Ready to supercharge your AI agents?

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

Options Strategy Advisor · nicepkg | DecimalAI

Financeby nicepkg

Options Strategy Advisor

Options trading strategy analysis and simulation tool. Provides theoretical pricing using Black-Scholes model, Greeks calculation, strategy P/L simulation, and risk management guidance.

Maintained

SkillScore

SkillScore86/100

Test results 86

Safety

3/3 safety checks passed

Code scan
Intent
Content

What it changes

73%86%of test cases passed +14 pts

Without skill16 of 22

With skill19 of 22

4 fixed15 passed either way2 still failing1 broke

Measured on gemini-3.6-flash8/24/2026v1

Track record

Agent runs: 0; All time

See one task, with and without the skill

One test taskWhen exporting the options strategy analysis summary markdown report for an AAPL Bull Call Spread generated on November 8, 2025, what exact file naming structure should be assigned?

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 nicepkg-options-strategy-advisor
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("nicepkg-options-strategy-advisor")
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 nicepkg-options-strategy-advisor

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/nicepkg-options-strategy-advisor/SKILL.md https://app.decimal.ai/s/nicepkg-options-strategy-advisor/SKILL.md

Copy SKILL.md

Save it in your project, as

.claude/skills/nicepkg-options-strategy-advisor/SKILL.md

This gets SKILL.md only. The skill's 1 other file is 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 nicepkg-options-strategy-advisor

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("nicepkg-options-strategy-advisor")
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/nicepkg-options-strategy-advisor/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/nicepkg-options-strategy-advisor/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 1 other file is 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 nicepkg-options-strategy-advisor

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("nicepkg-options-strategy-advisor")
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/nicepkg-options-strategy-advisor/SKILL.md

Give it to your agent

from pathlib import Path
from agents import Agent, Runner

skill = Path(".agents/skills/nicepkg-options-strategy-advisor/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 1 other file is 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 nicepkg-options-strategy-advisor

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("nicepkg-options-strategy-advisor")
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/nicepkg-options-strategy-advisor/SKILL.md

Give it to your agent

from pathlib import Path
from openai import OpenAI

client = OpenAI()
skill = Path(".agents/skills/nicepkg-options-strategy-advisor/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 1 other file is 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 nicepkg-options-strategy-advisor

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("nicepkg-options-strategy-advisor")
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/nicepkg-options-strategy-advisor/SKILL.md

Give it to your agent

from pathlib import Path
import anthropic

client = anthropic.Anthropic()
skill = Path(".agents/skills/nicepkg-options-strategy-advisor/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 1 other file is 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 nicepkg-options-strategy-advisor

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("nicepkg-options-strategy-advisor")
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/nicepkg-options-strategy-advisor/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/nicepkg-options-strategy-advisor/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 1 other file is 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 nicepkg-options-strategy-advisor

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("nicepkg-options-strategy-advisor")
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/nicepkg-options-strategy-advisor/SKILL.md

Give it to your agent

from pathlib import Path
from langchain.agents import create_agent

skill = Path(".agents/skills/nicepkg-options-strategy-advisor/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 1 other file is 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 nicepkg-options-strategy-advisor

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("nicepkg-options-strategy-advisor")
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/nicepkg-options-strategy-advisor/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 1 other file is 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 nicepkg-options-strategy-advisor

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("nicepkg-options-strategy-advisor")
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/nicepkg-options-strategy-advisor/SKILL.md

Give it to your agent

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

skill = Path(".agents/skills/nicepkg-options-strategy-advisor/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 1 other file is 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 nicepkg-options-strategy-advisor

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("nicepkg-options-strategy-advisor")
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/nicepkg-options-strategy-advisor/SKILL.md

Give it to your agent

from pathlib import Path
from pydantic_ai import Agent

skill = Path(".agents/skills/nicepkg-options-strategy-advisor/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 1 other file is 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 nicepkg-options-strategy-advisor

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("nicepkg-options-strategy-advisor")
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/nicepkg-options-strategy-advisor/SKILL.md

Give it to your agent

from pathlib import Path
from deepagents import create_deep_agent

skill = Path(".agents/skills/nicepkg-options-strategy-advisor/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 1 other file is 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 nicepkg-options-strategy-advisor

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("nicepkg-options-strategy-advisor")
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/nicepkg-options-strategy-advisor/SKILL.md

Give it to your agent

import asyncio
from pathlib import Path
from agent_framework import Agent

skill = Path(".agents/skills/nicepkg-options-strategy-advisor/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 1 other file is 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 nicepkg-options-strategy-advisor

