Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →EDFacts — K-12 outcomes: assessment proficiency, ACGR graduation rates, ESSA accountability at school/district level (2009-2020). Within-state trends and subgroup gaps. Complements CCD with outcome data. Cannot compare across states — use NAEP.
SkillScore100/100
Test results 100
3/3 safety checks passed
26%100%of test cases passed +74 pts
Passed 23 of 23 test cases with the skill, and 6 of 23 without it.
17 fixed6 passed either way0 still failing0 broke
One test taskTo filter EDFacts school assessment data for high school grades combined (grades 9-12), which grade code should be applied to the `grade_edfacts` column?
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-edfacts
claude --plugin-dir "$(git rev-parse --show-toplevel 2>/dev/null || pwd)/.agents"The same install from Python, for a notebook or a setup script.
pip install "decimalai>=0.15"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("brycewang-stanford-education-data-source-edfacts")
if result.exit_code:
raise SystemExit(result.problems)
print("Added. Start Claude Code with the command below.")claude --plugin-dir "$(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.
/plugin marketplace add decimal-labs/decimalai-claude-plugins
/plugin install decimalai@decimalai/decimalai:install brycewang-stanford-education-data-source-edfactsThe plugin needs python3 and curl on your machine.
No Python or account. Claude Code picks it up in its next session.
curl -fsSL --create-dirs -o .claude/skills/brycewang-stanford-education-data-source-edfacts/SKILL.md https://app.decimal.ai/s/brycewang-stanford-education-data-source-edfacts/SKILL.md.claude/skills/brycewang-stanford-education-data-source-edfacts/SKILL.mdThis gets SKILL.md only. The skill's 6 other files are not included.
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.
pip install "decimalai[claude-agent-sdk]"
decimalai skills add brycewang-stanford-education-data-source-edfactsimport 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.
pip install "decimalai[claude-agent-sdk]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("brycewang-stanford-education-data-source-edfacts")
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.
.agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.mdimport asyncio
from pathlib import Path
from claude_agent_sdk import ClaudeAgentOptions, query
skill = Path(".agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.md").read_text()
options = ClaudeAgentOptions(system_prompt=f"You are a helpful agent.\n\n{skill}", max_turns=6)
async def main():
async for message in query(prompt="Hello!", options=options):
print(message)
# In a notebook or async code: await main()
asyncio.run(main())This gets SKILL.md only. The skill's 6 other files are not included.
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.
pip install "decimalai[openai-agents]"
decimalai skills add brycewang-stanford-education-data-source-edfactsfrom 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.
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.
pip install "decimalai[openai-agents]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("brycewang-stanford-education-data-source-edfacts")
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.
.agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.mdfrom pathlib import Path
from agents import Agent, Runner
skill = Path(".agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.md").read_text()
agent = Agent(name="support", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await Runner.run(agent, "Hello!")
result = Runner.run_sync(agent, "Hello!")This gets SKILL.md only. The skill's 6 other files are not included.
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.
pip install "decimalai[openai]"
decimalai skills add brycewang-stanford-education-data-source-edfactsimport 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.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.
pip install "decimalai[openai]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("brycewang-stanford-education-data-source-edfacts")
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.
.agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.mdfrom pathlib import Path
from openai import OpenAI
client = OpenAI()
skill = Path(".agents/skills/brycewang-stanford-education-data-source-edfacts/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].messageThis gets SKILL.md only. The skill's 6 other files are not included.
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.
pip install "decimalai[anthropic]"
decimalai skills add brycewang-stanford-education-data-source-edfactsimport 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()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.
pip install "decimalai[anthropic]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("brycewang-stanford-education-data-source-edfacts")
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.
.agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.mdfrom pathlib import Path
import anthropic
client = anthropic.Anthropic()
skill = Path(".agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.md").read_text()
reply = client.messages.create(
model="claude-haiku-5-5",
max_tokens=4096,
system=f"You are a helpful agent.\n\n{skill}",
messages=[{"role": "user", "content": "Hello!"}],
)This gets SKILL.md only. The skill's 6 other files are not included.
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.
pip install "decimalai[google-genai]"
decimalai skills add brycewang-stanford-education-data-source-edfactsfrom 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)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.
pip install "decimalai[google-genai]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("brycewang-stanford-education-data-source-edfacts")
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.
.agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.mdfrom pathlib import Path
from google import genai
from google.genai import types
client = genai.Client()
skill = Path(".agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.md").read_text()
response = client.models.generate_content(
model="gemini-3.5-flash",
contents="Hello!",
config=types.GenerateContentConfig(system_instruction=f"You are a helpful agent.\n\n{skill}"),
)This gets SKILL.md only. The skill's 6 other files are not included.
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.
pip install "decimalai[langchain]" langchain-openai
decimalai skills add brycewang-stanford-education-data-source-edfactsfrom 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!"}]})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.
pip install "decimalai[langchain]" langchain-openaifrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("brycewang-stanford-education-data-source-edfacts")
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.
.agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.mdfrom pathlib import Path
from langchain.agents import create_agent
skill = Path(".agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.md").read_text()
agent = create_agent("openai:gpt-5.4-mini", tools=[], system_prompt=f"You are a helpful agent.\n\n{skill}")
result = agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})This gets SKILL.md only. The skill's 6 other files are not included.
CrewAI's own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" "crewai>=1.15.27"
decimalai skills add brycewang-stanford-education-data-source-edfactsimport 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.
pip install "decimalai>=0.16" "crewai>=1.15.27"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("brycewang-stanford-education-data-source-edfacts")
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.
.agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.mdfrom pathlib import Path
from crewai import Agent, Crew, Task
agent = Agent(
role="Support", goal="Help the customer", backstory="A support agent.",
llm=llm, # your own CrewAI LLM
skills=[Path(".agents/skills")],
)
task = Task(description="Hello!", expected_output="an answer", agent=agent)
Crew(agents=[agent], tasks=[task]).kickoff()This gets SKILL.md only. The skill's 6 other files are not included.
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.
pip install "decimalai[adk]"
decimalai skills add brycewang-stanford-education-data-source-edfactsfrom 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.
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.
pip install "decimalai[adk]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("brycewang-stanford-education-data-source-edfacts")
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.
.agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.mdfrom pathlib import Path
from google.adk.agents import LlmAgent
skill = Path(".agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.md").read_text()
agent = LlmAgent(
name="support",
model="gemini-3.5-flash",
instruction=lambda context: f"You are a helpful agent.\n\n{skill}",
)This gets SKILL.md only. The skill's 6 other files are not included.
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.
pip install "decimalai[pydantic-ai]"
decimalai skills add brycewang-stanford-education-data-source-edfactsfrom 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.
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.
pip install "decimalai[pydantic-ai]"from decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("brycewang-stanford-education-data-source-edfacts")
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.
.agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.mdfrom pathlib import Path
from pydantic_ai import Agent
skill = Path(".agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.md").read_text()
agent = Agent("openai:gpt-4o-mini", instructions=f"You are a helpful agent.\n\n{skill}")
# In a notebook or async code: result = await agent.run("Hello!")
result = agent.run_sync("Hello!")This gets SKILL.md only. The skill's 6 other files are not included.
Deep Agents' own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" deepagents
decimalai skills add brycewang-stanford-education-data-source-edfactsimport 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.
pip install "decimalai>=0.16" deepagentsfrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("brycewang-stanford-education-data-source-edfacts")
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.
.agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.mdfrom pathlib import Path
from deepagents import create_deep_agent
skill = Path(".agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.md").read_text()
agent = create_deep_agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent.invoke({"messages": [{"role": "user", "content": "Hello!"}]})This gets SKILL.md only. The skill's 6 other files are not included.
Its own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" agent-framework
decimalai skills add brycewang-stanford-education-data-source-edfactsimport 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.
pip install "decimalai>=0.16" agent-frameworkfrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("brycewang-stanford-education-data-source-edfacts")
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.
.agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.mdimport asyncio
from pathlib import Path
from agent_framework import Agent
skill = Path(".agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.md").read_text()
agent = Agent(client=client, instructions=f"You are a helpful agent.\n\n{skill}")
asyncio.run(agent.run("Hello!"))This gets SKILL.md only. The skill's 6 other files are not included.
