LinkedIn Inbox Triage

Li inbox

by Jakeschincariol · MIT license · ★ 1,856 on GitHub

Li inbox cover

Triage the LinkedIn inbox - sort connection requests and DMs into leads, recruiters, peers and spam, and draft the replies worth sending. Use when the user says "my inbox is a mess", "triage my DMs", "should I reply to this", pastes a…

---
name: li-inbox
description: >-
  Triage the LinkedIn inbox - sort connection requests and DMs into leads,
  recruiters, peers and spam, and draft the replies worth sending. Use when the
  user says "my inbox is a mess", "triage my DMs", "should I reply to this",
  pastes a batch of LinkedIn messages, or is drowning in connection requests.
---

# 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

Overview

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.

Manual install (npx, ZIP)
Claude Codenpx skills add Jakeschincariol/linkedin-agent-skill --skill li-inbox -g -a claude-code
Claude Code (degit)npx degit Jakeschincariol/linkedin-agent-skill/skills/li-inbox#main ~/.claude/skills/li-inbox
Claude.ai / desktopZip the folder and upload it under Settings → Capabilities → Skills.
Codex, Cursor, other agentsPoint them at SKILL.md. The other files are plain text.

Connects with Agent Alley MCP · agentalley.io/mcp

Files included

  • SKILL.md2.8 KB
Read SKILL.md here
Jakeschincariol/main1 file shown
SKILL.md
Show the full text68 lines
li-inbox/SKILL.md68 lines · 2.8 KB

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

bucket signal action
LEAD describes a problem the user solves, or asks about working together reply today, full answer
RECRUITER a role, a company, a salary band reply if the role is real, one line if not
PEER someone in the same field with something to say reply this week, keep it human
ASK wants advice, time, an intro, a favour reply if it is cheap and specific, decline cleanly if not
SPAM agency pitch, lead-gen sequence, crypto, "quick question" with no question archive, 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.
1---
2name: li-inbox
3description: >-
4 Triage the LinkedIn inbox - sort connection requests and DMs into leads,
5 recruiters, peers and spam, and draft the replies worth sending. Use when the
6 user says "my inbox is a mess", "triage my DMs", "should I reply to this",
7 pastes a batch of LinkedIn messages, or is drowning in connection requests.
8---
9 
10# li-inbox
11 
12Most LinkedIn inboxes are 80% noise, and the cost of that noise is that the
1320% goes unanswered for a week. This skill separates them, then writes only
14what is worth writing.
15 
16## Input
17 
18The user pastes the messages. Screenshots are fine. Do not log into their
19account or read their inbox with a browser tool.
20 
21## Sort into five
22 
23| bucket | signal | action |
24| --- | --- | --- |
25| **LEAD** | describes a problem the user solves, or asks about working together | reply today, full answer |
26| **RECRUITER** | a role, a company, a salary band | reply if the role is real, one line if not |
27| **PEER** | someone in the same field with something to say | reply this week, keep it human |
28| **ASK** | wants advice, time, an intro, a favour | reply if it is cheap and specific, decline cleanly if not |
29| **SPAM** | agency pitch, lead-gen sequence, crypto, "quick question" with no question | archive, no reply |
30 
31Print the counts first. Seeing "3 leads, 2 recruiters, 41 spam" is most of the
32value.
33 
34## Detecting a sequence
35 
36Automated outreach has a shape: an invite note with no specifics, a message
37that arrives within minutes of the accept, "quick question", "I noticed you're
38in {industry}", a calendar link in message one, then a bump exactly four days
39later. When you see it, mark it SPAM and say which tell gave it away. The user
40does not owe a reply to a script.
41 
42## Replies
43 
44- **LEAD** - answer the actual question in the message, in full, for free. If
45 it is a fit, the offer is one sentence at the end. If it is not, say so and
46 point them somewhere useful. Both outcomes are good.
47- **RECRUITER** - if the role is genuinely interesting, ask the three things
48 the message left out: comp band, level, and whether it is in-office. If it
49 is not, one line: not looking, happy to refer, and mean the refer.
50- **ASK** - if it costs under ten minutes and is specific, do it. If it is
51 "can I pick your brain", decline in one warm sentence and give them the one
52 answer you would have given on the call. That is the polite version and it
53 is also the more useful one.
54- **DECLINES** are short, warm and final. No "let's revisit in Q3" if there is
55 no Q3.
56 
57## Output
58 
59Grouped by bucket, counts first, drafts only for the buckets that get replies,
60each one humanized. Then the gate: the user sends them.
61 
62```
63INBOX · 52 items · 3 LEAD, 2 RECRUITER, 4 PEER, 2 ASK, 41 SPAM
64 
65SPAM (41) - archive. 38 are the same sequence: no-specifics invite,
66"quick question" within 4 minutes of accept, calendar link in message one.
67```
68 
View all files on GitHub →

Details

License
MIT
Stars on the repo
★ 1,856
Checked
Source
Jakeschincariol/linkedin-agent-skill ↗
Creator
Jakeschincariol · 34 listings
View creator

Similar skills

See all →

More from Jakeschincariol

SkillIG Story WriterJakeschincariol/instagram-agent-skill · by JakeschincariolWrite the day's Instagram Stories - the frame-by-frame sequence, which stickers to use where, and the one that moves people into the DMs. Use when the user says "stories", "what do I post on my story", "story sequence", poll idea", "I have nothing to story about", or wants to sell something without making a post about it.★ 6k GitHub starsSkillLinkedIn Post AuditJakeschincariol/linkedin-agent-skill · by JakeschincariolPost-mortem on what the user has already published - which posts actually worked, why, and what to stop doing. Use when the user pastes their LinkedIn analytics or past posts and asks "what's working", "why did this flop", "read my analytics", "audit my content", or wants to know what to double down on.★ 1.9k GitHub starsSkillLinkedIn Carousel BuilderJakeschincariol/linkedin-agent-skill · by JakeschincariolBuild a LinkedIn document post (carousel) - slide-by-slide copy, the cover that earns the swipe, and the PDF to upload. Use when the user says carousel", "document post", "slides for LinkedIn", "turn this into a carousel", or has a list-shaped idea that would die as a text post.★ 1.9k GitHub starsSkillLinkedIn Comment WriterJakeschincariol/linkedin-agent-skill · by JakeschincariolWrite comments on other people's LinkedIn posts that read as a person with an opinion, not a bot. Use when the user pastes a post and wants a comment, says comment on this", "engage with this", "what do I say here", or wants a batch of comments for their engagement round.★ 1.9k GitHub starsSkillYouTube Channel AuditorJakeschincariol/youtube-agent-skill · by JakeschincariolAudit a YouTube channel end to end - packaging, consistency, the first fifteen seconds, and what to fix first. Use for "audit my channel", "why isn't my channel growing", "review my videos", or a pasted channel URL.★ 1.1k GitHub starsSkillYouTube Chapter WriterJakeschincariol/youtube-agent-skill · by JakeschincariolWrite YouTube chapters from a transcript, validated against YouTube's own rules so they actually render. Use for "add chapters", "timestamps", break this video into sections".★ 1.1k GitHub stars