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("nicepkg-options-strategy-advisor")
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/nicepkg-options-strategy-advisor/SKILL.md

Give it to your agent

from pathlib import Path
from strands import Agent

skill = Path(".agents/skills/nicepkg-options-strategy-advisor/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 1 other file is 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 nicepkg-options-strategy-advisor

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/nicepkg-options-strategy-advisor/SKILL.md https://app.decimal.ai/s/nicepkg-options-strategy-advisor/SKILL.md

Copy SKILL.md

Save it in your project, as

.agents/skills/nicepkg-options-strategy-advisor/SKILL.md

This gets SKILL.md only. The skill's 1 other file is 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/nicepkg-options-strategy-advisor/SKILL.md

Read the summary as JSON

curl -fsSL https://app.decimal.ai/s/nicepkg-options-strategy-advisor.json

This gets SKILL.md only. The skill's 1 other file is not included.

Other ways to add it

Other setups docs

You don't need a DecimalAI account.

Version: v1, tested 8/24/2026
Source: nicepkg/ai-workflow ↗
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

Options Strategy Advisor

Overview

This skill provides comprehensive options strategy analysis and education using theoretical pricing models. It helps traders understand, analyze, and simulate options strategies without requiring real-time market data subscriptions.

Core Capabilities:

Black-Scholes Pricing: Theoretical option prices and Greeks calculation
Strategy Simulation: P/L analysis for major options strategies
Earnings Strategies: Pre-earnings volatility plays integrated with Earnings Calendar
Risk Management: Position sizing, Greeks exposure, max loss/profit analysis
Educational Focus: Detailed explanations of strategies and risk metrics

Data Sources:

FMP API: Stock prices, historical volatility, dividends, earnings dates
User Input: Implied volatility (IV), risk-free rate
Theoretical Models: Black-Scholes for pricing and Greeks

When to Use This Skill

Use this skill when:

User asks about options strategies ("What's a covered call?", "How does an iron condor work?")
User wants to simulate strategy P/L ("What's my max profit on a bull call spread?")
User needs Greeks analysis ("What's my delta exposure?")
User asks about earnings strategies ("Should I buy a straddle before earnings?")
User wants to compare strategies ("Covered call vs protective put?")
User needs position sizing guidance ("How many contracts should I trade?")
User asks about volatility ("Is IV high right now?")

Example requests:

"Analyze a covered call on AAPL"
"What's the P/L on a $100/$105 bull call spread on MSFT?"
"Should I trade a straddle before NVDA earnings?"
"Calculate Greeks for my iron condor position"
"Compare protective put vs covered call for downside protection"

Supported Strategies

Income Strategies

Covered Call - Own stock, sell call (generate income, cap upside)
Cash-Secured Put - Sell put with cash backing (collect premium, willing to buy stock)
Poor Man's Covered Call - LEAPS call + short near-term call (capital efficient)

Protection Strategies

Protective Put - Own stock, buy put (insurance, limited downside)
Collar - Own stock, sell call + buy put (limited upside/downside)

Directional Strategies

Bull Call Spread - Buy lower strike call, sell higher strike call (limited risk/reward bullish)
Bull Put Spread - Sell higher strike put, buy lower strike put (credit spread, bullish)
Bear Call Spread - Sell lower strike call, buy higher strike call (credit spread, bearish)
Bear Put Spread - Buy higher strike put, sell lower strike put (limited risk/reward bearish)

Volatility Strategies

Long Straddle - Buy ATM call + ATM put (profit from big move either direction)
Long Strangle - Buy OTM call + OTM put (cheaper than straddle, bigger move needed)
Short Straddle - Sell ATM call + ATM put (profit from no movement, unlimited risk)
Short Strangle - Sell OTM call + OTM put (profit from no movement, wider range)

Range-Bound Strategies

Iron Condor - Bull put spread + bear call spread (profit from range-bound movement)
Iron Butterfly - Sell ATM straddle, buy OTM strangle (profit from tight range)

Advanced Strategies

Calendar Spread - Sell near-term option, buy longer-term option (profit from time decay)
Diagonal Spread - Calendar spread with different strikes (directional + time decay)
Ratio Spread - Unbalanced spread (more contracts on one leg)

Analysis Workflow

Step 1: Gather Input Data

Required from User:

Ticker symbol
Strategy type
Strike prices
Expiration date(s)
Position size (number of contracts)

Optional from User:

Implied Volatility (IV) - if not provided, use Historical Volatility (HV)
Risk-free rate - default to current 3-month T-bill rate (~5.3% as of 2025)

Fetched from FMP API:

Current stock price
Historical prices (for HV calculation)
Dividend yield
Upcoming earnings date (for earnings strategies)

Example User Input:

Ticker: AAPL
Strategy: Bull Call Spread
Long Strike: $180
Short Strike: $185
Expiration: 30 days
Contracts: 10
IV: 25% (or use HV if not provided)

Step 2: Calculate Historical Volatility (if IV not provided)

Objective: Estimate volatility from historical price movements.

