StrategyQuant
Q AI AssistantAlgoCloudQuantAnalyzerQuantDataManager
Free CourseCompany
BlogDocumentationForumContact us
BlogMarketplace
Log in
Create free account

Product

  • Pricing & licenses
  • Learn
  • Marketplace
  • Start free trial

Legal

  • Terms of Service
  • Privacy Policy
  • Cookies

Contact

[email protected]

Company

StrategyQuant s.r.o.

Korunní 2569/108, Vinohrady, 101 00 Praha 10, Czech Republic, EU

IČ: 04000498

DIČ: CZ04000498

Social

  • Legal Notice | PROCESSING AND PROTECTION OF PERSONAL DATA

    Past performance is no guarantee of future success. All information should be viewed as educational only

    UNITED STATES Disclaimer required by Government - Commodity Futures Trading Commission informs: Futures and options trading have great potential rewards, but also great potential risk. You must be aware of the risks and be willing to accept them in order to invest in the futures and options markets. Don't trade with money you can't afford to lose. This is neither a solicitation nor an offer to buy/sell futures, shares or options on the same. No representation is being made that any account will or is likely to realise profits or losses similar to those discussed in this document. The past performance of any trading system or methodology is not necessarily indicative of future results.

    CFTC RULE 4.41 - HYPOTHETICAL OR SIMULATED PERFORMANCE RESULTS HAVE CERTAIN LIMITATIONS. UNLIKE A RECORD OF ACTUAL PERFORMANCE, SIMULATED RESULTS DO NOT REPRESENT ACTUAL TRADING. ALSO, SINCE THE TRADES WERE NOT EXECUTED, THE RESULTS MAY HAVE OFFSET THE IMPACT, IF ANY, OF CERTAIN MARKET FACTORS, SUCH AS LACK OF LIQUIDITY. SIMULATED TRADING PROGRAMMES IN GENERAL ARE ALSO SUBJECT TO THE FACT THAT THEY ARE DESIGNED WITH THE BENEFIT OF HINDSIGHT. NO REPRESENTATION IS BEING MADE THAT ANY ACCOUNT WILL OR IS LIKELY TO REALISE PROFITS OR LOSSES SIMILAR TO THOSE SHOWN.

    NO REPRESENTATION IS BEING MADE THAT ANY ACCOUNT WILL, OR IS LIKELY TO, REALISE PROFITS OR LOSSES SIMILAR TO THOSE DISCUSSED WITHIN THIS SITE. IF YOU DECIDE TO INVEST REAL MONEY, ALL TRADING DECISIONS IN THE FINANCIAL MARKETS SHOULD BE YOUR OWN.

    © StrategyQuant 2026

    Powered by Klaudie.ai

    Back to marketplaceDIGITAL

    Custom Blocks Skills

    StrategyQuantAI Plugins
    Custom Blocks Skills

    Build AlgoWizard blocks from plain-English trading ideas without clicking the block editor. The builder reads your SQX installation, validates every indicator you own, and produces import-ready blocks that always bind.

    The Custom Block Builder for StrategyQuant X — Describe a Trading Rule in Plain English, Get an Import-Ready AlgoWizard Block

    Tell it your idea in one sentence — "go long when RSI reclaims oversold" or "a trailing stop two ATRs under the Hull moving average" — and it builds a finished, validated custom block from the indicators your own StrategyQuant X install has. Import it into AlgoWizard and it's ready to use.


    TL;DR

    The Custom Block Builder is a Claude Code skill that turns plain-English trading ideas into ready-to-import AlgoWizard blocks. It reads your SQX installation, learns which indicators you have, assembles the block, and validates it before import.

    • 🧠 Plain-English in, working block out
    • 🔍 Reads your install — builds only from indicators your machine has
    • 🧱 Two block types — signals and price levels (stops, targets, bands)
    • ✅ Validated before import
    • 🛡️ Edge-checked — flags look-ahead, repainting, dead thresholds
    • 🔁 Long & short auto-paired
    • 🎛️ Optimizer-ready


    Who this is for

    • Strategy builders who want custom signals quickly
    • Discretionary traders crossing into algo with rules in mind
    • Researchers testing academic or blog ideas in SQX
    • Anyone who has hit import and watched a block fail to bind


    Core principles


    1. Install-aware

    Reads your SQX installation and builds a catalog of atoms you can use — nothing phantom.


    2. Finds your custom indicators — four ways

    Resolves registered, proven, coded-but-unregistered, and synthesized sources. Customs appear by name in a dedicated section.


    3. Two block types

    Condition blocks (yes/no for entry, exit, filter). Price-level blocks (stops, targets, bands) from anchor, anchor ± k·ATR, or confluence.


    4. Plain-English first, build second

    Nothing generated until you approve: name, description, operator shape, indicators, parameters with defaults and ranges.


    5. Validated before import

    Checks multi-output lines, parameters, naming, and blocks risky atoms.


    6. Edge-checked

    Flags look-ahead, repainting, and thresholds outside indicator ranges — fixes them before hand-off.


    7. One block = one idea

    Builds clean, single-signal blocks rather than stacking confirmations.


    Tutorial — how to use it


    Step 0 · One-time setup (per machine)

    Point the skill at your StrategyQuant X folder (e.g.

    C:\StrategyQuantX144
    ). It catalogs your indicators.