Strands' own skill loader reads the installed folder. No DecimalAI account needed.
pip install "decimalai>=0.16" strands-agents
decimalai skills add brycewang-stanford-education-data-source-edfactsfrom 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.
pip install "decimalai>=0.16" strands-agentsfrom decimalai import skillpkg
# Writes .agents/skills and .decimal/skills.toml. Safe to run twice.
result = skillpkg.add("brycewang-stanford-education-data-source-edfacts")
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.
.agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.mdfrom pathlib import Path
from strands import Agent
skill = Path(".agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.md").read_text()
agent = Agent(model=model, system_prompt=f"You are a helpful agent.\n\n{skill}")
agent("Hello!")This gets SKILL.md only. The skill's 6 other files are not included.
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-edfactsNo Python or account. Cursor, Copilot, Cline and Warp read this folder by themselves.
curl -fsSL --create-dirs -o .agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.md https://app.decimal.ai/s/brycewang-stanford-education-data-source-edfacts/SKILL.md.agents/skills/brycewang-stanford-education-data-source-edfacts/SKILL.mdThis gets SKILL.md only. The skill's 6 other files are not included.
Give its text to your model as instructions. No account or package needed.
This gets SKILL.md only. The skill's 6 other files are not included.
Raw files: /s/brycewang-stanford-education-data-source-edfacts/SKILL.md · /s/brycewang-stanford-education-data-source-edfacts.json
Fetch the file and give its text to your model as instructions. No account or package needed.
curl -fsSL https://app.decimal.ai/s/brycewang-stanford-education-data-source-edfacts/SKILL.mdcurl -fsSL https://app.decimal.ai/s/brycewang-stanford-education-data-source-edfacts.jsonThis gets SKILL.md only. The skill's 6 other files are not included.
You don't need a DecimalAI account.
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.
EDFacts — federal K-12 outcome data from State Education Agencies, covering state assessment proficiency rates, ACGR graduation rates, and ESSA accountability indicators at school and district level (assessments 2009-2020, graduation rates 2010-2019). Use when analyzing within-state achievement trends, subgroup proficiency gaps, or adjusted cohort graduation rates. Complements CCD (school characteristics) with outcome data. State assessment scores CANNOT be compared across states; use NAEP for cross-state comparisons.
EDFacts is the U.S. Department of Education's centralized data collection system for pre-K through grade 12 education data from State Education Agencies (SEAs). It provides state assessment proficiency rates, graduation rates, and accountability indicators — the authoritative federal source for state-level K-12 outcome data.
CRITICAL: Value Encoding
The Urban Institute Education Data Portal converts NCES string codes (e.g.,
ALL,CWD,LEP) to integer codes. Always verify actual data values before filtering — do not rely on documentation labels alone.
Context Subgroup "All" English Learner Sex "Male" Portal integer 9911NCES string ALLLEPMSee
./references/variable-definitions.mdfor complete encoding tables.
ncessch (school ID, Int64), leaid (district ID, Int64), fips (state FIPS code, Int64)| File | Purpose | When to Read |
|---|---|---|
accountability-context.md | ESSA, NCLB history, accountability systems | Understanding policy context |
assessment-data.md | Proficiency levels, test scores, limitations | Working with assessment data |
graduation-rates.md | ACGR methodology, cohort definitions | Analyzing graduation data |
variable-definitions.md | Key variables, suppression codes, special values | Interpreting specific variables |
data-quality.md | Known issues, state variations, COVID impacts | Data cleaning, limitations |
subgroup-reporting.md | Special populations, disaggregation | Analyzing by student groups |
What EDFacts data do you need?
├─ Assessment/proficiency data
│ ├─ Within-state trends → Valid analysis
│ ├─ Cross-state comparison → INVALID - use NAEP instead
│ └─ Subgroup gaps → See ./references/subgroup-reporting.md
├─ Graduation rates (ACGR)
│ ├─ Understand methodology → See ./references/graduation-rates.md
│ ├─ Extended rates (5-year, 6-year) → See ./references/graduation-rates.md
│ └─ Subgroup rates → See ./references/subgroup-reporting.md
├─ Understanding variables
│ ├─ Missing/suppressed values → See ./references/variable-definitions.md
│ ├─ Range vs. exact values → See ./references/variable-definitions.md
│ └─ Subgroup codes → See ./references/subgroup-reporting.md
└─ Data quality concerns
├─ COVID-19 impacts (2019-20) → See ./references/data-quality.md
├─ State reporting changes → See ./references/data-quality.md
└─ Suppression rates → See ./references/data-quality.md
What are you comparing?
