Ready to supercharge your AI agents?

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

FSA Data Source Reference · brycewang-stanford | DecimalAI

Databy brycewang-stanford

FSA Data Source Reference

FSA — Title IV aid at institution level (~5,500 institutions, 1999-2021). Pell Grants, Direct/PLUS loans, campus-based aid, financial responsibility scores, 90/10 metrics.

Never made a case worse

SkillScore

SkillScore74/100

Test results 74

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

26%74%of test cases passed +48 pts

Without skill6 of 23

With skill17 of 23

11 fixed6 passed either way6 still failing0 broke

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

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskI am building a query on `fsa/colleges_fsa_campus_based_volume` to calculate institutional allocations for Federal Work-Study. A researcher suggests filtering by `award_type == 'FWS'` or `award_type == 'Work-Study'`. How are award types actually encoded in this dataset?

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-fsa
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-fsa")
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-fsa

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

Copy SKILL.md

Save it in your project, as

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

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-fsa")
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-fsa/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-fsa/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-fsa

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-fsa")
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-fsa/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-fsa/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-fsa

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-fsa")
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-fsa/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-fsa/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-fsa

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-fsa")
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-fsa/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-fsa/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-fsa

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-fsa")
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-fsa/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-fsa/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-fsa

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-fsa")
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-fsa/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-fsa/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-fsa

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-fsa")
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-fsa/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-fsa

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-fsa")
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-fsa/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-fsa/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-fsa

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-fsa")
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-fsa/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-fsa/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-fsa

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-fsa")
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-fsa/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-fsa/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-fsa

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-fsa")
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-fsa/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-fsa/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-fsa

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-fsa")
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-fsa/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

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

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

Copy SKILL.md

Save it in your project, as

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

Read the summary as JSON

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

FSA Data Source Reference

Federal Student Aid (FSA) — institutional-level Title IV aid data for ~5,500 postsecondary institutions, covering Pell Grants, Direct and PLUS loans, campus-based aid (FWS, FSEOG, Perkins), financial responsibility composite scores, and 90/10 revenue metrics (1999-2021, varies by dataset). Use when analyzing Pell Grant distribution by institution type, student loan volume, campus-based aid allocation, or for-profit financial health and 90/10 compliance. Identified by IPEDS unitid.

Reference guide for FSA data available through the Urban Institute Education Data Portal. FSA data provides institutional-level information on Title IV federal student aid programs administered by the U.S. Department of Education.

CRITICAL: Value Encoding

The Education Data Portal converts categorical variables to integers. This differs from original FSA documentation which may use string codes. All categorical columns in the Portal parquet files are integer-typed.

Variable Example Value Meaning
grant_type 1 Federal Pell Grant
loan_type 1 Subsidized Direct Loan - Undergraduate
award_type 1 Federal Supplemental Educational Opportunity Grants
fips 6 California
allocation_flag 1 Yes

Missing data codes (-1, -2, -3) apply to numeric format variables, not categorical codes.

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

Variable	Example Value	Meaning
`grant_type`	`1`	Federal Pell Grant
`loan_type`	`1`	Subsidized Direct Loan - Undergraduate
`award_type`	`1`	Federal Supplemental Educational Opportunity Grants
`fips`	`6`	California
`allocation_flag`	`1`	Yes

Truth Hierarchy

When interpreting FSA data values and resolving discrepancies between this skill documentation and observed data, apply this priority:

Priority	Source	Rationale
1 (highest)	Actual data file (parquet)	What you observe IS the truth
2	Live codebook/metadata (.xls in mirror)	Authoritative documentation; may lag behind data
3 (lowest)	This skill documentation (variable-definitions.md, etc.)	Summarized; convenient but may drift

When this skill contradicts observed data: trust the data, flag the discrepancy
When codebook contradicts observed data: trust the data, but investigate
When this skill contradicts codebook: trust the codebook, update this skill

Codebook Access: Use get_codebook_url() from fetch-patterns.md with paths from datasets-reference.md:

