Ready to supercharge your AI agents?

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

CRDC Data Source Reference · brycewang-stanford | DecimalAI

Researchby brycewang-stanford

CRDC Data Source Reference

CRDC — biennial OCR survey of all U.S. public schools (2011-2021). Discipline, course access, harassment, restraint/seclusion by race/sex/disability/EL.

Never made a case worse

SkillScore

SkillScore82/100

Test results 82

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

55%82%of test cases passed +27 pts

Without skill12 of 22

With skill18 of 22

6 fixed12 passed either way4 still failing0 broke

Measured on gemini-3.6-flash8/9/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWhich 12-digit identifier column present in CRDC Education Data Portal files allows direct joining with school-level Common Core of Data (CCD) datasets?

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-crdc
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-crdc")
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-crdc

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

Copy SKILL.md

Save it in your project, as

.claude/skills/brycewang-stanford-education-data-source-crdc/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-crdc

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-crdc")
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-crdc/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-crdc/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-crdc

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-crdc")
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-crdc/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-crdc/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-crdc

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-crdc")
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-crdc/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-crdc/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-crdc

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-crdc")
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-crdc/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-crdc/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-crdc

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-crdc")
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-crdc/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-crdc/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-crdc

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-crdc")
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-crdc/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-crdc/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-crdc

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-crdc")
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-crdc/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-crdc

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-crdc")
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-crdc/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-crdc/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-crdc

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-crdc")
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-crdc/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-crdc/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-crdc

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-crdc")
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-crdc/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-crdc/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-crdc

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-crdc")
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-crdc/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-crdc/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-crdc

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-crdc")
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-crdc/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

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

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

Copy SKILL.md

Save it in your project, as

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

Read the summary as JSON

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

CRDC Data Source Reference

Civil Rights Data Collection (CRDC) — mandatory biennial OCR survey of all U.S. public schools measuring educational opportunity and civil rights compliance (2011-2021). Use when analyzing school discipline disparities by race/disability, course access equity, harassment, restraint/seclusion, or chronic absenteeism. Data disaggregated by race, sex, disability, and English learner status. Note: 2020-21 is COVID-impacted and not directly comparable to other years; 2011-14 are sampled, not universe.

The Civil Rights Data Collection is a mandatory biennial survey of all U.S. public schools measuring educational opportunity and civil rights compliance. It is the only national source for school-level discipline disparities, course access equity, harassment, and restraint/seclusion data disaggregated by race, sex, disability, and English learner status.

CRITICAL: Value Encoding

The Education Data Portal uses integer codes, not the string codes shown in OCR documentation. Always filter using integers.

Variable String Code (Raw) Portal Integer
Race: White WH 1
Race: Black BL 2
Race: Hispanic HI 3
Sex: Male M 1
Sex: Female F 2

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

Variable	String Code (Raw)	Portal Integer
Race: White	`WH`	`1`
Race: Black	`BL`	`2`
Race: Hispanic	`HI`	`3`
Sex: Male	`M`	`1`
Sex: Female	`F`	`2`

What is CRDC?

The Civil Rights Data Collection is a mandatory biennial survey of all public schools and districts that measures educational opportunity and civil rights compliance:

Collector: U.S. Department of Education, Office for Civil Rights (OCR)
Purpose: Enforce civil rights laws, identify discrimination, monitor equity
Coverage: All public LEAs and schools receiving federal financial assistance
Frequency: Biennial (every 2 school years)
Disaggregation: Race/ethnicity, sex, disability status, English learner status
History: Collected since 1968 (as Elementary and Secondary School Civil Rights Survey)
Available years: 2011, 2013, 2015, 2017, 2020, 2021 (biennial — no data for even-numbered school years)
Available through: Education Data Portal mirrors

Reference File Structure

File	Purpose	When to Read
`civil-rights-context.md`	Legal framework (Title VI, IX, Section 504, IDEA)	Understanding why data is collected
`data-elements.md`	All data categories and what's collected	Planning analysis, identifying variables
`collection-methodology.md`	Sampling, universe, timeline, reporting	Understanding coverage limitations
`variable-definitions.md`	Key variables, codes, disaggregation categories	Coding data, interpreting values
`data-quality.md`	Known issues, suppression, state variations	Addressing limitations in analysis
`historical-changes.md`	Evolution across collection years	Time series analysis, year comparison

Decision Trees

What CRDC data do I need?

