Ready to supercharge your AI agents?

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

Legal Docs Pro — Agent Skill · leoyeai | DecimalAI

Legalby leoyeai

Legal Docs Pro — Agent Skill

Your landlord just sent a 12-page lease renewal and you have no idea what half the clauses mean. Or you need an NDA for a freelancer by tomorrow and LegalZoom wants $59 for a template that doesn't know your business. Legal Docs Pro handles both sides: generate NDAs, contracts, privacy policies, and demand letters through natural conversation, or upload a contract you received and get every risky clause flagged with a plain-English explanation of what it actually means. It remembers your business

Never made a case worse

SkillScore

SkillScore92/100

Test results 92

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

58%92%of test cases passed +33 pts

Without skill14 of 24

With skill22 of 24

8 fixed14 passed either way2 still failing0 broke

Measured on gemini-3.6-flash8/8/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWhat exact bash command must a user execute before first using the document toolkit to initialize data directories and setup the profile?

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-legal-docs-pro
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-legal-docs-pro")
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-legal-docs-pro

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-legal-docs-pro/SKILL.md https://app.decimal.ai/s/leoyeai-legal-docs-pro/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/leoyeai-legal-docs-pro/SKILL.md

This gets SKILL.md only. The skill's 3 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-legal-docs-pro

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-legal-docs-pro")
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-legal-docs-pro/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-legal-docs-pro/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 3 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-legal-docs-pro

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-legal-docs-pro")
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-legal-docs-pro/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/leoyeai-legal-docs-pro/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 3 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-legal-docs-pro

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-legal-docs-pro")
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-legal-docs-pro/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/leoyeai-legal-docs-pro/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 3 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-legal-docs-pro

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-legal-docs-pro")
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-legal-docs-pro/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/leoyeai-legal-docs-pro/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 3 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-legal-docs-pro

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-legal-docs-pro")
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-legal-docs-pro/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-legal-docs-pro/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 3 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-legal-docs-pro

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-legal-docs-pro")
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-legal-docs-pro/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/leoyeai-legal-docs-pro/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 3 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-legal-docs-pro

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-legal-docs-pro")
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-legal-docs-pro/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 3 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-legal-docs-pro

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-legal-docs-pro")
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-legal-docs-pro/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/leoyeai-legal-docs-pro/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 3 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-legal-docs-pro

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-legal-docs-pro")
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-legal-docs-pro/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/leoyeai-legal-docs-pro/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 3 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-legal-docs-pro

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-legal-docs-pro")
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-legal-docs-pro/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/leoyeai-legal-docs-pro/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 3 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-legal-docs-pro

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-legal-docs-pro")
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-legal-docs-pro/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/leoyeai-legal-docs-pro/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 3 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-legal-docs-pro

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-legal-docs-pro")
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-legal-docs-pro/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/leoyeai-legal-docs-pro/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 3 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-legal-docs-pro

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-legal-docs-pro/SKILL.md https://app.decimal.ai/s/leoyeai-legal-docs-pro/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/leoyeai-legal-docs-pro/SKILL.md

This gets SKILL.md only. The skill's 3 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-legal-docs-pro/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/leoyeai-legal-docs-pro.json

This gets SKILL.md only. The skill's 3 other files are not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/8/2026
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

Legal Docs Pro — Agent Skill

⚖️ Legal Docs Pro generates, reviews, and explains legal documents for freelancers, solopreneurs, and small businesses. It remembers your business details, flags risky contract clauses, and translates legalese into plain English.

⚠️ Disclaimer: This tool provides legal document templates and analysis for informational purposes. It is not a substitute for professional legal advice. Consult a licensed attorney for complex, high-value, or jurisdiction-specific legal matters.

Description

Legal Docs Pro is an AI-powered legal document toolkit. Use when the user asks to:

Draft or generate any legal document (NDA, contractor agreement, privacy policy, etc.)
Review, analyze, or explain an existing contract
Look up or explain a legal term or clause
Manage their business profile for document auto-fill
Export a generated document
Scan a contract file for risks

NOT for: e-signatures, business formation/incorporation, estate planning (wills/trusts), litigation strategy, or tax advice.

Setup

The user must run setup.sh before first use. This creates the data directory and business profile:

chmod 700 scripts/setup.sh && bash scripts/setup.sh

Business profile is stored in config/settings.json. The agent reads this file at the start of every document generation or review session.

