Ready to supercharge your AI agents?

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

MEPS Data Source Reference · brycewang-stanford | DecimalAI

Researchby brycewang-stanford

MEPS Data Source Reference

MEPS — Urban Institute modeled school-level poverty (% at 100% FPL), from CCD + SAIPE (public schools, 2009-2022, 2-3yr lag).

Never made a case worse

SkillScore

SkillScore91/100

Test results 91

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

32%91%of test cases passed +59 pts

Without skill7 of 22

With skill20 of 22

13 fixed7 passed either way2 still failing0 broke

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

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskI am reading older research documentation that refers to MEPS variables as `meps`, `meps_mod`, and `meps_se`. What are the exact field names used for these three variables in the Education Data Portal?

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-meps
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-meps")
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-meps

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

Copy SKILL.md

Save it in your project, as

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

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-meps")
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-meps/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-meps/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-meps

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-meps")
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-meps/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-meps/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-meps

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-meps")
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-meps/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-meps/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-meps

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-meps")
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-meps/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-meps/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-meps

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-meps")
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-meps/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-meps/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-meps

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-meps")
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-meps/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-meps/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-meps

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-meps")
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-meps/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-meps

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-meps")
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-meps/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-meps/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-meps

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-meps")
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-meps/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-meps/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-meps

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-meps")
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-meps/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-meps/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-meps

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-meps")
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-meps/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-meps/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-meps

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-meps")
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-meps/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

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

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

Copy SKILL.md

Save it in your project, as

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

Read the summary as JSON

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

MEPS Data Source Reference

Model Estimates of Poverty in Schools (MEPS) — Urban Institute modeled estimates of school-level poverty (% students at or below 100% FPL), derived from CCD and Census SAIPE data (public schools, 2009-2022, 2-3 year lag). Use when analyzing school poverty rates, comparing poverty across states, or when FRPL data is unreliable due to CEP enrollment. Unlike FRPL, MEPS provides consistent cross-state measurement at a standardized 100% FPL threshold. Public schools only.

School-level poverty measure from the Urban Institute that is comparable across states and time, unlike Free/Reduced-Price Lunch (FRPL) data.

CRITICAL: Value Encoding

The Education Data Portal returns MEPS data with integer-encoded categorical and identifier columns. This differs from some external documentation:

Column Portal Type Example Value Notes
fips Int64 6 State FIPS as integer (California = 6)
ncessch Int64 10000200277 12-digit NCES school ID as integer
leaid Int64 100002 7-digit district ID as integer
gleaid Int64 100013 Geographic LEA ID as integer
year Int64 2018 Academic year (fall semester)

Missing values: Unlike CCD, MEPS uses native nulls rather than negative coded values (-1, -2, -3). While the codebook lists these codes, actual Portal data contains nulls for missing values.

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

Column	Portal Type	Example Value	Notes
`fips`	Int64	`6`	State FIPS as integer (California = 6)
`ncessch`	Int64	`10000200277`	12-digit NCES school ID as integer
`leaid`	Int64	`100002`	7-digit district ID as integer
`gleaid`	Int64	`100013`	Geographic LEA ID as integer
`year`	Int64	`2018`	Academic year (fall semester)

What is MEPS?

MEPS is a modeled estimate of the share of students from households with incomes at or below 100% of the Federal Poverty Level (FPL).

Purpose: Provide consistent school poverty measurement across all US states
Key advantage: Comparable across states (unlike FRPL which varies by state policy)
Data level: School-level (individual schools)
Coverage: 2009-2022 (actual Portal data range)
Source: Urban Institute, derived from CCD and SAIPE data
Primary identifier: ncessch (12-digit NCES school ID)
Public schools only: Does not cover private schools

Reference File Structure

File	Purpose	When to Read
`methodology.md`	How MEPS estimates are calculated	Understanding the model, research validation
`comparison-to-frpl.md`	Detailed FRPL vs MEPS comparison	Deciding which measure to use
`data-sources.md`	Input data (CCD, SAIPE, ISP)	Understanding data provenance
`variable-definitions.md`	MEPS variables and codes	Building queries, interpreting results
`data-quality.md`	Limitations, uncertainty, appropriate uses	Research design, caveats

Decision Trees

Should I use MEPS or FRPL?

What is your research goal?
├─ Compare poverty across states → Use MEPS
│   └─ FRPL varies by state policy, MEPS is standardized
├─ Track poverty over time (post-2010) → Use MEPS
│   └─ CEP adoption makes FRPL inconsistent
├─ Study CEP/universal meals impact → Use both
│   └─ Compare MEPS (true poverty) vs FRPL (program participation)
├─ Match historical research (pre-2010) → Consider FRPL
│   └─ MEPS only available 2006+, but FRPL was more reliable then
├─ Need 185% FPL threshold → Use FRPL with caveats
│   └─ MEPS only measures 100% FPL
└─ Federal funding formulas → Check formula requirements
    └─ Some formulas mandate FRPL; note limitations

Which MEPS variable should I use?

