Ready to supercharge your AI agents?

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

NHGIS Data Source Reference · brycewang-stanford | DecimalAI

Researchby brycewang-stanford

NHGIS Data Source Reference

NHGIS — census geography crosswalks via Portal: links schools (ncessch) and colleges (unitid) to tracts, block groups, CBSAs (1990-2020). Census demographics NOT in Portal — access NHGIS directly.

Never made a case worse

SkillScore

SkillScore95/100

Test results 95

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

32%95%of test cases passed +64 pts

Without skill7 of 22

With skill21 of 22

14 fixed7 passed either way1 still failing0 broke

Measured on gemini-3.6-flash8/9/2026v121 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskI need to check the principal city status of a metropolitan statistical area for a college in the 2010 dataset. What column name stores this indicator, and what integer value indicates 'Yes'?

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 brycewang-stanford-education-data-source-nhgis
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("brycewang-stanford-education-data-source-nhgis")
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 brycewang-stanford-education-data-source-nhgis

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/brycewang-stanford-education-data-source-nhgis/SKILL.md https://app.decimal.ai/s/brycewang-stanford-education-data-source-nhgis/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/brycewang-stanford-education-data-source-nhgis/SKILL.md

This gets SKILL.md only. The skill's 6 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 brycewang-stanford-education-data-source-nhgis

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("brycewang-stanford-education-data-source-nhgis")
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/brycewang-stanford-education-data-source-nhgis/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/brycewang-stanford-education-data-source-nhgis/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 6 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 brycewang-stanford-education-data-source-nhgis

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("brycewang-stanford-education-data-source-nhgis")
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/brycewang-stanford-education-data-source-nhgis/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/brycewang-stanford-education-data-source-nhgis/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 6 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 brycewang-stanford-education-data-source-nhgis

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("brycewang-stanford-education-data-source-nhgis")
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/brycewang-stanford-education-data-source-nhgis/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/brycewang-stanford-education-data-source-nhgis/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 6 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 brycewang-stanford-education-data-source-nhgis

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("brycewang-stanford-education-data-source-nhgis")
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/brycewang-stanford-education-data-source-nhgis/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/brycewang-stanford-education-data-source-nhgis/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 6 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 brycewang-stanford-education-data-source-nhgis

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("brycewang-stanford-education-data-source-nhgis")
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/brycewang-stanford-education-data-source-nhgis/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/brycewang-stanford-education-data-source-nhgis/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 6 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 brycewang-stanford-education-data-source-nhgis

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("brycewang-stanford-education-data-source-nhgis")
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/brycewang-stanford-education-data-source-nhgis/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/brycewang-stanford-education-data-source-nhgis/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 6 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 brycewang-stanford-education-data-source-nhgis

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("brycewang-stanford-education-data-source-nhgis")
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/brycewang-stanford-education-data-source-nhgis/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 6 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 brycewang-stanford-education-data-source-nhgis

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("brycewang-stanford-education-data-source-nhgis")
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/brycewang-stanford-education-data-source-nhgis/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/brycewang-stanford-education-data-source-nhgis/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 6 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 brycewang-stanford-education-data-source-nhgis

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("brycewang-stanford-education-data-source-nhgis")
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/brycewang-stanford-education-data-source-nhgis/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/brycewang-stanford-education-data-source-nhgis/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 6 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 brycewang-stanford-education-data-source-nhgis

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("brycewang-stanford-education-data-source-nhgis")
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/brycewang-stanford-education-data-source-nhgis/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/brycewang-stanford-education-data-source-nhgis/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 6 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 brycewang-stanford-education-data-source-nhgis

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("brycewang-stanford-education-data-source-nhgis")
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/brycewang-stanford-education-data-source-nhgis/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/brycewang-stanford-education-data-source-nhgis/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 6 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 brycewang-stanford-education-data-source-nhgis

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("brycewang-stanford-education-data-source-nhgis")
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/brycewang-stanford-education-data-source-nhgis/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/brycewang-stanford-education-data-source-nhgis/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 6 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 brycewang-stanford-education-data-source-nhgis

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/brycewang-stanford-education-data-source-nhgis/SKILL.md https://app.decimal.ai/s/brycewang-stanford-education-data-source-nhgis/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/brycewang-stanford-education-data-source-nhgis/SKILL.md

This gets SKILL.md only. The skill's 6 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/brycewang-stanford-education-data-source-nhgis/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/brycewang-stanford-education-data-source-nhgis.json

This gets SKILL.md only. The skill's 6 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/9/2026
Source: brycewang-stanford/Auto-Empirical-Research-Skills ↗
License: NOASSERTION

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

NHGIS Data Source Reference

IPUMS NHGIS — census geography crosswalks and demographic data for education research. Via the Education Data Portal: geographic crosswalk tables linking K-12 schools (ncessch) and colleges (unitid) to census tracts, block groups, CBSAs, and regions (census 1990-2020). Census demographic variables (income, poverty, race, educational attainment) are NOT in the Portal — access directly from NHGIS via free IPUMS registration. Use when linking school or institutional data to census geography for contextual analysis.

