agentleFS
aashariaashari/ai-agent-skills/skills/apple-mail/mail-search/SKILL.md

mail-search

Skill7 starsChanged 9 months agoMITView on GitHub

Search Apple Mail across all synced accounts by keyword, subject, sender, or any combination. Use when user asks to find an email, search for a message, or look for something in their mail. Arguments: search terms, optionally with sender:, subject:, from:, account: prefixes, and time filters like "last 30 days" or "this year".

1 other project uses a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If user wants to read specific results, find the emlx and parse:

    line 72
  2. Distinctive:

    If more than 20 results, summarize by sender/thread and ask if they want to narrow down.

    line 82

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Mail Search — Full-Text Search Across All Accounts

Search query: $ARGUMENTS

Argument Parsing

Parse $ARGUMENTS for modifiers:

  • from:name@domain.com or sender: → filter by sender
  • subject:keyword → filter subject only
  • account:gmail or account:work → restrict to account type
  • last N days/weeks → time filter
  • Anything else → search both subject and sender

Query

DB="$HOME/Library/Mail/V10/MailData/Envelope Index"
TERM="<extracted search term>"  # URL-encode % as %% in shell

sqlite3 "$DB" "
SELECT datetime(m.date_received,'unixepoch','localtime') as dt,
       s.subject, a.address as sender, a.comment as name,
       mb.url as mailbox, m.ROWID, m.read,
       CASE WHEN m.size > 0 THEN m.size ELSE 0 END as size
FROM messages m
JOIN subjects  s  ON m.subject  = s.ROWID
JOIN addresses a  ON m.sender   = a.ROWID
JOIN mailboxes mb ON m.mailbox  = mb.ROWID
WHERE m.deleted = 0
  AND mb.url NOT LIKE '%Spam%'
  AND mb.url NOT LIKE '%Trash%'
  AND mb.url NOT LIKE '%Junk%'
  AND (
    s.subject LIKE '%TERM%'
    OR a.address LIKE '%TERM%'
    OR a.comment LIKE '%TERM%'
  )
ORDER BY m.date_received DESC
LIMIT 50;" 2>/dev/null

For sender-only search:

WHERE a.address LIKE '%TERM%' OR a.comment LIKE '%TERM%'

For subject-only search:

WHERE s.subject LIKE '%TERM%'

For recipient search (TO/CC):

JOIN recipients r ON r.message = m.ROWID
JOIN addresses ra ON r.address = ra.ROWID
WHERE ra.address LIKE '%TERM%'

Reading Email Bodies

If user wants to read specific results, find the emlx and parse:

python3 ~/.claude/skills/_mail-shared/parser.py <ROWID>

Output Format

Show results as a table:

DateFromSubjectAccountRead

If more than 20 results, summarize by sender/thread and ask if they want to narrow down. For each result, note the account it belongs to (extract UUID from mailbox URL to identify account). Offer to read any specific email if user asks.

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.