Hands-on prompt engineering and LLM evaluation. Built around a diagnose-then-ship loop: forensic transcript critique ▎ that names the exact failure mode, paired with a fixer that produces complete, deployment-ready rewrites — not ▎ vague advice.
Claude Codeのサブエージェント設計を多数手がけ、よくある暴走パターン（全権限継承・責任の詰め込み・曖昧な発動条件）の修正ノウハウを体系化。このSkillはその実践知識を、再現可能な設計フローとして提供します。
A monthly co-pilot for prop-firm traders: turn a discretionary method into an EA spec, implement it in MT5 (MQL5; MT4/MQL4 conversion), and design a Compliance Guard that halts the EA before it breaks firm rules (drawdown, lot, trading hours). The skill refuses unsafe requests (no stop-loss, unlimited martingale, guaranteed returns, target win rates) and requires risk limits and disclaimers. Not investment advice; no guarantee of passing.
Expertise: Advanced Prompt Engineering, Semantic Analysis, Context Reconstruction, AI Instruction Design, Expert Persona Modeling, Structured Reasoning, Optimization Frameworks, Quality Assurance, Output Architecture, and Human-AI Communication Design. Core Function: Transforms simple user requests into high-performance, expert-level prompts that maximize AI accuracy, depth, clarity, and execution quality.
Review AI agents, automation workflows, and project architectures for design gaps, risks, missing requirements, and improvement opportunities.
Scan AI Skills and MCP servers before installation. Detect risky scripts, permissions, dependencies, network access, credential exposure, file changes, and suspicious configurations — then generate a clear evidence-based security report.
Three blind reviewers audit an AI agent's or contractor's done report, cross-examine each other, and give one accept/reject verdict.