Census geography and demographic data source for education research. NHGIS provides the foundation for linking schools to community characteristics via census tracts, block groups, and school district boundaries.

CRITICAL: Value Encoding

When accessing NHGIS data through the Education Data Portal (not NHGIS directly), categorical variables use integer encodings, not string labels. Always verify the exact codes in the mirror codebook.

Variable Integer Code Meaning
census_region 1 Northeast
census_region 2 Midwest
census_region 3 South
census_region 4 West
cbsa_type 1 Metropolitan
cbsa_type 2 Micropolitan
geocode_accuracy 4 Did not geocode

See ./references/variable-catalog.md for complete encoding tables.

Variable	Integer Code	Meaning
`census_region`	`1`	Northeast
`census_region`	`2`	Midwest
`census_region`	`3`	South
`census_region`	`4`	West
`cbsa_type`	`1`	Metropolitan
`cbsa_type`	`2`	Micropolitan
`geocode_accuracy`	`4`	Did not geocode

CRITICAL: Portal Data Scope

The Education Data Portal provides ONLY geographic crosswalk tables that link schools and colleges to census geography (tracts, block groups, regions, CBSAs). These contain geographic identifiers and assignment columns — approximately 35-47 columns per file.

The Portal does NOT provide census demographic data (population, income, poverty, race, education attainment, housing, language, etc.). For demographic variables, you must access NHGIS directly via IPUMS (free registration required). See ./references/data-access.md for direct access methods.

This skill documents both contexts: Portal crosswalk data (with integer encodings above) and direct NHGIS census variables (in ./references/variable-catalog.md, clearly marked as requiring direct NHGIS access).

What is NHGIS?

NHGIS (from IPUMS, University of Minnesota) provides free access to census geography and demographic data.

Collector: IPUMS, University of Minnesota
Coverage: US census data from 1790-present (decennial census + ACS)
Content: Summary tables, GIS boundary files, time series tables, geographic crosswalks
Frequency: Decennial census (every 10 years) + ACS (annual, 5-year rolling)
Available years: 1790-2020 (decennial), 2005-2023 (ACS 5-year)
Primary identifiers: GISJOIN (NHGIS internal), GEOID (Census Bureau standard)
Education relevance: Links school locations to community demographics via census tracts, block groups, and school district boundaries
Available through Education Data Portal: Geographic crosswalk tables only (school-to-census and college-to-census links for census 1990, 2000, 2010, 2020). Census demographic data requires direct NHGIS access.

Reference File Structure

File	Purpose	When to Read
`geographic-units.md`	Census geography hierarchy (tracts, blocks, districts)	Understanding census geography
`school-geography-links.md`	Linking schools to census areas	Connecting school data to demographics
`time-series.md`	Historical data, harmonization methods	Longitudinal analysis
`variable-catalog.md`	Key demographic variables, codes, special values	Selecting census variables or interpreting encodings
`boundary-changes.md`	How boundaries change between censuses	Handling geographic inconsistencies
`data-access.md`	Direct NHGIS access methods (registration, Data Finder, ipumspy)	Custom census analysis beyond Portal

Decision Trees

What geographic level should I use?

Research question about...
├─ Individual schools
│   ├─ School's immediate neighborhood → Census tract or block group
│   ├─ School attendance zone → SABINS (limited years) or block-to-school crosswalk
│   └─ School district overall → School district boundaries
├─ School districts
│   ├─ District-level demographics → School district geographic level
│   ├─ Within-district variation → Census tracts within district
│   └─ District poverty estimates → SAIPE (via Education Data Portal)
├─ Regional patterns
│   ├─ County-level → County boundaries
│   ├─ Metro area → CBSA (Core Based Statistical Area)
│   └─ State-level → State boundaries
└─ Historical analysis
    ├─ Consistent boundaries needed → Geographically standardized tables
    └─ Original boundaries OK → Nominally integrated tables

How do I link schools to census data?

