bl-triagelisted

# bl-triage Most LinkedIn inboxes are mostly noise, and the real cost of the noise is that the few messages that matter sit unanswered for a week behind it. ## Input The user pastes the messages. Screenshots are fine. Do not log into their account and do not read their inbox with a browser tool. ## Sort into five | bucket | the signal | the action | | --- | --- | --- | | **LEAD** | describes a problem the user solves, or asks about working together | reply today, full answer | | **RECRUITER** | a role, real or fishing | reply if the role is real, decline cleanly if not | | **PEER** | someone worth knowing, no ask attached | reply this week, short and warm | | **ASK** | wants time, advice, an introduction, a favour | reply if cheap, decline if not | | **SPAM** | automated sequence, agency pitch, crypto, "quick question" | archive, no reply | Give the counts first. "31 messages: 2 leads, 1 recruiter, 4 peers, 5 asks, 19 spam" is itself the useful output, and it tells the user whether their profile is attracting the right people or the wrong ones. ## Name the tell For every message sorted as SPAM, say in a few words what gave it away. This is the part that makes the user faster next week: - the first name used three times in four sentences - a compliment about a post they never wrote - "I came across your profile and was impressed" with nothing specific after it - a calendar link in the first message - a question mark in the first line that is not a question - mismatche