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

mail-newsletter

Skill7 starsChanged 9 months agoMITView on GitHub

Identify newsletters and mailing lists in email, show volume per sender, and help clean up subscriptions. Use when user wants to see what newsletters they're subscribed to, audit mailing lists, or identify email noise. Arguments: optional time range or "unsubscribe" to surface opt-out links.

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:

    Look for unsubscribe URLs in the body text.

    line 80

≈ “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 Newsletter — Subscription and Mailing List Audit

Analysis: $ARGUMENTS (default: last 90 days)

Step 1: Detect newsletters via unsubscribe_type (most accurate)

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

sqlite3 "$DB" "
SELECT a.address, a.comment as name,
       m.unsubscribe_type,
       COUNT(*) as count,
       SUM(CASE WHEN m.read=1 THEN 1 ELSE 0 END) as read_count,
       ROUND(100.0 * SUM(m.read) / COUNT(*), 0) as read_pct,
       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%'
  AND m.unsubscribe_type > 0
GROUP BY a.address
ORDER BY count DESC;" 2>/dev/null

Step 2: Catch high-volume bulk senders without unsubscribe headers

sqlite3 "$DB" "
SELECT a.address, a.comment, COUNT(*) as cnt,
       ROUND(100.0 * SUM(m.read) / COUNT(*), 0) as read_pct
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 m.automated_conversation = 2
  AND m.unsubscribe_type = 0
  AND mb.url NOT LIKE '%Spam%' AND mb.url NOT LIKE '%Sent%'
GROUP BY a.address
HAVING cnt >= 10
ORDER BY cnt DESC LIMIT 20;" 2>/dev/null

Step 3: Group by mailing list (list_id_hash)

To see distinct mailing lists (e.g. a company using multiple sender addresses):

sqlite3 "$DB" "
SELECT m.list_id_hash, COUNT(*) as cnt, COUNT(DISTINCT a.address) as sender_variants,
       MAX(a.comment) as name_sample
FROM messages m
JOIN addresses a ON m.sender = a.ROWID
WHERE m.date_received >= ${SINCE}
  AND m.deleted=0
  AND m.list_id_hash IS NOT NULL AND m.list_id_hash != 0
GROUP BY m.list_id_hash
ORDER BY cnt DESC LIMIT 20;" 2>/dev/null

Step 4: If "unsubscribe" requested, find opt-out links

For senders with low read rates (< 30%), find unsubscribe links in body:

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

Look for unsubscribe URLs in the body text.

Step 5: Calculate noise impact

Total emails from newsletter/automated senders vs. total inbox volume = % noise.

Output Format

Newsletter/Mailing List Audit — [PERIOD]

SenderEmailsRead RateVerdict
newsletter@service.com4512%Rarely read
updates@useful.com2889%Engaged

Unsubscribe Candidates (high volume + low read rate): [list with unsubscribe links if available]

Total newsletter volume: X emails = Y% of inbox Estimated time saved if unsubscribed from low-engagement ones: [estimate]

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.