Method:

# Fetch 90 days of price data
prices = get_historical_prices("AAPL", days=90)

# Calculate daily returns
returns = np.log(prices / prices.shift(1))

# Annualized volatility
HV = returns.std() * np.sqrt(252)  # 252 trading days

Output:

Historical Volatility (annualized percentage)
Note to user: "HV = 24.5%, consider using current market IV for more accuracy"

User Can Override:

Provide IV from broker platform (ThinkorSwim, TastyTrade, etc.)
Script accepts --iv 28.0 parameter

Step 3: Price Options Using Black-Scholes

Black-Scholes Model:

For European-style options:

Call Price = S * N(d1) - K * e^(-r*T) * N(d2)
Put Price = K * e^(-r*T) * N(-d2) - S * N(-d1)

Where:
d1 = [ln(S/K) + (r + σ²/2) * T] / (σ * √T)
d2 = d1 - σ * √T

S = Current stock price
K = Strike price
r = Risk-free rate
T = Time to expiration (years)
σ = Volatility (IV or HV)
N() = Cumulative standard normal distribution

Adjustments:

Subtract present value of dividends from S for calls
American options: Use approximation or note "European pricing, may undervalue American options"

Python Implementation:

from scipy.stats import norm
import numpy as np

def black_scholes_call(S, K, T, r, sigma, q=0):
    """
    S: Stock price
    K: Strike price
    T: Time to expiration (years)
    r: Risk-free rate
    sigma: Volatility
    q: Dividend yield
    """
    d1 = (np.log(S/K) + (r - q + 0.5*sigma**2)*T) / (sigma*np.sqrt(T))
    d2 = d1 - sigma*np.sqrt(T)

    call_price = S*np.exp(-q*T)*norm.cdf(d1) - K*np.exp(-r*T)*norm.cdf(d2)
    return call_price

def black_scholes_put(S, K, T, r, sigma, q=0):
    d1 = (np.log(S/K) + (r - q + 0.5*sigma**2)*T) / (sigma*np.sqrt(T))
    d2 = d1 - sigma*np.sqrt(T)

    put_price = K*np.exp(-r*T)*norm.cdf(-d2) - S*np.exp(-q*T)*norm.cdf(-d1)
    return put_price

Output for Each Option Leg:

Theoretical price
Note: "Market price may differ due to bid-ask spread and American vs European pricing"

Step 4: Calculate Greeks

The Greeks measure option price sensitivity to various factors:

Delta (Δ): Change in option price per $1 change in stock price

def delta_call(S, K, T, r, sigma, q=0):
    d1 = (np.log(S/K) + (r - q + 0.5*sigma**2)*T) / (sigma*np.sqrt(T))
    return np.exp(-q*T) * norm.cdf(d1)

def delta_put(S, K, T, r, sigma, q=0):
    d1 = (np.log(S/K) + (r - q + 0.5*sigma**2)*T) / (sigma*np.sqrt(T))
    return np.exp(-q*T) * (norm.cdf(d1) - 1)

Gamma (Γ): Change in delta per $1 change in stock price

def gamma(S, K, T, r, sigma, q=0):
    d1 = (np.log(S/K) + (r - q + 0.5*sigma**2)*T) / (sigma*np.sqrt(T))
    return np.exp(-q*T) * norm.pdf(d1) / (S * sigma * np.sqrt(T))

Theta (Θ): Change in option price per day (time decay)

def theta_call(S, K, T, r, sigma, q=0):
    d1 = (np.log(S/K) + (r - q + 0.5*sigma**2)*T) / (sigma*np.sqrt(T))
    d2 = d1 - sigma*np.sqrt(T)

    theta = (-S*norm.pdf(d1)*sigma*np.exp(-q*T)/(2*np.sqrt(T))
             - r*K*np.exp(-r*T)*norm.cdf(d2)
             + q*S*norm.cdf(d1)*np.exp(-q*T))

    return theta / 365  # Per day

Vega (ν): Change in option price per 1% change in volatility

def vega(S, K, T, r, sigma, q=0):
    d1 = (np.log(S/K) + (r - q + 0.5*sigma**2)*T) / (sigma*np.sqrt(T))
    return S * np.exp(-q*T) * norm.pdf(d1) * np.sqrt(T) / 100  # Per 1%