Which estimate type?
├─ Standard analysis → `meps_poverty_pct`
│   └─ Original modeled estimate
├─ High-poverty district adjustment → `meps_mod_poverty_pct`
│   └─ Modified MEPS for districts where model underestimates
├─ Need confidence bounds → `meps_poverty_se`
│   └─ Standard error for uncertainty analysis
└─ Categorical analysis → Derive from `meps_poverty_pct`
    └─ Create quartiles/quintiles as needed

How do I access MEPS data?

Access method?
├─ Mirror download (recommended) → See "Data Access" section below
└─ Join with other data → Use `ncessch` as join key

Quick Reference: MEPS Variables

Data Access: MEPS data is fetched from mirrors (parquet/CSV). See datasets-reference.md for canonical paths, mirrors.yaml for mirror configuration, and fetch-patterns.md for fetch code patterns.

Portal Field Names

The Portal field names differ from some external MEPS documentation:

External Documentation	Portal Field Name
`meps` / `school_poverty`	`meps_poverty_pct`
`meps_mod`	`meps_mod_poverty_pct`
`meps_se`	`meps_poverty_se`

Variable Reference

All ID and categorical columns use integer encoding in Portal data:

Variable	Description	Type	Range/Notes
`ncessch`	NCES school ID (12-digit)	Int64	e.g., `10000200277`
`ncessch_num`	NCES school ID (numeric duplicate)	Int64	Same as ncessch
`year`	School year (fall)	Int64	2009-2022 (actual data range)
`fips`	State FIPS code	Int64	1-56
`leaid`	District ID (7-digit)	Int64	e.g., `100002`
`gleaid`	Geographic LEA ID	Int64	e.g., `100013`
`meps_poverty_pct`	Estimated share in poverty (100% FPL)	Float64	0.0-60.5% (actual range)
`meps_mod_poverty_pct`	Modified MEPS estimate	Float64	0.0-100.0%
`meps_poverty_se`	Standard error of estimate	Float64	0.5-3.8 (typical range)
`meps_poverty_ptl`	National percentile (enrollment-weighted)	Int64	1-100
`meps_mod_poverty_ptl`	Modified percentile (enrollment-weighted)	Int64	1-100

Key Identifiers

ID	Format	Level	Example	Notes
`ncessch`	Int64 (12-digit)	School	`10000200277`	Primary join key for school-level joins
`leaid`	Int64 (7-digit)	District	`100002`	Use for district-level joins (e.g., with SAIPE)
`gleaid`	Int64	Geographic LEA	`100013`	Geographic LEA ID
`fips`	Int64	State	`6`	State FIPS code

Missing Data Codes

Code	Meaning	When Used
`null`	Missing / Not available	All missing values — MEPS uses native nulls, not negative coded values

Important: Unlike CCD and most other Portal sources, MEPS does not use -1, -2, -3 coded values. Use null checks:

# Correct
valid_data = df.filter(pl.col("meps_poverty_pct").is_not_null())

# Wrong (MEPS doesn't use -1, -2, -3 coded values)
# df.filter(pl.col("meps_poverty_pct") >= 0)  # Unnecessary

Data Access

Datasets for MEPS 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
School Poverty	Single	2009-2022	`meps/schools_meps`	`meps/codebook_schools_meps`

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

url = get_codebook_url("meps/codebook_schools_meps")

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

# Filter to valid poverty estimates only (drop nulls)
df = df.filter(pl.col("meps_poverty_pct").is_not_null())

# High-poverty schools (top quartile nationally)
high_poverty = df.filter(pl.col("meps_poverty_ptl") >= 75)

# Use modified MEPS for high-poverty districts
df = df.with_columns(
    pl.when(pl.col("meps_mod_poverty_pct").is_not_null())
    .then(pl.col("meps_mod_poverty_pct"))
    .otherwise(pl.col("meps_poverty_pct"))
    .alias("poverty_pct_best")
)

Common Pitfalls

Pitfall	Issue	Solution
Using negative value filters	Filtering `>= 0` to remove missing values; MEPS uses nulls, not `-1`/`-2`/`-3`	Use `.is_not_null()` instead of `>= 0`
Confusing MEPS with FRPL thresholds	MEPS measures 100% FPL; FRPL uses 130-185% FPL — rates are not comparable	State clearly which measure and threshold; never mix in same analysis
Using wrong field names	Documentation says `meps` but actual Portal field is `meps_poverty_pct`	Always use Portal field names: `meps_poverty_pct`, `meps_mod_poverty_pct`, `meps_poverty_se`
Ignoring standard errors	Treating MEPS as exact counts; they are modeled estimates with uncertainty	Use `meps_poverty_se` for close comparisons; flag when SE exceeds meaningful difference
Including private schools	MEPS only covers public schools; joining with datasets containing private schools inflates nulls	Filter to public schools before joining
Expecting recent data	MEPS has 2-3 year data lag; latest available may be several years behind	Check actual year range (2009-2022) before planning analysis

Why MEPS Instead of FRPL?

