Ready to supercharge your AI agents?

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

NCCS Data Source Reference · brycewang-stanford | DecimalAI

Researchby brycewang-stanford

NCCS Data Source Reference

NCCS — Form 990 data for private nonprofit colleges (Portal: IPEDS-matched, 1993-2016). Revenue, expenses, assets, endowment, governance beyond IPEDS.

Never made a case worse

SkillScore

SkillScore73/100

Test results 73

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

18%73%of test cases passed +55 pts

Without skill4 of 22

With skill16 of 22

12 fixed4 passed either way6 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 taskWhen migrating legacy queries that reference the original NCCS Form 990 field name TOTREV to the Education Data Portal dataset nccs/colleges_nccs_all, what column name should be used?

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-nccs
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-nccs")
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-nccs

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

Copy SKILL.md

Save it in your project, as

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

This gets SKILL.md only. The skill's 5 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-nccs

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-nccs")
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-nccs/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-nccs/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 5 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-nccs

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-nccs")
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-nccs/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-nccs/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 5 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-nccs

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-nccs")
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-nccs/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-nccs/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 5 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-nccs

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-nccs")
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-nccs/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-nccs/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 5 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-nccs

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-nccs")
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-nccs/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-nccs/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 5 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-nccs

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-nccs")
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-nccs/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-nccs/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 5 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-nccs

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-nccs")
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-nccs/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 5 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-nccs

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-nccs")
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-nccs/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-nccs/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 5 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-nccs

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-nccs")
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-nccs/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-nccs/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 5 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-nccs

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-nccs")
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-nccs/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-nccs/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 5 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-nccs

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-nccs")
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-nccs/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-nccs/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 5 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-nccs

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-nccs")
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-nccs/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/brycewang-stanford-education-data-source-nccs/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 5 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-nccs

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

Copy SKILL.md

Save it in your project, as

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

This gets SKILL.md only. The skill's 5 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-nccs/SKILL.md

Read the summary as JSON

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

This gets SKILL.md only. The skill's 5 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

NCCS Data Source Reference

National Center for Charitable Statistics (NCCS) Form 990 data for private nonprofit colleges and universities (Portal mirror: IPEDS-matched institutions, 1993-2016). Use when IRS-based financial data — revenue, expenses, assets, endowment details — or governance information (board composition, executive compensation) is needed beyond what IPEDS provides. Portal data ends at 2016; for current filings use full NCCS directly. Public institutions do not file Form 990 and are excluded.

The NCCS (National Center for Charitable Statistics) is the principal U.S. repository for empirical data on the nonprofit sector, derived from IRS Form 990 filings. It provides financial depth, governance detail, and historical coverage for private nonprofit colleges and universities that goes well beyond what IPEDS collects.

CRITICAL: Value Encoding

The Education Data Portal encodes ALL categorical variables as integers, not strings. Variable names are lowercase in Portal data. Always verify codes against codebooks.

Context fips mult_ein_flag
Portal integer 6 (California) 1 (Yes)
Original NCCS "06" or string N/A

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

Context	`fips`	`mult_ein_flag`
Portal integer	`6` (California)	`1` (Yes)
Original NCCS	`"06"` or string	N/A

What is NCCS?

Operator: Urban Institute, Center on Nonprofits and Philanthropy
Coverage: All U.S. tax-exempt nonprofit organizations (~3.8M in BMF)
Primary data source: IRS Form 990 tax filings
Frequency: Annual (with filing lag)
Available years: 1989-present (Core Series); 2012-present (Efile); 1993-2016 (Portal)
Primary identifier: EIN (Employer Identification Number, 9-digit)
Education relevance: Private nonprofit colleges/universities are 501(c)(3) orgs filing Form 990; NTEE codes B40-B50 cover higher education

Reference File Structure

File	Purpose	When to Read
`nonprofit-data.md`	NCCS datasets and what they contain	Understanding available data sources
`form-990.md`	IRS Form 990 structure and data elements	Understanding what information is collected
`education-relevance.md`	How NCCS relates to higher education	Connecting nonprofit data to education research
`ntee-codes.md`	Nonprofit classification system	Finding and filtering educational institutions
`variable-definitions.md`	Key financial and organizational variables, codes, special values	Interpreting specific data elements or building queries

Decision Trees

What data am I looking for?

