li-inbox

1# li-inbox
2 
3Most LinkedIn inboxes are 80% noise, and the cost of that noise is that the
420% goes unanswered for a week. This skill separates them, then writes only
5what is worth writing.
6 
7## Input
8 
9The user pastes the messages. Screenshots are fine. Do not log into their
10account or read their inbox with a browser tool.
11 
12## Sort into five
13 
14| bucket | signal | action |
15| --- | --- | --- |
16| **LEAD** | describes a problem the user solves, or asks about working together | reply today, full answer |
17| **RECRUITER** | a role, a company, a salary band | reply if the role is real, one line if not |
18| **PEER** | someone in the same field with something to say | reply this week, keep it human |
19| **ASK** | wants advice, time, an intro, a favour | reply if it is cheap and specific, decline cleanly if not |
20| **SPAM** | agency pitch, lead-gen sequence, crypto, "quick question" with no question | archive, no reply |
21 
22Print the counts first. Seeing "3 leads, 2 recruiters, 41 spam" is most of the
23value.
24 
25## Detecting a sequence
26 
27Automated outreach has a shape: an invite note with no specifics, a message
28that arrives within minutes of the accept, "quick question", "I noticed you're
29in {industry}", a calendar link in message one, then a bump exactly four days
30later. When you see it, mark it SPAM and say which tell gave it away. The user
31does not owe a reply to a script.
32 
33## Replies
34 
35- **LEAD** - answer the actual question in the message, in full, for free. If
36…