Agent skill

Options Strategy Backtesting

Backtests multi-leg option strategies by synthesizing Black-Scholes prices from the underlying, simulating PnL, Greeks exposure and expiration for crypto and equity options.

MITAuto-check passedBusiness, Finance & HR

Install Options Strategy Backtesting

skills CLI

$ npx skills add HKUDS/Vibe-Trading --skill options-strategy -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install HKUDS/Vibe-Trading options-strategy --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agent/src/skills/options-strategy .claude/skills/options-strategy && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "options-strategy" agent skill from https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/options-strategy into .claude/skills/options-strategy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "options-strategy", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/options-strategy

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add HKUDS/Vibe-Trading --skill options-strategy -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install HKUDS/Vibe-Trading options-strategy --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git skills-src && mkdir -p .agents/skills && cp -r skills-src/agent/src/skills/options-strategy .agents/skills/options-strategy && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "options-strategy" agent skill from https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/options-strategy into .agents/skills/options-strategy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "options-strategy", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add HKUDS/Vibe-Trading --skill options-strategy -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install HKUDS/Vibe-Trading options-strategy --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/agent/src/skills/options-strategy .cursor/skills/options-strategy && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "options-strategy" agent skill from https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/options-strategy into .cursor/skills/options-strategy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "options-strategy", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/HKUDS/Vibe-Trading.git --path agent/src/skills/options-strategy

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add HKUDS/Vibe-Trading --skill options-strategy -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install HKUDS/Vibe-Trading options-strategy --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/agent/src/skills/options-strategy .gemini/skills/options-strategy && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "options-strategy" agent skill from https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/options-strategy into .gemini/skills/options-strategy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "options-strategy", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install HKUDS/Vibe-Trading options-strategy

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add HKUDS/Vibe-Trading --skill options-strategy -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git skills-src && mkdir -p .github/skills && cp -r skills-src/agent/src/skills/options-strategy .github/skills/options-strategy && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "options-strategy" agent skill from https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/options-strategy into .github/skills/options-strategy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "options-strategy", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add HKUDS/Vibe-Trading --skill options-strategy -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install HKUDS/Vibe-Trading options-strategy --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/HKUDS/Vibe-Trading.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/agent/src/skills/options-strategy .opencode/skills/options-strategy && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "options-strategy" agent skill from https://github.com/HKUDS/Vibe-Trading/tree/main/agent/src/skills/options-strategy into .opencode/skills/options-strategy/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "options-strategy", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: options-strategy
GitHub stars: 35k
Token cost: ~2k tokens
SKILL.md length: 695 words
Files: 1
Skills in repo: 89
Repo updated: Oct 9, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Backtests multi-leg option strategies by synthesizing Black-Scholes prices from the underlying, simulating PnL, Greeks exposure and expiration for crypto and equity options.

Backtesting an iron condor, butterfly or calendar spread
SKILL.md covers Purpose, Supported Strategy Types, OptionsSignalEngine Interface and config.json Format, plus 5 more sections
Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
Pricing options with Black-Scholes from an underlying price series

What it does

Starting from the underlying price, the engine synthesizes theoretical option prices with the Black-Scholes model and then simulates profit and loss, Greek exposure and expiration exercise for multi-leg portfolios. It is meant for backtesting and for pricing and sensitivity research on cryptocurrency and equity options.

A table lists the supported structures together with the market view each one suits: covered call, protective put, straddle, strangle, iron condor, butterfly and calendar spread. The named use cases fall into three groups, hedging with covered calls or protective puts, volatility trading with straddles or strangles, and spread strategies, plus option pricing and Greek sensitivity research. The config sets engine to options, a risk-free rate defaulting to 0.05 and volatility from 30-day rolling history, and signals fill on the next bar's close by default.

When your agent uses it

Backtesting an iron condor, butterfly or calendar spread
Pricing options with Black-Scholes from an underlying price series
Studying the Greek sensitivity of a multi-leg position
Testing a covered call or protective put overlay

Example prompts

“Backtest an iron condor on this price series using Black-Scholes prices.”
“Compare a straddle and a strangle for an expected large move.”
“Show the Greeks exposure of a butterfly spread over time.”
“Simulate a covered call on my holding and report PnL at expiration.”

What it can do on your machine

Read from SKILL.md and the folder at commit b1f6ce7. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are python and json).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Options Strategy Backtesting loads about 2k tokens when it runs. Until then it costs about 42 tokens; SKILL.md has 695 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~42
When it runs · the whole SKILL.md, loaded when a task matches: ~2k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from HKUDS/Vibe-Trading at commit b1f6ce7, republished under its MIT licence (© HKUDS). 695 words, ~1,991 tokens.

