekgpd/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/k-dense-ai-onekgpd/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 4 other files are not included.

Other ways to add it

Gemini API docs

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

Install

pip install "decimalai[langchain]" langchain-openai
decimalai skills add k-dense-ai-onekgpd

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("k-dense-ai-onekgpd")
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/k-dense-ai-onekgpd/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/k-dense-ai-onekgpd/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 4 other files are not included.

Other ways to add it

LangChain docs

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

Install

pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add k-dense-ai-onekgpd

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("k-dense-ai-onekgpd")
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/k-dense-ai-onekgpd/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 4 other files are not included.

Other ways to add it

CrewAI docs

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

Install

pip install "decimalai[adk]"
decimalai skills add k-dense-ai-onekgpd

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("k-dense-ai-onekgpd")
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/k-dense-ai-onekgpd/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/k-dense-ai-onekgpd/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 4 other files are not included.

Other ways to add it

Google ADK docs

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

Install

pip install "decimalai[pydantic-ai]"
decimalai skills add k-dense-ai-onekgpd

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("k-dense-ai-onekgpd")
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/k-dense-ai-onekgpd/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/k-dense-ai-onekgpd/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 4 other files are not included.

Other ways to add it

Pydantic AI docs

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

Install

pip install "decimalai>=0.16" deepagents
decimalai skills add k-dense-ai-onekgpd

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("k-dense-ai-onekgpd")
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/k-dense-ai-onekgpd/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/k-dense-ai-onekgpd/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 4 other files are not included.

Other ways to add it

Deep Agents docs

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

Install

pip install "decimalai>=0.16" agent-framework
decimalai skills add k-dense-ai-onekgpd

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("k-dense-ai-onekgpd")
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/k-dense-ai-onekgpd/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/k-dense-ai-onekgpd/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 4 other files are not included.

Other ways to add it

Microsoft Agent Framework docs

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

Install

pip install "decimalai>=0.16" strands-agents
decimalai skills add k-dense-ai-onekgpd

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("k-dense-ai-onekgpd")
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/k-dense-ai-onekgpd/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/k-dense-ai-onekgpd/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 4 other files are not included.

Other ways to add it

Strands docs

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

pip install "decimalai>=0.15"
decimalai skills add k-dense-ai-onekgpd

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/k-dense-ai-onekgpd/SKILL.md https://app.decimal.ai/s/k-dense-ai-onekgpd/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/k-dense-ai-onekgpd/SKILL.md

This gets SKILL.md only. The skill's 4 other files are not included.

Other ways to add it

Cursor and other editors docs

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

Get the file

curl -fsSL https://app.decimal.ai/s/k-dense-ai-onekgpd/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/k-dense-ai-onekgpd.json

This gets SKILL.md only. The skill's 4 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v2 (v1 tested 8/11/2026)
Source: k-dense-ai/scientific-agent-skills ↗
License: MIT

Manage it in DecimalAI

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Use this skill

SKILL.md

OneKGPd: Individual-Level Queries over the 1000 Genomes Project

Scope

This skill queries the 1000 Genomes Project dataset — the extended high-coverage cohort of 3,202 whole-genome-sequenced individuals, on the GRCh38 assembly. All results are drawn from this cohort, and sample names returned by the skill (for example HG00096 or NA21130) identify its participants.

Queries resolve against the cohort's per-individual genotype data. This supports two complementary classes of question: selecting variants carried within a region (across the whole cohort or within a specified set of individuals), and selecting the individuals who carry variants matching given criteria. Variant selection can be filtered by allele frequency, predicted consequence, clinical significance, AlphaMissense classification, and the other annotation axes listed below. Relatedness between two named individuals is also available.

The genotype state in which a variant is carried — heterozygous or homozygous — is a criterion that queries may specify; results are returned as variants or as sample names, not as raw genotypes.

The public service is TLS gRPC at db.dnaerys.org:443, accessed with dnaerys 0.2.1 (Python 3.11+); it is not a REST base URL. The maintained service snapshot advertises VEP 115 / GENCODE 49, ClinVar 202502, and gnomAD 4.1. These are the service's annotation releases, not the latest release of each upstream resource. Record them when interpreting results.

