refactor: convert mac-optimizer from raw skill to proper plugin
Restructured 92-mac-optimizer from a CLAUDE.md-based skill into a full Claude Code plugin with .claude-plugin/plugin.json, 6 slash commands (/mac-doctor, /mac-packages, /mac-environment, /mac-security, /mac-cleanup, /mac-resources), and auto-trigger SKILL.md. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
44
custom-skills/92-mac-optimizer/skills/mac-optimizer/SKILL.md
Normal file
44
custom-skills/92-mac-optimizer/skills/mac-optimizer/SKILL.md
Normal file
@@ -0,0 +1,44 @@
|
||||
---
|
||||
name: mac-optimizer
|
||||
description: macOS system health toolkit — use when user mentions system optimization, cleanup, packages, security audit, disk space, performance, brew updates, cache clearing, or system health on Mac
|
||||
version: 1.0.0
|
||||
---
|
||||
|
||||
# Mac Optimizer
|
||||
|
||||
Modular macOS system health toolkit. Runs read-only audits first, then recommends actions with user consent.
|
||||
|
||||
## Module Routing
|
||||
|
||||
| Keywords | Command |
|
||||
|---|---|
|
||||
| brew, homebrew, npm, nvm, pip, pyenv, packages, update, outdated | /mac-packages |
|
||||
| path, shell, zshrc, environment, env, config, symlink | /mac-environment |
|
||||
| security, firewall, sip, gatekeeper, filevault, ports, ssh | /mac-security |
|
||||
| cache, cleanup, clean, logs, clutter, disk space, free space, trash | /mac-cleanup |
|
||||
| cpu, memory, ram, disk, battery, processes, resources, slow | /mac-resources |
|
||||
| doctor, audit, health, full check, everything, system check | /mac-doctor (all) |
|
||||
|
||||
Default to **/mac-doctor** when the request is ambiguous.
|
||||
|
||||
When the user's request matches a specific module, suggest the appropriate slash command. When the request is broad (e.g., "check my system", "run a health check"), use /mac-doctor.
|
||||
|
||||
## Execution Model
|
||||
|
||||
Every module follows this flow:
|
||||
|
||||
1. **Audit** — run the module's script (read-only)
|
||||
2. **Report** — parse JSON output, present findings as a severity-ranked table
|
||||
3. **Recommend** — list available actions grouped by risk
|
||||
4. **Consent** — ask user which actions to approve
|
||||
5. **Act** — execute only approved actions
|
||||
|
||||
## Safety Rules
|
||||
|
||||
- **Never execute cleanup without explicit user approval**
|
||||
- **Always show sizes before deleting anything**
|
||||
- **Security module is read-only** — present findings and remediation guidance only
|
||||
- **Back up shell configs** before modifying
|
||||
- **Process deny-list**: never suggest killing kernel_task, launchd, WindowServer, loginwindow, mds, mds_stores, opendirectoryd, coreaudiod, SystemUIServer, Finder, Dock
|
||||
- **No sudo by default** — if an action needs sudo, state why and ask first
|
||||
- Docker cleanup uses `docker system prune`, never direct file deletion
|
||||
Reference in New Issue
Block a user