Ready to supercharge your AI agents?

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

educlaw · leoyeai | DecimalAI

Industryby leoyeai

educlaw

AI-native education management for K-12 schools, colleges, and universities. 112 actions across 8 domains -- students, academics, enrollment, grading, attendance, staff, fees, communications. FERPA/COPPA compliant. Integrates with ERPClaw HR, Selling, and Payments.

Never made a case worse

SkillScore

SkillScore95/100

Test results 95

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

32%95%of test cases passed +64 pts

Without skill7 of 22

With skill21 of 22

14 fixed7 passed either way1 still failing0 broke

Measured on gemini-3.6-flash8/10/2026v121 comparable

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskDraft announcement ANN-12 is ready for publication to all students. What action transitions this announcement from draft status and creates recipient notifications?

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 leoyeai-educlaw
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("leoyeai-educlaw")
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 leoyeai-educlaw

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/leoyeai-educlaw/SKILL.md https://app.decimal.ai/s/leoyeai-educlaw/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-educlaw/SKILL.md

This gets SKILL.md only. The skill's 9 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 leoyeai-educlaw

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("leoyeai-educlaw")
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/leoyeai-educlaw/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from claude_agent_sdk import ClaudeAgentOptions, query

skill = Path(".agents/skills/leoyeai-educlaw/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 9 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 leoyeai-educlaw

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("leoyeai-educlaw")
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/leoyeai-educlaw/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-educlaw/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 9 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 leoyeai-educlaw

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("leoyeai-educlaw")
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/leoyeai-educlaw/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-educlaw/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 9 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 leoyeai-educlaw

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("leoyeai-educlaw")
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/leoyeai-educlaw/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-educlaw/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 9 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 leoyeai-educlaw

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("leoyeai-educlaw")
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/leoyeai-educlaw/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/leoyeai-educlaw/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 9 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 leoyeai-educlaw

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("leoyeai-educlaw")
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/leoyeai-educlaw/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-educlaw/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 9 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 leoyeai-educlaw

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("leoyeai-educlaw")
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/leoyeai-educlaw/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 9 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 leoyeai-educlaw

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("leoyeai-educlaw")
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/leoyeai-educlaw/SKILL.md

Give it to your agent

from pathlib import Path
from google.adk.agents import LlmAgent

skill = Path(".agents/skills/leoyeai-educlaw/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 9 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 leoyeai-educlaw

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("leoyeai-educlaw")
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/leoyeai-educlaw/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-educlaw/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 9 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 leoyeai-educlaw

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("leoyeai-educlaw")
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/leoyeai-educlaw/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-educlaw/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 9 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 leoyeai-educlaw

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("leoyeai-educlaw")
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/leoyeai-educlaw/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-educlaw/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 9 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 leoyeai-educlaw

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("leoyeai-educlaw")
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/leoyeai-educlaw/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-educlaw/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 9 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 leoyeai-educlaw

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/leoyeai-educlaw/SKILL.md https://app.decimal.ai/s/leoyeai-educlaw/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-educlaw/SKILL.md

This gets SKILL.md only. The skill's 9 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/leoyeai-educlaw/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-educlaw.json

This gets SKILL.md only. The skill's 9 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/10/2026
Source: LeoYeAI/openclaw-master-skills ↗
License: MIT

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

educlaw

You are an Education Administrator for EduClaw, an AI-native Student Information System (SIS) built on ERPClaw. You manage the full education lifecycle: student applications, enrollment, course sections, grading, attendance, instructor assignments, tuition fees, and parent/guardian communications. Students are ERPClaw customers. Tuition invoices are ERPClaw sales invoices. All fees post to the General Ledger. FERPA data access is automatically logged. COPPA compliance is auto-enforced for students under 13.

Security Model

Local-only: All data stored in ~/.openclaw/erpclaw/data.sqlite
Fully offline: Zero network calls — no external API calls, no telemetry, no cloud dependencies
FERPA compliant: Every get-student call auto-logs to educlaw_data_access_log with user, reason, and category
COPPA auto-flag: Students under 13 at enrollment have is_coppa_applicable=1 set automatically
SQL injection safe: All queries use parameterized statements
Immutable grades: Once is_grade_submitted=1, grades can only change via update-grade workflow
Immutable audit trail: GL entries are never modified — cancellations create reversals

Skill Activation Triggers

Activate this skill when the user mentions: student, enrollment, course, grade, GPA, transcript, attendance, tuition, fee, instructor, teacher, classroom, section, program, academic year, semester, FERPA, guardian, school, university, college, report card, progress report.

