agentleFS
trac3r00trac3r00/agent-skills/skills/apple-suite/SKILL.md

apple-suite

Skill0 starsChanged 3 months agoMITView on GitHub

Automates macOS apps via AppleScript and URL schemes — Notes, Reminders, Maps, Mail, Calendar, Terminal, Shortcuts, Contacts, Photos, App Store search, and Phone. Runs locally through osascript with no API keys and no network for the AppleScript operations. Each app's scriptability is honestly assessed; non-scriptable apps (VoiceMemos, Passwords, Find My, Activity Monitor, App Store listing) are documented with their real limitations rather than faked.

The file

Files
SKILL.md

Apple Suite

Drive macOS built-ins directly from an agent session — no API keys, no network for the AppleScript operations, just the apps already on the machine.

Commands

# Notes
python3 scripts/apple_suite.py notes list [--limit 20] [--json]
python3 scripts/apple_suite.py notes create --title "Title" --body "Body text"
python3 scripts/apple_suite.py notes search "keyword"

# Reminders
python3 scripts/apple_suite.py reminders list [--json]
python3 scripts/apple_suite.py reminders add --title "Task" [--due "2026-08-27 09:00"]
python3 scripts/apple_suite.py reminders complete --title "Task"

# Maps
python3 scripts/apple_suite.py maps search "coffee near me"
python3 scripts/apple_suite.py maps directions --from "Home" --to "Office"
python3 scripts/apple_suite.py maps open "123 Main St, City"

# Mail
python3 scripts/apple_suite.py mail unread
python3 scripts/apple_suite.py mail list [--limit 20]

# Calendar
python3 scripts/apple_suite.py calendar list
python3 scripts/apple_suite.py calendar today
python3 scripts/apple_suite.py calendar add --title "Meeting" --date "2026-08-27 14:00"

# Terminal
python3 scripts/apple_suite.py terminal run "echo hello"

# Shortcuts
python3 scripts/apple_suite.py shortcuts list
python3 scripts/apple_suite.py shortcuts run "Calculate Tip"

# Contacts
python3 scripts/apple_suite.py contacts count
python3 scripts/apple_suite.py contacts search "Jane"

# Photos
python3 scripts/apple_suite.py photos count
python3 scripts/apple_suite.py photos albums

# App Store
python3 scripts/apple_suite.py appstore search "terminal"

# Phone
python3 scripts/apple_suite.py phone open "+1234567890"

What is scriptable

AppListCreateCompleteSearchNotes
Notesyesyes—yesfolders included in list
Remindersyesyesyesby titledue dates optional
Maps———yesopens Maps.app with query or directions
Mailyes———unread count, inbox list with sender/date
Calendaryesyes——calendars, today's events, add events
Terminal————run commands, capture output
Shortcutsyes———run by name (may timeout on interactive shortcuts)
Contactsyes——yescount, search by name
Photosyes———media item count, album names
App Store———yessearch via macappstore:// URL scheme
Phone————opens tel: URL

Not scriptable (documented honestly)

AppLimitation
VoiceMemosNo AppleScript dictionary (-2741 on every access pattern). Recordings are in ~/Library/Application Support/com.apple.voicememos/ but the format is private.
PasswordsNo AppleScript API. Only the Settings UI.
Find MyNo AppleScript API. Use the Find My app or Siri.
Activity MonitorNo AppleScript API for process data. Use ps, top, or vm_stat.
App Store (listing)No AppleScript API for installed apps or updates. Search works via URL scheme.

Permissions

macOS will prompt for Automation permission the first time each app is driven. Grant it once and subsequent calls are silent. The skill never requests broader access than the specific app it drives.

Exit codes

0 = success, 1 = app-level error (not found, permission denied), 2 = usage error or non-macOS host.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.