Useful when a topic calls for rigorous research, multi-source analysis, and a deliverable you can confidently share. Provide the research question, and the skill will scope the work, gather relevant evidence, compare sources, synthesize findings, and verify each claim. The result is a structured report with sentence-level citations, a bibliography, stable source IDs, and claims checked against stored source excerpts to reduce unsupported or invented citations.
A full analysis pipeline that turns a dataset into a finished report, not just charts. Hand it a CSV, Excel, Parquet, or JSON file and it cleans the data, scores its quality, runs EDA, and where the data supports it, trains a prediction model with SHAP attribution and a backtested forecast. You get a trust score, ranked findings, and recommendations as a Word doc, an interactive HTML report, and an optional PowerPoint deck. The numbers come from code, so they stay consistent, never invented.
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.
Create polished reports and business documents from user-supplied notes, transcripts, briefs, technical findings, and strategy material.
Review selected public X posts about Japanese stocks in a source-linked English brief. Compare account counts, automated labels, topics, and original post links in a dated sample.
一则 AI 合作公告，究竟是意向、订单，还是已确认收入？贴上公开原文，取得证据对照、待核实清单与下一个验证节点；也可整理美股多空情境、计算公开日线。逐项标明资料日期、来源与缺口。最新资料核实取决于可用的搜索／浏览工具。仅供研究，不构成专业财务或投资建议。
一次付費 US$5，下載可讀 Skill 與中文本機投研程式，在自己的電腦整理多空研究、來源證據與 HTML 報告。基於開源 TradingAgents 的非官方整合版，需相容 Agent 客戶端、Python 3.11+，並自備模型 API Key；API 用量與行情服務另計。Windows 桌面介面，富途 OpenD 與 FRED 為選配；不含自動交易或買賣保證。僅供資訊及教育研究，非專業財務／投資建議。
掃描你的價格資料、找出候選策略——而且對每一個講真話。它回測上百個經典組合、排成 leaderboard，然後做 hype 工具不敢做的事：照你試的個數幫最佳 Sharpe 打折（Deflated Sharpe）、檢查樣本外還剩多少、估過擬合機率——漂亮的曲線一律當成待驗證的假設、不是能交易的策略。睡前設好讓它整夜掃，掃越久對你越懷疑。自包含 HTML 報告（中／英）、跑在你自己的 CSV 上。