Research need?
├─ Financial data for private colleges → ./references/form-990.md
│   ├─ Revenue breakdown → Part VIII (Statement of Revenue)
│   ├─ Expenses by function → Part IX (Statement of Functional Expenses)
│   ├─ Assets and liabilities → Part X (Balance Sheet)
│   └─ Endowment details → Schedule D
├─ Governance/leadership → ./references/form-990.md
│   ├─ Board members → Part VII (Compensation)
│   ├─ Executive compensation → Part VII, Schedule J
│   └─ Policies and procedures → Part VI (Governance)
├─ Organizational characteristics → ./references/nonprofit-data.md
│   ├─ Basic info (name, address, EIN) → BMF
│   ├─ Tax-exempt type → BMF (SUBSECCD)
│   └─ NTEE classification → BMF (NTEECC)
└─ Identify institutions → ./references/ntee-codes.md
    ├─ All higher education → NTEE B40-B50
    ├─ Universities → B40, B41, B42, B43
    └─ Community colleges → B44

Which NCCS dataset should I use?

Dataset selection?
├─ Need universe of all nonprofits?
│   └─ Business Master File (BMF) → ./references/nonprofit-data.md
├─ Need detailed financial variables?
│   ├─ Large organizations (full 990 filers) → Core PC files
│   ├─ All organizations (990 + 990EZ) → Core PZ files
│   └─ Maximum detail (2000+ fields) → Efile database
├─ Need private foundations?
│   └─ Core PF or 990-PF Efile data
└─ Need small grassroots orgs?
    └─ 990-N ePostcard database

How do I connect NCCS to other education data?

Linking NCCS to education data?
├─ Need to match to IPEDS?
│   └─ See ./references/education-relevance.md (EIN-UNITID crosswalk)
├─ Need geographic analysis?
│   └─ Use BMF geocoded addresses + Census crosswalks
├─ Want institutional comparisons?
│   └─ Filter by NTEE codes B40-B50 for higher ed
└─ Analyzing trends over time?
    └─ Use Core data panel (1989-present)

Quick Reference: NCCS Datasets and Variables

Available Datasets

Portal mirror (via fetch_from_mirrors()):

Dataset	Description	Coverage	Rows
990 Forms (`nccs/colleges_nccs_all`)	Form 990 data for higher ed institutions matched to IPEDS	1993-2016, ~2,600 institutions	~30K

Full NCCS (direct download, outside Portal):

Dataset	Description	Coverage	Key Use
Business Master File (BMF)	All active tax-exempt organizations	~3.8M orgs	Sampling frame, basic info
NCCS Core Series	990/990EZ filer financials	1989-2022	Historical financial analysis
IRS 990 Efile	Full electronic filings (2000+ fields)	2012-present	Detailed governance, programs
Form 990-N ePostcard	Small nonprofits (<$50K revenue)	2007-present	Grassroots organizations
Pub78	Organizations eligible for tax-deductible donations	Current	Verify charitable status

Scope note: The Portal mirror dataset contains NCCS Form 990 data matched to IPEDS institutions only (~2,600 institutions). It does NOT include the full NCCS universe of ~3.8M nonprofits. For non-education nonprofits, NTEE-based filtering, or BMF/Core/Efile data, download directly from NCCS.

Key Identifiers

Portal dataset:

ID	Format	Level	Example	Notes
`unitid`	Integer	Institution	`110635`	IPEDS institution ID (Portal addition)
`ein`	Integer	Organization	`10211484`	Employer Identification Number
`fips`	Integer	State	`6` (California)	State FIPS code

Full NCCS (direct download, outside Portal):

ID	Format	Level	Example	Notes
`EIN`	9-digit number	Organization	`123456789`	Unique to each nonprofit
`NTEECC`	Letter + 2 digits	Classification	`B42` (4-year college)	May be imprecise (~25%); NOT in Portal data
`SUBSECCD`	2-digit code	Tax subsection	`03` (501(c)(3) charity)	NOT in Portal data
`FIPS`	5-digit code	Geography	`06037` (LA County)	State + county; Portal uses state-level integer

Education NTEE Codes

Code	Description
B20-B29	Elementary & Secondary Schools
B40	Higher Education Institutions (General)
B41	Two-Year Colleges
B42	Undergraduate Colleges (4-year)
B43	Universities
B50	Graduate/Professional Schools
B60	Adult/Continuing Education
B70	Libraries
B80	Student Services/Organizations
B90	Educational Services/Schools N.E.C.