Research topic?
├─ School discipline
│   ├─ Suspensions (ISS/OSS) → ./references/data-elements.md#discipline
│   ├─ Expulsions → ./references/data-elements.md#discipline
│   ├─ Referrals to law enforcement → ./references/data-elements.md#discipline
│   ├─ School-related arrests → ./references/data-elements.md#discipline
│   └─ Preschool suspensions → ./references/data-elements.md#discipline
├─ Restraint and seclusion
│   └─ Physical restraint, mechanical, seclusion → ./references/data-elements.md#restraint-seclusion
├─ Harassment and bullying
│   ├─ Allegations by type → ./references/data-elements.md#harassment
│   └─ Disciplined for harassment → ./references/data-elements.md#harassment
├─ Course access and enrollment
│   ├─ AP/IB courses → ./references/data-elements.md#advanced-courses
│   ├─ Gifted/talented → ./references/data-elements.md#gifted-talented
│   ├─ Math/science courses → ./references/data-elements.md#course-access
│   └─ Computer science → ./references/data-elements.md#course-access
├─ Chronic absenteeism
│   └─ Students missing 15+ days → ./references/data-elements.md#chronic-absenteeism
├─ Special populations
│   ├─ Students with disabilities (IDEA) → ./references/data-elements.md#students-with-disabilities
│   ├─ English learners → ./references/data-elements.md#english-learners
│   └─ Preschool enrollment → ./references/data-elements.md#preschool
├─ School staffing
│   ├─ Teacher experience/certification → ./references/data-elements.md#staffing
│   └─ Counselors, nurses, etc. → ./references/data-elements.md#staffing
└─ School safety
    └─ Offenses, violence, weapons → ./references/data-elements.md#school-offenses

Understanding the legal context?

Civil rights law question?
├─ Race/ethnicity discrimination → ./references/civil-rights-context.md#title-vi
├─ Sex/gender discrimination → ./references/civil-rights-context.md#title-ix
├─ Disability discrimination → ./references/civil-rights-context.md#section-504
├─ Special education services → ./references/civil-rights-context.md#idea
├─ Age discrimination → ./references/civil-rights-context.md#age-discrimination-act
└─ OCR enforcement process → ./references/civil-rights-context.md#ocr-enforcement

Data quality concerns?

Data quality issue?
├─ Missing or suppressed data → ./references/data-quality.md#suppression
├─ Definition inconsistencies → ./references/data-quality.md#definition-variation
├─ Year-to-year comparability → ./references/historical-changes.md
├─ COVID-19 impact (2020-21) → ./references/data-quality.md#covid-impact
├─ Underreporting concerns → ./references/data-quality.md#underreporting
└─ State-level variations → ./references/data-quality.md#state-variations

Quick Reference: CRDC Data Categories

Collection Years

School Year	Collection	Coverage	Key Notes
2011-12	Sample	~7,000 districts	First modern CRDC; sampled
2013-14	Expanded	~16,000 districts	Larger sample
2015-16	Near-universe	~96,000 schools	First near-complete
2017-18	Universe	~96,000 schools	Full universe collection
2020-21	Universe	~97,500 schools	COVID-impacted year
2021-22	Universe	~98,000 schools	Post-pandemic baseline
2023-24	Universe	In progress	Current collection

Critical: CRDC is biennial - no data for odd years (2012, 2014, 2016, 2018, 2019).

Data Categories

Category	Description	Disaggregation
Enrollment	Student counts by grade level	Race, sex, disability, LEP
Discipline	Suspensions, expulsions, arrests	Race, sex, disability, LEP
Restraint/Seclusion	Physical/mechanical restraint, seclusion	Race, sex, disability
Harassment	Allegations and discipline by type	Race, sex, disability
Course Access	AP, IB, math, science, CS offerings	School-level, enrollment by race/sex
Chronic Absenteeism	15+ days missed	Race, sex, disability, LEP
Staffing	Teachers, counselors, nurses, etc.	FTE counts, qualifications
Offenses	Violence, weapons, drugs at school	Type of offense
Retention	Students retained in grade	Race, sex, disability

Key Identifiers

ID	Format	Level	Example	Notes
`crdc_id`	12-digit string	School	`010000201705`	Primary CRDC identifier; always present
`ncessch`	12-digit string	School	`010000201705`	NCES school ID, joins to CCD; may be null for some entries
`leaid`	7-digit string	District	`0100002`	NCES district ID, joins to CCD; always present

Note: The OCR-internal combokey (e.g., AL-0010-00002) does NOT appear as a column in Portal data. Use crdc_id or ncessch for school-level identification.

WARNING: String Type Override Required. When reading CRDC data from CSV, ncessch, leaid, and crdc_id must be read as String (pl.Utf8) via schema_overrides. Polars infers these as Int64, silently destroying leading zeros for ~19% of rows (FIPS 01-09 states: AL, AK, AZ, AR, CA, CO, CT). Parquet files preserve types automatically.

