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

mail-banking

Skill7 starsChanged 9 months agoMITView on GitHub

Show bank notifications, transaction alerts, and account activity from email. Use when user asks about bank emails, account notifications, transfer confirmations, or banking activity. Arguments: optional bank name, time range, or transaction type like "transfers", "payments", "top-ups".

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    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 specifies "mandiri", "BCA", "BRI", etc., add:

    line 66

≈ “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 Banking — Bank Notifications and Account Activity

Filter: $ARGUMENTS (default: last 7 days, all banks)

Step 1: Find bank notification emails

DB="$HOME/Library/Mail/V10/MailData/Envelope Index"
SINCE=$(($(date +%s) - 604800))  # 7 days

sqlite3 "$DB" "
SELECT datetime(m.date_received,'unixepoch','localtime') as dt,
       s.subject, a.address as sender,
       mb.url, m.ROWID
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.date_received >= ${SINCE}
  AND m.deleted = 0
  AND mb.url NOT LIKE '%Spam%' AND mb.url NOT LIKE '%Trash%'
  AND (
    -- By sender domain
    a.address LIKE '%bank%'
    OR a.address LIKE '%livin%'
    OR a.address LIKE '%bca%'
    OR a.address LIKE '%bri%'
    OR a.address LIKE '%bni%'
    OR a.address LIKE '%mandiri%'
    OR a.address LIKE '%seabank%'
    OR a.address LIKE '%sinarmas%'
    OR a.address LIKE '%wise%'
    OR a.address LIKE '%revolut%'
    OR a.address LIKE '%n26%'
    OR a.address LIKE '%chase%'
    OR a.address LIKE '%paypal%'
    -- By subject
    OR s.subject LIKE '%transfer%'
    OR s.subject LIKE '%transaction%'
    OR s.subject LIKE '%top-up%'
    OR s.subject LIKE '%top up%'
    OR s.subject LIKE '%payment successful%'
    OR s.subject LIKE '%debit%'
    OR s.subject LIKE '%credit%'
    OR s.subject LIKE '%transfer successful%'
    OR s.subject LIKE '%BI Fast%'
    OR s.subject LIKE '%RTGS%'
    OR s.subject LIKE '%QRIS%'
  )
ORDER BY m.date_received DESC;" 2>/dev/null

Step 2: Filter by bank if specified in $ARGUMENTS

If user specifies "mandiri", "BCA", "BRI", etc., add:

AND (a.address LIKE '%mandiri%' OR s.subject LIKE '%mandiri%')

Step 3: Parse transaction details

python3 ~/.claude/skills/_mail-shared/parser.py <ROWID1> <ROWID2> ...

Extract from body:

  • Transaction type (transfer, payment, top-up, withdrawal)
  • Amount + currency
  • Recipient name and bank
  • Sender/source account (masked card/account number)
  • Reference/transaction number
  • Date and time

Step 4: Summarize by type

Group: Transfers out | Payments | Top-ups | Incoming | Credit card payments

Output Format

Banking Activity — [PERIOD]

Table per transaction type:

TimeTypeAmountTo/FromRef No.

Total outflow, total inflow, net. Flag any unusually large single transactions. Note any failed or pending transactions if subject indicates.

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.