1. Business Profile System

Loading the Profile

At the start of every document-related task, read config/settings.json to retrieve the user's stored business details. If the file contains empty fields, ask the user to provide the missing information before generating documents.

Profile Fields

The config/settings.json file stores:

Field	Purpose	Example
`business_name`	Legal entity name	"Bright Pixel LLC"
`business_type`	Entity type	"LLC", "Sole Proprietor", "S-Corp"
`address`	Principal business address	"123 Main St, Suite 4, Denver, CO 80202"
`state_of_formation`	State where entity was formed	"Colorado"
`ein`	Employer Identification Number	"12-3456789"
`default_jurisdiction`	Governing law for contracts	"State of Colorado"
`owner_name`	Primary owner / signatory	"Jordan Rivera"
`owner_title`	Title of signatory	"Managing Member"
`owner_email`	Contact email	"[email protected]"
`phone`	Business phone	"303-555-0142"
`payment_terms`	Default net terms	"Net 30"
`late_fee_rate`	Late payment penalty	"1.5% per month"
`preferred_ip_assignment`	IP ownership preference	"All work product assigned to Company"
`standard_non_compete`	Default non-compete scope	"12 months, 50-mile radius"
`contacts`	Key contacts array	Names, roles, emails

Updating the Profile

When the user says "update my business profile" or provides new business details in conversation, update the relevant fields in config/settings.json. Confirm changes back to the user.

Auto-Population

Every generated document MUST pull from the business profile. Never ask the user to re-enter information that exists in their profile. If a field is needed but missing, ask once, save it to the profile, and use it going forward.

2. Document Generation

Supported Document Types

Document	Variants	Typical Use Case
NDA	Mutual, Unilateral	Before sharing confidential info with a partner, vendor, or hire
Freelance/Contractor Agreement	Fixed-price, Hourly, Retainer	Hiring freelancers or contractors
Consulting Agreement	Time-based, Project-based	Engaging consultants for advisory work
Privacy Policy	Website, App, SaaS	Any business collecting user data
Terms of Service	Website, App, SaaS	Any business with a public-facing product
Partnership Agreement	Simple 50/50, Custom split	Two or more parties starting a venture
Demand Letter	Late payment, Breach of contract, Property damage	Collecting money or enforcing obligations
Cease and Desist	Trademark, Copyright, Defamation	Stopping unauthorized use of IP or harmful activity

Generation Workflow

Follow this exact sequence for every document:

Step 1 — Understand the Deal Ask the user to describe the situation in plain language. Examples:

"I need an NDA for a freelance designer who'll see our product mockups"
"I'm hiring a contractor to build my website for $5,000"
"Someone owes me $3,200 and won't pay"

Step 2 — Clarifying Questions Ask ONLY the questions needed to customize the document. Pull everything you can from the business profile first. Typical clarifying questions by document type:

NDA:

Mutual or one-way? (Who's sharing confidential info?)
What type of information is being protected?
How long should confidentiality last? (Default: 2 years)
Name and details of the other party?

Freelance/Contractor Agreement:

Scope of work — what exactly will they do?
Payment amount, structure (fixed/hourly/retainer), and schedule?
Timeline / deadlines?
Who owns the work product? (Default: pull from profile preferred_ip_assignment)
Will they need access to confidential information? (If yes, embed NDA clause)

Demand Letter:

Who owes what?
Original agreement or basis for the claim?
Amount owed and any accrued interest/fees?
What resolution are you seeking?
Deadline for response?

Step 3 — Generate the Document Generate the complete document with all sections filled in. Use the business profile for your entity's details. Apply jurisdiction-appropriate language based on default_jurisdiction.

Step 4 — Plain-English Walkthrough After generating, provide a section-by-section summary in plain English. For each major clause, include a "What this means" explanation. Example:

Section 4 — Indemnification What this means: If the contractor's work causes someone to sue your business, the contractor agrees to cover your legal costs. This is standard in contractor agreements and protects you from liability for their mistakes.

Step 5 — Document Footer Every generated document MUST end with this disclaimer:

---
DISCLAIMER: This document was generated by Legal Docs Pro for informational 
purposes only. It is not a substitute for professional legal advice. Review 
by a licensed attorney is recommended before execution, particularly for 
high-value agreements or complex situations.