Race/Ethnicity (Portal Integer Codes)

Code	Category
`1`	White
`2`	Black or African American
`3`	Hispanic/Latino of any race
`4`	Asian
`5`	American Indian or Alaska Native
`6`	Native Hawaiian or Other Pacific Islander
`7`	Two or more races
`99`	Total

Empirically observed values: Codes 1-7 and 99 appear in CRDC data. Additional codes (8 Nonresident alien, 9 Unknown, 20 Other) are defined in the codebook but are not observed in practice for K-12 CRDC datasets. See variable-definitions.md for the full codebook listing.

Sex (Portal Integer Codes)

Code	Category
`1`	Male
`2`	Female
`3`	Non-binary/other (newer collections; rows exist but mostly contain -1 or -2 values)
`99`	Total

Disability Status (Portal Integer Codes)

Code	Category
`0`	Students without disabilities
`1`	Students with disabilities (served under IDEA)
`2`	Students with Section 504 only
`3`	Students not served under IDEA (includes 504-only and non-disabled)
`4`	Students with disabilities (combined: IDEA + Section 504)
`99`	Total

Note: Not all disability codes appear in every dataset. Enrollment data typically has [1, 2, 99]; discipline data has [0, 1, 2, 4, 99]. Verify codes against the live codebook for your specific dataset.

English Learner Status (Portal Integer Codes)

Code	Category
`1`	English learner (EL/LEP)
`99`	All students

Missing Data Codes

Code	Meaning	When Used
`-1`	Missing	Data not reported by school/district
`-2`	Not applicable	Item doesn't apply to this entity
`-3`	Suppressed	Data suppressed for privacy (small cell sizes)
`-9`	Skip pattern	Question not asked in this collection year (rare; check codebook)
`null`	Not available	Value absent from dataset (e.g., `ncessch` is null for some schools)

Verify these codes against the live codebook for your specific dataset. Use get_codebook_url() from fetch-patterns.md.

Data Access

Datasets for CRDC are available via the Education Data Portal mirror system. See datasets-reference.md for canonical paths, mirrors.yaml for mirror configuration, and fetch-patterns.md for fetch code patterns including fetch_from_mirrors() and fetch_yearly_from_mirrors().

Key datasets (6 of 22 total):

Dataset	Path	Type	Codebook
Discipline	`crdc/schools_crdc_discipline_k12_{year}`	Yearly	`crdc/codebook_schools_crdc_discipline`
AP/IB Enrollment	`crdc/schools_crdc_apib_enroll`	Single	`crdc/codebook_schools_crdc_ap-ib-enrollment`
Enrollment	`crdc/schools_crdc_enrollment_k12_{year}`	Yearly	`crdc/codebook_schools_crdc_enrollment`
Chronic Absenteeism	`crdc/schools_crdc_chronic_absenteeism_{year}`	Yearly	`crdc/codebook_schools_crdc_chronic-absenteeism`
Harassment/Bullying	`crdc/schools_crdc_harass_bully_students_{year}`	Yearly	`crdc/codebook_schools_crdc_harrassment-bullying-students`
Restraint/Seclusion	`crdc/schools_crdc_restraint_seclusion_students_{year}`	Yearly	`crdc/codebook_schools_crdc_restraint-seclusion-students`

22 CRDC datasets exist total (6 yearly, 16 single-file). See datasets-reference.md for the complete list with all paths and codebook references.

CRDC naming note: Some data file paths use concatenated names (e.g., disciplineinstances, mathandscience) while their codebook counterparts use underscored names (e.g., discipline_instances, math_and_science). Always use the exact paths from datasets-reference.md.

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

from fetch_patterns import get_codebook_url
url = get_codebook_url("crdc/codebook_schools_crdc_discipline")

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 single state (California) and disaggregated race groups
df = df.filter(
    (pl.col("fips") == 6) &       # California
    (pl.col("race") < 99)          # Exclude totals row
)

# Filter to specific demographic intersection
df = df.filter(
    (pl.col("race") == 2) &        # Black students
    (pl.col("sex") == 99) &         # Both sexes (total)
    (pl.col("disability") == 99)    # All disability statuses
)