Issue	FRPL Problem	MEPS Solution
CEP schools	All students counted as "free lunch" regardless of income	Uses modeled estimates independent of meal programs
State variation	Different states use different eligibility criteria	Standardized 100% FPL threshold nationwide
Direct certification	Varies by state program participation	Calibrated to Census SAIPE data
Income threshold	130-185% FPL (varies)	Consistent 100% FPL
Time consistency	Policy changes affect comparability over time	Methodology consistent across years

Critical insight: As of 2020, ~60% of schools participate in CEP or other universal meal programs, making FRPL increasingly unreliable as a poverty proxy.

Key Methodological Points

Model-based: MEPS uses a linear probability model, not direct counts
Calibrated to SAIPE: District totals align with Census poverty estimates
School-specific: Reflects enrolled students, not neighborhood demographics
100% FPL threshold: Lower than FRPL (185%) - captures deeper poverty
Public schools only: Does not cover private schools

Common Use Cases

Use Case	Recommended Approach
School poverty rankings	Use `meps_poverty_pct`, note `meps_poverty_se` for close comparisons
State-level aggregation	Sum weighted by enrollment
Poverty-achievement gaps	Join MEPS with EDFacts assessments on `ncessch`
Resource allocation analysis	Join MEPS with CCD finance on `leaid`
CEP impact research	Compare MEPS vs FRPL trends over time
Title I targeting analysis	Use `meps_poverty_pct` to identify high-poverty schools

Joining MEPS with Other Data

Source	Join Key	Use Case
CCD Directory	`ncessch`, `year`	Add school characteristics
CCD Enrollment	`ncessch`, `year`	Get enrollment for weighting
CRDC	`ncessch`, `year`	Discipline, AP courses + poverty
EDFacts	`ncessch`, `year`	Achievement + poverty analysis
SAIPE (district)	`leaid`, `year`	Validate against Census estimates

Limitations

Years available: 2009-2022 (actual Portal data range)
Public schools only: No private school coverage
Modeled estimates: Subject to estimation error (use meps_poverty_se)
100% FPL only: Does not capture near-poverty (100-185% FPL)
Not real-time: 2-3 year data lag typical

Related Data Sources

Source	Relationship	When to Use
`education-data-source-saipe`	District-level poverty (Census)	District-level analysis; MEPS calibration source
`education-data-source-ccd`	School/district characteristics	Join for enrollment, demographics, finance
`education-data-source-crdc`	Civil rights/discipline data	Join on `ncessch` for poverty + discipline analysis
`education-data-source-edfacts`	State assessment data	Join on `ncessch` for poverty + achievement analysis
`education-data-explorer`	Parent discovery skill	Finding available endpoints
`education-data-query`	Data fetching	Downloading MEPS parquet/CSV files

Topic Index

Topic	Reference File
Linear probability model	`./references/methodology.md`
SAIPE calibration	`./references/methodology.md`
Modified MEPS	`./references/methodology.md`
Validation evidence	`./references/methodology.md`
CEP impact on FRPL	`./references/comparison-to-frpl.md`
Direct certification	`./references/comparison-to-frpl.md`
State policy variation	`./references/comparison-to-frpl.md`
CCD data inputs	`./references/data-sources.md`
SAIPE data inputs	`./references/data-sources.md`
ISP data (MEPS 2.0)	`./references/data-sources.md`
Variable definitions	`./references/variable-definitions.md`
Poverty thresholds	`./references/variable-definitions.md`
Standard errors	`./references/data-quality.md`
Appropriate uses	`./references/data-quality.md`
Known limitations	`./references/data-quality.md`

When it activates

Automatically, when a task matches. Use when FRPL is unreliable due to CEP. Consistent cross-state measurement. Public schools only.

About this skill

Automatic

Research pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v8 — 10/22/2026

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-meps/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/2/2026Version v1Bundled 5 files

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

MEPS Data Source Reference

What is MEPS?

Reference File Structure

Decision Trees

Should I use MEPS or FRPL?

Which MEPS variable should I use?

How do I access MEPS data?

Quick Reference: MEPS Variables

Portal Field Names

Variable Reference

Key Identifiers

Missing Data Codes

Data Access

Filtering

Common Pitfalls

Why MEPS Instead of FRPL?

Key Methodological Points

Common Use Cases

Joining MEPS with Other Data

Limitations

Related Data Sources

Topic Index

When it activates

SkillSafety

Source

Related skills

More in the registry