# Example: Get codebook for FSA grants
url = get_codebook_url("fsa/codebook_colleges_fsa_grants")

Dataset	Codebook Path
Grants	`fsa/codebook_colleges_fsa_grants`
Loans	`fsa/codebook_colleges_fsa_loans`
Campus-Based Volume	`fsa/codebook_colleges_fsa_campus_based_volume`
Financial Responsibility	`fsa/codebook_colleges_fsa_financial_responsibility`
90/10 Revenue	`fsa/codebook_colleges_fsa_90-10_revenue_percentages`

FSA naming note: The Financial Responsibility dataset uses composite_scores in its data path but financial_responsibility in its codebook path. The 90/10 Revenue dataset uses underscores (90_10) in the data path but hyphens (90-10) in the codebook path. Always use the exact paths shown above.

What is Federal Student Aid?

Federal Student Aid (FSA) is the office within the U.S. Department of Education that administers Title IV aid programs:

Title IV Programs: Federal financial aid authorized under Title IV of the Higher Education Act (HEA)
Institutional Coverage: All Title IV-eligible postsecondary institutions (approximately 5,500+ schools)
Data Types: Aid disbursements, recipient counts, loan/grant volumes, financial responsibility metrics
Primary Identifier: unitid (6-digit IPEDS institution ID)
Years Available: 1999-2021 depending on dataset

Reference File Structure

File	Purpose	When to Read
`title-iv-programs.md`	Pell Grants, Direct Loans, PLUS, campus-based aid	Understanding aid program types
`financial-responsibility.md`	Composite scores, institutional oversight	Analyzing institutional financial health
`90-10-rule.md`	For-profit revenue requirements	Working with proprietary institutions
`variable-definitions.md`	Key variables, aid types, amounts	Building queries, interpreting results
`data-quality.md`	Known issues, coverage, timing	Understanding data limitations

Decision Trees

What FSA topic am I researching?

FSA research topic?
├─ Grant programs
│   ├─ Federal Pell Grants → ./references/title-iv-programs.md
│   ├─ FSEOG (campus-based) → ./references/title-iv-programs.md
│   └─ Grant amounts/recipients → ./references/variable-definitions.md
├─ Loan programs
│   ├─ Direct Subsidized/Unsubsidized → ./references/title-iv-programs.md
│   ├─ Parent PLUS loans → ./references/title-iv-programs.md
│   ├─ Graduate PLUS loans → ./references/title-iv-programs.md
│   ├─ Perkins Loans (legacy) → ./references/title-iv-programs.md
│   └─ Loan volumes/disbursements → ./references/variable-definitions.md
├─ Campus-based programs
│   ├─ Federal Work-Study → ./references/title-iv-programs.md
│   ├─ FSEOG → ./references/title-iv-programs.md
│   └─ Program allocations → ./references/variable-definitions.md
├─ Institutional oversight
│   ├─ Financial responsibility scores → ./references/financial-responsibility.md
│   ├─ 90/10 rule compliance → ./references/90-10-rule.md
│   └─ Eligibility/participation → ./references/data-quality.md
└─ Data quality concerns
    └─ Coverage, timing, limitations → ./references/data-quality.md

Which FSA dataset do I need?

FSA dataset selection?
├─ Need grant data (Pell, FSEOG)
│   └─ fsa/colleges_fsa_grants (single-file, 1999-2021)
├─ Need loan data (Direct, PLUS)
│   └─ fsa/colleges_fsa_loans (single-file, 1999-2021)
├─ Need campus-based program data
│   └─ fsa/colleges_fsa_campus_based_volume (single-file, 2001-2021)
├─ Need institutional financial health
│   └─ fsa/colleges_fsa_composite_scores (single-file, 2006-2016)
└─ Need 90/10 compliance (for-profits)
    └─ fsa/colleges_fsa_90_10_revenue_percentages (single-file, 2014-2021)