Common Pitfalls

Pitfall	Issue	Solution
Using string codes	Portal uses integers, not strings	`race == 2` not `race == "BL"`
Raw counts	Different enrollment sizes	Use rates per 100/1000 students
Missing years	Assuming annual data	Remember biennial schedule
COVID year	2020-21 not comparable	Flag or exclude from trends
Suppression	Small cell suppression	Check suppression rates first
Sample years	Early years sampled	Use 2015+ for national estimates
Definition drift	Variables change over time	Check codebooks for each year
Forgetting code 99	Including totals in calculations	Filter `race < 99` for disaggregated analysis
CSV type inference	Polars infers `ncessch`/`leaid`/`crdc_id` as Int64	Use `schema_overrides={"ncessch": pl.Utf8, "leaid": pl.Utf8, "crdc_id": pl.Utf8}`

Equity Analysis Framework

CRDC data is designed for civil rights analysis. Key analytical approaches:

Disparity Ratios

import polars as pl

# Calculate discipline disparity using Portal integer codes
def discipline_disparity(df, discipline_var, group_a, group_b):
    """
    Calculate risk ratio between two groups.
    Value > 1 indicates group_a has higher rate.

    Args:
        df: DataFrame with CRDC data
        discipline_var: Column with discipline counts
        group_a: Integer race code (e.g., 2 for Black)
        group_b: Integer race code (e.g., 1 for White)

    Example:
        # Black vs White OSS disparity
        disparity = discipline_disparity(df, 'students_susp_out_sch_single', 2, 1)
    """
    # Filter to each group (using integer codes)
    df_a = df.filter(pl.col('race') == group_a)
    df_b = df.filter(pl.col('race') == group_b)

    # Calculate rates
    rate_a = df_a.select(pl.col(discipline_var).sum()).item() / \
             df_a.select(pl.col('enrollment_crdc').sum()).item()
    rate_b = df_b.select(pl.col(discipline_var).sum()).item() / \
             df_b.select(pl.col('enrollment_crdc').sum()).item()

    return rate_a / rate_b

# Example: Black (race=2) vs White (race=1) disparity
# disparity = discipline_disparity(df, 'students_susp_out_sch_single', 2, 1)

Composition vs. Representation

Composition: What share of suspended students are Black?
Representation: Are Black students suspended at higher rates than enrollment share?

Risk Ratios

Compare discipline/outcome rates across groups
Adjust for school-level factors when appropriate

Related Data Sources

Source	Relationship	When to Use
`education-data-source-ccd`	School/district characteristics	Linking CRDC to school demographics, locale, Title I status (join on `ncessch` or `leaid`)
`education-data-source-edfacts`	Assessment outcomes	Comparing discipline patterns to academic outcomes
`education-data-explorer`	Parent discovery skill	Finding available CRDC endpoints and variables
`education-data-query`	Data fetching	Downloading CRDC parquet/CSV files from mirrors
`education-data-context`	General interpretation	Education data interpretation and citation generation

Topic Index

Topic	Reference File
Title VI (race)	`./references/civil-rights-context.md`
Title IX (sex)	`./references/civil-rights-context.md`
Section 504 (disability)	`./references/civil-rights-context.md`
IDEA	`./references/civil-rights-context.md`
OCR enforcement	`./references/civil-rights-context.md`
Discipline data	`./references/data-elements.md`
Restraint/seclusion	`./references/data-elements.md`
Harassment	`./references/data-elements.md`
Course access	`./references/data-elements.md`
AP/IB/Gifted	`./references/data-elements.md`
Chronic absenteeism	`./references/data-elements.md`
Staffing	`./references/data-elements.md`
Preschool	`./references/data-elements.md`
Sampling approach	`./references/collection-methodology.md`
Collection timeline	`./references/collection-methodology.md`
Variable codes	`./references/variable-definitions.md`
Suppression rules	`./references/data-quality.md`
COVID impact	`./references/data-quality.md`
Year changes	`./references/historical-changes.md`

When it activates

Automatically, when a task matches. Use for civil rights and equity analysis. 2020-21 COVID-impacted; 2011-14 sampled, not universe.

About this skill

Automatic

Data Analyst 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-crdc/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/2/2026Version v1Bundled 6 files

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

CRDC Data Source Reference

What is CRDC?

Reference File Structure

Decision Trees

What CRDC data do I need?

Understanding the legal context?

Data quality concerns?

Quick Reference: CRDC Data Categories

Collection Years

Data Categories

Key Identifiers

Race/Ethnicity (Portal Integer Codes)

Sex (Portal Integer Codes)

Disability Status (Portal Integer Codes)

English Learner Status (Portal Integer Codes)

Missing Data Codes

Data Access

Filtering

Common Pitfalls

Equity Analysis Framework

Disparity Ratios

Composition vs. Representation

Risk Ratios

Related Data Sources

Topic Index

When it activates

SkillSafety

Source

Related skills

More in the registry