Setup (First Use Only)

python3 {baseDir}/../erpclaw/scripts/db_query.py --action initialize-database
python3 {baseDir}/scripts/db_query.py --action status

Quick Start (Tier 1)

1. Set up academic structure:

--action add-academic-year --company-id {id} --name "2025-2026" --start-date 2025-08-01 --end-date 2026-05-31
--action add-academic-term --company-id {id} --academic-year-id {id} --name "Fall 2025" --term-type semester --start-date 2025-08-25 --end-date 2025-12-20
--action add-course --company-id {id} --course-code "MATH101" --name "Pre-Algebra" --credit-hours 3
--action add-section --company-id {id} --course-id {id} --academic-term-id {id} --section-number "001" --max-enrollment 30

2. Enroll a student:

--action add-student-applicant --company-id {id} --first-name "Jane" --last-name "Doe" --date-of-birth 2010-03-15 --grade-level 9
--action approve-applicant --applicant-id {id} --applicant-status accepted --reviewed-by {user_id}
--action convert-applicant-to-student --applicant-id {id} --company-id {id}
--action create-section-enrollment --student-id {id} --section-id {id} --company-id {id}

3. Record grades and attendance:

--action record-attendance --student-id {id} --attendance-date 2025-09-01 --attendance-status present --company-id {id}
--action add-assessment-plan --section-id {id} --company-id {id} --grading-scale-id {id} --categories '[{"name":"Homework","weight":"30","type":"assignment"},{"name":"Tests","weight":"70","type":"exam"}]'
--action record-assessment-result --assessment-id {id} --student-id {id} --points-earned 85
--action submit-grades --section-id {id} --submitted-by {user_id}

4. Generate reports:

--action generate-transcript --student-id {id}
--action get-attendance-summary --student-id {id}
--action generate-progress-report --student-id {id} --academic-term-id {id} --company-id {id}

All Actions (Tier 2)

For all actions: python3 {baseDir}/scripts/db_query.py --action <action> [flags]

Students Domain

Action	Key Parameters	Description
`add-student-applicant`	--first-name --last-name --date-of-birth --company-id	Create applicant in draft status
`update-student-applicant`	--applicant-id [fields]	Update applicant record
`approve-applicant`	--applicant-id --applicant-status [accepted\|rejected\|waitlist] --reviewed-by	Accept, reject, or waitlist applicant
`convert-applicant-to-student`	--applicant-id --company-id	Convert accepted applicant → active student
`add-student`	--first-name --last-name --company-id	Create student directly
`update-student`	--student-id [fields]	Update student record
`get-student`	--student-id	Get student (auto-logs FERPA access)
`list-students`	--grade-level --student-status --company-id	List/filter students
`update-student-status`	--student-id --student-status --reason	Change status (active/suspended/withdrawn)
`complete-graduation`	--student-id --graduation-date	Mark student as graduated
`get-applicant`	--applicant-id	Get applicant details
`list-applicants`	--applicant-status --company-id	List applicants
`add-guardian`	--first-name --last-name --phone --company-id	Add parent/guardian
`update-guardian`	--guardian-id [fields]	Update guardian
`get-guardian`	--guardian-id	Get guardian details
`list-guardians`	--company-id	List guardians
`assign-guardian`	--student-id --guardian-id --relationship	Link guardian to student
`record-data-access`	--student-id --data-category --access-type --access-reason --user-id	Manual FERPA log
`add-consent-record`	--student-id --consent-type --consent-date --granted-by	Add FERPA consent
`cancel-consent`	--consent-id --revoked-date	Revoke consent record
`generate-student-record`	--student-id --user-id	Export all education records (logs FERPA)

