agentleFS
Sign inStart free
prosyo-aiprosyo-ai/gtm-skill/skills/linkedin-message-sequence/SKILL.md

linkedin-message-sequence

Skill13 starsChanged 21 days agoMITView on GitHub

Use this skill when you need a LinkedIn outreach sequence that starts conversations instead of collecting ignored pitches: \"write a LinkedIn message sequence\", \"what do I send after they accept\", \"LinkedIn prospecting messages\". Designs the steps from connection to meeting (note, first message, value message, soft ask, close), writes each message in a conversational tone, sets timing and exit rules, and includes reply branches for the most common answers.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    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:

    Use this to plan a LinkedIn campaign end to end.

    line 16
  2. Distinctive:

    Stop on any reply (switch to manual), if they decline, or if someone at the same account books a meeting.

    line 47
  3. Distinctive:

    No message is longer than a phone screen.

    line 52
  4. Distinctive:

    MUST wait at least a day after acceptance before the first message.

    line 58
  5. Distinctive:

    MUST stop automation the moment someone replies.

    line 59
  6. Distinctive:

    MUST stay within safe daily limits for invitations and messages.

    line 60
  7. Distinctive:

    NEVER pitch in the connection note or message 1.

    line 61
  8. Distinctive:

    NEVER send links in the first message.

    line 62

≈ “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

Use this to plan a LinkedIn campaign end to end. LinkedIn is a conversation channel; messages that read like emails pasted into a chat window get ignored.

Inputs

  • Persona and the problem the campaign is about.
  • Offer and approved proof.
  • The reason to connect (from research, an event, content or a trigger).

The play

1. Shape the sequence

StepTimingJobLength
Connection requestDay 0Get acceptedUnder 200 characters, no pitch
Message 11-3 days after acceptStart a conversation on the topic1-3 sentences, ends in a question
Message 24-5 days laterGive value: an insight, resource or story2-4 sentences
Message 35-7 days laterSoft ask tied to their answer or the topic2-3 sentences
Message 47-10 days laterClose the loop warmly1-2 sentences

Voice notes and short videos can replace message 2 or 3 for Tier 1 contacts; they stand out because few people use them.

2. Write like a chat

Short lines, no subject, no sign-off block, no bullet lists, no links in message 1. Ask questions people can answer from their phone in five seconds.

3. Bridge from topic to problem

Message 1 is about the topic that made you connect. The bridge to your problem comes through their answer, or in message 2 with a peer insight. Read references/linkedin-sequence-example.md for a full example with reply branches.

4. Handle replies fast

LinkedIn replies expect a response within hours. Positive replies get a meeting link or two time options; questions get a direct answer, not a pitch.

5. Exit rules

Stop on any reply (switch to manual), if they decline, or if someone at the same account books a meeting. Withdraw connection requests not accepted after 14-21 days.

What good looks like

  • Message 1 gets a reply because it is a question about their world, not your product.
  • No message is longer than a phone screen.
  • Acceptance 30%+, reply rate on accepted connections 15-25%+ for a well-targeted list.
  • The common mistake is "Thanks for connecting! We help companies like yours..." sent seconds after acceptance.

Rules

  • MUST wait at least a day after acceptance before the first message.
  • MUST stop automation the moment someone replies.
  • MUST stay within safe daily limits for invitations and messages.
  • NEVER pitch in the connection note or message 1.
  • NEVER send links in the first message.

Example prompts

  • "Build a LinkedIn sequence for heads of finance at 50-200 person companies. Problem: slow month-end close."
  • "What should I send after people accept my connection request?"
  • "Rewrite our LinkedIn messages; they read like emails."

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