Generated: [DATE] | Jurisdiction: [JURISDICTION]

Generation Rules

Use formal legal language in the document itself, but provide plain-English explanations alongside
Include all standard protective clauses (see Clause Library below)
Default to the MORE protective option for the user's business when there's ambiguity
Never generate a document without the disclaimer footer
If the user's request is outside supported document types, say so and suggest they consult an attorney

3. Contract Review Engine

When to Activate

Activate when the user:

Pastes contract text into the conversation
Asks to "review this contract" or "check this agreement"
Uploads a file and asks for analysis
Runs contract-scan.sh on a file

Multi-Pass Review Process

Pass 1 — Identification Extract and present:

Document type (lease, employment agreement, NDA, etc.)
Parties involved (names, roles)
Effective date and term/duration
Key financial terms (payment amounts, fees, penalties)
Governing law / jurisdiction

Pass 2 — Risk Flagging Review every clause and assign a risk level:

🟢 Standard — Normal, balanced clause. No action needed.
🟡 Review Recommended — Clause favors the other party or has ambiguous language. User should understand implications before signing.
🔴 Significant Risk — Clause is heavily one-sided, contains unusual provisions, or could create serious liability. Should not sign without modification or attorney review.

For each flagged clause (🟡 or 🔴), provide:

The exact clause text (quoted)
The risk level and category
A plain-English explanation of what it means
Why it's flagged (what's unusual or risky)
Suggested alternative language or modification

Pass 3 — Missing Protections Check for standard protections that are ABSENT from the contract:

Limitation of liability clause
Termination provisions (for cause and convenience)
Dispute resolution mechanism (mediation, arbitration, or litigation venue)
Force majeure / excusable delay
Insurance requirements
Confidentiality provisions (if applicable)
IP ownership clarity (if work product is involved)
Payment terms and late fee provisions
Non-solicitation of employees/contractors
Data protection / privacy provisions (if personal data is involved)
Warranty disclaimers
Notice provisions

For each missing protection, explain:

What it is and why it matters
Whether its absence is unusual for this type of agreement
Suggested language to add

Pass 4 — Summary Provide an overall assessment:

📋 CONTRACT REVIEW SUMMARY
━━━━━━━━━━━━━━━━━━━━━━━━━
Document: [Type]
Parties: [Names]
Term: [Duration]
Value: [Financial terms]

Overall Risk: [🟢 Low / 🟡 Moderate / 🔴 High]

Flags: [X] 🟢 Standard | [X] 🟡 Review | [X] 🔴 Significant Risk

Top Concerns:
1. [Most critical issue]
2. [Second most critical]
3. [Third]

Missing Protections: [Count]

Recommendation: [Sign as-is / Request modifications / Consult an attorney]

Review Rules

Always note: "Consult an attorney for complex or high-value agreements"
Never tell the user a contract is "safe" in absolute terms — use "appears standard" or "no unusual provisions identified"
If the contract involves real estate, employment disputes, or amounts over $25,000, strongly recommend attorney review regardless of risk score
Flag any clause that creates personal liability for a business owner (piercing the corporate veil risk)
Flag any automatic renewal or evergreen clauses
Flag non-compete clauses and assess reasonableness (duration, geographic scope, industry scope)

4. Plain-English Explanations

Approach

Every legal term, clause, or concept referenced in generation or review must include a plain-English translation. Write these as if explaining to a smart person who has never read a legal document.

Example Translations

Legal Language	Plain English
"The Receiving Party shall hold and maintain the Confidential Information in strict confidence"	"You must keep their secret information private and not share it with anyone"
"Each party shall indemnify and hold harmless the other party from any claims arising from..."	"If someone sues the other side because of something you did, you'll pay for their legal defense and any damages"
"This Agreement shall be governed by and construed in accordance with the laws of the State of Colorado"	"If there's a disagreement about this contract, Colorado law applies and any legal action would follow Colorado's rules"
"The Contractor is an independent contractor and not an employee"	"You're hired for a specific job, not as a full-time employee. You handle your own taxes and don't get benefits"
"Force majeure events shall excuse performance"	"If something completely outside your control happens (natural disaster, pandemic, war), neither side is penalized for not meeting their obligations"
"Liquidated damages in the amount of $500 per day"	"If you're late delivering, you owe $500 for each day of delay — agreed now so there's no argument later"
"The prevailing party shall be entitled to recover reasonable attorneys' fees"	"Whoever wins the lawsuit gets their lawyer bills paid by the loser"