Rho (ρ): Change in option price per 1% change in interest rate

def rho_call(S, K, T, r, sigma, q=0):
    d2 = (np.log(S/K) + (r - q + 0.5*sigma**2)*T) / (sigma*np.sqrt(T)) - sigma*np.sqrt(T)
    return K * T * np.exp(-r*T) * norm.cdf(d2) / 100  # Per 1%

Position Greeks:

For a strategy with multiple legs, sum Greeks across all legs:

# Example: Bull Call Spread
# Long 1x $180 call
# Short 1x $185 call

delta_position = (1 * delta_long) + (-1 * delta_short)
gamma_position = (1 * gamma_long) + (-1 * gamma_short)
theta_position = (1 * theta_long) + (-1 * theta_short)
vega_position = (1 * vega_long) + (-1 * vega_short)

Greeks Interpretation:

Greek	Meaning	Example
Delta	Directional exposure	Δ = 0.50 → $50 profit if stock +$1
Gamma	Delta acceleration	Γ = 0.05 → Delta increases by 0.05 if stock +$1
Theta	Daily time decay	Θ = -$5 → Lose $5/day from time passing
Vega	Volatility sensitivity	ν = $10 → Gain $10 if IV increases 1%
Rho	Interest rate sensitivity	ρ = $2 → Gain $2 if rates increase 1%

Step 5: Simulate Strategy P/L

Objective: Calculate profit/loss at various stock prices at expiration.

Method:

Generate stock price range (e.g., ±30% from current price):

current_price = 180
price_range = np.linspace(current_price * 0.7, current_price * 1.3, 100)

For each price point, calculate P/L:

def calculate_pnl(strategy, stock_price_at_expiration):
    pnl = 0

    for leg in strategy.legs:
        if leg.type == 'call':
            intrinsic_value = max(0, stock_price_at_expiration - leg.strike)
        else:  # put
            intrinsic_value = max(0, leg.strike - stock_price_at_expiration)

        if leg.position == 'long':
            pnl += (intrinsic_value - leg.premium_paid) * 100  # Per contract
        else:  # short
            pnl += (leg.premium_received - intrinsic_value) * 100

    return pnl * num_contracts

Key Metrics:

Max Profit: Highest possible P/L
Max Loss: Worst possible P/L
Breakeven Point(s): Stock price(s) where P/L = 0
Profit Probability: Percentage of price range that's profitable (simplified)

Example Output:

Bull Call Spread: $180/$185 on AAPL (30 DTE, 10 contracts)

Current Price: $180.00
Net Debit: $2.50 per spread ($2,500 total)

Max Profit: $2,500 (at $185+)
Max Loss: -$2,500 (at $180-)
Breakeven: $182.50
Risk/Reward: 1:1

Probability Profit: ~55% (if stock stays above $182.50)

Step 6: Generate P/L Diagram (ASCII Art)

Visual representation of P/L across stock prices:

def generate_pnl_diagram(price_range, pnl_values, current_price, width=60, height=15):
    """Generate ASCII P/L diagram"""

    # Normalize to chart dimensions
    max_pnl = max(pnl_values)
    min_pnl = min(pnl_values)

    lines = []
    lines.append(f"\nP/L Diagram: {strategy_name}")
    lines.append("-" * width)

    # Y-axis levels
    levels = np.linspace(max_pnl, min_pnl, height)

    for level in levels:
        if abs(level) < (max_pnl - min_pnl) * 0.05:
            label = f"    0 |"  # Zero line
        else:
            label = f"{level:6.0f} |"

        row = label
        for i in range(width - len(label)):
            idx = int(i / (width - len(label)) * len(price_range))
            pnl = pnl_values[idx]
            price = price_range[idx]

            # Determine character
            if abs(pnl - level) < (max_pnl - min_pnl) / height:
                if pnl > 0:
                    char = '█'  # Profit
                elif pnl < 0:
                    char = '░'  # Loss
                else:
                    char = '─'  # Breakeven
            elif abs(level) < (max_pnl - min_pnl) * 0.05:
                char = '─'  # Zero line
            elif abs(price - current_price) < (price_range[-1] - price_range[0]) * 0.02:
                char = '│'  # Current price line
            else:
                char = ' '

            row += char

        lines.append(row)

    lines.append(" " * 6 + "|" + "-" * (width - 6))
    lines.append(" " * 6 + f"${price_range[0]:.0f}" + " " * (width - 20) + f"${price_range[-1]:.0f}")
    lines.append(" " * (width // 2 - 5) + "Stock Price")

    return "\n".join(lines)