├─ Same state, different years
│ ├─ Same assessment system? → Valid
│ └─ Different tests? → Break in time series
├─ Schools within same state → Valid
├─ Districts within same state → Valid
├─ Subgroups within same school → Valid (check suppression)
├─ Different states
│ ├─ Proficiency rates → INVALID
│ ├─ Graduation rates (ACGR) → More comparable
│ └─ Use NAEP instead → Valid
└─ National ranking by proficiency → INVALID
| Data Element | Description | Available Years |
|---|---|---|
| Proficiency rates | % meeting state standards in reading/math | 2009-10 to present |
| Participation rates | % of students assessed | 2012-13 to present |
| Achievement levels | Below Basic, Basic, Proficient, Advanced | Varies by state |
| Grade levels | Grades 3-8, high school (varies) | 2009-10 to present |
| Data Element | Description | Available Years |
|---|---|---|
| 4-year ACGR | Adjusted Cohort Graduation Rate | 2010-11 to present |
| 5-year ACGR | Extended graduation rate | 2011-12 to present |
| 6-year ACGR | Further extended rate | 2012-13 to present |
| Diploma types | Regular diploma only in ACGR | All years |
Portal Data Types: All identifiers are Int64 in the Portal parquet files. The NCES source format (zero-padded strings) is shown for reference only. When joining with other Portal datasets, join on the integer columns directly.
| ID | Portal Type | NCES Source Format | Level | Example (Int64) |
|---|---|---|---|---|
ncessch | Int64 | 12-char zero-padded | School | 10000500870 |
ncessch_num | Int64 | Same as ncessch | School | 10000500870 |
leaid | Int64 | 7-char zero-padded | District/LEA | 100005 |
leaid_num | Int64 | Same as leaid | District/LEA | 100005 |
fips | Int64 | 2-digit | State | 1 (Alabama) |
| Level | Identifier | Dataset Path Pattern |
|---|---|---|
| School | ncessch (Int64) | edfacts/schools_edfacts_* |
| District/LEA | leaid (Int64) | edfacts/districts_edfacts_* |
| State | fips (Int64) | Aggregate from lower levels |
Note: Not all subgroup columns are present in every dataset. Grad rates data does NOT have
sex,migrant, ormilitary_connectedcolumns.
| Subgroup | NCES Code | Portal Integer | Column | Available In |
|---|---|---|---|---|
| All students | ALL | 99 | race, sex, lep, disability | Assessments, Grad Rates |
| Economically disadvantaged | ECODIS | 1 | econ_disadvantaged | Assessments, Grad Rates |
| Students with disabilities | CWD | 1 | disability | Assessments, Grad Rates |
| English learners | LEP | 1 | lep | Assessments, Grad Rates |
| Homeless | HOM | 1 | homeless | Assessments, Grad Rates |
| Foster care | FCS | 1 | foster_care | Assessments, Grad Rates |
| Migrant | MIG | 1 | migrant | Assessments only |
| Military connected | MIL | 1 | military_connected | Assessments only |
| Race/ethnicity | Multiple | 1-7, 99 | race | Assessments, Grad Rates |
| Sex | M/F | 1, 2, 99 | sex | Assessments only |
EDFacts Filter Column Pattern:
1 = subgroup, 99 = total1 = Male, 2 = Female, 99 = Total (assessments only)| Code | Grade Level |
|---|---|
3-8 | Grades 3-8 (individual) |
9 | Grades 9-12 combined |
99 | Total (all grades) |
Empirically verified from 2018 school assessment data. Only these values appear in the
racecolumn:
| Code | Category |
|---|---|
1 | White |
2 | Black |
3 | Hispanic |
4 | Asian |
5 | American Indian/Alaska Native |
7 | Two or More Races |
99 | Total |
Note: Code
6(Native Hawaiian/Pacific Islander) is NOT observed in the data. Codes8(Nonresident alien),9(Unknown),20(Other),-1,-2,-3are also not observed in the race column. These codes may exist in other Portal sources but are absent from EDFacts.
