Cboe Options Exchange Api Integration logo

Cboe Options Exchange Api Integration

Community
HimanshuJ16
cboe-options-exchange-api-integration

Use when trading multi-leg option strategies on Cboe options exchanges over Titanium FIX: New Order Multileg construction, leg ratio normalisation and Complex Order Auction participation. Single-leg orders use New Order Single instead.

Overview

PublisherHimanshuJ16
RepositoryAlgo-Trading-Skills
Skill namecboe-options-exchange-api-integration
Stars
50
Forks
7
Bundled files
5
LicenseApache-2.0
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 5 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by HimanshuJ16 on GitHub. Read the source before you install it.

Installation

Install the Cboe Options Exchange Api Integration AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/HimanshuJ16/Algo-Trading-Skills/tree/main/skills/cboe-options-exchange-api-integration
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/HimanshuJ16/Algo-Trading-Skills.git /tmp/Algo-Trading-Skills
mkdir -p .claude/skills
cp -r /tmp/Algo-Trading-Skills/skills/cboe-options-exchange-api-integration .claude/skills/cboe-options-exchange-api-integration
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Cboe Options Exchange Api Integration in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Cboe Options Exchange Api Integration on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Cboe Options Exchange Api Integration is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

When to Use

Use this skill when integrating directly with Cboe Options Exchanges (Cboe Options Exchange [C1], C2 Options Exchange, Cboe BZX Options, Cboe EDGX Options) over Cboe Titanium FIX to trade multi-leg option strategies. Specifically:

  • Construct and serialize New Order Multileg (MsgType=AB) messages with the NoLegs (555) repeating group.
  • Eliminate legging risk by routing spreads, straddles, strangles, condors, butterflies, collars and ratio spreads to the Complex Order Book (COB) as one package that executes within a net price and ratio.
  • Control Complex Order Auction (COA) exposure through RoutingInst (9303).
  • Execute stock-option combination orders (buy-writes, collars) on C1 and EDGX, including the Cboe Rule 5.33 conforming-ratio test.
  • Reconcile a complex fill from the package report plus the per-leg reports Cboe sends alongside it.

When NOT to Use

  • Single-Leg Option Orders: use MsgType=D (New Order Single). Cboe requires at least 2 legs on MsgType=AB.
  • AIM / paired auctions: AIM is entered through New Order Cross Multileg (C1 and EDGX only), not by tagging a standard complex order. No ExecInst value converts an ordinary order into an AIM order.
  • Short-form COB requests: this skill's helper emits the long form only. The short form (pricing against an already-listed COB strategy symbol via Symbol (55) + Side (54)) has a side-dependent net-price sign and needs its own builder.
  • BOEv3 wire encoding: the helper implements FIX only; take binary layouts from the Cboe BOE v3 specification.
  • Venues Lacking Native Combo Books: use algorithmic synthetic legging with hedge monitoring instead (see calendar-spread-and-multi-leg-order-atomicity).
  • OTC / bilateral options not listed or cleared through the OCC.

Prerequisites

  • Active Cboe Titanium FIX order-entry session with market access credentials and a valid EFID.
  • FIX engine that serializes and parses repeating groups; it supplies BeginString (8), BodyLength (9) and CheckSum (10).
  • OCC clearing parameters for LegPositionEffect (564) and, where applicable, CMTA fields.
  • Pre-trade risk controls per SEC Rule 15c3-5.
  • For stock-option orders: C1 or EDGX access, plus an equity matching destination (EquityExDestination (22016)).

Workflow

  1. Choose the request form. Long form (legs in the 555 group) or short form (a listed COB strategy symbol in Symbol (55) with Side (54)). Do not mix them: sending the underlying root in Symbol (55) alongside a leg group is neither form. The rest of this workflow is the long form.
  2. Define legs. Each OptionLeg needs LegSymbol (600), LegRatioQty (623), LegSide (624) and, unless OrderCapacity (47) is M/N, LegPositionEffect (564). When 600 is an OSI root, LegCFICode (608), LegMaturityDate (611) and LegStrikePrice (612) are required too. Mark the equity leg with 608=E — there is no LegSecurityType (609) in this message.
  3. Normalize ratios (CRITICAL). Reduce all leg ratios by their GCD and multiply OrderQty (38) by the same GCD, so net exposure is unchanged. Cboe rejects unreduced ratios outright.
  4. Re-validate after scaling, not before. GCD scaling is a multiplication: OrderQty (38) must still be ≤ 999,999 afterwards. On C2 and EDGX the reduced smallest-to-largest leg ratio must also be no wider than 1:3.
  5. Stock-option conformance (Cboe Rule 5.33). Compute the ratio from the smallest option leg against the stock leg and require ≤ 8:1. Using the sum of all option legs over-rejects legitimate collars. A non-conforming order is not invalid — it receives different priority and auction handling, so decide deliberately.
  6. Price the package. Long form: positive = net debit, negative = net credit, 0 = even. Whole pennies for option-only spreads; up to 4 decimals only with a stock leg or FLEX. Check the class increment separately — SPX/SPXW non-box/roll spreads trade in $0.05, not $0.01.
  7. Set routing. RoutingInst (9303): first character B/P/D, second character S (expose via COA) or L (suppress). Leave unset to accept Cboe's defaults (S for non-IOC, L for IOC). PS is rejected. ExecInst (18) has exactly one documented value here — G (All or None) — and plays no part in auction selection.
  8. Serialize. 35=AB with 167=MLEG and 47 (both required), then 555=N followed by leg groups that each start with LegRefID (654), then 38, 40, 44, 9303, 47, 59.
  9. Reconcile the fill. Branch on MultilegReportingType (442): 3 is the package fill, 2 is a per-leg fill carrying LegRefID (654), LastPx (31) and LastShares (32) at the top level. Join by LegRefID and assert leg_qty == package_qty × reduced_ratio. A breach is a position-integrity incident, not a retry trigger.

