linkedin-icp-definer
Skill9 starsChanged 4 months agoMITView on GitHub
Define and lock the ICP and disqualifiers from real evidence, then write a ready-to-paste ICP block into the brief. Use before any warming or outreach so the other skills score against a real target, not a guess.
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-objection-handlerSkill
- linkedin-onboardSkill
- linkedin-outreachSkill
- linkedin-post-autopsySkill
- linkedin-post-writerSkill
- linkedin-profile-auditorSkill
- linkedin-reply-triagerSkill
- 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
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 18
Write explicit disqualifiers.
- Distinctive: line 28
Every attribute must be something a sibling skill can score against.
- Distinctive: line 29
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 ICP Definer
Your ICP is not who you wish bought from you. It is who actually does. This skill reads the evidence, names the disqualifiers out loud, and locks it into the brief so every other skill scores against the same target.
Inputs
- Won and lost notes, descriptions of your best clients, and who you do NOT want: $ARGUMENTS
- The brief (offer, pains, voice) loads automatically. If the offer section is thin, fixing it is the first thing to flag.
Do this
- Derive the ICP from the evidence, not from aspiration. From the won notes, pull the pattern: title, seniority, company size, industry, and the trigger that made them buy (the event or pain that started the conversation).
- Cross-check the lost notes. If a profile shape keeps losing, it is a disqualifier, not a stretch target. Say so.
- Write explicit disqualifiers. Name the titles, company sizes, stages, or situations that look close but never convert. Be specific enough that a person could be ruled out in five seconds.
- List the 2 or 3 buying signals that mark a live one right now (a hiring post, a funding event, a role change, a public complaint about the exact pain the offer solves).
- Phrase every line so the other skills can score against it. Concrete attributes, not adjectives.
Output
A ready-to-paste "## ICP" block for linkedin-brief.md, with three labelled parts: Fit criteria (title, seniority, company size, industry, buying trigger), Disqualifiers (explicit, ruled-out shapes), and Buying signals (the 2 or 3 live markers). Hand it back ready to drop straight into the brief.
Rules
- ICP from evidence, not aspiration. If a claim is not backed by a won or lost note, mark it an assumption to test, not a fact.
- Name disqualifiers explicitly. A target with no disqualifiers is not defined yet.
- Every attribute must be something a sibling skill can score against. No vague adjectives.
- No em-dashes. Use a comma, a period, or " - ".
- This writes to the brief but does not send anything. It only shapes who the outreach skills aim at.
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.