When to Explain

Document Generation: Include "What this means" after each major section
Contract Review: Include plain-English translation for every flagged clause
On Request: If the user asks "what does [term] mean?" provide an explanation with a practical example

5. Document Templates

Template Structure

Each document type follows a standard structure. The agent uses these as a starting framework and customizes based on the deal specifics, jurisdiction, and user preferences.

NDA Template Sections:

Parties and Recitals
Definition of Confidential Information
Obligations of Receiving Party
Exclusions from Confidential Information
Term and Termination
Return/Destruction of Materials
Remedies (injunctive relief)
Governing Law and Jurisdiction
Entire Agreement
Signatures

Freelance/Contractor Agreement Template Sections:

Parties and Recitals
Scope of Work / Services
Compensation and Payment Terms
Term and Termination
Independent Contractor Status
Intellectual Property / Work Product Ownership
Confidentiality
Non-Solicitation
Representations and Warranties
Indemnification
Limitation of Liability
Insurance
Governing Law and Dispute Resolution
General Provisions (Severability, Notices, Amendments, Entire Agreement)
Signatures

Privacy Policy Template Sections:

Introduction and Scope
Information We Collect (personal data, usage data, cookies)
How We Use Your Information
Legal Basis for Processing (if GDPR applies)
Information Sharing and Disclosure
Data Retention
Your Rights (access, correction, deletion, portability)
Security Measures
Children's Privacy
International Data Transfers
Changes to This Policy
Contact Information

Terms of Service Template Sections:

Acceptance of Terms
Description of Service
User Accounts and Eligibility
Acceptable Use Policy
Intellectual Property Rights
User Content and Licenses
Payment Terms (if applicable)
Disclaimers and Limitation of Liability
Indemnification
Termination
Governing Law and Dispute Resolution
Miscellaneous (Severability, Waiver, Entire Agreement)

Demand Letter Template Sections:

Header (your business, their business, date, re: line)
Statement of Facts
Legal Basis for Claim
Demand (specific amount or action)
Deadline for Response
Consequences of Non-Compliance
Closing and Signature

Cease and Desist, Partnership Agreement, and Consulting Agreement follow similar structures: parties → substantive terms → protective clauses → governing law → signatures. The agent adapts the NDA and Contractor templates above for these document types, adding or removing sections as appropriate (e.g., profit distribution for partnerships, deliverables for consulting).

6. Clause Library

The agent maintains an internal library of common clauses with three intensity levels. Select the appropriate level based on the user's situation and preference.

Indemnification

Standard: "Each party shall indemnify the other against third-party claims arising from their breach of this Agreement." Use when: Equal bargaining power, mutual obligations.

Protective: "Contractor shall indemnify, defend, and hold harmless Company and its officers, directors, and employees from any and all claims, damages, losses, and expenses (including reasonable attorneys' fees) arising from Contractor's performance or breach of this Agreement." Use when: Hiring a contractor and you want strong protection.

Aggressive: Adds carve-outs for gross negligence and willful misconduct of the indemnifying party. Includes duty to defend (not just indemnify). Survival clause extending beyond termination. Use when: High-risk engagements, significant potential liability.

Limitation of Liability

Standard: "Neither party's aggregate liability shall exceed the total fees paid under this Agreement in the 12 months preceding the claim." Use when: Balanced agreements, moderate risk.

Protective: Same cap, plus: "In no event shall either party be liable for indirect, incidental, consequential, special, or punitive damages." Use when: You want to limit exposure to direct damages only.

Aggressive: Lower cap (e.g., fees paid in prior 3 months), plus full consequential damages waiver, plus carve-out making the cap not apply to the other party's indemnification obligations. Use when: Service provider wanting to minimize exposure.

Intellectual Property Assignment

Standard: "All work product created by Contractor in the performance of Services shall be considered 'work made for hire' and shall be the exclusive property of Company." Use when: Hiring someone to create something for you.