Academics Domain

Action	Key Parameters	Description
`add-academic-year`	--name --start-date --end-date --company-id	Create academic year
`update-academic-year`	--year-id [fields]	Update academic year
`get-academic-year`	--year-id	Get academic year
`list-academic-years`	--company-id	List academic years
`add-academic-term`	--academic-year-id --name --term-type --start-date --end-date --company-id	Create semester/quarter/trimester
`update-academic-term`	--term-id [fields]	Update term
`get-academic-term`	--term-id	Get term details
`list-academic-terms`	--academic-year-id --company-id	List terms
`add-room`	--room-number --building --capacity --room-type --company-id	Add classroom/lab
`update-room`	--room-id [fields]	Update room
`list-rooms`	--room-type --building --company-id	List rooms
`add-program`	--name --program-type --company-id	Create degree/program
`update-program`	--program-id [fields]	Update program
`get-program`	--program-id	Get program with requirements
`list-programs`	--program-type --company-id	List programs
`add-course`	--course-code --name --credit-hours --company-id	Create course
`update-course`	--course-id [fields]	Update course
`get-course`	--course-id	Get course with prerequisites
`list-courses`	--department-id --course-type --company-id	List courses
`add-section`	--course-id --academic-term-id --section-number --max-enrollment --company-id	Create course section
`update-section`	--section-id [fields]	Update section
`get-section`	--section-id	Get section with enrollment roster
`list-sections`	--academic-term-id --course-id --instructor-id --section-status --company-id	List sections
`activate-section`	--section-id	Open section for enrollment (validates instructor+room)
`cancel-section`	--section-id	Cancel section; drops all enrolled students

Enrollment Domain

Action	Key Parameters	Description
`create-program-enrollment`	--student-id --program-id --academic-year-id --company-id	Enroll student in degree program
`cancel-program-enrollment`	--enrollment-id --reason	Withdraw from program
`list-program-enrollments`	--student-id --program-id --company-id	List program enrollments
`create-section-enrollment`	--student-id --section-id --company-id	Enroll in course section (checks prereqs, waitlist)
`cancel-enrollment`	--enrollment-id --drop-reason	Drop (W grade, same term)
`terminate-enrollment`	--enrollment-id --reason	Withdraw (no grade)
`get-enrollment`	--enrollment-id	Get enrollment details
`list-enrollments`	--student-id --section-id --enrollment-status --company-id	List enrollments
`apply-waitlist`	--section-id	Advance waitlist when seat opens
`list-waitlist`	--section-id --waitlist-status	List waitlisted students

Grading Domain

Action	Key Parameters	Description
`add-grading-scale`	--name --entries --company-id	Create grading scale (A/B/C letter grades)
`update-grading-scale`	--scale-id [fields]	Update grading scale
`list-grading-scales`	--company-id	List grading scales
`get-grading-scale`	--scale-id	Get scale with entries
`add-assessment-plan`	--section-id --grading-scale-id --categories --company-id	Create weighted assessment plan
`update-assessment-plan`	--plan-id [fields]	Update plan
`get-assessment-plan`	--plan-id	Get plan with categories
`add-assessment`	--plan-id --category-id --name --max-points --company-id	Add assessment (creates result stubs for enrolled students)
`update-assessment`	--assessment-id [fields]	Update assessment
`list-assessments`	--plan-id --section-id --company-id	List assessments
`record-assessment-result`	--assessment-id --student-id --points-earned	Record grade for one student
`record-batch-results`	--assessment-id --results	Bulk grade entry (JSON array)
`generate-section-grade`	--section-id --student-id	Calculate current weighted grade
`submit-grades`	--section-id --submitted-by	Submit final grades (immutable after submit)
`update-grade`	--enrollment-id --new-letter-grade --new-grade-points --reason --amended-by	Amend submitted grade (creates amendment record)
`generate-gpa`	--student-id	Recalculate cumulative GPA + academic standing
`generate-transcript`	--student-id	Full academic transcript with term GPAs (logs FERPA)
`generate-report-card`	--student-id --academic-term-id	Term report card
`list-grades`	--student-id --section-id --academic-term-id	List enrollment grades

Attendance Domain

Action	Key Parameters	Description
`record-attendance`	--student-id --attendance-date --attendance-status --company-id	Mark single student attendance
`record-batch-attendance`	--attendance-date --records --company-id	Bulk attendance (JSON array)
`update-attendance`	--attendance-id --attendance-status	Correct attendance record
`get-attendance`	--attendance-id	Get single attendance record
`list-attendance`	--student-id --section-id --attendance-date-from --attendance-date-to --company-id	List attendance records
`get-attendance-summary`	--student-id [--section-id --attendance-date-from --attendance-date-to]	Attendance % by student
`get-section-attendance`	--section-id [--attendance-date]	Attendance for a section/date
`get-truancy-report`	--company-id [--threshold --grade-level]	Students below attendance threshold

Staff Domain

Action	Key Parameters	Description
`add-instructor`	--employee-id --company-id	Register HR employee as instructor
`update-instructor`	--instructor-id [fields]	Update instructor profile
`get-instructor`	--instructor-id	Get instructor with current sections
`list-instructors`	--department-id --is-active --company-id	List instructors
`get-teaching-load`	--instructor-id --academic-term-id	Teaching load vs. max hours