Full procedure: see references/workflows.md. Standards reference: see references/standards.md. Printable pre-flight checklist: see assets/checklist.md.

Common Pitfalls

  • Selecting COA through ExecInst (18): COA exposure lives in the second character of RoutingInst (9303) (S/L). ExecInst values borrowed from base FIX are not Cboe values — sending 18=A transmits "No cross", not "COA eligible".
  • Emitting LegSecurityType (609): it is not a field of Cboe's New Order Multileg. Leg type is LegCFICode (608) = OC / OP / E.
  • Starting the leg group on LegSymbol (600): Cboe documents LegRefID (654) as "the required tag to start each repeated group". A group opened on another tag is not a valid repeating group, and 654 is also the only key that maps leg fills back to legs.
  • Expecting LegLastPx (637) / LegLastQty (638): they do not exist in the Cboe message set. A parser that looks for them silently reports every leg as filled at 0.00 for 0 contracts.
  • Applying the debit-positive rule to a short-form Sell order: under the short form, a positive Price (44) on a Sell order is a credit. Inverting it crosses the market or is rejected off-market.
  • Validating OrderQty before GCD scaling: 200,000 packages of a 10:20 spread normalizes to 2,000,000 contracts and breaches the documented 999,999 ceiling only after normalization.
  • Summing option legs for the 8:1 test: Cboe's ratio check uses the smallest option leg. Summing rejects conforming collars and buy-writes.
  • Assuming FOK is available: TimeInForce (59) on this message is 0, 1, 2, 3 or 6 — FOK is not documented.
  • Assuming pennies everywhere: SPX/SPXW non-box/roll complex orders price in $0.05 increments.
  • Serializing prices from binary floats: format from Decimal; 0.1 + 0.2 reaches the wire as 0.30000000000000004.
  • Retrying on a request timeout: a lost response does not mean the order was not accepted. Query order state or cancel the original ClOrdId; Cboe enforces ClOrdId uniqueness only among live orders, so it is not a duplicate guard once an order is no longer live.

Verification

  • Run the test suite: python -m unittest discover -s skills/cboe-options-exchange-api-integration/scripts.
  • Validate structure: python tools/validate_skills.py --skill cboe-options-exchange-api-integration.
  • Confirm a generated debit spread contains 35=AB, 167=MLEG, 47, 555=2, and that the text following 555=2 begins with 654=.
  • Confirm 609= and 18= never appear in generated output, and that 55= / 54= are absent from long-form output.
  • Confirm a 10:20 ratio spread reduces to 1:2 with OrderQty scaled ×10, and that a scaled quantity above 999,999 is rejected.
  • Confirm reconcile_leg_fills raises when a 442=2 leg quantity does not equal package_qty × reduced_ratio.

Limitations

  • Class-level net price increments (e.g. $0.05 for SPX/SPXW) are not enforced — only the whole-penny / 4-decimal precision rule from the FIX specification is.
  • FLEX-specific fields (LegPrice (566), LegDelta (22024), FLEXAuctionDuration (21010)) and floor routing (FloorRoutingInst (22303)) are documented in references/standards.md but not implemented.
  • Cboe's field table marks Price (44) as required on New Order Multileg without stating an exception for OrdType=1; the helper omits 44 on market orders. Confirm market complex-order handling with the Cboe Trade Desk before enabling it.

Related Skills

  • calendar-spread-and-multi-leg-order-atomicity
  • fix-protocol-session-management-across-venues
  • multi-leg-strategy-margin-optimization
  • order-placement-idempotency

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Cboe Options Exchange Api Integration AI skill do?

Use when trading multi-leg option strategies on Cboe options exchanges over Titanium FIX: New Order Multileg construction, leg ratio normalisation and Complex Order Auction participation. Single-leg orders use New Order Single instead.

Why use Cboe Options Exchange Api Integration on TypingMind?

Because you install it once and use it with any model. Cboe Options Exchange Api Integration is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Cboe Options Exchange Api Integration in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/HimanshuJ16/Algo-Trading-Skills/tree/main/skills/cboe-options-exchange-api-integration. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Cboe Options Exchange Api Integration?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Cboe Options Exchange Api Integration?

As many as you like. As long as a model supports skills, you can use Cboe Options Exchange Api Integration with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Cboe Options Exchange Api Integration AI skill free?

Yes. It is published on GitHub by HimanshuJ16 under the Apache-2.0 license. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