When to Use

Use this skill when you need to:

Find variants carried in a region or set of regions matching some criteria across the whole cohort (select-variants).
Find variants carried in a region or set of regions matching some criteria in specific set of individuals (select-variants-in-samples).
Find which 1000 Genomes individuals carry variants matching some criteria in a region or set of regions (select-samples).
Count how many individuals carry specific variants (count-samples).
Restrict any variant query to heterozygous-only or homozygous-only carriage, or query both together (default).
Identify which individuals are homozygous reference at a single position (select-samples-hom-ref).
Determine the relatedness between two named 1000 Genomes individuals — both the degree (twin / 1st / 2nd / 3rd / unrelated) and the KING kinship coefficient (kinship).
Get dataset totals — sample count, sex split, variant count, assembly (dataset-info).
Variant selection can be specified by KGP allele frequency, gnomAD 4.1 exome and gnomAD 4.1 genome allele frequency, AlphaMissense Score and AlphaMissense Class, ClinVar significance (202502), and VEP annotations (impact, biotype, feature type, variant class, consequences).

Do NOT use this skill for:

Resolving a gene symbol, rsID, or transcript to coordinates, or fetching reference sequence. Resolve coordinates first (see Coordinate Provenance below), then query this skill with the resolved GRCh38 region.
Any cohort other than the 1000 Genomes Project — this skill serves only that dataset.

Prerequisites

uv: This skill's script is run with uv run, which reads the script's inline dependency metadata and provisions an ephemeral environment. Ensure uv is installed and on PATH (https://docs.astral.sh/uv/).
Data use terms: The 1000 Genomes Project data is open; users should be aware of the 1000 Genomes Project / IGSR data-use terms (https://www.internationalgenome.org/data).
Access constraints: There is no API key, no .env file, and no rate-limit token to configure.
Timeouts: network commands use --timeout 30 seconds per RPC by default. A positive finite override is allowed. Pagination makes several RPCs and retryable failures retry the whole fetch up to three times, so this is not a deadline for the whole command.

Core Rules

Use the Wrappers: ALWAYS execute the provided helper scripts rather than constructing your own client calls or network requests. Use scripts/onekgpd_api.py for variant/sample/kinship queries (it handles the connection, streaming, pagination, and JSON serialization), and scripts/onekgpd_meta.py for sample/population metadata (offline, see Sample & population metadata).
Coordinates MUST be resolved against an authoritative source first — see Coordinate Provenance. This is mandatory, not advisory.
Count before you select: every variant and sample selection has a paired counting command. Call the count command FIRST to size the result set, then select only if the count is manageable.
Zygosity defaults to both: selection and counting commands include both heterozygous and homozygous carriage by default. Narrow with --het-only or --hom-only when the question is specifically about one state. (You do not need to pass anything to get both.)
Output: scripts write full JSON to a file (--output, default under /tmp/) and print a concise summary to stdout. Do not read large JSON files into context — use jq or a small disposable uv run python snippet to extract fields. --page-size retrieves every page but accumulates all variants in RAM; it is not a bounded-memory export. Size the query first.
Check completeness: result_incomplete=true means results cannot support a definitive zero/absence claim. Re-run after service recovery. For capped variant selections, truncated=true means the limit was reached and more records may exist, even if the cluster result itself was complete.

Coordinate Provenance (MANDATORY FIRST STEP)

Before any region-based query, resolve the gene or feature to GRCh38 coordinates against an authoritative source (for example Ensembl or NCBI), and query with those resolved coordinates. Inputs are 1-based, inclusive: a BED interval [start0, end0) becomes start=start0+1, end=end0. Record the source accession, annotation release, and retrieval date; gene boundaries can differ by annotation release even on the same assembly. The assembly must be explicit, and a gene-range must be resolved to precise positions before use. This is structural, not advisory: there is no source-side guardrail that would catch a misplaced region, so an unverified coordinate produces results for an unintended location with no error.

# Resolve gene symbol -> GRCh38 region with an authoritative source FIRST,
# then pass the verified coordinates to the OneKGPd query below.

[!CAUTION] The dataset is GRCh38. A GRCh37 coordinate, or any region that does not correctly correspond to the intended feature on GRCh38, will return results for an unintended location without raising an error. Verify the assembly and the resolved coordinates before querying.

Command Selection Guide

Match the question to the command. Counting commands are cheap and should precede their selection counterpart.

Which individuals carry matching variants in a region → count-samples then select-samples
Which variants are carried in a region, cohort-wide → count-variants then select-variants
Which variants are carried in a region, within a named set of individuals → count-variants-in-samples then select-variants-in-samples
Who is homozygous-reference at a single position → count-samples-hom-ref then select-samples-hom-ref
Relatedness (degree + coefficient) between two named individuals → kinship
Dataset totals (sample count, sex split, variant total, assembly) → dataset-info

Cohort interpretation

The 3,202-sample cohort includes relatives: the additional 698 high-coverage samples extend the original 2,504-sample panel. Carrier counts therefore are not counts of independent observations, and cohort AF is not a population prevalence estimate. For association or frequency comparisons, document the selected populations and relatedness policy; use the bundled pedigree metadata and kinship when choosing or auditing the analysis set. See the IGSR cohort announcement.

