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

mail-top-senders

Skill7 starsChanged 9 months agoMITView on GitHub

Show who sends the most email, communication frequency analysis, and relationship mapping. Use when user asks who emails them most, top contacts, communication patterns, or wants to understand their email social graph. Arguments: optional time range (default: last 90 days), account filter, or "humans only" to exclude automated senders.

The file

We split this skill into the rules it gives an agent

1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈0

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 1

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Use automated_conversation and unsubscribe_type columns (more reliable than address-pattern matching):

    line 42

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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 Top Senders — Communication Frequency Analysis

Analysis period: $ARGUMENTS (default: last 90 days)

Step 1: All senders ranked by volume

DB="$HOME/Library/Mail/V10/MailData/Envelope Index"
SINCE=$(($(date +%s) - 7776000))  # 90 days

sqlite3 "$DB" "
SELECT a.address, a.comment as name,
       COUNT(*) as total,
       SUM(CASE WHEN m.read=0 THEN 1 ELSE 0 END) as unread,
       MIN(datetime(m.date_received,'unixepoch','localtime')) as first,
       MAX(datetime(m.date_received,'unixepoch','localtime')) as latest
FROM messages m
JOIN addresses a  ON m.sender  = a.ROWID
JOIN mailboxes mb ON m.mailbox = mb.ROWID
WHERE m.date_received >= ${SINCE}
  AND m.deleted = 0
  AND mb.url NOT LIKE '%Spam%' AND mb.url NOT LIKE '%Trash%'
  AND mb.url NOT LIKE '%Sent%'
GROUP BY a.address
ORDER BY total DESC
LIMIT 50;" 2>/dev/null

Step 2: Separate humans from automated senders

Use automated_conversation and unsubscribe_type columns (more reliable than address-pattern matching):

  • automated_conversation = 0 + unsubscribe_type = 0 → real humans
  • automated_conversation = 1 → transactional (Jira, Slack, alerts)
  • automated_conversation = 2 OR unsubscribe_type > 0 → bulk/newsletters (noise)
# Human senders only (automated_conversation = 0, no unsubscribe header)
sqlite3 "$DB" "
SELECT a.address, a.comment as name, COUNT(*) as cnt
FROM messages m
JOIN addresses a ON m.sender = a.ROWID
JOIN mailboxes mb ON m.mailbox = mb.ROWID
WHERE m.date_received >= ${SINCE}
  AND m.deleted = 0
  AND mb.url NOT LIKE '%Spam%' AND mb.url NOT LIKE '%Sent%'
  AND m.automated_conversation = 0
  AND m.unsubscribe_type = 0
GROUP BY a.address ORDER BY cnt DESC LIMIT 20;" 2>/dev/null

Step 3: Domain-level analysis

sqlite3 "$DB" "
SELECT substr(a.address, instr(a.address,'@')+1) as domain,
       COUNT(*) as cnt
FROM messages m
JOIN addresses a ON m.sender = a.ROWID
JOIN mailboxes mb ON m.mailbox = mb.ROWID
WHERE m.date_received >= ${SINCE}
  AND m.deleted = 0
  AND mb.url NOT LIKE '%Spam%'
GROUP BY domain ORDER BY cnt DESC LIMIT 20;" 2>/dev/null

Step 4: Thread participation (two-way communication)

Find senders you also replied to — true relationships vs. one-way communication:

sqlite3 "$DB" "
SELECT a.address, COUNT(*) as received
FROM messages m
JOIN addresses a ON m.sender = a.ROWID
JOIN mailboxes mb ON m.mailbox = mb.ROWID
WHERE m.date_received >= ${SINCE} AND m.deleted=0
  AND mb.url NOT LIKE '%Sent%'
GROUP BY a.address
ORDER BY received DESC LIMIT 30;" 2>/dev/null

Output Format

Top Email Relationships — [PERIOD]

Most Frequent Human Contacts:

RankNameAddressEmails ReceivedUnread

Top Automated Senders (noise):

ServiceCountType

Top Domains:

DomainCount

Insight: note anyone with high unread rate (you receive a lot but don't read → de-prioritize subscription?). Note anyone with very recent last email who you haven't read → potential missed message.

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.