optimize-system-performance

Installation
SKILL.md

Optimize System Performance

Use a diagnose-first workflow. The default mode is read-only: capture a baseline, explain the causes in plain Chinese, show a short low-risk cleanup choice, then wait for the user before any cleanup. Treat this as a diagnosis and decision skill, not an automatic cleaner.

Safety Rules

  • Default actions must be L0/L1 only: low-permission sampling, Chinese explanation, and cleanup recommendations.
  • Do not use sudo, elevated PowerShell, reboot, log out, clear caches, delete configs, disable startup items, unload plists, edit registry, change services, change scheduled tasks, or force-kill processes by default.
  • Do not stop browser main processes, remote control, VPN/proxy, sync drives, input methods, security software, enterprise management, meeting software, IDEs, Docker/VMs, Codex/Claude sessions, or local business services unless the user confirms that specific high-risk target after seeing the risk.
  • Batch cleanup is allowed only for the report's explicit low-risk cleanup list after the user confirms a simple choice such as 清理低风险项. Never include protected, ambiguous, startup, service, Docker/VM/browser/IDE, or business-service targets in that batch.
  • When cleanup is confirmed, use only gentle user-process termination: macOS kill -TERM <pid>; Windows Stop-Process -Id <pid> without -Force. If it fails, report it and stop.
  • Deep forensics are opt-in only. Before any high-risk tool, read the relevant reference and explain use, risk, permissions, duration, artifacts, and low-permission alternatives.
  • For macOS deep forensics, run a command-path preflight first. Prefer system absolute paths such as /usr/bin/sample and /usr/sbin/spindump; never assume a bare command is the Apple tool because Python, Homebrew, or third-party installs may shadow it in PATH.
  • Default snapshots store executable/process names rather than full process arguments. Full command-line capture can expose tokens, paths, URLs, and business context, so treat it as opt-in deep inspection.
  • Redact sensitive text in user-facing reports. Keep snapshot paths visible so the user can decide whether to delete them.
  • Make decision ownership explicit but simple: the agent explains evidence and tradeoffs; the user can choose 清理低风险项 or 只观察. High-risk targets still need specific confirmation.

Dangerous Action Gate

Installs
3
GitHub Stars
5
First Seen
Jun 9, 2026
optimize-system-performance — wisewong6/wise-skills