Annotation filters (shared across variant and sample selection/counting)

All variant- and sample-selection commands (count-variants, select-variants, their -in-samples forms, count-samples, select-samples) accept the same annotation filters. Different filter fields are combined with AND; multiple values within one field are combined with OR. Enum values are case-insensitive (e.g. missense_variant or MISSENSE_VARIANT).

These are selection criteria applied on the server. The fields returned on a selected variant are listed under Variant-returning commands; a criterion used for filtering is not necessarily echoed back on the returned variant.

--af-lt / --af-gt: 1000 Genomes dataset allele frequency bounds
--gnomad-exomes-af-lt / --gnomad-exomes-af-gt: gnomAD v4.1 exome AF bounds
--gnomad-genomes-af-lt / --gnomad-genomes-af-gt: gnomAD v4.1 genome AF bounds
--clin-significance: ClinVar significance terms, CSV (e.g. PATHOGENIC,LIKELY_PATHOGENIC)
--consequence: Sequence Ontology consequence terms, CSV (e.g. MISSENSE_VARIANT,STOP_GAINED)
--impact: VEP impact, CSV (HIGH,MODERATE,LOW,MODIFIER)
--variant-type, --feature-type, --bio-type: SO variant class / VEP feature / VEP biotype, CSV
--alpha-missense-class: AM_LIKELY_BENIGN,AM_LIKELY_PATHOGENIC,AM_AMBIGUOUS (CSV)
--alpha-missense-score-lt / --alpha-missense-score-gt: AlphaMissense score bounds
--biallelic-only / --multiallelic-only
--exclude-males / --exclude-females
--min-len-bp / --max-len-bp: alternate-allele length bounds (bp)

[!NOTE] --alpha-missense-class and --alpha-missense-score-* are mutually exclusive (the engine ignores the class when a score bound is set). --biallelic-only and --multiallelic-only are mutually exclusive. --exclude-males and --exclude-females are mutually exclusive. Setting a *-gt bound greater than or equal to its matching *-lt bound defines an empty range and will return nothing.

[!NOTE] gnomad_exomes_af, gnomad_genomes_af, and am_score use 0.0 for not annotated in this service snapshot. This does not establish absence from the current gnomAD release, biological rarity, or a benign prediction. The dataset's own af field is a different statistic, not this sentinel.

[!CAUTION] A zero numeric filter is unset on the server, so --gnomad-exomes-af-gt 0 does not exclude missing annotations. The wrapper rejects zero, nonfinite, out-of-range, and float32-underflowing bounds. Choose an explicit positive threshold (for example --gnomad-exomes-af-gt 0.000001 means AF > 1e-6, not merely annotation presence). For exact > 0, retrieve a complete variant set and post-filter the returned AF locally. A < X filter alone includes unannotated zero values. Apply the same missing-score caution to AlphaMissense.

Categorical annotations are retained across transcripts. Combining consequence and impact filters does not establish that they describe the same transcript. amino_acids may contain multiple HGVSp entries; the generic gRPC service places canonical annotations first, whereas the separate MCP layer trims its output. Preserve transcript identifiers, and do not treat a model's likely-pathogenic class as a clinical diagnosis or a participant phenotype.

Quick Start

# Step 1. NCBI Gene 672, GRCh38.p14 / NC_000017.11, RS_2025_08:
# BRCA1 spans chr17:43044295-43170327 (1-based inclusive).
# Source: https://www.ncbi.nlm.nih.gov/gene/672 ; re-resolve for your analysis.
# Step 2. Size the result set: how many individuals carry predicted likely-pathogenic
#    missense variants in this region?
uv run scripts/onekgpd_api.py count-samples \
  --chrom chr17 --start 43044295 --end 43170327 \
  --consequence MISSENSE_VARIANT \
  --alpha-missense-class AM_LIKELY_PATHOGENIC \
  --output /tmp/count.json
# Step 3. If the count is manageable, list those individuals.
uv run scripts/onekgpd_api.py select-samples \
  --chrom chr17 --start 43044295 --end 43170327 \
  --consequence MISSENSE_VARIANT \
  --alpha-missense-class AM_LIKELY_PATHOGENIC \
  --output /tmp/samples.json
# Step 4. Count then select variants for actual returned sample IDs.
# HG03169,NA20506 below are illustrative IDs; substitute the Step 3 results.
uv run scripts/onekgpd_api.py count-variants-in-samples \
  --chrom chr17 --start 43044295 --end 43170327 \
  --samples HG03169,NA20506 \
  --consequence MISSENSE_VARIANT --alpha-missense-class AM_LIKELY_PATHOGENIC \
  --output /tmp/variant_count.json
uv run scripts/onekgpd_api.py select-variants-in-samples \
  --chrom chr17 --start 43044295 --end 43170327 \
  --samples HG03169,NA20506 \
  --consequence MISSENSE_VARIANT --alpha-missense-class AM_LIKELY_PATHOGENIC \
  --output /tmp/variants.json