Example Output:

P/L Diagram: Bull Call Spread $180/$185
------------------------------------------------------------
 +2500 |                               ████████████████████
       |                         ██████
       |                   ██████
       |             ██████
     0 |       ──────
       | ░░░░░░
       |░░░░░░
 -2500 |░░░░░
      |____________________________________________________________
       $126                  $180                   $234
                          Stock Price

Legend: █ Profit  ░ Loss  ── Breakeven  │ Current Price

Step 7: Strategy-Specific Analysis

Provide tailored guidance based on strategy type:

Covered Call:

Income Strategy: Generate premium while capping upside

Setup:
- Own 100 shares of AAPL @ $180
- Sell 1x $185 call (30 DTE) for $3.50

Max Profit: $850 (Stock at $185+ = $5 stock gain + $3.50 premium)
Max Loss: Unlimited downside (stock ownership)
Breakeven: $176.50 (Cost basis - premium received)

Greeks:
- Delta: -0.30 (reduces stock delta from 1.00 to 0.70)
- Theta: +$8/day (time decay benefit)

Assignment Risk: If AAPL > $185 at expiration, shares called away

When to Use:
- Neutral to slightly bullish
- Want income in sideways market
- Willing to sell stock at $185

Exit Plan:
- Buy back call if stock rallies strongly (preserve upside)
- Let expire if stock stays below $185
- Roll to next month if want to keep shares

Protective Put:

Insurance Strategy: Limit downside while keeping upside

Setup:
- Own 100 shares of AAPL @ $180
- Buy 1x $175 put (30 DTE) for $2.00

Max Profit: Unlimited (stock can rise infinitely)
Max Loss: -$7 per share = ($5 stock loss + $2 premium)
Breakeven: $182 (Cost basis + premium paid)

Greeks:
- Delta: +0.80 (stock delta 1.00 - put delta 0.20)
- Theta: -$6/day (time decay cost)

Protection: Guaranteed to sell at $175, no matter how far stock falls

When to Use:
- Own stock, worried about short-term drop
- Earnings coming up, want protection
- Alternative to stop-loss (can't be stopped out)

Cost: "Insurance premium" - typically 1-3% of stock value

Exit Plan:
- Let expire worthless if stock rises (cost of insurance)
- Exercise put if stock falls below $175
- Sell put if stock drops but want to keep shares

Iron Condor:

Range-Bound Strategy: Profit from low volatility

Setup (example on AAPL @ $180):
- Sell $175 put for $1.50
- Buy $170 put for $0.50
- Sell $185 call for $1.50
- Buy $190 call for $0.50

Net Credit: $2.00 ($200 per iron condor)

Max Profit: $200 (if stock stays between $175-$185)
Max Loss: $300 (if stock moves outside $170-$190)
Breakevens: $173 and $187
Profit Range: $175 to $185 (58% probability)

Greeks:
- Delta: ~0 (market neutral)
- Theta: +$15/day (time decay benefit)
- Vega: -$25 (short volatility)

When to Use:
- Expect low volatility, range-bound movement
- After big move, think consolidation
- High IV environment (sell expensive options)

Risk: Unlimited if one side tested
- Use stop loss at 2x credit received (exit at -$400)

Adjustments:
- If tested on one side, roll that side out in time
- Close early at 50% max profit to reduce tail risk

Step 8: Earnings Strategy Analysis

Integration with Earnings Calendar:

When user asks about earnings strategies, fetch earnings date:

from earnings_calendar import get_next_earnings_date

earnings_date = get_next_earnings_date("AAPL")
days_to_earnings = (earnings_date - today).days

Pre-Earnings Strategies:

Long Straddle/Strangle:

Setup (AAPL @ $180, earnings in 7 days):
- Buy $180 call for $5.00
- Buy $180 put for $4.50
- Total Cost: $9.50

Thesis: Expect big move (>5%) but unsure of direction

Breakevens: $170.50 and $189.50
Profit if: Stock moves >$9.50 in either direction

Greeks:
- Delta: ~0 (neutral)
- Vega: +$50 (long volatility)
- Theta: -$25/day (time decay hurts)

IV Crush Risk: ⚠️ CRITICAL
- Pre-earnings IV: 40% (elevated)
- Post-earnings IV: 25% (typical)
- IV drop: -15 points = -$750 loss even if stock doesn't move!

