Quant Mathematician

Invent brand new strategies from mathematical hypotheses, code them in Pine Script, and prove or kill them across many crypto pairs.

⚠️ **Trading warning / Avertissement trading** : informational only, not investment advice. Most new strategy ideas have no edge, and this skill is built to kill them; the rare survivor of its backtests is a candidate for more testing, not a promise of profit. Curated by Skill Harbor: the greenfield researcher of DaviddTech's ai-trading-agent repo, a persona prompt that forbids the easy paths: it may not reuse, fork, copy or take inspiration from existing strategies, and it may not start from RSI, MACD, Bollinger Bands or moving average crossovers. Every strategy must begin as a mathematical hypothesis about a market behaviour (short-term overreaction, volatility compression and expansion cycles, autocorrelation decay, return distribution asymmetry, entropy shifts in price movement, liquidity sweep reversals and similar), with an explanation of the inefficiency targeted, why it might exist in crypto, which regimes could break it, and how it can be expressed in Pine Script. The workflow selects one hypothesis on simplicity, testability and robustness potential, converts it into full trading rules (entries, exits, stops, take profits, invalidation, cooldowns, regime and volatility filters), codes it cleanly with no repainting and no lookahead, and backtests it through Trader Dev across random pairs from the top 100 Bybit listings and several timeframes. Evaluation ranks robustness across symbols and drawdown control above net profit, diagnoses failures before changing anything (one major concept per iteration), and classifies each idea as Reject, Watchlist, Incubate, Candidate or Production candidate. From the DaviddTech/ai-trading-agent repository (MIT). Honest caveats: the Renaissance-inspired framing is the author's style, not a result; the skill needs the third-party Trader Dev platform; and a Production candidate label still means forward testing next, never live money on the strength of a backtest. Skill Harbor never reviews the code, review it yourself before use.

At a glance

What: Invent brand new strategies from mathematical hypotheses, code them in Pine Script, and prove or kill them across many crypto pairs.
Cost: Free
Needs: Use "Quant Mathematician" with your Muse.
Install: Copy the installer prompt below into your Muse — your agent does the rest.

⚠️ **Trading warning / Avertissement trading** : informational only, not investment advice. Most new strategy ideas have no edge, and this skill is built to kill them; the rare survivor of its backtests is a candidate for more testing, not a promise of profit. Curated by Skill Harbor: the greenfield researcher of DaviddTech's ai-trading-agent repo, a persona prompt that forbids the easy paths: it may not reuse, fork, copy or take inspiration from existing strategies, and it may not start from RSI, MACD, Bollinger Bands or moving average crossovers. Every strategy must begin as a mathematical hypothesis about a market behaviour (short-term overreaction, volatility compression and expansion cycles, autocorrelation decay, return distribution asymmetry, entropy shifts in price movement, liquidity sweep reversals and similar), with an explanation of the inefficiency targeted, why it might exist in crypto, which regimes could break it, and how it can be expressed in Pine Script. The workflow selects one hypothesis on simplicity, testability and robustness potential, converts it into full trading rules (entries, exits, stops, take profits, invalidation, cooldowns, regime and volatility filters), codes it cleanly with no repainting and no lookahead, and backtests it through Trader Dev across random pairs from the top 100 Bybit listings and several timeframes. Evaluation ranks robustness across symbols and drawdown control above net profit, diagnoses failures before changing anything (one major concept per iteration), and classifies each idea as Reject, Watchlist, Incubate, Candidate or Production candidate. From the DaviddTech/ai-trading-agent repository (MIT). Honest caveats: the Renaissance-inspired framing is the author's style, not a result; the skill needs the third-party Trader Dev platform; and a Production candidate label still means forward testing next, never live money on the strength of a backtest. Skill Harbor never reviews the code, review it yourself before use.

Version:

D

Created by: DaviddTech

Not verified? How to check before you trust →

Install — Free · open source (MIT) View source code

⌁

Install

Copy the install package below, then paste it into Muse

Wanna be extra careful?

The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?

How to check a build before installing →

After installation, ask me if I want to leave private feedback
Private for now: only the Skill Harbor team sees it. Sellers may be looped in later.

Use "Quant Mathematician" with your Muse. Prerequisites: access to the Trader Dev MCP backtesting platform (a third-party service; check its current terms), used here only to submit and backtest newly created Pine Script strategies. Greenfield research only; no existing strategy is needed or allowed as a template. 1. Open the skill: https://github.com/DaviddTech/ai-trading-agent/blob/main/skills/quant-mathematician/SKILL.md and copy the full SKILL.md text. 2. Paste it into a chat with Muse and add: "Generate four brand new mathematical strategy hypotheses, explain the inefficiency behind each, then pick the most testable one and turn it into trading rules." 3. Require the multi-symbol, multi-timeframe backtest and the final classification, and read the diagnosis section before allowing any iteration. Tip: the hypothesis round is where the value is; reject any idea that cannot state what market behaviour it exploits and what would break it. Safety: a skill is plain-text instructions; it runs nothing by itself. New strategies are unproven by definition until forward testing says otherwise. Informational only, not investment advice.

?

Questions

How do I install a build?

Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the build up for you — no manual configuration.

Where does my money go?

Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.

What does the ✓ next to a creator’s name mean?

It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a build before installing it.