    Step 1 · Describe your rule

    "Go long when RSI comes back up through oversold, and short on the mirror." Or ask for a price level. You can hand it a paper, blog post, or URL.


    Step 2 · Review and approve the spec

    The skill shows you the plain-English spec — name, rule, shape, indicators, tunable parameters with defaults and ranges. Approve or redirect.


    Step 3 · It generates, validates and edge-checks

    Builds the block, selects correct lines for multi-output indicators, exposes tunables as optimization knobs, auto-pairs long and short. Won't hand over results until all checks pass.


    Step 4 · Import into AlgoWizard

    Receive a file plus summary table. Import: AlgoWizard → Custom Blocks → Import → select file. Your blocks appear ready to use.


    Step 5 · If anything needs a tweak

    Tell the skill and it fixes the specific block rather than rebuilding everything.


    Bonus: Research mode

    Don't have a specific rule? Hand it "find me momentum filters" or a research paper. It proposes catalog-grounded specs, then an adversarial critic kills weak, overfit, repainting or duplicate ideas. You pick survivors and it authors them.


    Part of a bigger toolkit

    First of a three-skill pipeline: build the rules → pool them → wire into a strategy:

    • Custom Block Builder — author individual signals and price levels
    • Random Group Builder — pool blocks into random groups
    • Strategy Template Builder — wire groups into importable .sqx templates


    Requirements

    • StrategyQuant X / AlgoWizard
    • Python 3.8+ — standard library only, no pip installs
    • Claude Code with the skill installed


    At a glance

    Input: A trading rule in plain English (or paper / URL)
    Output: A validated, import-ready block — signal or price level, long + short
    Builds from: Your install's real indicators (native + customs)
    Safety: Validated for import and edge-checked for look-ahead / repaint
    Best for: Turning ideas into testable signals and levels quickly


    FAQ

    Does it work with Stock Picker engine?
    No — supports only standard engines. Stock Picker support will be added later.

    Will this work on my version of SQX?
    Yes — reads your install and only offers atoms you have.

    Can it build stops, targets and price levels, or only signals?
    Both — price-level blocks including anchor ± k·ATR buffers and max/min confluence levels.

    Do I still build blocks in AlgoWizard?
    Build with the skill and import the result — works like any block you create in the editor.

    What if it can't find one of my custom indicators?
    It resolves four sources so it finds them all. Synthesized ones are flagged "verify on first import."

    How does it stop me building a block that looks ahead or repaints?
    Every block goes through an edge-hygiene check that flags and fixes look-ahead, repainting, and bad thresholds.

    Can it build both long and short at once?
    Yes — pairs are generated together and correctly cross-linked.

    I don't have a specific rule — just a theme.
    Use research mode: hand it a theme or paper and pick from buildable specs after an adversarial critic weeds out weak ones.

    You know me as clonex. I'm Ivan Hudec — I built the free blocks here, and I write about the research at algotrading.space. Need something built? Work with me.

    Past performance is no guarantee of future success. All information should be viewed as educational only UNITED STATES Disclaimer required by Government - Commodity Futures Trading Commission informs: Futures and options trading have great potential rewards, but also great potential risk. You must be aware of the risks and be willing to accept them in order to invest in the futures and options markets. Don't trade with money you can't afford to lose. This is neither a solicitation nor an offer to buy/sell futures, shares or options on the same. No representation is being made that any account will or is likely to realise profits or losses similar to those discussed in this document. The past performance of any trading system or methodology is not necessarily indicative of future results. CFTC RULE 4.41 - HYPOTHETICAL OR SIMULATED PERFORMANCE RESULTS HAVE CERTAIN LIMITATIONS. UNLIKE A RECORD OF ACTUAL PERFORMANCE, SIMULATED RESULTS DO NOT REPRESENT ACTUAL TRADING. ALSO, SINCE THE TRADES WERE NOT EXECUTED, THE RESULTS MAY HAVE OFFSET THE IMPACT, IF ANY, OF CERTAIN MARKET FACTORS, SUCH AS LACK OF LIQUIDITY. SIMULATED TRADING PROGRAMMES IN GENERAL ARE ALSO SUBJECT TO THE FACT THAT THEY ARE DESIGNED WITH THE BENEFIT OF HINDSIGHT. NO REPRESENTATION IS BEING MADE THAT ANY ACCOUNT WILL OR IS LIKELY TO REALISE PROFITS OR LOSSES SIMILAR TO THOSE SHOWN. NO REPRESENTATION IS BEING MADE THAT ANY ACCOUNT WILL, OR IS LIKELY TO, REALISE PROFITS OR LOSSES SIMILAR TO THOSE DISCUSSED WITHIN THIS SITE. IF YOU DECIDE TO INVEST REAL MONEY, ALL TRADING DECISIONS IN THE FINANCIAL MARKETS SHOULD BE YOUR OWN.
    Free2 downloads

    Files

    • AIPlugin-CustomBlocksSkills.sqm66 KBLocked

    Download unlocks after purchase or with an active tier.

    Details
    Version1.0.0
    PublishedOctober 19, 2026
    Last updatedNovember 2, 2026
    AppSQ
    TypeAIPlugin
    Authorclonex / Ivan Hudec
    App version145.3058
    Codebase categoryAlgoWizard