Download SKILL.mdSave it as .claude/skills/options-strategy/SKILL.md (or your agent's skills folder).

name: options-strategy
description: Options strategy framework supporting Black-Scholes pricing, Greeks analysis, and multi-leg backtesting. Suitable for cryptocurrency and equity options.
category: asset-class

Purpose

Backtesting of option portfolio strategies. Starting from the underlying price, the engine synthesizes theoretical option prices with the Black-Scholes model, then simulates PnL, Greeks exposure, and expiration exercise for multi-leg option portfolios.

Applicable scenarios:

Hedging strategies (covered call, protective put)
Volatility trading (straddle, strangle)
Spread strategies (iron condor, butterfly, calendar spread)
Option pricing analysis and Greeks sensitivity research

Supported Strategy Types

Strategy	Structure	Applicable Market View
Covered Call	Hold underlying + short call	Mildly bullish, collect premium
Protective Put	Hold underlying + long put	Bullish but wants downside protection
Straddle	Buy same-strike call + put	Expect large movement, direction uncertain
Strangle	Buy different-strike call + put	Expect large movement, lower cost
Iron Condor	Sell put spread + sell call spread	Range-bound market, collect premium
Butterfly	Buy low call + sell 2 middle calls + buy high call	Expect narrow-range movement
Calendar Spread	Sell near-month + buy far-month at same strike	Exploit differences in time decay

`OptionsSignalEngine` Interface

Write the strategy in code/signal_engine.py, with class name SignalEngine, implementing the generate method:

python

class SignalEngine:
    """Option strategy signal engine."""

    def generate(self, data_map: dict) -> list:
        """Generate option trading instructions.

        Args:
            data_map: code -> DataFrame (columns: open, high, low, close, volume)

        Returns:
            List of trading instructions. Each instruction has the format:
            {
                "date": "2024-01-15",        # Trading date
                "action": "open" / "close",  # Open or close position
                "underlying": "BTC-USDT",    # Underlying code
                "legs": [                    # List of option legs
                    {
                        "type": "call" / "put",  # Option type
                        "strike": 50000,          # Strike price
                        "expiry": "2024-02-15",   # Expiration date
                        "qty": 1                  # Quantity (positive = long, negative = short)
                    }
                ]
            }
        """

Multi-Leg Combination Example

Iron Condor opening signal:

python

{
    "date": "2024-01-15",
    "action": "open",
    "underlying": "000300.SH",
    "legs": [
        {"type": "put",  "strike": 3800, "expiry": "2024-02-15", "qty": -1},  # Sell put
        {"type": "put",  "strike": 3700, "expiry": "2024-02-15", "qty":  1},  # Buy protective put
        {"type": "call", "strike": 4200, "expiry": "2024-02-15", "qty": -1},  # Sell call
        {"type": "call", "strike": 4300, "expiry": "2024-02-15", "qty":  1},  # Buy protective call
    ]
}

`config.json` Format

json

{
    "codes": ["000300.SH"],
    "start_date": "2020-01-01",
    "end_date": "2024-12-31",
    "source": "tushare",
    "engine": "options",
    "initial_cash": 1000000,
    "commission": 0.001,
    "options_config": {
        "risk_free_rate": 0.05,
        "iv_source": "historical",
        "contract_multiplier": 1.0,
        "same_day_fill": false,
        "default_iv": 0.3
    }
}

Key fields:

engine must be set to "options" so the runner selects the option backtest engine
options_config.risk_free_rate: risk-free rate, default 0.05
options_config.iv_source: volatility source, currently supports "historical" (30-day rolling historical volatility computed from underlying closes)
options_config.contract_multiplier: contract multiplier, default 1.0
options_config.same_day_fill: false (default) fills a signal dated T on the next bar's close; true restores the legacy same-date fill (signal and fill share T's close and IV)
options_config.default_iv: volatility used for bars without a full rolling window (warm-up and NaN gaps), default 0.3; must be finite and positive

BS Model Principles

Black-Scholes formula (European options):

Call = S * N(d1) - K * e^(-rT) * N(d2)
Put  = K * e^(-rT) * N(-d2) - S * N(-d1)

d1 = [ln(S/K) + (r + sigma^2/2) * T] / (sigma * sqrt(T))
d2 = d1 - sigma * sqrt(T)

Where S = underlying price, K = strike, T = time to expiry in years, r = risk-free rate, sigma = volatility, and N() = cumulative distribution function of the standard normal.

