mcpField
L
li-inbox

li-inbox

github.com/jakeschincariolProductivity2.9k243 installsUpdated 7w ago
Repository

About li-inbox

li-inbox is a skill for sorting LinkedIn messages pasted by the user and drafting replies only where appropriate. It groups messages into five categories and leaves sending to the user.

Key features

  1. 01Classifies messages into five categories
  2. 02Counts and summarizes each category
  3. 03Detects automated outreach patterns
  4. 04Drafts replies for messages worth answering
  5. 05Leaves message sending to the user

Use cases

  1. 01Triage a pasted LinkedIn inbox
  2. 02Identify leads and scripted outreach
  3. 03Prepare concise replies or declines

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/jakeschincariol/linkedin-agent-skill --skill li-inbox

After installing, type/li-inboxin Claude Code to confirm it loaded.

Details

From the project README

li-inbox

Most LinkedIn inboxes are 80% noise, and the cost of that noise is that the 20% goes unanswered for a week. This skill separates them, then writes only what is worth writing.

Input

The user pastes the messages. Screenshots are fine. Do not log into their account or read their inbox with a browser tool.

Sort into five

bucketsignalaction
LEADdescribes a problem the user solves, or asks about working togetherreply today, full answer
RECRUITERa role, a company, a salary bandreply if the role is real, one line if not
PEERsomeone in the same field with something to sayreply this week, keep it human
ASKwants advice, time, an intro, a favourreply if it is cheap and specific, decline cleanly if not
SPAMagency pitch, lead-gen sequence, crypto, "quick question" with no questionarchive, no reply

Print the counts first. Seeing "3 leads, 2 recruiters, 41 spam" is most of the value.

Detecting a sequence

Automated outreach has a shape: an invite note with no specifics, a message that arrives within minutes of the accept, "quick question", "I noticed you're in {industry}", a calendar link in message one, then a bump exactly four days later. When you see it, mark it SPAM and say which tell gave it away. The user does not owe a reply to a script.

Replies

  • LEAD - answer the actual question in the message, in full, for free. If it is a fit, the offer is one sentence at the end. If it is not, say so and point them somewhere useful. Both outcomes are good.
  • RECRUITER - if the role is genuinely interesting, ask the three things the message left out: comp band, level, and whether it is in-office. If it is not, one line: not looking, happy to refer, and mean the refer.
  • ASK - if it costs under ten minutes and is specific, do it. If it is "can I pick your brain", decline in one warm sentence and give them the one answer you would have given on the call. That is the polite version and it is also the more useful one.
  • DECLINES are short, warm and final. No "let's revisit in Q3" if there is no Q3.

Output

Grouped by bucket, counts first, drafts only for the buckets that get replies, each one humanized. Then the gate: the user sends them.

INBOX  ·  52 items  ·  3 LEAD, 2 RECRUITER, 4 PEER, 2 ASK, 41 SPAM

SPAM  (41) - archive. 38 are the same sequence: no-specifics invite,
"quick question" within 4 minutes of accept, calendar link in message one.

Comments

Markdown supported