Analysis:
- Implied Move: √(DTE/365) × IV × Stock Price
  = √(7/365) × 0.40 × 180 = ±$10.50
- Breakeven Move Needed: ±$9.50
- Probability Profit: ~30-40% (implied move > breakeven move)

Recommendation:
✅ Consider if you expect >10% move (larger than implied)
❌ Avoid if expect normal ~5% earnings move (IV crush will hurt)

Alternative: Buy further OTM strikes to reduce cost
- $175/$185 strangle cost $4.00 (need >$8 move, but cheaper)

Short Iron Condor:

Setup (AAPL @ $180, earnings in 7 days):
- Sell $170/$175 put spread for $2.00
- Sell $185/$190 call spread for $2.00
- Net Credit: $4.00

Thesis: Expect stock to stay range-bound ($175-$185)

Profit Zone: $175 to $185
Max Profit: $400
Max Loss: $100

IV Crush Benefit: ✅
- Short high IV before earnings
- IV drops after earnings → profit on vega
- Even if stock moves slightly, IV drop helps

Greeks:
- Delta: ~0 (market neutral)
- Vega: -$40 (short volatility - good here!)
- Theta: +$20/day

Recommendation:
✅ Good if expect normal earnings reaction (<8% move)
✅ Benefit from IV crush regardless of direction
⚠️ Risk if stock gaps outside range (>10% move)

Exit Plan:
- Close next day if IV crushed (capture profit early)
- Use stop loss if one side tested (-2x credit)

Step 9: Risk Management Guidance

Position Sizing:

Account Size: $50,000
Risk Tolerance: 2% per trade = $1,000 max risk

Iron Condor Example:
- Max loss per spread: $300
- Max contracts: $1,000 / $300 = 3 contracts
- Actual position: 3 iron condors

Bull Call Spread Example:
- Debit paid: $2.50 per spread
- Max contracts: $1,000 / $250 = 4 contracts
- Actual position: 4 spreads

Portfolio Greeks Management:

Portfolio Guidelines:
- Delta: -10 to +10 (mostly neutral)
- Theta: Positive preferred (seller advantage)
- Vega: Monitor if >$500 (IV risk)

Current Portfolio:
- Delta: +5 (slightly bullish)
- Theta: +$150/day (collecting $150 daily)
- Vega: -$300 (short volatility)

Interpretation:
✅ Neutral delta (safe)
✅ Positive theta (time working for you)
⚠️ Short vega: If IV spikes, lose $300 per 1% IV increase
→ Reduce short premium positions if VIX rising

Adjustments and Exits:

Exit Rules by Strategy:

Covered Call:
- Profit: 50-75% of max profit
- Loss: Stock drops >5%, buy back call to preserve upside
- Time: 7-10 DTE, roll to avoid assignment

Spreads:
- Profit: 50% of max profit (close early, reduce tail risk)
- Loss: 2x debit paid (cut losses early)
- Time: 21 DTE, close or roll (avoid gamma risk)

Iron Condor:
- Profit: 50% of credit (close early common)
- Loss: One side tested, 2x credit lost
- Adjustment: Roll tested side out in time

Straddle/Strangle:
- Profit: Stock moved >breakeven, close immediately
- Loss: Theta eating position, stock not moving
- Time: Day after earnings (if earnings play)

Output Format

Strategy Analysis Report Template:

# Options Strategy Analysis: [Strategy Name]

**Symbol:** [TICKER]
**Strategy:** [Strategy Type]
**Expiration:** [Date] ([DTE] days)
**Contracts:** [Number]

---

## Strategy Setup

### Leg Details
| Leg | Type | Strike | Price | Position | Quantity |
|-----|------|--------|-------|----------|----------|
| 1 | Call | $180 | $5.00 | Long | 1 |
| 2 | Call | $185 | $2.50 | Short | 1 |

**Net Debit/Credit:** $2.50 debit ($250 total for 1 spread)

---

## Profit/Loss Analysis

**Max Profit:** $250 (at $185+)
**Max Loss:** -$250 (at $180-)
**Breakeven:** $182.50
**Risk/Reward Ratio:** 1:1

**Probability Analysis:**
- Probability of Profit: ~55% (stock above $182.50)
- Expected Value: $25 (simplified)

---

## P/L Diagram

[ASCII art diagram here]