Commands

Each command writes full JSON to a file (--output PATH, default a temp file) and prints a concise stdout summary. All region/sample commands share: the region input (--chrom/--start/--end with optional --ref/--alt, or one or more repeated --region CHR:START-END), the zygosity flags (--het-only/--hom-only, default both), and the annotation filters above. The full per-flag tables live in references/onekgpd_commands.md.

Variant-returning commands

select-* return matching variants; count-* return an integer count.

count-variants — count variants in a region, cohort-wide.
select-variants — select variants in a region, cohort-wide. Use --limit N (hard cap, default 200) or --page-size N (retrieve the full set in pages); the two are mutually exclusive. The summary flags truncated when the cap is reached.
count-variants-in-samples — as count-variants, restricted to --samples NAME1,NAME2,... (required).
select-variants-in-samples — as select-variants, restricted to --samples NAME1,NAME2,... (required).

Each returned variant carries these 22 keys: chr, start, end, ref, alt, af, ac, an, hom_samples, het_samples, mis_samples, hom_samples_fx, het_samples_fx, mis_samples_fx, hom_samples_mxy, het_samples_mxy, mis_samples_mxy, gnomad_exomes_af, gnomad_genomes_af, am_score, amino_acids, biallelic. ClinVar significance and VEP consequence are filter criteria only and are not returned. Full schema: references/onekgpd_commands.md.

Sample-returning commands

count-samples — count individuals carrying a matching variant in a region.
select-samples — list the names of individuals carrying a matching variant. Supports --skip N and --limit N. Returns names only; to see which variants qualified an individual, feed the names into select-variants-in-samples.

Homozygous-reference commands

Single position via --chrom + --position (not a region).

count-samples-hom-ref — count individuals with a 0/0 call at the position. The count uses a sentinel: -1 = no variant exists at that position at all; 0 = a variant exists but no individual is homozygous reference; >0 = the number of homozygous-reference individuals. These interpretations require result_incomplete=false; otherwise variant_present is null. No variant record is not evidence that all 3,202 individuals have callable 0/0 genotypes.
select-samples-hom-ref — list the individuals with a 0/0 call at the position.

Relatedness command

kinship --sample1 NAME --sample2 NAME — relatedness between two named individuals: the degree (TWINS_MONOZYGOTIC / FIRST_DEGREE / SECOND_DEGREE / THIRD_DEGREE / UNRELATED) and the KING kinship coefficient (phi_bwf).

Dataset metadata command

dataset-info — dataset totals: samples_total (3,202), female/male split, variants_total, assembly (GRCh38), and the cohort breakdown. No region required; doubles as a connectivity check.

Sample & population metadata (offline)

Population, sex, pedigree, and superpopulation questions are answered by a second script, scripts/onekgpd_meta.py, from a data file bundled in the skill — no network, no credentials, no coordinates. The sample IDs are the same names the variant commands use, so the two layers compose (e.g. pick a cohort by population, then query its variants). Run uv run scripts/onekgpd_meta.py <command>.

The cohort has 5 superpopulations (AFR, AMR, EAS, EUR, SAS) and 26 populations. Population/superpopulation values match case-insensitively by short code or full name; sample IDs are case-sensitive.

sample-metadata --samples NA19240,HG00096 — family, gender, parents, children, population, superpopulation, and phase3 status for the given samples.
list-populations — all 26 populations with superpopulation and sample count (use to discover valid values).
list-superpopulations — the 5 superpopulations with sample count and constituent populations.
population-stats --populations YRI [--populations CHS …] — per-population sex split, phase3 count, and trio membership. Repeat --populations for multiple values (full names contain commas, so they are not comma-separated).
superpopulation-summary --superpopulations EAS [--superpopulations EUR …] — per-superpopulation totals with a per-population breakdown.
select-samples-by-population --population YRI and/or --superpopulation AFR, with optional --skip/--limit (default 0 / 50, max 3202) — the sample IDs in a population and/or superpopulation; both given intersects. Feed the names into select-variants-in-samples to see their variants.

