mail-thread
Skill7 starsChanged 9 months agoMITView on GitHub
Read and summarize a complete email thread or conversation. Show all messages in order, who said what, and what was decided. Use when user wants to read a specific email thread, catch up on a conversation, or understand what happened in an email chain. Arguments: subject line keywords, ROWID of any message in the thread, sender name, or conversation topic.
In this repository32 other files it gives its agents.
- calendar-accountsSkill
- calendar-attendeesSkill
- calendar-conflictsSkill
- calendar-coreSkill
- calendar-eventSkill
- calendar-freeSkill
- calendar-recurringSkill
- calendar-searchSkill
- calendar-statsSkill
- calendar-todaySkill
- calendar-upcomingSkill
- mail-accountsSkill
- mail-action-itemsSkill
- mail-attachmentsSkill
- mail-bankingSkill
- mail-contactsSkill
- mail-coreSkill
- mail-digestSkill
- mail-expensesSkill
- mail-fromSkill
- mail-meetingsSkill
- mail-needs-replySkill
- mail-newsletterSkill
- mail-readSkill
- mail-searchSkill
- mail-securitySkill
- mail-statsSkill
- mail-subscriptionsSkill
- mail-top-sendersSkill
- mail-travelSkill
- mail-triageSkill
- mail-workSkill
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
- Distinctive: line 71
After showing the conversation:
≈ “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.
Files
Mail Thread — Read a Full Email Conversation
Thread: $ARGUMENTS
Step 1: Find the thread
Option A: Search by subject keyword
DB="$HOME/Library/Mail/V10/MailData/Envelope Index"
QUERY="<extracted from $ARGUMENTS>"
sqlite3 "$DB" "
SELECT m.ROWID, m.conversation_id, s.subject,
datetime(m.date_received,'unixepoch','localtime') as dt,
a.address as sender
FROM messages m
JOIN subjects s ON m.subject = s.ROWID
JOIN addresses a ON m.sender = a.ROWID
WHERE s.subject LIKE '%${QUERY}%' AND m.deleted=0
ORDER BY m.date_received DESC LIMIT 10;" 2>/dev/nullOption B: If ROWID provided directly
sqlite3 "$DB" "
SELECT conversation_id FROM messages WHERE ROWID = <ROWID>;" 2>/dev/nullStep 2: Get all messages in the thread by conversation_id
CONV_ID=<from step 1>
sqlite3 "$DB" "
SELECT m.ROWID,
datetime(m.date_received,'unixepoch','localtime') as dt,
a.address as sender, a.comment as name,
s.subject, mb.url as mailbox, m.read
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.conversation_id = ${CONV_ID}
AND m.deleted = 0
ORDER BY m.date_received ASC;" 2>/dev/nullStep 3: Read all message bodies
python3 ~/.claude/skills/_mail-shared/parser.py <ROWID1> <ROWID2> <ROWID3> ...Step 4: Reconstruct the conversation
Present chronologically:
- Who sent each message and when
- Key content of each message (summarize long ones, quote short ones)
- Reply chain structure
Step 5: Summarize the thread
After showing the conversation:
- What was the original question/issue?
- What was discussed/debated?
- What was decided or concluded?
- Are there any open questions or pending actions?
- Who is waiting on whom?
Output Format
Thread: [Subject] [N messages | started: date | participants: list]
[Date] [Sender Name] [→ Reply to: ...]
[message content, summarized if long]
[repeat for each message]
Summary: [2-3 sentence summary of the thread outcome]
Status: [Resolved / Ongoing / Waiting for response] Next action: [if any]
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
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.

