linkedin-reply-triager
Skill9 starsChanged 4 months agoMITView on GitHub
Classify every inbound LinkedIn reply and route it to the right next move. Use when replies land in the inbox and you need to decide who is hot, who needs nurture, and who to drop.
In this repository28 other files it gives its agents.
- linkedin-booking-closerSkill
- linkedin-carousel-writerSkill
- linkedin-cold-reviverSkill
- linkedin-comment-engineSkill
- linkedin-comment-warmerSkill
- linkedin-connection-noteSkill
- linkedin-content-calendarSkill
- linkedin-engage-planSkill
- linkedin-engager-analyticsSkill
- linkedin-first-dmSkill
- linkedin-followup-adapterSkill
- linkedin-hook-labSkill
- linkedin-humanizerSkill
- linkedin-icp-definerSkill
- linkedin-objection-handlerSkill
- linkedin-onboardSkill
- linkedin-outreachSkill
- linkedin-post-autopsySkill
- linkedin-post-writerSkill
- linkedin-profile-auditorSkill
- linkedin-repurposerSkill
- linkedin-sell-by-chatSkill
- linkedin-signal-stackSkill
- linkedin-story-minerSkill
- linkedin-strategistSkill
- linkedin-voice-profilerSkill
- linkedin-warm-list-builderSkill
- linkedin-warm-trackerSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 17
Read the actual words, not the timing.
- Distinctive: line 27
Write a one-line suggested next message in the operator's voice.
- Distinctive: line 34
Read the words, not a timer.
- Distinctive: line 36
No em-dashes. Use a comma, a period, or " - ".
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
LinkedIn Reply Triager
The inbox sorter. Replies are not equal. This skill reads each one, names what bucket it belongs in, and hands it to the right next skill so nothing rots and nothing gets a sales pitch it did not ask for.
Inputs
- One reply or a batch of replies, pasted in (include who said what if it is a thread): $ARGUMENTS
- The brief (persona, offer, pains) loads automatically.
Do this
For each reply, in order:
- Read the actual words, not the timing. A reply that came in slow can still be HOT; a fast one can be a brush-off.
- Classify into exactly one bucket: HOT, WARM, COLD, OBJECTION, WRONG-PERSON, or HOSTILE.
- Name the tell. Quote the one phrase or signal that put it in that bucket. One line.
- Route it:
- HOT (buying signal, asking how it works, wants a call) to /linkedin-sell-by-chat, or /linkedin-booking-closer if they are ready for a time.
- WARM (interested but not now, soft yes, "keep me posted") to /linkedin-followup-adapter.
- COLD (one-word, flat, polite-but-dead) to /linkedin-cold-reviver.
- OBJECTION (price, timing, trust, "already have someone") to /linkedin-objection-handler.
- WRONG-PERSON (not their call, not their remit) ask for the right contact, warmly.
- HOSTILE (annoyed, "stop messaging me") stop the sequence, no further outreach.
- Write a one-line suggested next message in the operator's voice.
Output
Per reply: the class, the tell (quoted), the route (the slash-skill or the action), and a one-line suggested next message. Label each clearly. Batch input gets one block per reply.
Rules
- Route every reply. No reply is left unclassified.
- Read the words, not a timer. The bucket comes from what they said.
- Nothing sends here. This skill only sorts and suggests; the routed skill drafts, the operator approves.
- No em-dashes. Use a comma, a period, or " - ".
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