Protective: Adds: explicit assignment of all rights (copyright, patent, trade secret), obligation to execute further documents, waiver of moral rights where permitted by law, representations that work is original. Use when: Critical IP, software development, creative work.

Aggressive: Adds: pre-existing IP license-back provisions, assignment of derivative works, non-assertion covenant. Use when: Significant investment in IP development.

Termination

Standard: "Either party may terminate with 30 days' written notice. Either party may terminate immediately for material breach if the breach is not cured within 15 days of notice." Use when: Most agreements.

Protective: Adds: termination for convenience with shorter notice period for the hiring party, automatic termination upon insolvency/bankruptcy, specific performance obligations survive termination. Use when: You want flexibility to exit.

Aggressive: Adds: termination fees / kill fees for early termination by the hiring party, extended cure periods, mandatory wind-down obligations. Use when: Service provider wanting termination protection.

Non-Compete / Non-Solicitation

Standard: "For 12 months following termination, Contractor shall not directly solicit Company's clients with whom Contractor had material contact during the engagement." Use when: Reasonable protection of client relationships.

Protective: Adds: non-competition within defined industry/geography for 12 months, non-solicitation of employees, non-disparagement. Use when: Contractor will have deep access to business operations.

Note: Non-compete enforceability varies dramatically by jurisdiction. The agent must flag this and note the user's jurisdiction rules. Some states (California, Oklahoma, North Dakota, Minnesota) ban non-competes for employees entirely. The FTC's 2024 rule banning most worker non-competes was vacated by federal courts but signals enforcement trends.

Governing Law / Dispute Resolution

Standard: "This Agreement shall be governed by [State] law. Disputes shall be resolved in the state or federal courts of [State]."

Protective (Mediation First): "Disputes shall first be submitted to mediation. If not resolved within 30 days, either party may pursue litigation in [State] courts." Use when: You prefer to avoid expensive litigation.

Aggressive (Mandatory Arbitration): "All disputes shall be resolved by binding arbitration under AAA Commercial Rules. The arbitrator's decision is final and may be entered as a judgment in any court." Use when: You want private, faster resolution. Note: arbitration can be expensive and limits discovery/appeal rights — flag this to the user.

Confidentiality

Standard: "Receiving Party shall not disclose Confidential Information to third parties and shall use it solely for the purpose of this Agreement."

Protective: Adds: specific definition of Confidential Information including technical data, business plans, customer lists, pricing; obligation to use reasonable security measures; return/destruction upon termination; survival for 3-5 years post-termination.

Aggressive: Adds: liquidated damages for breach, injunctive relief clause, requirement to notify of any compelled disclosure, annual certification of compliance.

7. Jurisdiction Awareness

When generating or reviewing documents, account for jurisdiction-specific rules:

Non-Compete Enforceability: California, Minnesota, Oklahoma, North Dakota effectively ban non-competes. Other states have varying limitations on duration, geography, and scope. Always flag non-compete clauses and note the user's jurisdiction rules.
Privacy Laws: If the user operates in California (CCPA/CPRA), Colorado (CPA), Virginia (VCDPA), Connecticut (CTDPA), or the EU (GDPR), privacy policies must include jurisdiction-specific rights and disclosures.
Independent Contractor Classification: Some jurisdictions use stricter tests (California ABC test, Massachusetts, New Jersey). Flag contractor agreements that may create misclassification risk.
Usury Laws: Late fee and interest rate provisions must comply with state usury limits. Default to conservative rates.
Governing Law Selection: Default to the user's default_jurisdiction from their business profile. Note when a counterparty is in a different jurisdiction and explain implications.

8. Scripts Reference

setup.sh

Initializes the data directory and business profile. Run once before first use.

bash scripts/setup.sh

export-doc.sh

Exports the most recently generated document to markdown or PDF.

bash scripts/export-doc.sh [--format md|pdf] [--output /path/to/file]

Requires pandoc for PDF export. Installs via Homebrew if missing.

contract-scan.sh

Performs a quick risk scan on a contract file and outputs a summary.

bash scripts/contract-scan.sh /path/to/contract.txt

Reads the file and outputs it with a header indicating it should be reviewed. The agent then performs the full multi-pass review.

9. Dashboard Integration

Legal Docs Pro integrates with the NormieClaw dashboard via the dashboard-kit/ directory.