---

## Greeks Analysis

### Position Greeks (1 spread)
- **Delta:** +0.20 (gains $20 if stock +$1)
- **Gamma:** +0.03 (delta increases by 0.03 if stock +$1)
- **Theta:** -$5/day (loses $5 per day from time decay)
- **Vega:** +$8 (gains $8 if IV increases 1%)

### Interpretation
- **Directional Bias:** Slightly bullish (positive delta)
- **Time Decay:** Working against you (negative theta)
- **Volatility:** Benefits from IV increase (positive vega)

---

## Risk Assessment

### Maximum Risk
**Scenario:** Stock falls below $180
**Max Loss:** -$250 (100% of premium paid)
**% of Account:** 0.5% (if $50k account)

### Assignment Risk
**Early Assignment:** Low (calls have time value)
**At Expiration:** Manage positions if in-the-money

---

## Trade Management

### Entry
✅ Enter if: [Conditions]
- Stock price $178-$182
- IV below 30%
- >21 DTE

### Profit Taking
- **Target 1:** 50% profit ($125) - Close half
- **Target 2:** 75% profit ($187.50) - Close all

### Stop Loss
- **Trigger:** Stock falls below $177 (-$150 loss)
- **Action:** Close position immediately

### Adjustments
- If stock rallies to $184, consider rolling short call higher
- If stock drops to $179, add second spread at $175/$180

---

## Suitability

### When to Use This Strategy
✅ Moderately bullish on AAPL
✅ Expect upside to $185-$190
✅ Want defined risk
✅ 21-45 DTE timeframe

### When to Avoid
❌ Very bullish (buy stock or long call instead)
❌ High IV environment (wait for IV to drop)
❌ Earnings in <7 days (IV crush risk)

---

## Alternatives Comparison

| Strategy | Max Profit | Max Loss | Complexity | When Better |
|----------|-----------|----------|------------|-------------|
| Bull Call Spread | $250 | -$250 | Medium | Moderately bullish |
| Long Call | Unlimited | -$500 | Low | Very bullish |
| Covered Call | $850 | Unlimited | Medium | Own stock already |
| Bull Put Spread | $300 | -$200 | Medium | Want credit spread |

**Recommendation:** Bull call spread is good balance of risk/reward for moderate bullish thesis.

---

*Disclaimer: This is theoretical analysis using Black-Scholes pricing. Actual market prices may differ. Trade at your own risk. Options are complex instruments with significant loss potential.*

File Naming Convention:

options_analysis_[TICKER]_[STRATEGY]_[DATE].md

Example: options_analysis_AAPL_BullCallSpread_2025-11-08.md

Key Principles

Theoretical Pricing Limitations

What Users Should Know:

Black-Scholes Assumptions:
- European-style options (can't exercise early)
- Constant volatility (IV changes in reality)
- No transaction costs
- Continuous trading
Real vs Theoretical:
- Bid-ask spread: Actual cost higher than theoretical
- American options: Can be exercised early (especially ITM puts)
- Liquidity: Wide markets on illiquid options
- Dividends: Ex-dividend dates affect pricing
Best Practices:
- Use as educational tool and comparative analysis
- Get real quotes from broker before trading
- Understand theoretical price ≈ mid-market price
- Account for commissions and slippage

Volatility Guidance

Historical vs Implied Volatility:

Historical Volatility (HV): What happened
- Calculated from past price movements
- Objective, based on data
- Available for free (FMP API)

Implied Volatility (IV): What market expects
- Derived from option prices
- Subjective, based on supply/demand
- Requires live options data (user provides)

Comparison:
- IV > HV: Options expensive (consider selling)
- IV < HV: Options cheap (consider buying)
- IV = HV: Fairly priced

IV Percentile:

User provides current IV, we calculate percentile:

# Fetch 1-year HV data
historical_hvs = calculate_hv_series(prices_1yr, window=30)

# Calculate IV percentile
iv_percentile = percentileofscore(historical_hvs, current_iv)

if iv_percentile > 75:
    guidance = "High IV - consider selling premium (credit spreads, iron condors)"
elif iv_percentile < 25:
    guidance = "Low IV - consider buying options (long calls/puts, debit spreads)"
else:
    guidance = "Normal IV - any strategy appropriate"

Integration with Other Skills

Earnings Calendar:

Fetch earnings dates automatically
Suggest earnings-specific strategies
Calculate days to earnings (DTE critical for IV)
Warn about IV crush risk

Technical Analyst:

Use support/resistance for strike selection
Trend analysis for directional strategies
Breakout potential for straddle/strangle timing

US Stock Analysis:

Fundamental analysis for longer-term strategies (LEAPS)
Dividend yield for covered call/put analysis
Earnings quality for earnings plays