See references/onekgpd_commands.md for full argument tables and JSON output schemas.

Typical Workflows

Which individuals, then which variants they carry

The following is an illustrative template; replace all angle-bracket placeholders.

# Step 1: resolve gene -> verified GRCh38 region (authoritative source).
# Step 2: count individuals carrying a qualifying variant in the region.
uv run scripts/onekgpd_api.py count-samples \
  --chrom <chr> --start <start> --end <end> \
  --consequence MISSENSE_VARIANT --alpha-missense-class AM_LIKELY_PATHOGENIC \
  --output /tmp/n.json
# Step 3: list those individuals.
uv run scripts/onekgpd_api.py select-samples \
  --chrom <chr> --start <start> --end <end> \
  --consequence MISSENSE_VARIANT --alpha-missense-class AM_LIKELY_PATHOGENIC \
  --output /tmp/who.json
# Step 4: count variants for those individuals before selecting.
uv run scripts/onekgpd_api.py count-variants-in-samples \
  --chrom <chr> --start <start> --end <end> \
  --samples <name1,name2,...> \
  --consequence MISSENSE_VARIANT --alpha-missense-class AM_LIKELY_PATHOGENIC \
  --output /tmp/variant_count.json
uv run scripts/onekgpd_api.py select-variants-in-samples \
  --chrom <chr> --start <start> --end <end> \
  --samples <name1,name2,...> \
  --consequence MISSENSE_VARIANT --alpha-missense-class AM_LIKELY_PATHOGENIC \
  --output /tmp/variants.json

Homozygous-reference carriers at a position of interest

Illustrative template; replace the placeholders with verified coordinates.

# After identifying a position of interest (verified coordinate):
uv run scripts/onekgpd_api.py count-samples-hom-ref \
  --chrom <chr> --position <pos> --output /tmp/homref_n.json
uv run scripts/onekgpd_api.py select-samples-hom-ref \
  --chrom <chr> --position <pos> --output /tmp/homref.json

Common Mistakes

Mistake: Querying with an unverified coordinate. Fix: Always resolve gene/feature → GRCh38 against an authoritative source first. A misplaced region returns results for an unintended location without error.
Mistake: Calling a selection command before its counting command. Fix: Count first; selection result sets can be large.
Mistake: Assuming a GRCh37 coordinate will work. Fix: The dataset is GRCh38 only.

References

references/onekgpd_commands.md — full per-command argument tables and the returned-variant output schema.
references/annotation_vocabularies.md — the controlled-vocabulary terms accepted by the CSV filter flags (consequence, impact, biotype, feature type, ClinVar significance, AlphaMissense class, variant class).
Current API contract and live-check scope: the command reference.
1000 Genomes Project / IGSR: https://www.internationalgenome.org/
1000 Genomes Project dataset online: https://dnaerys.org/online/

When it activates

Automatically, when a task matches. Use when a question is about individuals or variants in the 1000 Genomes Project cohort: which individuals carry variants matching specific criteria in a gene or region, which individuals are homozygous-reference at a position, which variants exist in the dataset or carried by specified individuals in a gene or region, the relatedness between two specified individual

About this skill

Automatic

Research pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v6 — 10/15/2026

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

k-dense-ai / scientific-agent-skills

skills/onekgpd/SKILL.md

View on GitHub ↗

License MITImported 10/8/2026Version v2Bundled 4 files · scripts

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

Related skills

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

From the same source and nearby in the catalogue.

Ready to supercharge your AI agents?

SkillScore

Safety

What it changes

Track record

Use this skill

OneKGPd: Individual-Level Queries over the 1000 Genomes Project

Scope

When to Use

Prerequisites

Core Rules

Coordinate Provenance (MANDATORY FIRST STEP)

Command Selection Guide

Cohort interpretation

Annotation filters (shared across variant and sample selection/counting)

Quick Start

Commands

Variant-returning commands

Sample-returning commands

Homozygous-reference commands

Relatedness command

Dataset metadata command

Sample & population metadata (offline)

Typical Workflows

Which individuals, then which variants they carry

Homozygous-reference carriers at a position of interest

Common Mistakes

References

When it activates

SkillSafety

Source

Related skills

More in the registry