Quick Reference: FSA Datasets and Codes

Datasets

Dataset Path	Description	Years	Key Variables
`fsa/colleges_fsa_grants`	Grant recipients and amounts by type	1999-2021	`grant_type`, `grant_recipients_unitid`, `value_grants_disbursed_unitid`
`fsa/colleges_fsa_loans`	Loan recipients and volumes by type	1999-2021	`loan_type`, `loan_recipients_unitid`, `value_loan_disbursements_unitid`
`fsa/colleges_fsa_campus_based_volume`	FWS, FSEOG, Perkins by award type	2001-2021	`award_type`, `campus_award_recipients_unitid`, `value_campus_disbursed_unitid`
`fsa/colleges_fsa_composite_scores`	Composite scores by institution	2006-2016	`financial_resp_score`
`fsa/colleges_fsa_90_10_revenue_percentages`	For-profit Title IV revenue ratios	2014-2021	`rev_pct_90_10`

Data access: All FSA datasets are single-file (all years in one file). Fetch using fetch_from_mirrors() from fetch-patterns.md with the canonical path from datasets-reference.md. See mirrors.yaml for mirror configuration.

Key Identifiers

ID	Format	Level	Example	Notes
`unitid`	6-digit integer	Institution	`110635`	IPEDS institution ID; primary join key across FSA datasets and to IPEDS/Scorecard
`fips`	2-digit integer	State	`6`	State FIPS code

Title IV Programs

Program	Type	Eligibility	Max Amount (2025-26)
Federal Pell Grant	Need-based grant	Undergrad with financial need	$7,395
Direct Subsidized Loan	Need-based loan	Undergrad with financial need	$3,500-$5,500/yr
Direct Unsubsidized Loan	Non-need loan	Undergrad/Grad students	$5,500-$20,500/yr
Parent PLUS Loan	Credit-based loan	Parents of dependent undergrads	Cost of attendance
Graduate PLUS Loan	Credit-based loan	Graduate/professional students	Cost of attendance
FSEOG	Need-based grant	Undergrad with exceptional need	$100-$4,000/yr
Federal Work-Study	Employment program	Students with financial need	Varies by school
Perkins Loan	Need-based loan	Discontinued (no new loans after 2017)	N/A

Financial Responsibility Scores

Score Range	Classification	Meaning
1.5 to 3.0	Financially Responsible	Meets all standards
1.0 to 1.49	In the Zone	Provisionally certified, monitoring required
Below 1.0	Not Financially Responsible	Must post letter of credit or face sanctions
-1.0	Minimum score	Lowest possible composite score

Grant Type Codes (grants dataset)

Code	Grant Type
`1`	Federal Pell Grant
`2`	Federal Supplemental Educational Opportunity Grant (FSEOG)
`3`	TEACH Grant
`4`	Iraq and Afghanistan Service Grant
`5`	Children of Fallen Heroes Grant

Loan Type Codes (loans dataset)

Code	Loan Type
`1`	Subsidized Direct Loan - Undergraduate
`2`	Subsidized Direct Loan - Graduate
`3`	Subsidized Direct Loan - Total
`4`	Unsubsidized Direct Loan - Undergraduate
`5`	Unsubsidized Direct Loan - Graduate
`6`	Unsubsidized Direct Loan - Total
`7`	Direct Loan, Parent PLUS
`8`	Direct Loan, Grad PLUS
`9`	Direct Loan PLUS (sum of Parent PLUS and Grad PLUS)
`10`	Subsidized Federal Family Education Loans
`11`	Unsubsidized Federal Family Education Loans
`12`	Parent PLUS Federal Family Education Loans
`13`	Grad PLUS Federal Family Education Loans
`14`	PLUS Federal Family Education Loans

Award Type Codes (campus-based-volume dataset)

Code	Award Type
`1`	Federal Supplemental Educational Opportunity Grants
`2`	Federal Work-Study
`3`	Perkins Loans

Yes/No Codes (allocation_flag, combined_flag)