Linking schools to census demographics?
├─ Have school coordinates (lat/lon)
│   ├─ Point-in-polygon → Spatial join to tract/block group boundaries
│   └─ Need tract ID only → Geocoding service or FCC API
├─ Have school NCES ID only
│   ├─ Use NCES EDGE files → School District Geographic Relationship Files
│   └─ Use Education Data Portal → NHGIS source provides tract links
├─ Need school attendance zones
│   ├─ 2009-2012 data → SABINS school areas
│   └─ Current data → Contact school district (no national source)
└─ See ./references/school-geography-links.md for details

What time period data do I need?

Time period?
├─ Single recent year
│   ├─ Tract/block group level → ACS 5-year (most recent)
│   ├─ Larger areas (65K+ pop) → ACS 1-year
│   └─ Full census count → 2020 Decennial Census
├─ Historical comparison
│   ├─ Same boundaries across time → Geographically standardized tables (to 2010)
│   ├─ Original boundaries → Nominally integrated time series
│   └─ Custom standardization → Use geographic crosswalks
├─ Long time series (1970+)
│   └─ See ./references/time-series.md
└─ Pre-1970
    └─ Limited tract coverage; county/state more complete

Quick Reference: Geographic Levels and Variables

Geographic Levels

Level	Typical Size	Education Use	NHGIS Coverage
Block	~40 people	Point locations	1990-2020
Block Group	~1,500 people	School neighborhoods	1990-2020
Census Tract	~4,000 people	Community context	1910-2020
County Subdivision	Varies	Rural areas	1980-2020
Place	City/town	Urban context	1980-2020
School District	Varies	District analysis	2000-2020
County	~100,000 people	Regional patterns	1790-2020
State	Varies	Policy analysis	1790-2020

Key Identifiers

ID	Format	Level	Example	Notes
`ncessch`	Int64	School	`10000201704`	NCES school ID (schools Portal data)
`unitid`	Int64	College	`100654`	IPEDS institution ID (colleges Portal data)
`GISJOIN`	String with prefix	Any	`G0600010`	NHGIS internal ID; use for direct NHGIS joins (not in Portal data)
`GEOID`	Numeric string	Any	`06001402100`	Census Bureau standard; use for non-NHGIS joins (not in Portal data)
`tract`	Int64	Tract	`402100`	Census tract number (in Portal data)
`block_group`	Int64	Block Group	`1`	Block group within tract (1-9; 0=unassigned)
`geoid_block`	Int64	Block	`60014021001001`	Full block FIPS code (in Portal data — stored as Int64, not String)
`cbsa`	Int64	Metro area	`41860`	Core Based Statistical Area code (2000+ census files only)

Key Education Variables

Topic	Example Variables	Source
Child population	Under 18, 5-17 school-age	Decennial, ACS
Race/ethnicity	Hispanic, White, Black, Asian, etc.	Decennial, ACS
Poverty	Persons below poverty, SNAP receipt	ACS (sample)
Education attainment	HS diploma, BA+ (adults)	ACS (sample)
Language	English proficiency, language at home	ACS (sample)
Housing	Owner/renter, median value, crowding	Decennial, ACS
Family structure	Single-parent, grandparent households	ACS (sample)
Immigration	Foreign-born, recent immigrants	ACS (sample)

Data Sources by Type

Source	Years	Geographic Detail	Content
Decennial Census	1790-2020	Block (1990+)	100% count: age, sex, race, housing
ACS 5-Year	2005-2023	Block group	Sample: income, education, language
ACS 1-Year	2010-2023	Areas 65K+ pop	Sample: same as 5-year
Time Series	1790-2020	Varies	Harmonized across years
Geographic Crosswalks	1990-2020	Block+	Interpolation weights

Portal Variables (Schools NHGIS)

Key geographic and identifying columns in the schools NHGIS datasets. Census 2020 files have 47 columns; earlier census years have fewer (e.g., 1990 has 35 columns — no CBSA or legislative district fields).

