suyuan-skill

Audit and safely modify local Claude Code and Claude Desktop cleanup/privacy settings on macOS. Use when the user asks to review, clean, disable, preserve, or verify Claude local data, telemetry-related settings, login/browser-opening behavior, timezone, device name, macOS username, Keychain credentials, desktop app data, browser profiles, or local Claude cleanup checklists.

Break AI Slop — force the AI to think like a real expert before doing anything. Extracts tacit knowledge, surfaces hidden failure modes, and distills the one constraint that decides success or failure. Use before any non-trivial task to eliminate generic, low-quality AI output. Triggers: 'break-ai-slop', 'anti-slop', 'slopbreak', 'slop check', '行家模式', '专家预检', '防止AI水货', '别给我水货', '认真做', '先想清楚再做', '这个别敷衍', '高质量输出'.

Dual-model code review via Codex CLI. Two GPT models review independently, Claude arbitrates disagreements. Supports review (read-only), fix (write), audit (full security scan), and autopilot (unattended) modes. Triggers on "review", "let Codex check", "security audit", "OWASP", "full scan". Also auto-triggers after complex coding tasks.

Claude Code account protection — disable telemetry, clean device fingerprints, safe account switching after ban. Trigger this skill whenever the user mentions ANY of these: telemetry, privacy, ban, account switch, fingerprint, device ID, blocked, suspended, rate limit, data collection, analytics tracking, or Chinese equivalents: 遥测, 隐私, 封号, 换号, 指纹, 设备ID, 被封, 被ban, 限流, 数据收集, 关闭追踪, 账号保护, 防封, 清理设备信息, 隐私审查, 隐私检查. Also trigger when the user says things like "protect my account", "stop tracking", "Claude Code is collecting data", "I got banned", "switch to a new account", "what does Claude Code know about me", "帮我关掉遥测", "我被封了", "怎么换号", "Claude Code 收集了什么数据", "帮我查一下隐私", even if they don't mention this skill by name.

Task triage with position-based thinking. 5+1 scoring dimensions (15 max + -3 penalty). Helps you decide whether a task is worth doing, and whether YOU should be the one doing it. Use when evaluating new tasks, prioritizing your backlog, or deciding what to cut.