One subscription, three certifications: CompTIA Security+, AWS Cloud Practitioner, and Cisco CCNA. Spaced repetition weights review time by the real exam's domain percentages, not equal time on everything. Full-length, correctly-timed mock exams give an honest score estimate, always labeled an estimate, never a prediction. Every question is written fresh from the public exam blueprint; nothing copied from real exams or braindumps, and requests to check leaked questions are refused outright.
你跟 AI 說「幫我規劃一個 X」，它兩秒就吐出一份看起來無懈可擊的計畫——問題是，裡面一半假設是它自己掰的，你分不出是哪一半。照著做，兩天後才發現方向從第一步就錯了，全部重來。這支反過來做：先把你腦中真正在想的東西窮追猛打地挖出來，逼你自己想清楚，在你確認達成共識之前，它一個字都不動。四條硬規則讓它不惹人厭：每題都附推薦答案不丟空白問卷、事實自己查只問真正該你決定的、一次只問一題不讓你腦當機、沒共識就不開工。附 18 個追問鏡頭——被否決的替代方案、機會成本、這是誰的渴望、Pre-mortem。
Know if your backtest is a real edge or overfit noise. Runs bar-permutation MCPT, Deflated Sharpe, PBO/CSCV, Hansen SPA, Romano-Wolf StepM, a stationary bootstrap and an out-of-sample split on your own returns — no market feed, no API keys.
Personal JLPT tutor (N5–N1): generates an original daily Japanese practice quiz as interactive HTML, grades your pasted answers, tracks weak points over time, and promotes you level by level. Coaching language auto-matches yours (zh-TW / zh-CN / en / ja).
Guides, a 56-item checklist, a ready PR template, and a fill-in team policy for code review culture. Includes 10 good/bad comment pairs and 30 situational review comments, unified by a blocker/suggestion/nit/question/praise severity system.
Run authorized penetration tests / vulnerability assessments end to end: Rules of Engagement (authorization & scope) → recon/enumeration → OWASP Top 10 review → CVSS triage → concrete remediation → a formal assessment report for executives and engineers. Defense-focused: it centers authorization management, systematic enumeration, risk evaluation, and a client-actionable deliverable — not offensive payloads. Authorized targets only; no DoS, destruction, or evasion.