Portal Variable Name Mapping (Selected)

The Portal dataset has 161 columns. Key mappings from original NCCS/990 names to Portal lowercase names:

Portal Name	Original NCCS/990	Description
`year`	`FISYR`	Academic year (fall semester) — Portal-aligned year (1993-2016)
`fiscal_year`	—	IRS fiscal year ending year from 990 filing (1994-2017); typically `year` + 1
`unitid`	—	IPEDS institution ID (Portal addition)
`ein`	`EIN`	Employer Identification Number
`fips`	`FIPS`	State FIPS code (integer)
`inst_name_nccs`	`NAME`	Organization name from 990 filing
`mult_ein_flag`	—	Multiple-EIN indicator (0=No, 1=Yes)
`contributions_total`	`CONT`	Total contributions
`prog_serv_rev`	`PROGREV`	Program service revenue
`revenue_total`	`TOTREV`	Total revenue
`expenses_total`	`EXPS`	Total expenses
`total_assets_eoy`	`TOTASS`	Total assets (end of year)
`net_assets_eoy`	`NETASS`	Net assets (end of year)
`compensation_officers`	`COMPENS`	Officer compensation
`salaries_other`	`OTHSAL`	Other salaries

Note: The full 161 columns include detailed revenue breakdowns (Part VIII), expense breakdowns (Part IX), and balance sheet items (Part X). Consult the codebook for the complete list. Use get_codebook_url("nccs/codebook_colleges_nccs_form_990") from fetch-patterns.md to download it.

Missing Data Codes

Code	Meaning	When Used
`-1`	Data unavailable	Not collected for this form/year
`-2`	Not applicable	Field doesn't apply to this entity
`-3`	Suppressed	Confidentiality restriction
`null`	Not reported	Organization did not report (may have data)
`0`	Zero value	Explicitly reported as zero

Important: In Portal data, -1/-2/-3 are integer values. However, empirically these codes are rare in the NCCS Portal dataset — most missing data appears as null rather than negative codes. Only a handful of financial columns (e.g., sale_sec_gross_net, changes_net_assets_other) contain any -1/-2/-3 values. A 0 means the organization reported zero; null means the organization did not report. These are distinct conditions.

Data Access

Datasets for NCCS 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
990 Forms	Single	1993-2016	`nccs/colleges_nccs_all`	`nccs/codebook_colleges_nccs_form_990`

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

The Portal dataset is pre-filtered to higher education institutions matched to IPEDS UNITIDs. NTEE codes are NOT included in the Portal data — for NTEE-based filtering, use the full NCCS BMF directly.

import polars as pl

# Filter by year
df_2015 = df.filter(pl.col("year") == 2015)

# Filter by state (integer FIPS codes)
df_ca = df.filter(pl.col("fips") == 6)  # California

# Filter out null values from financial columns
df_valid = df.filter(
    (pl.col("revenue_total").is_not_null()) &
    (pl.col("revenue_total") >= 0)  # Excludes rare -1/-2/-3 codes
)

# Replace negative codes with null for analysis (precautionary)
df = df.with_columns(
    pl.when(pl.col("revenue_total") < 0)
    .then(None)
    .otherwise(pl.col("revenue_total"))
    .alias("revenue_total_clean")
)

Common Pitfalls

Pitfall	Issue	Solution
Using string codes	Portal uses integer FIPS (`6`), not string (`"CA"` or `"06"`)	Always use integer comparisons; filter `>= 1` to exclude missing codes
Filing threshold confusion	Organizations under $200K revenue may file 990-EZ with fewer variables	Check form type; use Core PZ files for combined 990/990-EZ coverage
Fiscal year variation	Nonprofits have different fiscal year ends (June 30 common for colleges)	`year` = Portal academic year (fall semester); `fiscal_year` = IRS fiscal year end (typically `year` + 1). Filter on `year` for IPEDS joins.
No NTEE in Portal data	Portal dataset does not include NTEE codes; pre-filtered to higher ed institutions	Cannot filter by NTEE code; use full NCCS BMF for NTEE-based filtering
NTEE classification accuracy	~25% of NTEE codes estimated to be imprecise	Use NCCS-corrected codes (`NTEE_NCCS`) over IRS-assigned codes when available
Consolidated filings	Some university systems file consolidated 990s covering multiple campuses	Check `mult_ein_flag`; one EIN may represent multiple institutions
Form version changes	Form 990 was redesigned in 2008; variable definitions changed	Be cautious comparing pre-2008 and post-2008 data for governance variables
Missing vs. zero	`0` means explicitly reported zero; `null` means not reported	Distinguish between zero-value and not-reported before aggregating

