Decide whether to buy, wait, or skip before you spend — with regret-risk scoring, future-self checks, and a 7-day purchase test.
A historical backtesting and validation-research protocol for algorithmic trading strategies: it treats your entry/exit/TP-SL/capital/leverage as fixed test inputs, stress-tests them with real costs and anti-overfit gates (plateau rule, walk-forward, random control, per-year robustness), and reports a research verdict (VALIDATION GATES PASSED / FAILED / INSUFFICIENT EVIDENCE). Analysis only: never deployment, sizing, leverage, or allocation advice.
問一般 AI「川普今天說了什麼」，你會拿到它訓練資料裡三個月前的舊聞，講得頭頭是道但完全過期。 這支每次都真的去抓——Truth Social、白宮文告、八個財經源——過濾掉政治攻擊與轉發，只留會動到價格的那幾則，然後告訴你會打到哪些股票、偏多還是偏空、什麼情況代表這個判斷錯了。 給方向前一定先抓即時報價，因為利空新聞配上正在漲的股價，代表市場三天前就反應完了——順著新聞喊空是最常見的虧法。
Know if a betting record is luck or skill. Paste any betting history — get a full statistical audit: ROI with 95% confidence interval, the probability a losing bettor would show the same record, drawdown analysis, risk of ruin, and curation red flags. Retrospective analysis only — never predictions.
把「股價碰到均線」變成一份帶失敗條件的判決書。 均線往哪走、價在哪一邊、碰到之後誰贏——三個問題答不齊就明說「不判」，不硬湊訊號給你。 每份判決都必須寫出「什麼價格出現代表我錯了」，寫「看情況」視同沒寫。附一支自己算均線斜率、前高前低、量能與 ATR 的腳本，不必貼圖也能跑。
Use when you paste today’s portfolio or watchlist snapshot before a daily review. For self-directed investors who want consistent questions, not a market-data feed. Proof: checks every pasted position on 8 fixed risk and thesis axes, then labels missing evidence [UNVERIFIED]. It reasons only from the numbers and notes you supply.
Say “dashboard” and see this week’s 8-K Item 3.01 listing notices — exchange, rule cited, notice type, cure period — each row linked to EDGAR.