| Code | Category |
|---|---|
1 | Male |
2 | Female |
9 | Unknown |
99 | Total |
Empirically verified from 2018 school assessment and 2019 grad rate data. Only
1and99are observed in thedisabilitycolumn. The expanded codes (0-4) documented in other Portal sources are NOT present in EDFacts datasets.
| Code | Category |
|---|---|
1 | Students with disabilities (IDEA-eligible) |
99 | Total (all students) |
| Code | Category |
|---|---|
1 | Students who are limited English proficient |
99 | All students (total) |
For homeless, migrant, econ_disadvantaged, foster_care, military_connected:
| Code | Category |
|---|---|
1 | Yes (in subgroup) |
99 | Total (all students) |
| Code | Meaning | When Used |
|---|---|---|
-1 | Missing/not applicable | Data not reported |
-2 | Not reported | Item doesn't apply to this entity |
-3 | Suppressed for privacy | Data suppressed for small N-size |
-9 | Rounds to zero | Value rounds to zero |
| Range values | Exact value suppressed | Range provided instead of exact value |
_midpt suffix | Calculated midpoint of suppressed range | Use for analysis when exact values are suppressed |
Always use _midpt variables for analysis when exact values are suppressed.
All EDFacts data is fetched via the Education Data Portal mirror system. There is no API access.
Key references:
mirrors.yaml -- Mirror definitions, URL templates, read strategiesdatasets-reference.md -- Canonical dataset paths (one path works for all mirrors)fetch-patterns.md -- fetch_from_mirrors() and fetch_yearly_from_mirrors() patternsTruth 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.
| Dataset | Path | Type | Columns |
|---|---|---|---|
| School Assessments | edfacts/schools_edfacts_assessments_{year} | Yearly (2009-2018, 2020) | 26 cols |
| School Grad Rates | edfacts/schools_edfacts_grad_rates_{year} | Yearly (2010-2019) | 18 cols |
| District Assessments | edfacts/districts_edfacts_assessments_{year} | Yearly (2009-2018, 2020) | 23 cols |
| District Grad Rates | edfacts/districts_edfacts_grad_rates_{year} | Yearly (2010-2019) | 15 cols |
Note: 2019 assessment data is NOT available (at any level) due to COVID testing waivers.
Codebook .xls files are available for both assessment and graduation rate datasets. Use get_codebook_url() from fetch-patterns.md:
# Assessment codebooks:
url = get_codebook_url("edfacts/codebook_schools_edfacts_assessments")
url = get_codebook_url("edfacts/codebook_districts_edfacts_assessments")
# Graduation rate codebooks:
url = get_codebook_url("edfacts/codebook_schools_edfacts_graduation")
url = get_codebook_url("edfacts/codebook_districts_edfacts_graduation")
Codebook naming note: Graduation rate codebooks use
_graduation(not_grad_rates), while the data files use_grad_rates. This follows the same pattern as other Portal sources where codebook names differ from data file names. Seedatasets-reference.mdfor the authoritative path mapping.
