icp-definer
Skill0 starsChanged 47 days agoMITView on GitHub
Define the Ideal Customer Profile from real pipeline evidence, won deals, lost deals, and churn, with concrete qualification criteria and hard disqualifiers. Use when the user wants to know "who should we actually target", "build our ICP", "who closes fastest", or is about to build a prospect list and needs targeting rules. Pulls from won/lost/churn data, not guesses, and writes the ICP into outreach-brief.md. Use it before any list-building or copywriting.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- vicfromthegtmclub/gtmskillstheir own version, first seen Aug 10, 2026
- paulnugentuk/pmmstacktheir own version, first seen Apr 24, 2026
- l3mpire/claude-skillstheir own version, first seen Apr 13, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- l3mpire/claude-skills★ 9same name
- paulnugentuk/pmmstack★ 2same name
- vicfromthegtmclub/gtmskills★ 1same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository15 other files it gives its agents.
- cold-call-scriptSkill
- competitor-finderSkill
- copywriting-first-touchSkill
- copywriting-follow-upSkill
- copywriting-linkedin-dmSkill
- deep-company-analyserSkill
- n8n-workflow-builderSkill
- offer-definerSkill
- outreach-strategistSkill
- pain-identifierSkill
- persona-definerSkill
- pipeline-analyserSkill
- reply-rate-analyserSkill
- tam-sam-som-sizerSkill
- value-prop-listerSkill
The file
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
If the user lacks hard data, work from their best recollection of their best and worst customers, and clearly mark it provisional until …
- Very specific: line 23
Write into section 3 (ICP) of outreach-brief.md:
“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
ICP Definer
Your ICP is not who you wish bought from you. It's who actually buys, stays, and is easy to win. This skill reads the pipeline evidence and writes targeting rules a list-builder can follow.
Input needed
- Won-deal data: who closed, how fast, deal size.
- Lost-deal and churn data: who said no, who left, and why.
If the user lacks hard data, work from their best recollection of their best and worst customers, and clearly mark it provisional until real data exists.
Method
- Study the winners: what do the best, fastest-closing, longest-staying customers share? Industry, size, buyer role, trigger or situation, tech stack, geography.
- Study the losers and churned: what patterns predicted a bad fit?
- Turn the winner-patterns into fit criteria a person could filter a list on.
- Turn the loser-patterns into disqualifiers, hard "do not target" rules that save wasted sends.
Output
Write into section 3 (ICP) of outreach-brief.md:
- Fit criteria: bulleted and filterable (e.g., "B2B SaaS, 10-50 employees, founder still in sales").
- Disqualifiers: bulleted, hard rules.
- A one-line best-fit trigger: the buying situation that makes someone ripe right now.
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.

