Apple Mail logo

Apple Mail

Organization
sundial-org
apple-mail

Apple Mail.app integration for macOS. Read inbox, search emails, send emails, reply, and manage messages with fast direct access (no enumeration).

Overview

Publishersundial-org
Repositoryawesome-openclaw-skills
Skill nameapple-mail
Stars
664
Forks
97
Bundled files
13
Links
  • Markdown instructions

    A SKILL.md file the model loads on demand, so it only costs tokens when a request actually matches.

  • Works with any LLM

    AI skills are plain Markdown, not provider-specific code, so this works with GPT, Claude, Gemini, Grok, or a local model.

  • 13 bundled files

    Scripts, templates, and references the model can read while it works. Files are read-only and never executed.

  • Open source

    Published by sundial-org on GitHub. Read the source before you install it.

Installation

Install the Apple Mail AI skill in TypingMind to use it with any LLM, or drop it into another agent that reads SKILL.md.

1

Install in TypingMind

TypingMind installs a skill straight from its GitHub folder — it reads SKILL.md, bundles the resource files, and stores the result locally.

  1. Open the app and go to Plugins → Skills.
  2. Choose "Install from GitHub".
  3. Paste the skill folder URL below and confirm.
    https://github.com/sundial-org/awesome-openclaw-skills/tree/main/skills/apple-mail
  4. Enable the skill in any chat where you want it available.
Plugins → Skills → Add skill → From GitHub URL, then paste the folder URL and press Continue.
2

Install in another agent

Any agent that reads the Agent Skills format can use this skill — copy the folder into that agent's skills directory.

Claude Code — .claude/skills
git clone --depth 1 https://github.com/sundial-org/awesome-openclaw-skills.git /tmp/awesome-openclaw-skills
mkdir -p .claude/skills
cp -r /tmp/awesome-openclaw-skills/skills/apple-mail .claude/skills/apple-mail
Restart Claude Code after copying so it picks up the new skill.

Use it in TypingMind

Enable Apple Mail in any TypingMind chat and the model takes it from there. Its name and description sit in the system prompt, and the moment a request matches, the model loads the full instructions itself — you never invoke it by hand, and it costs no tokens until it is actually used.

The model loads Apple Mail on its own as soon as a request matches it.

Works with any AI model

AI skills are plain Markdown instructions rather than provider-specific code, so Apple Mail is not tied to the model it was written for. Install it once in TypingMind and use it with GPT-5, Claude, Gemini, Grok, DeepSeek, Mistral, Llama, or a local model you run yourself — all on your own API keys.

  • Loaded only when it is needed

    The system prompt carries just the name and description. The instructions are fetched on the first matching request, so an idle skill costs nothing.

  • Switch models mid-chat

    Because the skill is instructions rather than code, changing model does not break it — the next model reads the same SKILL.md.

Skill instructions

This is the SKILL.md content the model loads. Read it before installing — a skill is instructions your model will follow.

Apple Mail

Interact with Mail.app via AppleScript and SQLite. Run scripts from: cd {baseDir}

Commands

CommandUsage
Refreshscripts/mail-refresh.sh [account] [wait_seconds]
List recentscripts/mail-list.sh [mailbox] [account] [limit]
Searchscripts/mail-search.sh "query" [mailbox] [limit]
Fast searchscripts/mail-fast-search.sh "query" [limit]
Read emailscripts/mail-read.sh <message-id> [message-id...]
Deletescripts/mail-delete.sh <message-id> [message-id...]
Mark readscripts/mail-mark-read.sh <message-id> [message-id...]
Mark unreadscripts/mail-mark-unread.sh <message-id> [message-id...]
Sendscripts/mail-send.sh "to@email.com" "Subject" "Body" [from-account] [attachment] ¹
Replyscripts/mail-reply.sh <message-id> "body" [reply-all]
List accountsscripts/mail-accounts.sh
List mailboxesscripts/mail-mailboxes.sh [account]

Refreshing Mail

Force Mail.app to check for new messages:

bash
scripts/mail-refresh.sh                    # All accounts, wait up to 10s
scripts/mail-refresh.sh Google             # Specific account only
scripts/mail-refresh.sh "" 5               # All accounts, max 5 seconds
scripts/mail-refresh.sh Google 0           # Google account, no wait

Smart sync detection:

  • Script monitors database message count
  • Returns early when sync completes (no changes for 2s)
  • Reports new message count: Sync complete in 2s (+3 messages)

Notes:

  • Mail.app must be running (script will error if not)
  • mail-list.sh does NOT auto-refresh — call mail-refresh.sh first if you need fresh data

Output Format

List/search returns: ID | ReadStatus | Date | Sender | Subject

  • ● = unread, blank = read

Gmail Mailboxes

⚠️ Gmail special folders need [Gmail]/ prefix:

Shows asUse
Spam[Gmail]/Spam
Sent Mail[Gmail]/Sent Mail
All Mail[Gmail]/All Mail
Trash[Gmail]/Trash

Custom labels work without prefix.

Fast Search (SQLite)

✨ Now safe even if Mail.app is running — copies database to temp file first.

bash
scripts/mail-fast-search.sh "query" [limit]  # ~50ms vs minutes

Previously required Mail.app to be quit. Now works anytime by copying the database to a temp file before querying.

