agentleFS
styfinitystyfinity/linkedin-engine/skills/linkedin-connection-note/SKILL.md

linkedin-connection-note

Skill9 starsChanged 4 months agoMITView on GitHub

Write two LinkedIn connection notes under 200 characters, each opening on one real specific hook so the request is easy to accept. Use when sending a connection request to a named prospect.

2 other projects use a version of this.

Adopted by

Most recently taken up by

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
  1. Distinctive:

    Write Variant A: a connection note that opens on that exact detail.

    line 17
  2. Distinctive:

    Write Variant B: a different angle on the same hook, or a second real detail.

    line 18
  3. Distinctive:

    No pitch, no ask, no offer.

    line 26
  4. Distinctive:

    No em-dashes. Use a comma, a period, or " - ".

    line 28

≈ “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 Connection Note

A connection note is not a pitch. It earns the accept by referencing one real, specific detail. This skill writes two short variants so the operator can pick.

Inputs

  • The target profile (name, role, company) and how you found them, plus the one real hook (a post they wrote, a comment, a mutual, a signal): $ARGUMENTS
  • The brief (persona tone, pains, voice) loads automatically.

Do this

  1. Pull the single most specific real hook from the input. If there is no real hook, say so and ask for one. Do not invent it.
  2. Write Variant A: a connection note that opens on that exact detail. Under 200 characters. No pitch.
  3. Write Variant B: a different angle on the same hook, or a second real detail. Under 200 characters. No pitch.
  4. Count the characters in each. If either is over 200, cut it down and recount.

Output

Variant A and Variant B, each on its own line, with the exact character count in brackets after it (for example: [184 chars]). One line below: each is draft only, pick one, then approve before it goes out.

Rules

  • Under 200 characters, counted and shown. No exceptions.
  • No pitch, no ask, no offer. The note buys the accept, nothing more.
  • No "I came across your profile", no "hope you're well", no exclamation marks.
  • No em-dashes. Use a comma, a period, or " - ".
  • Reads like one peer messaging another about a real thing they noticed.
  • Draft only. Claude drafts, the operator approves and sends.
  • Sending happens only through the connected opt-in CLI/MCP layer wired to your own LinkedIn session or provider key, and is hard-capped at 20 actions per day on new accounts. This skill never sends.

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.