This engine starts from the underlying daily price series, substitutes historical volatility for implied volatility, and computes theoretical option prices through the BS formula. This is a synthetic-data mode, meaning no real option market data is required.

Greeks Meaning and Usage

Greek	Meaning	Usage
Delta	Change in option price for a 1-unit move in the underlying	Directional exposure management, hedge-ratio calculation
Gamma	Change in Delta for a 1-unit move in the underlying	Measures hedge stability; high Gamma = frequent rebalancing required
Theta	Time decay of option value per day (usually negative)	Time-value management, source of return for short-option strategies
Vega	Change in option price for a 1% volatility move	Core metric for volatility trading, measures volatility exposure

The backtest engine computes portfolio-level Greeks aggregates on each trading day and outputs them to greeks.csv.

Show full SKILL.md (270 more words)Show less

Common Pitfalls

Volatility Smile

The BS model assumes constant volatility, but in real markets implied volatility differs across strikes and expiries (volatility smile / skew). This engine approximates with historical volatility, so pricing may be biased for deep OTM / deep ITM options. Strategy design should avoid over-reliance on pricing precision at extreme strikes.

Time Decay (Theta Decay)

Theta decay is not linear — the closer the option is to expiry, the faster the decay. The last 30 days decay much faster than the prior 30 days. Short-vol strategies benefit from this, but Gamma risk also rises sharply near expiry.

Early Exercise

This engine supports European options only (exercise only at expiry), not American options. In scenarios with meaningful early-exercise value (for example, deep ITM puts or calls on high-dividend underlyings), pricing will be biased.

Liquidity and Slippage

In synthetic-data mode there are no bid-ask spreads or liquidity constraints. In real trading, deep OTM options have poor liquidity and wide spreads, so backtest results will be overly optimistic.

Contract Multiplier

Option contract multipliers differ across markets (for example, China A-share ETF options often use a 10,000 multiplier, while crypto is typically 1). Make sure options_config.contract_multiplier is set correctly.

Artifact Description

After backtesting, the following files are generated in the artifacts/ directory:

File	Contents
`equity.csv`	Daily equity, cash, market value of holdings
`metrics.csv`	Return, Sharpe ratio, maximum drawdown, and similar metrics
`trades.csv`	Trade-by-trade records (open / close / exercise / expire)
`greeks.csv`	Daily portfolio Greeks aggregates (`delta/gamma/theta/vega`)
`ohlcv_{code}.csv`	Raw underlying candlestick data

Pricing Tool

The Agent can call the options_pricing tool for one-off pricing:

Call the options_pricing tool with:
  spot: 50000
  strike: 52000
  expiry_days: 30
  volatility: 0.6
  option_type: "call"

It returns the theoretical price and Greeks, which is suitable for interactive analysis.

Files

Just SKILL.md in agent/src/skills/options-strategy of HKUDS/Vibe-Trading.

Open the folder on GitHubat commit b1f6ce7

Compare with similar skills

Options Strategy Backtesting next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Options Strategy Backtesting compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Options Strategy Backtesting this skillHKUDS/Vibe-Trading	35k	—	~2k	Automated safety check: Pass	MIT	today
Relative ValuationYijia-Xiao/FinanceHarness	196	—	~446	Automated safety check: Pass	Apache-2.0	1 mo ago
Forecastingericrisco/rsc-harness	180	—	~2.8k	Automated safety check: Pass	MIT	today
Multi-Symbol Market Scannertradesdontlie/tradingview-mcp	6.8k	2 repos	~447	Automated safety check: Pass	Custom licence	2 mo ago
Pine Script Development Looptradesdontlie/tradingview-mcp	6.8k	2 repos	~617	Automated safety check: Pass	Custom licence	2 mo ago
Creating Financial ModelsChen-zexi/open-ptc-agent	729	3 repos	~1.3k	Automated safety check: Pass	MIT	8 mo ago

