Menu

Individual skill

icp-to-linkedin-search

0upvotes

Use this skill when someone describes who they sell to, in a sentence, a website URL or a rough persona, and needs it turned into something LinkedIn can search: a structured ICP in seven facets, normalized title families, a boolean string for the title field, an exclusion list, and a company count that says whether the audience is a motion, a campaign or a market. Fires on "build me a LinkedIn search", "Sales Navigator boolean", "people search for <persona>", "size this audience", "normalize these job titles", "CMO plus Chief Marketing Officer plus VP Marketing", or "exclude fractional, freelance and interns".

skills/thomas-maitre/icp-to-linkedin-search/SKILL.md

Read pinned source

Source commit 5d786aad0c7b2ca59b1abf1f601f9407ca261996

What was checked

Matches the observed repository HEAD
Yes
Scanner rules are current
Yes
Repository scan complete
No
Skill scan complete
Yes
Observed behavior
Instructions only
Last checked
Nov 11, 2026

These are observations at the recorded commit, not a guarantee of safety. Review the source before running it.

Install this skill

Choose an agent in your Stack or copy a command below. Commands fetch the pinned commit and copy only this skill directory. Existing destinations are refused. Copying a command does not install anything.

An install command is unavailable: current rules, complete repository and skill scans, an eligible behavior level and a permitted license are required.

Repository context

Repository stars (not skill ratings)
237
Repository last updated
Oct 20, 2026
License
MIT

Observed agent integration: No specific integration evidence. Standard SKILL.md installation does not imply verified compatibility.

Files and excerpt

File metadata and permitted, redacted excerpts come from the recorded scan. Source links are pinned to that commit.

Browse files
Read excerpt

Applies before any list is built or any outreach starts, whenever the buyer exists only
as a sentence. Produces an ICP card, a boolean title string with its exclusions, and a
company count with what to change if the count is wrong.

Input: "CFOs at Swiss fintechs", a website URL, or a paragraph about the buyer. The
mistake to avoid is treating a title as a string; it is a family, and the search that
uses one wording finds a third of the people.

## The play

1. **Extract the seven facets.** `titles`, `seniority`, `languages`, `industries`,
   `sizes`, `locations`, `exclude`, as plain-word lists. Name only the facets the input
   gave or that follow from the product; an empty facet means "any", not "unknown". From
   a website URL, read the pricing page for the size band, the customer logos for the
Back to top