agentleFS
Sign inStart free
styfinitystyfinity/linkedin-engine/skills/linkedin-warm-list-builder/SKILL.md

linkedin-warm-list-builder

Skill9 starsChanged 4 months agoMITView on GitHub

Build a prioritised warming target list by scoring ICP-fit candidates and attaching the strongest why-now signal to each. Use when you need a ranked list of who to warm next, not generic prospecting.

The file

We split this skill into the rules it gives an agent

2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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
  1. Distinctive:

    No em-dashes. Every why-now signal must be real and dated, not invented.

    line 28
  2. Distinctive:

    If a target has no genuine why-now signal, mark it evergreen, do not fabricate one.

    line 29

≈ “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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

LinkedIn Warm List Builder

Warming is wasted on the wrong people. This skill assembles the right ones, scores them against the ICP, and sorts so the warmest sit at the top, because viral and signal warmth both decay fast.

Inputs

  • Any seed lists, search filters, or signals to weight (recent posters, role changes, mutuals, event attendees): $ARGUMENTS
  • The ICP, pains, and offer load automatically from the brief.

Do this

  1. Assemble candidates. If the connected layer is available, run a live search off the filters. Otherwise work off the pasted or seed lists. Do not scrape.
  2. Score each against the ICP. Use a 0 to 10 fit score on role, company size, and pain match. Drop anything under the floor the brief implies.
  3. Attach the strongest why-now signal to each: a recent post, a role change, a funding event, a comment thread, a mutual. One signal per target, the freshest one.
  4. Sort warmest to coldest. A strong recent signal beats a marginally higher fit score, because warmth decays and fit does not.
  5. Suggest a first touch per target: engage on the post, comment, or a connect via /linkedin-connection-note.

Output

A ranked table: name, title, company, ICP score (0 to 10), why-now signal (with the date), suggested first touch. Top of the table is who to warm today. End with a one-line note on which rows are signal-fresh (act this week) versus evergreen.

Rules

  • Live search needs the connected CLI/MCP layer. Without it, work off seed lists only. No scraping by default.
  • This is a list to warm, not a list to blast. Building it sends nothing.
  • No em-dashes. Every why-now signal must be real and dated, not invented.
  • If a target has no genuine why-now signal, mark it evergreen, do not fabricate one.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free