Bubble Detector:

High bubble risk → focus on protective puts
Low risk → bullish strategies
Critical risk → avoid long premium (theta hurts)

Portfolio Manager:

Track options positions alongside stock positions
Aggregate Greeks across portfolio
Options as hedging tool for stock positions

Important Notes

All analysis in English
Educational focus: Strategies explained clearly
Theoretical pricing: Black-Scholes approximation
User IV input: Optional, defaults to HV
No real-time data required: FMP Free tier sufficient
Dependencies: Python 3.8+, numpy, scipy, pandas

Common Use Cases

Use Case 1: Learn Strategy

User: "Explain a covered call"

Workflow:
1. Load strategy reference (references/strategies_guide.md)
2. Explain concept, risk/reward, when to use
3. Simulate example on AAPL
4. Show P/L diagram
5. Compare to alternatives

Use Case 2: Analyze Specific Trade

User: "Analyze $180/$185 bull call spread on AAPL, 30 days"

Workflow:
1. Fetch AAPL price from FMP
2. Calculate HV or ask user for IV
3. Price both options (Black-Scholes)
4. Calculate Greeks
5. Simulate P/L
6. Generate analysis report

Use Case 3: Earnings Strategy

User: "Should I trade options before NVDA earnings?"

Workflow:
1. Fetch NVDA earnings date (Earnings Calendar)
2. Calculate days to earnings
3. Estimate IV percentile (if user provides IV)
4. Suggest straddle/strangle vs iron condor
5. Warn about IV crush
6. Simulate both strategies

Use Case 4: Portfolio Greeks Check

User: "What are my total portfolio Greeks?"

Workflow:
1. User provides current positions
2. Calculate Greeks for each position
3. Sum Greeks across portfolio
4. Assess overall exposure
5. Suggest adjustments if needed

Troubleshooting

Problem: IV not available

Solution: Use HV as proxy, note to user
Ask user to provide IV from broker platform

Problem: Negative option price

Solution: Check inputs (strike vs stock price)
Deep ITM options may have numerical issues

Problem: Greeks seem wrong

Solution: Verify inputs (T, sigma, r)
Check if using annual vs daily values

Problem: Strategy too complex

Solution: Break into legs, analyze separately
Refer to references for strategy details

Resources

References:

references/strategies_guide.md - All 17+ strategies explained
references/greeks_explained.md - Greeks deep dive
references/volatility_guide.md - HV vs IV, when to trade

Scripts:

scripts/black_scholes.py - Pricing engine and Greeks
scripts/strategy_analyzer.py - Strategy simulation
scripts/earnings_strategy.py - Earnings-specific analysis

External Resources:

Options Playbook: https://www.optionsplaybook.com/
CBOE Education: https://www.cboe.com/education/
Black-Scholes Calculator: Various online tools for verification

Version: 1.0 Last Updated: 2025-11-08 Dependencies: Python 3.8+, numpy, scipy, pandas, requests API: FMP API (Free tier sufficient)

When it activates

Automatically, when a task matches. Use when user requests options strategy analysis, covered calls, protective puts, spreads, iron condors, earnings plays, or options risk management. Includes volatility analysis, position sizing, and earnings-based strategy recommendations. Educational focus with practical trade simulation.

About this skill

Automatic

Finance & Accounting pack

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

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

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

nicepkg / ai-workflow

workflows/stock-trader-workflow/.claude/skills/options-strategy-advisor/SKILL.md

View on GitHub ↗

License MITImported 8/3/2026Version v1Bundled 1 file · scripts

Illustrative Want to see what nicepkg/options-strategy-advisor 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

Options Strategy Advisor

Overview

When to Use This Skill

Supported Strategies

Income Strategies

Protection Strategies

Directional Strategies

Volatility Strategies

Range-Bound Strategies

Advanced Strategies

Analysis Workflow

Step 1: Gather Input Data

Step 2: Calculate Historical Volatility (if IV not provided)

Step 3: Price Options Using Black-Scholes

Step 4: Calculate Greeks

Step 5: Simulate Strategy P/L

Step 6: Generate P/L Diagram (ASCII Art)

Step 7: Strategy-Specific Analysis

Step 8: Earnings Strategy Analysis

Step 9: Risk Management Guidance

Output Format

Key Principles

Theoretical Pricing Limitations

Volatility Guidance

Integration with Other Skills

Important Notes

Common Use Cases

Troubleshooting

Resources

When it activates

SkillSafety

Source

Related skills

More in the registry