Variable	Description	Type
`ncessch`	NCES school ID	Int64
`leaid`	NCES district ID	Int64
`tract`	Census tract number	Int64
`block_group`	Block group number (1-9; 0 = unassigned)	Int64
`geoid_block`	Full block FIPS identifier	Int64
`census_region`	Census Bureau region (1-4, 9)	Int64
`census_division`	Census Bureau division (1-9)	Int64
`cbsa`	CBSA code (2000+ census files only)	Int64
`cbsa_type`	Metropolitan (1) or Micropolitan (2)	Int64
`cbsa_city`	Principal city indicator (0=No, 1=Yes; 2000+ only). See note below.	Int64
`geocode_accuracy`	Geocode confidence (1=High, 2=Medium, 3=Low, 4=Did not geocode, -2=N/A)	Float64
`geocode_accuracy_detailed`	Geocode match type (1-12)	Int64
`class_code`	FIPS place class code	Int64
`lower_chamber_type`	State legislative district lower chamber type (1-8; census 2010 only). See `variable-catalog.md` for code mapping.	Int64
`geo_latitude` / `geo_longitude`	Geocoded coordinates	Float64
`latitude` / `longitude`	CCD-reported coordinates (many nulls in early years)	Float64
`fips`	State FIPS code	Int64
`puma`	Public Use Microdata Area (2000+ census files only)	Int64

Portal Variables (Colleges NHGIS)

Colleges NHGIS datasets have 38 columns (2020 census). Different identifier set from schools.

Variable	Description	Type
`unitid`	IPEDS institution ID	Int64
`opeid`	Office of Postsecondary Education ID	String
`tract`	Census tract number	Int64
`block_group`	Block group number (1-9)	Int64
`geoid_block`	Full block FIPS identifier	Int64
`census_region`	Census Bureau region (1-4, 9)	Int64
`census_division`	Census Bureau division (1-9)	Int64
`cbsa`	CBSA code	Int64
`cbsa_type`	Metropolitan (1) or Micropolitan (2)	Int64
`cbsa_city`	Principal city indicator (0=No, 1=Yes; 2000+ only)	Int64
`geocode_accuracy`	Geocode match score (Int64 in colleges, Float64 in schools)	Int64
`county_fips`	County FIPS code	Int64
`county_name`	County name	String
`state_abbr`	State abbreviation	String

Missing Data Codes

Code	Meaning	When Used
`-2`	Not geocoded	`geocode_accuracy` field in Portal data
`-1`	Missing/not reported	General missing data indicator (e.g., `latitude`, `county_code`)
`0`	Unassigned	`block_group` (rare, ~4 rows in schools)
`null`	Not available	Variable not applicable to this record; many columns heavily null in early years

Schema Difference: Schools NHGIS 2020 files (47 columns) have a different schema than colleges NHGIS 2020 files (38 columns). Schools data includes school-specific identifiers (ncessch, leaid, school_name, mailing/location address fields) while colleges data includes institution-specific identifiers (unitid, opeid, inst_name, county_name). Both entity types have block-level geographic precision. Earlier census years have fewer columns (e.g., Schools 1990 has 35 columns — no CBSA or legislative district fields). Do not assume identical column structures when working across entities or census years.

Data Access

Datasets for NHGIS are available via the mirror system. See datasets-reference.md for canonical paths, mirrors.yaml for mirror configuration, and fetch-patterns.md for fetch code patterns.

Dataset	Type	Years	Path	Codebook
Schools Census 1990	Single	1986-2023	`nhgis/schools_nhgis_geog_1990`	`nhgis/codebook_schools_nhgis_census1990`
Schools Census 2000	Single	1986-2023	`nhgis/schools_nhgis_geog_2000`	`nhgis/codebook_schools_nhgis_census2000`
Schools Census 2010	Single	1986-2023	`nhgis/schools_nhgis_geog_2010`	`nhgis/codebook_schools_nhgis_census2010`
Schools Census 2020	Single	1986-2023	`nhgis/schools_nhgis_geog_2020`	`nhgis/codebook_schools_nhgis_census2020`
Colleges Census 1990	Single	1980-2023	`nhgis/colleges_nhgis_geog_1990`	`nhgis/codebook_colleges_nhgis_census1990`
Colleges Census 2000	Single	1980-2023	`nhgis/colleges_nhgis_geog_2000`	`nhgis/codebook_colleges_nhgis_census2000`
Colleges Census 2010	Single	1980-2023	`nhgis/colleges_nhgis_geog_2010`	`nhgis/codebook_colleges_nhgis_census2010`
Colleges Census 2020	Single	1980-2023	`nhgis/colleges_nhgis_geog_2020`	`nhgis/codebook_colleges_nhgis_census2020`

Codebooks are .xls files co-located with data in all mirrors. Use get_codebook_url() from fetch-patterns.md to construct download URLs.

Truth Hierarchy: When interpreting variable values, apply this priority:

Actual data file (what you observe in the parquet/CSV) — this IS the truth

Live codebook (.xls in mirror) — authoritative documentation, may lag

This skill documentation — convenient summary, may drift from codebook

If this documentation contradicts the codebook, trust the codebook. If the codebook contradicts observed data, trust the data and investigate.

