Paste a contract, lease, ToS, or vendor clause and get a plain-English red-flag review: which clauses are risky, what they mean in practice, and what to ask before you sign. Flags sneaky auto-renewals, one-sided termination, broad non-competes, and vague liability terms. Reasons from your pasted text plus general contract-pattern knowledge only — never fetches the real document or your jurisdiction's law. Not legal advice; for awareness, not a replacement for a real lawyer.
I specialize in safe Codex skill onboarding. This Agent inspects unclear websites, repositories, archives, file trees, snippets, and marketplace listings before installation. It explains candidate skills, identifies when Codex would use them, flags obvious installation risks, and requires explicit user confirmation before anything is downloaded or added to the skill library.
Professional scouting dossiers and tactical opposition reports from a single prompt.
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。
Paste the client's message and your SOW. Get a scope verdict, the dollar cost of saying yes, and three ready-to-send replies in 60 seconds.
Audit AI agents, Skills, MCP configurations, tool permissions, and coding-agent setups for prompt injection, excessive agency, credential exposure, data leakage, unsafe code execution, supply-chain risks, memory risks, missing approval controls, and runaway autonomy. Get a calibrated Security Score, Audit Confidence, evidence-backed findings, remediation steps, verification checks, and residual-risk analysis.
Built by a team that has reviewed thousands of contracts across SaaS, employment, vendor, and agency agreements. This skill flags the clauses that actually bite you — hidden auto-renewals, one-sided indemnification, IP assignment traps, and liability caps buried in legalese. Think of it as a trained legal eye that never misses the fine print.
Audit and manage local AI Skills across Codex, Claude Code, and project workspaces. See what is actually active, detect duplicates and variants, compare changes over time, and generate an offline interactive management map. Read-only by default; every real change requires your approval.