Similar skills

Relative Valuation
Yijia-Xiao/FinanceHarness
Value an equity against its peers — peer-median trading multiples applied to the company's metrics for an implied range, cross-read against its own valuation ratios.
196 GitHub stars~446 tokensUpdated 1 mo ago
Business, Finance & HRAuto-check passed
Forecasting
ericrisco/rsc-harness
A skill your agent uses when projecting history forward — sales, demand, units, revenue, signups, traffic — into a defensible number with an error band: method by data shape, rolling-origin…
180 GitHub stars~2.8k tokensUpdated today
Data & AnalyticsAuto-check passed
Multi-Symbol Market Scanner
tradesdontlie/tradingview-mcp
Scans a list of trading symbols in TradingView for setups, patterns or strategy results and reports them as a ranked comparison table.
6.8k GitHub starsUsed in 2 repos~447 tokens
Business, Finance & HRAuto-check passed
Pine Script Development Loop
tradesdontlie/tradingview-mcp
Runs a write, compile, fix and verify loop for TradingView Pine Script indicators and strategies, pushing code into the Pine Editor and checking it on the chart.
6.8k GitHub starsUsed in 2 repos~617 tokens
Business, Finance & HRAuto-check passed
Creating Financial Models
Chen-zexi/open-ptc-agent
This skill provides an advanced financial modeling suite with DCF analysis, sensitivity testing, Monte Carlo simulations, and scenario planning for investment decisions
729 GitHub starsUsed in 3 repos~1.3k tokens
Business, Finance & HRAuto-check passed
CCXT Crypto Exchange Library
2025Emma/vibe-coding-cn
Reference help for the CCXT library covering crypto exchange APIs, market data, trading and order management across 150+ exchanges in JavaScript, Python and PHP.
23k GitHub starsUsed in 1 repo~4.4k tokens
Business, Finance & HRAuto-check passed

Questions about Options Strategy Backtesting

What does Options Strategy Backtesting do?

Backtests multi-leg option strategies by synthesizing Black-Scholes prices from the underlying, simulating PnL, Greeks exposure and expiration for crypto and equity options. Starting from the underlying price, the engine synthesizes theoretical option prices with the Black-Scholes model and then simulates profit and loss, Greek exposure and expiration exercise for multi-leg portfolios. It is meant for backtesting and for pricing and sensitivity research on cryptocurrency and equity options.

When should I use Options Strategy Backtesting?

Options Strategy Backtesting fits situations like: backtesting an iron condor, butterfly or calendar spread; pricing options with Black-Scholes from an underlying price series; studying the Greek sensitivity of a multi-leg position; testing a covered call or protective put overlay.

How do I install Options Strategy Backtesting in Claude Code?

Run `npx skills add HKUDS/Vibe-Trading --skill options-strategy -a claude-code`. Or copy the skill folder (agent/src/skills/options-strategy in HKUDS/Vibe-Trading) into .claude/skills/options-strategy in your project. Claude Code loads it when a task matches its description.

How do I install Options Strategy Backtesting in Codex?

Run `npx skills add HKUDS/Vibe-Trading --skill options-strategy -a codex`. Or copy the skill folder (agent/src/skills/options-strategy in HKUDS/Vibe-Trading) into .agents/skills/options-strategy in your project. Codex loads it when a task matches its description.

Can I use Options Strategy Backtesting in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add HKUDS/Vibe-Trading --skill options-strategy -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/options-strategy, .gemini/skills/options-strategy, .github/skills/options-strategy and .opencode/skills/options-strategy in your project.

What does Options Strategy Backtesting need to run?

SKILL.md names no scripts, command-line tools or credentials: Options Strategy Backtesting is instructions for the agent only.

Does Options Strategy Backtesting access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Options Strategy Backtesting safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Options Strategy Backtesting use?

Options Strategy Backtesting is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Options Strategy Backtesting use?

About 2k tokens (SKILL.md is roughly 8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Options Strategy Backtesting?

Skills that share tags, products or a category with Options Strategy Backtesting: Relative Valuation (Yijia-Xiao/FinanceHarness, 196 stars), Forecasting (ericrisco/rsc-harness, 180 stars), Multi-Symbol Market Scanner (tradesdontlie/tradingview-mcp, 6.8k stars) and Pine Script Development Loop (tradesdontlie/tradingview-mcp, 6.8k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Options Strategy Backtesting?

HKUDS (a GitHub organization) maintains it in HKUDS/Vibe-Trading, which has 35,097 GitHub stars. The repository holds 89 skills in this directory. The repository was last updated on October 9, 2026.

Source: HKUDS/Vibe-Trading on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Options Strategy Backtesting

Facts

At a glance

What it does

When your agent uses it

Example prompts

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Purpose

Supported Strategy Types

OptionsSignalEngine Interface

Multi-Leg Combination Example

config.json Format

BS Model Principles

Greeks Meaning and Usage

Common Pitfalls

Volatility Smile

Time Decay (Theta Decay)

Early Exercise

Liquidity and Slippage

Contract Multiplier

Artifact Description

Pricing Tool

Files

Compare with similar skills

Similar skills

More from HKUDS/Vibe-Trading

Related

Questions about Options Strategy Backtesting

`OptionsSignalEngine` Interface

`config.json` Format