Classify a batch of emails into action categories (reply now, reply later, archive, delete, unsubscribe) and surface unsubscribe candidates. Use after a busy week, running inbox zero, or triaging email overload.
SkillScore95Maintained
Automatic
◆Personal Assistant pack
Last verified 8/20/2026
What it changes
Passed 21 of 22 test cases with the skill, and 11 of 22 without it.
Without skill50%
With skill95%
Checks it passed that the model alone missed
Recommends processing archive items before unsubscribe items
Routes completed transaction receipts into the archive bucket
Inquires about unsubscribe tolerance before performing the classification
and 8 more in the full report
10 fixed11 passed either way1 still failing0 broke
Pass-rate lift
+45 pp
Tokens
+23%
Agent turns
0%
Response time
-29%
Model gemini-3.6-flashMeasured 8/20/2026v121 of 22 cases passed with skill
Tokens, turns and time describe resource use, not a dollar price.
See it in action
One of 10 test cases the skill fixed. Same model, same prompt, with and without the skill.
1 of 10
Prompt
I exported my Gmail messages to a file named recent_inbox.csv. What standard terminal command should I run using the provided repository script to parse this file and display the output in JSON format?
What was checked, without and with the skill
Checked
Without skill
With skill
Specifies the python execution of scripts/email_classifier.py with the --json flag
Missed
Passed
case-05 · gemini-3.6-flash · 8/20/2026 · answers are capped and redacted
What's inside
The instructions your model reads when the skill loads.
SKILL.md97 lines4 filesincludes scripts
Email Triage
Classify a batch of email subjects + senders into action buckets and surface inbox-zero candidates.
Priority / VIP senders — who always routes to reply_now regardless of content
Unsubscribe tolerance — purge all marketing vs keep newsletters you value; sets how aggressive the unsubscribe/delete buckets are
Stop rule: ask only the 2-3 that most change the output. If the user says "just draft it," proceed and list your assumptions at the top of the artifact.
Quick Start
Export inbox to CSV with columns: subject,sender,snippet,received_at
Run: python scripts/email_classifier.py inbox.csv
Review action buckets; act on each in order
Core Workflows
Workflow 1: Weekly Inbox Triage
Export the past week's inbox
Run classifier
Action in order: reply-now → reply-later (move to follow-up folder) → archive → unsubscribe → delete
Apply Gmail filters (see assets/gmail_filter_template.md) so future similar emails route automatically