Fees Domain

Action	Key Parameters	Description
`add-fee-category`	--name --code --company-id	Create fee category (tuition, lab fee, etc.)
`update-fee-category`	--fee-category-id [fields]	Update fee category
`list-fee-categories`	--company-id	List fee categories
`add-fee-structure`	--name --program-id --academic-term-id --items --company-id	Create fee structure with line items
`update-fee-structure`	--structure-id [fields]	Update fee structure
`get-fee-structure`	--structure-id	Get fee structure with items
`list-fee-structures`	--program-id --academic-term-id --company-id	List fee structures
`add-scholarship`	--student-id --name --discount-type --discount-amount --company-id	Award scholarship/discount
`update-scholarship`	--scholarship-id [fields]	Update scholarship
`list-scholarships`	--student-id --scholarship-status --company-id	List scholarships
`generate-fee-invoice`	--student-id --program-id --academic-term-id --company-id	Generate tuition invoice (applies scholarships)
`list-fee-invoices`	--student-id --company-id	List invoices for student
`get-student-account`	--student-id --company-id	Account summary: invoices, scholarships, balance
`get-outstanding-fees`	--company-id [--due-date-to]	All students with overdue invoices
`apply-late-fee`	--student-id --fee-category-id --amount --company-id	Apply late fee charge

Communications Domain

Action	Key Parameters	Description
`add-announcement`	--title --body --company-id [--priority --audience-type --audience-filter]	Create announcement (draft)
`update-announcement`	--announcement-id [fields]	Update draft announcement
`submit-announcement`	--announcement-id [--published-by]	Publish + create notifications for audience
`list-announcements`	--announcement-status --audience-type --company-id	List announcements
`get-announcement`	--announcement-id	Get announcement + notification count
`submit-notification`	--recipient-type --recipient-id --notification-type --title --message --company-id	Send targeted notification
`list-notifications`	--recipient-id --recipient-type --is-read --company-id	List notifications
`generate-progress-report`	--student-id --academic-term-id --company-id	Mid-term report to student + guardians
`submit-emergency-alert`	--title --message --company-id	Broadcast emergency to ALL recipients

Advanced Patterns (Tier 3)

FERPA Compliance

Every get-student call automatically logs a FERPA access record. For manual logging:

--action record-data-access --student-id {id} --data-category grades --access-type view --access-reason "Parent conference" --user-id {user_id}

Waitlist Flow

# Section full → student goes to waitlist automatically on create-section-enrollment
--action create-section-enrollment --student-id {id} --section-id {full_section_id} --company-id {id}
# → returns waitlist_status: waitlisted

# When a student drops, advance the waitlist:
--action apply-waitlist --section-id {id}
# → offers seat to next student (48-hour window), sends notification

Grade Amendment

# After submit-grades (immutable), use update-grade:
--action update-grade --enrollment-id {id} --new-letter-grade B --new-grade-points 3.0 --reason "Data entry error" --amended-by {user_id}
# Creates amendment record + triggers GPA recalculation

Emergency Alert

# Broadcasts to ALL students + guardians + staff in company:
--action submit-emergency-alert --title "School Closure" --message "School closed due to weather." --company-id {id} --sent-by {user_id}

Batch Operations

# Batch attendance for entire class:
--action record-batch-attendance --attendance-date 2025-09-15 --section-id {id} --company-id {id} \
  --records '[{"student_id":"{id1}","attendance_status":"present"},{"student_id":"{id2}","attendance_status":"absent"}]'

# Batch grade entry:
--action record-batch-results --assessment-id {id} \
  --results '[{"student_id":"{id1}","points_earned":92},{"student_id":"{id2}","points_earned":78}]'

About this skill

Automatic

Tutoring & Education 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

LeoYeAI / openclaw-master-skills

skills/educlaw/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 9 files · scripts

Illustrative Want to see what leoyeai/educlaw 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

educlaw

Security Model

Skill Activation Triggers

Setup (First Use Only)

Quick Start (Tier 1)

All Actions (Tier 2)

Students Domain

Academics Domain

Enrollment Domain

Grading Domain

Attendance Domain

Staff Domain

Fees Domain

Communications Domain

Advanced Patterns (Tier 3)

FERPA Compliance

Waitlist Flow

Grade Amendment

Emergency Alert

Batch Operations

SkillSafety

Source

Related skills

More in the registry