Performance Notes

Speed by operation:

OperationSpeedNotes
mail-fast-search.sh~50msSQLite query, fastest
mail-accounts.sh<1sSimple AppleScript
mail-list.sh1-3sAppleScript, direct mailbox access
mail-send.sh1-2sCreates and sends message
mail-read.sh~2sPosition-optimized lookup
mail-delete.sh~0.5sPosition-optimized lookup
mail-mark-*.sh~1.5sPosition-optimized lookup

Optimization technique: SQLite provides account UUID and approximate message position. AppleScript jumps directly to that position instead of iterating from the start.

Batch operations supported:

  • mail-read.sh 123 456 789 - Read multiple (separator between each)
  • mail-delete.sh 123 456 789 - Delete multiple
  • mail-mark-read.sh 123 456 - Mark multiple as read
  • mail-mark-unread.sh 123 456 - Mark multiple as unread

⚠️ No auto-refresh: Scripts read cached data. Call mail-refresh.sh first if you need latest emails.

Managing Emails

Delete emails:

bash
scripts/mail-delete.sh 12345                    # Delete one
scripts/mail-delete.sh 12345 12346 12347        # Delete multiple

Mark as read/unread:

bash
scripts/mail-mark-read.sh 12345 12346           # Mark as read
scripts/mail-mark-unread.sh 12345               # Mark as unread

Bulk operations example:

bash
# Find spam emails
scripts/mail-fast-search.sh "spam" 50 > spam.txt

# Extract IDs and delete them
grep "^[0-9]" spam.txt | cut -d'|' -f1 | xargs scripts/mail-delete.sh

Reading Email Bodies

bash
scripts/mail-read.sh 12345              # Single email
scripts/mail-read.sh 12345 12346 12347  # Multiple emails (separated output)

Uses position-optimized lookup (~2s per message). Multiple emails are separated by ======== with a summary at the end.

Errors

ErrorCause
Mail.app is not runningOpen Mail.app before running scripts
Account not foundInvalid account — check mail-accounts.sh
Message not foundInvalid/deleted ID — get fresh from mail-list.sh
Can't get mailboxInvalid name — check mail-mailboxes.sh
Mail database not foundSQLite DB missing — check ~/Library/Mail/V{9,10,11}/MailData/

Technical Details

Database: ~/Library/Mail/V{9,10,11}/MailData/Envelope Index

Message lookup method (optimized):

  1. Query SQLite for account UUID, mailbox path, and approximate position
  2. AppleScript accesses the specific account directly (no iteration)
  3. Search starts at the approximate position (±5 messages buffer)
  4. Falls back to full mailbox search only if position hint fails

Safety:

  • Fast search copies database to temp file before querying
  • Safe to use even if Mail.app is running
  • Delete/read/mark operations query live database but access is minimal

Notes

  • Message IDs are internal, get fresh ones from list/search
  • Confirm recipient before sending
  • AppleScript search is slow but comprehensive; SQLite is fast for metadata
  • Delete/mark operations support bulk actions (pass multiple IDs)
  • Always refresh before listing if you need the absolute latest emails

¹ Known limitation: Mail.app adds a leading blank line to sent emails. This is an AppleScript/Mail.app behavior that cannot be bypassed.

Bundled files

The model reads these on demand while the skill is loaded. They are exposed as readable files and are never executed.

Frequently asked questions

What does the Apple Mail AI skill do?

Apple Mail.app integration for macOS. Read inbox, search emails, send emails, reply, and manage messages with fast direct access (no enumeration).

Why use Apple Mail on TypingMind?

Because you install it once and use it with any model. Apple Mail is plain Markdown rather than provider-specific code, so the same skill runs on GPT-5, Claude, Gemini, Grok, or a local model — and you can switch model mid-chat without it breaking. TypingMind runs on your own API keys, so you pay providers directly instead of a per-seat subscription, and your skills and chats stay in your own storage.

How do I install Apple Mail in TypingMind?

Open Plugins → Skills → Install from GitHub in TypingMind and paste https://github.com/sundial-org/awesome-openclaw-skills/tree/main/skills/apple-mail. TypingMind reads its SKILL.md and bundles its files and installs it as a skill you can enable per chat.

Which AI models can use Apple Mail?

Any model you connect in TypingMind. AI skills are plain Markdown instructions rather than provider-specific code, so GPT, Claude, Gemini, Grok, and local models can all load this skill when a request matches it.

How many AI models can I use with Apple Mail?

As many as you like. As long as a model supports skills, you can use Apple Mail with it — GPT, Claude, Gemini, Grok, DeepSeek, Mistral, Llama and more — all on TypingMind with your own API keys.

Is the Apple Mail AI skill free?

It is published on GitHub by sundial-org. Check the repository for licensing terms. You only pay your own AI provider for the tokens you use.

What are AI skills?

An AI skill is a reusable instruction bundle that teaches an AI model how to do one specific task. It follows the open Agent Skills format: a SKILL.md file with a name and description, plus any scripts, templates or reference files the model may need. The model reads the instructions only when your request matches the skill, so an installed skill costs nothing until it is used.

How are AI skills different from plugins or MCP servers?

A plugin or MCP server gives a model new tools to call — code that runs somewhere and returns a result. An AI skill gives the model knowledge and process instead: how to approach a task, which steps to follow, what good output looks like. Skills are plain Markdown, so they need no server, no API key and no runtime, and they work with any model.

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