agentleFS
Sign inStart free
styfinitystyfinity/linkedin-engine/skills/linkedin-sell-by-chat/SKILL.md

linkedin-sell-by-chat

Skill9 starsChanged 4 months agoMITView on GitHub

Draft the single next message in the 6-stage warm-to-booked chat framework, gating the offer behind a confirmed problem and the calendar link behind a yes. Use when you have a live LinkedIn conversation and need to know what to say next.

The file

We split this skill into the rules it gives an agent

5 rules. About 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈5

    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:

    Read the thread and identify which of the six stages it is at right now.

    line 16
  2. Distinctive:

    Never skip a stage. Never pitch before the problem is confirmed (stages 3 and 4).

    line 24
  3. Distinctive:

    If the thread is ambiguous, name the most likely stage, say why, and draft for that one.

    line 25
  4. Distinctive:

    Run /linkedin-humanizer on the draft if it reads stiff.

    line 36
  5. Distinctive:

    No em-dashes. No guaranteed-result or "10x in a week" promises.

    line 38

≈ “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 Sell By Chat

The hero outreach skill. Selling on LinkedIn is a six-stage conversation, not a pitch. This skill reads where the thread actually is and drafts only the next message, so you never run ahead of the buyer.

Inputs

  • The conversation so far, pasted in full, plus the offer: $ARGUMENTS
  • The brief (offer, pains, voice profile) loads automatically.

Do this

  1. Read the thread and identify which of the six stages it is at right now. The six stages:
    1. Open on their world, not your offer. A genuine, specific opener about them.
    2. One real insight that earns the reply. Useful on its own, no ask attached.
    3. Qualify the problem, message one: confirm the problem actually exists for them.
    4. Qualify the problem, message two: confirm the problem actually hurts.
    5. Introduce the offer, ONLY after they have confirmed the problem exists.
    6. Send the calendar link, ONLY after they say yes to a call.
  2. Draft only the next single message for the stage they are at. One message, not a sequence.
  3. Never skip a stage. Never pitch before the problem is confirmed (stages 3 and 4). Never send the link before a clear yes (stage 6).
  4. If the thread is ambiguous, name the most likely stage, say why, and draft for that one.

Output

  • The next message, ready to copy.
  • The stage it belongs to (1 to 6).
  • What a yes vs a no looks like at this stage, so the user knows whether to advance or hold.

Rules

  • One message at a time. Never draft ahead of the buyer.
  • Gate the offer behind problem-confirmation, and the link behind an explicit yes.
  • Once they say yes, stop selling and book. Hand to /linkedin-booking-closer.
  • Run /linkedin-humanizer on the draft if it reads stiff.
  • Draft only. Claude drafts, the operator approves and sends. Sending happens only through the connected CLI/MCP layer, wired to your own LinkedIn session or provider key, hard-capped at 20 actions per day for new accounts.
  • No em-dashes. No guaranteed-result or "10x in a week" promises.

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