資料交給 ChatGPT、Claude、客戶或外包前，先在本機檢查 CSV、Excel、TSV 與 JSONL。預覽候選項目後，再遮罩、假名化或移除欄位，另存副本並附稽核報告。保留原檔、不需 API；繁體中文版。
Academic sanity-check with interactive HTML dashboard. Detects look-ahead bias, over-parameterization, and benchmarks against 10 canonical blueprints via animated SVG gauges and color-coded KPI cards. Parses natural language, code, or CSV uploads. Output auto-adapts (EN/ZH-TW/ZH-CN). Built on De Prado (2018). For students and strategy developers. Not financial advice.
This Skill is built on practical expertise in AI file-workflow governance, source authority classification, copy-first editing, prompt-injection resistance, private-to-external dataflow review, and publish/delete/send boundary checks. It helps AI agents decide what can be read, copied, edited, deleted, zipped, or sent while keeping originals protected and untrusted file, web, or tool content from becoming instructions.
漂亮的回測不等於真的有 edge。多數散戶「會賺」的策略其實是過擬合——那個 Sharpe 是掃了一堆參數挑出來最好的、是停損停利湊出來的假象、或只是運氣好的一段區間。 策略 Edge 驗證器用一整套統計檢定,幫你分辨「真訊號」還是「資料探勘出的雜訊」,全部只跑在你自己的報酬序列或權益曲線上: • 平穩 Bootstrap — 這條曲線跟零 edge 的雜訊分得出來嗎? • Deflated Sharpe — 扣掉「掃 N 組挑最佳」的選擇偏差後還站得住嗎? • PBO / CSCV — 回測期最強的參數,樣本外還是最強嗎? • Hansen SPA & Romano-Wolf StepM — 一籃子規則裡的贏家撐得過 data-snooping 嗎? • Bar-permutation MCPT — 利潤是訊號賺的,還是出場路徑湊的? • 樣本外分割 — 多少 edge 撐得過 holdout? 命令列 + JSON 輸出、自帶測試、標註學術出處。不需市場數據源、不需 API 金鑰、不需你的策略邏輯——你的數字全程不離開你的電腦。
Analyzes football forecasts provided by the user to identify consensus, agreement levels, prediction ranges, and key disagreements in one structured report.
交件前，找出漏檔、錯版與審核回條不一致。需要檔案與已接受的清單；Python 本機執行，不需模型。Catch missing files, wrong versions and mismatched review receipts. Local Python download; accepted manifest required. No model needed.
用配對 CSV 核對原始值與報告值、單位、期間及容許誤差。Compare explicitly paired source/report numbers, units and periods from CSV. Readable Python download; no model required.
Catch dangerous Postgres DDL before merge. Paste SQL or ORM migration files and get a GREEN/AMBER/RED verdict, 0-100 score, exact findings, and a merge-gate checklist. Free local Download; no API key or database connection.
20+ US states have privacy laws now. Most require a consent mechanism, a "Do Not Sell or Share" link, and honoring the Global Privacy Control signal. Enter a URL. Get a snapshot: which trackers load before consent, whether GPC is recognized, whether opt-out and data request links exist, whether your privacy policy is present. Ranked by severity, with the exact fix for each gap. Not a compliance certificate. A radar for what regulators check first.