Code	Meaning
`0`	No
`1`	Yes
`null`	Not reported

Missing Data Codes

Code	Meaning	When Used
`-1`	Missing/not reported	Data not reported by institution
`-2`	Not applicable	Item doesn't apply to this entity
`-3`	Suppressed data	Data suppressed for privacy
`null`	Not available	Field not populated for this record

Data Access

All FSA datasets are fetched via the mirror system. Three reference files govern data access:

Reference File	Purpose
`mirrors.yaml`	Mirror URLs, read strategies, timeouts, discovery endpoints
`datasets-reference.md`	Canonical dataset paths and codebook paths
`fetch-patterns.md`	`fetch_from_mirrors()` function and codebook URL helper

Key datasets (all single-file, all years in one file):

Dataset	Canonical Path	Years	Codebook Path
Grants	`fsa/colleges_fsa_grants`	1999-2021	`fsa/codebook_colleges_fsa_grants`
Loans	`fsa/colleges_fsa_loans`	1999-2021	`fsa/codebook_colleges_fsa_loans`
Campus-Based Volume	`fsa/colleges_fsa_campus_based_volume`	2001-2021	`fsa/codebook_colleges_fsa_campus_based_volume`
Financial Responsibility	`fsa/colleges_fsa_composite_scores`	2006-2016	`fsa/codebook_colleges_fsa_financial_responsibility`
90/10 Revenue	`fsa/colleges_fsa_90_10_revenue_percentages`	2014-2021	`fsa/codebook_colleges_fsa_90-10_revenue_percentages`

Naming mismatches (intentional): Financial Responsibility uses composite_scores in data path but financial_responsibility in codebook path. 90/10 Revenue uses underscores (90_10) in data path but hyphens (90-10) in codebook path.

Fetch Example

import polars as pl

# Using fetch_from_mirrors() from fetch-patterns.md
df_grants = fetch_from_mirrors("fsa/colleges_fsa_grants", years=[2019, 2020, 2021])

# Filter by grant type (1 = Federal Pell Grant)
df_pell = df_grants.filter(pl.col("grant_type") == 1)

# Filter by institution
df_inst = df_grants.filter(pl.col("unitid") == 110635)

# Filter by year range
df_recent = df_grants.filter(pl.col("year").is_between(2015, 2021))

Common Pitfalls

Pitfall	Issue	Solution
Using string codes	Portal encodes categoricals as integers; original FSA docs may reference string labels	Always use integer codes (e.g., `grant_type == 1` not `"Pell"`)
Ignoring missing data codes	`-1`, `-2`, `-3` in numeric columns are sentinel values, not real amounts	Filter or handle missing codes before aggregation; exclude negative values from sums/means
Stale financial responsibility data	`colleges_fsa_composite_scores` only covers 2006-2016	Check year coverage before analysis; do not assume current availability
90/10 percentage is a proportion	`rev_pct_90_10` is stored as 0-1 (e.g., 0.87), NOT 0-100	Multiply by 100 for display; compare to 0.90 threshold, not 90
Perkins Loan discontinuation	Perkins Loans ended after 2017; campus-based data still includes historical records	Filter by year or award_type to avoid mixing discontinued and active programs
Data lag	FSA data typically lags 1-2 years behind the current award year	Verify latest available year before planning analysis
Mixing aggregate and detail loan types	Loan type codes include both individual types (1-8, 10-13) and aggregate totals (3, 6, 9, 14)	Filter to specific types or aggregates, never sum both together
Pell recipient counts unavailable for 2020+	`grant_recipients_unitid` is 100% NULL for Pell grants (`grant_type==1`) in the 2020-2021 data year. Disbursement amounts also appear null	Use IPEDS SFA (`sfa_grants_and_net_price`) as a proxy for grant recipient counts. Note that SFA `type_of_aid=9` captures all grant/scholarship aid, not Pell-specific (see IPEDS skill)