Key Differences: NCCS vs. IPEDS

Aspect	NCCS (Form 990)	IPEDS
Coverage	All 501(c)(3) nonprofits	Title IV institutions only
Reporting Basis	IRS fiscal year	IPEDS survey cycles
Financial Framework	Nonprofit accounting (GAAP)	Education-specific categories
Governance	Detailed board/compensation data	Limited HR data
Programs	Mission statements, activities	Degree programs, enrollment
Identifier	EIN	UNITID
Update Frequency	Annual (with lag)	Annual

Exploration Workflow

Using Portal Data (Recommended for Education Research)

Fetch data via fetch_from_mirrors("nccs/colleges_nccs_all")
- Data is pre-filtered to higher education institutions matched to IPEDS
- Already includes unitid for IPEDS joining
- 161 financial/organizational variables, 1993-2016
Filter and clean
- Filter by year, state (FIPS), or institution
- Handle nulls (primary missing data form in Portal)
- Check for rare negative codes (-1/-2/-3) in financial columns
Link to IPEDS using unitid and year columns
- Join with IPEDS directory, enrollment, finance, etc.
Analyze — See variable definitions for meaning and limitations

Using Full NCCS (for Non-Education or Pre-Portal Research)

Identify target organizations
- Filter BMF by NTEE codes (B40-B50 for higher ed)
- Verify 501(c)(3) status (SUBSECCD = 03)
- Note EINs for organizations of interest
Select appropriate dataset
- Core PZ for broad coverage
- Core PC for detailed financials (larger orgs)
- Efile for maximum detail (governance, compensation)
Extract and clean data
- Download relevant years from NCCS directly
- Merge with BMF for organizational attributes
- Handle missing data codes
Analyze — See variable definitions for meaning and limitations

Related Data Sources

Source	Relationship	When to Use
`education-data-source-ipeds`	Complementary institution data	Join on EIN-UNITID crosswalk for enrollment, degrees, and education-specific financials
`education-data-explorer`	Parent discovery skill	Finding available endpoints
`education-data-query`	Data fetching	Downloading parquet/CSV files

Topic Index

Topic	Reference File
BMF overview	`./references/nonprofit-data.md`
Core data series	`./references/nonprofit-data.md`
Efile database	`./references/nonprofit-data.md`
Form 990 structure	`./references/form-990.md`
Revenue variables	`./references/form-990.md`
Expense variables	`./references/form-990.md`
Balance sheet	`./references/form-990.md`
Governance data	`./references/form-990.md`
Schedule details	`./references/form-990.md`
Linking to IPEDS	`./references/education-relevance.md`
Private college identification	`./references/education-relevance.md`
Supplementing education research	`./references/education-relevance.md`
NTEE code structure	`./references/ntee-codes.md`
Education NTEE codes	`./references/ntee-codes.md`
NTEEV2 format	`./references/ntee-codes.md`
Financial variables	`./references/variable-definitions.md`
Variable naming conventions	`./references/variable-definitions.md`
Data quality issues	`./references/variable-definitions.md`

When it activates

Automatically, when a task matches. Use when IRS financial depth needed. Portal ends 2016; public institutions excluded (no Form 990).

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-nccs/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/2/2026Version v1Bundled 5 files

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

NCCS Data Source Reference

What is NCCS?

Reference File Structure

Decision Trees

What data am I looking for?

Which NCCS dataset should I use?

How do I connect NCCS to other education data?

Quick Reference: NCCS Datasets and Variables

Available Datasets

Key Identifiers

Education NTEE Codes

Portal Variable Name Mapping (Selected)

Missing Data Codes

Data Access

Filtering

Common Pitfalls

Key Differences: NCCS vs. IPEDS

Exploration Workflow

Using Portal Data (Recommended for Education Research)

Using Full NCCS (for Non-Education or Pre-Portal Research)

Related Data Sources

Topic Index

When it activates

SkillSafety

Source

Related skills

More in the registry