Filtering

import polars as pl

# Filter to a specific school
school_census = df.filter(pl.col("ncessch") == 10000201704)

# Filter to metropolitan areas only (cbsa_type only in 2000+ census files)
metro = df.filter(pl.col("cbsa_type") == 1)

# Filter to a specific census region (South)
south = df.filter(pl.col("census_region") == 3)

# Filter to a specific year
recent = df.filter(pl.col("year") == 2023)

Note: The Portal provides pre-processed school/college-to-census-geography links. For custom census analysis (tract-level demographics, time series, boundary files), use NHGIS directly via methods in ./references/data-access.md (requires free IPUMS registration).

Common Pitfalls

Pitfall	Issue	Solution
Boundary changes	Tracts split/merged between censuses break longitudinal analysis	Use crosswalks or geographically standardized tables
ACS margins of error	Small-area estimates have high uncertainty	Check MOE; aggregate areas if needed
Block data limitations	Only 100% count variables available (no income/poverty)	Use block groups for sample data (ACS)
GISJOIN vs GEOID	Different ID formats cause join failures	Use GISJOIN for NHGIS joins, GEOID for Census Bureau joins
2020 Census noise	Differential privacy added noise to small-area counts	Check for negative values; prefer ACS for detailed characteristics
Schools vs colleges schema	Different column counts (47 vs 38 for 2020) and identifier sets	Check schema before joining; do not assume identical structures
Census year schema drift	Earlier census files have fewer columns (e.g., 1990 lacks CBSA/legislative fields)	Check available columns per census year before relying on them
geocode_accuracy type	Float64 in schools, Int64 in colleges	Cast to consistent type before cross-entity comparison
Using string codes	Portal data uses integer encodings, not string labels	Always verify codes against codebook (see encoding warning above)

Related Data Sources

Source	Relationship	When to Use
`education-data-source-ccd`	School identifiers for linking	Join school data to census geography via `ncessch`
`education-data-source-saipe`	District-level poverty	Use SAIPE for district poverty; NHGIS for tract/block group poverty
`education-data-source-meps`	School-level poverty	MEPS provides school-level poverty estimates; NHGIS provides community context
`education-data-source-ipeds`	College identifiers for linking	Join college data to census geography via `unitid`
`education-data-explorer`	Parent discovery skill	Finding available endpoints
`education-data-query`	Data fetching	Downloading parquet/CSV files

Topic Index

Topic	Reference File
Census tract definition	`./references/geographic-units.md`
Block group definition	`./references/geographic-units.md`
School district boundaries	`./references/geographic-units.md`
School-to-tract linking	`./references/school-geography-links.md`
SABINS attendance areas	`./references/school-geography-links.md`
NCES EDGE files	`./references/school-geography-links.md`
Time series tables	`./references/time-series.md`
Geographic standardization	`./references/time-series.md`
Geographic crosswalks	`./references/time-series.md`
Population variables	`./references/variable-catalog.md`
Income/poverty variables	`./references/variable-catalog.md`
Education variables	`./references/variable-catalog.md`
Tract boundary changes	`./references/boundary-changes.md`
2022 Connecticut changes	`./references/boundary-changes.md`
TIGER/Line versions	`./references/boundary-changes.md`
Direct NHGIS access	`./references/data-access.md`
ipumspy Python package	`./references/data-access.md`
Data Finder workflow	`./references/data-access.md`

When it activates

Automatically, when a task matches. Use for linking education data to census geography.

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 — 8/2/2026

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

brycewang-stanford / Auto-Empirical-Research-Skills

skills/17-DAAF-Contribution-Community-daaf/dot-claude/skills/education-data-source-nhgis/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/2/2026Version v1Bundled 6 files

Illustrative Want to see what brycewang-stanford/education-data-source-nhgis 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

NHGIS Data Source Reference

What is NHGIS?

Reference File Structure

Decision Trees

What geographic level should I use?

How do I link schools to census data?

What time period data do I need?

Quick Reference: Geographic Levels and Variables

Geographic Levels

Key Identifiers

Key Education Variables

Data Sources by Type

Portal Variables (Schools NHGIS)

Portal Variables (Colleges NHGIS)

Missing Data Codes

Data Access

Filtering

Common Pitfalls

Related Data Sources

Topic Index

When it activates

SkillSafety

Source

Related skills

More in the registry