Assessment and graduation rate datasets have different column sets:
| Column | Assessments | Grad Rates |
|---|---|---|
sex | Yes (1, 2, 99) | No |
migrant | Yes (1, 99) | No |
military_connected | Yes (1, 99) | No |
grade_edfacts | Yes (3-9, 99) | No |
read_test_* / math_test_* | Yes | No |
grad_rate_* | No | Yes |
cohort_num | No | Yes |
school_name / lea_name | Yes | Yes |
# Grade filtering: grade_edfacts uses integer codes
df = df.filter(pl.col("grade_edfacts") == 4) # Grade 4
df = df.filter(pl.col("grade_edfacts") == 99) # All grades combined
# Subgroup filtering: special population columns use 1/99 pattern
df_total = df.filter(pl.col("sex") == 99) # All students (total)
df_econ = df.filter(pl.col("econ_disadvantaged") == 1) # Economically disadvantaged only
# Race filtering: integer codes
df_black = df.filter(pl.col("race") == 2) # Black students
| Pitfall | Issue | Solution |
|---|---|---|
| Ranking states by proficiency | Different tests, different cut scores make comparisons meaningless | Use NAEP for cross-state comparisons |
| Comparing 2019-20 to other years | COVID testing waivers created data gaps | Note data gap, exclude year |
| Ignoring suppression | Results biased toward larger schools/subgroups | Document suppression rates, use _midpt variables |
| Assuming proficiency = same thing | State definitions of "proficient" vary widely | Clarify each state's definition |
| Pre/post ESSA comparison | Different accountability systems (NCLB vs ESSA) | Note policy change at 2015 boundary |
| Using string codes for filtering | Portal uses integer encoding, not NCES strings | Always check actual data values; see encoding tables above |
| Law | Years | Key Features |
|---|---|---|
| NCLB | 2002-2015 | AYP, 100% proficiency goal, HQT |
| ESSA | 2015-present | State flexibility, multiple indicators |
State assessment proficiency rates CANNOT be compared across states.
| Factor | Why It Varies |
|---|---|
| Assessment content | Each state creates its own tests |
| Proficiency cut scores | Each state sets own thresholds |
| Standards alignment | State academic standards differ |
| Test difficulty | Not calibrated nationally |
A student "proficient" in one state may score "below basic" in another state taking a harder test with higher cut scores. Rankings of states by proficiency rates are meaningless.
Use NAEP (National Assessment of Educational Progress) for valid cross-state comparisons.
Valid Analysis:
# Within-state trend analysis
state_df = df.filter(pl.col("fips") == 6) # California only
trend = state_df.group_by("year").agg(
pl.col("read_test_pct_prof_midpt").mean()
)
# Valid: Same state, same test system
INVALID Analysis:
# DO NOT DO THIS - Cross-state comparison
# This comparison is MEANINGLESS
state_comparison = df.group_by("fips").agg(
pl.col("read_test_pct_prof_midpt").mean()
).sort("read_test_pct_prof_midpt", descending=True)
# INVALID: Different tests, different standards
| Source | Relationship | When to Use |
|---|---|---|
education-data-source-ccd | CCD provides school/district demographics | Combining outcome data with school characteristics |
education-data-source-crdc | CRDC has discipline, AP, school climate data | Analyzing school equity alongside achievement |
education-data-source-saipe | SAIPE provides district poverty estimates | Linking poverty to achievement |
education-data-source-meps | MEPS provides school poverty estimates | School-level poverty and assessment analysis |
education-data-explorer | Parent discovery skill | Finding available endpoints |
education-data-query | Data fetching | Downloading via mirrors |
| Topic | Reference File |
|---|---|
| NCLB to ESSA transition | ./references/accountability-context.md |
| State accountability systems | ./references/accountability-context.md |
| Federal reporting requirements | ./references/accountability-context.md |
| Proficiency levels | ./references/assessment-data.md |
| Why states can't be compared | ./references/assessment-data.md |
| NAEP comparison | ./references/assessment-data.md |
| Assessment system changes | ./references/assessment-data.md |
| ACGR calculation | ./references/graduation-rates.md |
| Cohort adjustments | ./references/graduation-rates.md |
| Extended graduation rates | ./references/graduation-rates.md |
| Diploma types | ./references/graduation-rates.md |
| Suppression codes | ./references/variable-definitions.md |
| Missing data values | ./references/variable-definitions.md |
| Range/midpoint variables | ./references/variable-definitions.md |
| Participation rates | ./references/variable-definitions.md |
| COVID-19 data gaps | ./references/data-quality.md |
| State reporting variations | ./references/data-quality.md |
| Known data issues | ./references/data-quality.md |
| Time series breaks | ./references/data-quality.md |
| Students with disabilities | ./references/subgroup-reporting.md |
| English learners | ./references/subgroup-reporting.md |
| Economically disadvantaged | ./references/subgroup-reporting.md |
| Race/ethnicity reporting | ./references/subgroup-reporting.md |
| Homeless/foster/migrant | ./references/subgroup-reporting.md |
| N-size requirements | ./references/subgroup-reporting.md |
Skills that do similar work, with their headline benchmark lift.
From the same source and nearby in the catalogue.