agentleFS
holaroluwaholaroluwa/outbound-skills/skills/copywriting-linkedin-dm/SKILL.md

copywriting-linkedin-dm

Skill0 starsChanged 48 days agoMITView on GitHub

Write LinkedIn outreach, a connection request plus a first and second DM, two variants each, from a prospect's profile and how you found them. Use when the user wants "LinkedIn DMs", "a connection request", "social selling messages", or is reaching out on LinkedIn rather than email. Reads persona, pains, and offer from outreach-brief.md and keeps it human and specific, never a copy-paste pitch-slap.

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
  1. Distinctive:

    Write, with two variants each:

    line 16
  2. Distinctive:

    No em-dashes. No "I'd love to connect and explore synergies."

    line 24
  3. Distinctive:

    Don't pitch on the connection request.

    line 25

≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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

Copywriting: LinkedIn DM

LinkedIn is a conversation, not an inbox. The instant you pitch on connect, you're dead. This skill writes messages that open a real exchange.

Input needed

  • The prospect's profile: role, recent activity, anything specific.
  • How you found them (the context that makes reaching out make sense).
  • Persona, pains, and offer from outreach-brief.md if present.

Method

Write, with two variants each:

  1. Connection request, under 200 characters, a real reason tied to them, no pitch.
  2. First DM (after they accept), warm, specific, still no pitch. Start a conversation or offer something useful.
  3. Second DM, only now a soft bridge to the pain and a low-friction ask.

Pull the prospect's own language and a real signal. Generic equals ignored.

Voice rules (non-negotiable)

  • No em-dashes. No "I'd love to connect and explore synergies."
  • Don't pitch on the connection request. Don't pitch in the first DM.
  • Short, human, specific. Sound like a peer, not a vendor.

Output

Connection request (2 variants), first DM (2 variants), and second DM (2 variants), each labelled, with a one-line note on timing between them.

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.