Joining FSA Data with Other Sources

Source 1	Source 2	Join Key	Use Case
FSA Grants	IPEDS Directory	`unitid`	Aid by institution type
FSA Loans	IPEDS Enrollment	`unitid`	Loan volume per student
FSA Financial Responsibility	IPEDS Finance	`unitid`	Financial health analysis
FSA 90/10	IPEDS Directory	`unitid`	For-profit compliance
FSA	College Scorecard	`unitid`	Aid and student outcomes

Common Research Applications

Research Question	FSA Datasets	Complementary Data
Pell Grant distribution by institution type	`fsa/colleges_fsa_grants`	IPEDS Directory
Student loan burden by sector	`fsa/colleges_fsa_loans`	IPEDS Enrollment
Financial stability of for-profit schools	`fsa/colleges_fsa_composite_scores`, `fsa/colleges_fsa_90_10_revenue_percentages`	IPEDS Directory
Campus-based aid allocation patterns	`fsa/colleges_fsa_campus_based_volume`	IPEDS Directory
Title IV participation trends	`fsa/colleges_fsa_grants`, `fsa/colleges_fsa_loans`	Multiple years

Data Update Schedule

FSA data typically lags 1-2 years behind the current award year
Financial responsibility scores published annually
90/10 percentages updated after institutional fiscal year audits
Campus-based data tied to FISAP reporting cycle

Related Data Sources

Source	Relationship	When to Use
`education-data-source-ipeds`	Institutional characteristics and enrollment	Joining aid data with institution type, enrollment, or finances via `unitid`
`education-data-source-scorecard`	Student outcomes after enrollment	Linking aid patterns to post-college earnings and repayment
`education-data-source-fsa`	Self (cross-dataset joins)	Combining grants + loans + campus-based for holistic aid picture
`education-data-explorer`	Parent discovery skill	Finding available FSA datasets and variables
`education-data-query`	Data fetching	Downloading FSA data from mirrors via `fetch_from_mirrors()`

Topic Index

Topic	Reference File
Pell Grant program	`./references/title-iv-programs.md`
Direct Loan program	`./references/title-iv-programs.md`
PLUS loans	`./references/title-iv-programs.md`
Federal Work-Study	`./references/title-iv-programs.md`
FSEOG grants	`./references/title-iv-programs.md`
Perkins Loans	`./references/title-iv-programs.md`
Composite score calculation	`./references/financial-responsibility.md`
Primary reserve ratio	`./references/financial-responsibility.md`
Equity ratio	`./references/financial-responsibility.md`
Net income ratio	`./references/financial-responsibility.md`
90/10 rule requirements	`./references/90-10-rule.md`
For-profit revenue sources	`./references/90-10-rule.md`
Grant variables	`./references/variable-definitions.md`
Loan variables	`./references/variable-definitions.md`
Campus-based variables	`./references/variable-definitions.md`
Data coverage	`./references/data-quality.md`
Missing data handling	`./references/data-quality.md`
Year coverage by dataset	`./references/data-quality.md`

When it activates

Automatically, when a task matches. Use for aid distribution, loan volume, or for-profit analysis. By unitid.

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-fsa/SKILL.md

View on GitHub ↗

License NOASSERTIONImported 8/2/2026Version v1Bundled 5 files

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

FSA Data Source Reference

Truth Hierarchy

What is Federal Student Aid?

Reference File Structure

Decision Trees

What FSA topic am I researching?

Which FSA dataset do I need?

Quick Reference: FSA Datasets and Codes

Datasets

Key Identifiers

Title IV Programs

Financial Responsibility Scores

Grant Type Codes (grants dataset)

Loan Type Codes (loans dataset)

Award Type Codes (campus-based-volume dataset)

Yes/No Codes (allocation_flag, combined_flag)

Missing Data Codes

Data Access

Fetch Example

Common Pitfalls

Joining FSA Data with Other Sources

Common Research Applications

Data Update Schedule

Related Data Sources

Topic Index

When it activates

SkillSafety

Source

Related skills

More in the registry