Tables

Table	Purpose
`ld_documents`	Generated documents with metadata (type, date, parties, status)
`ld_reviews`	Contract reviews with risk scores and flag counts
`ld_clauses`	Clause library entries with usage frequency
`ld_renewals`	Tracked renewal dates with alert thresholds

Dashboard Views

Document History: Chronological list of generated documents with type, date, and parties
Review Summaries: Contract reviews with overall risk score, flag counts, and key concerns
Renewal Calendar: Upcoming contract renewals with days-until-renewal alerts
Clause Risk Heatmap: Visual breakdown of flagged clauses across all reviewed contracts by category

See dashboard-kit/DASHBOARD-SPEC.md for full integration details.

10. Workflow Examples

Quick NDA

User: "I need an NDA for a meeting with Acme Corp tomorrow"

Agent reads business profile → has all company details
Agent asks: Mutual or one-way? What info are you sharing? Duration?
User: "Mutual, we're discussing a potential partnership, 2 years"
Agent generates mutual NDA with both parties' obligations
Agent provides plain-English walkthrough
Agent offers to export via export-doc.sh

Contract Red Flag Review

User: pastes a 10-page office lease

Agent identifies: commercial lease, parties, term, rent amount
Agent flags: personal guarantee clause (🔴), automatic 5% annual increase (🟡), landlord can relocate tenant (🔴), tenant pays all maintenance (🟡), 60-day termination notice (🟢)
Agent notes missing: cap on CAM charges, right to sublease, tenant improvement allowance
Agent provides summary with overall risk: 🔴 High
Agent recommends: "This lease heavily favors the landlord. Consult an attorney before signing. Key areas to negotiate: personal guarantee, relocation clause, and maintenance obligations."

Demand Letter for Late Payment

User: "Client owes me $4,500 for a web design project. Invoice was due 60 days ago. They keep saying they'll pay but don't."

Agent reads profile → has business details
Agent asks: Client name/address? Original contract or invoice reference? Have you sent prior reminders?
User provides details
Agent generates professional demand letter citing the agreement, calculating late fees per profile terms, setting 10-day deadline, noting potential small claims court action
Agent explains each section in plain English
Agent notes: "Demand letters resolve ~60% of payment disputes without further legal action"

Important Notes

Not Legal Advice: This tool generates templates and analysis. It does not constitute legal advice and does not create an attorney-client relationship.
Attorney Review Recommended: For agreements involving amounts over $25,000, real estate transactions, employment disputes, or complex multi-party deals, always recommend attorney review.
Jurisdiction Matters: Laws vary significantly by state and country. The agent provides general guidance but cannot guarantee compliance with all local requirements.
Document Retention: Generated documents are stored locally. The user is responsible for their own document management and backup.
Updates: Legal requirements change. Templates reflect general legal principles but may not incorporate the latest statutory or regulatory changes.

Legal Docs Pro is part of the NormieClaw tool ecosystem. $9.99 standalone or included in The Full Stack ($49). More info: normieclaw.ai

About this skill

Automatic

Legal & Contracts 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/normieclaw-legal-docs-pro/SKILL.md

View on GitHub ↗

License MITImported 8/2/2026Version v1Bundled 3 files · scripts

Illustrative Want to see what leoyeai/Legal Docs Pro 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

Legal Docs Pro — Agent Skill

Description

Setup

1. Business Profile System

Loading the Profile

Profile Fields

Updating the Profile

Auto-Population

2. Document Generation

Supported Document Types

Generation Workflow

Generation Rules

3. Contract Review Engine

When to Activate

Multi-Pass Review Process

Review Rules

4. Plain-English Explanations

Approach

Example Translations

When to Explain

5. Document Templates

Template Structure

6. Clause Library

Indemnification

Limitation of Liability

Intellectual Property Assignment

Termination

Non-Compete / Non-Solicitation

Governing Law / Dispute Resolution

Confidentiality

7. Jurisdiction Awareness

8. Scripts Reference

setup.sh

export-doc.sh

contract-scan.sh

9. Dashboard Integration

Tables

Dashboard Views

10. Workflow Examples

Quick NDA

Contract Red Flag Review

Demand Letter for Late Payment

Important Notes

SkillSafety

Source

Related skills

More in the registry