agentleFS
styfinitystyfinity/linkedin-engine/skills/linkedin-comment-warmer/SKILL.md

linkedin-comment-warmer

Skill9 starsChanged 4 months agoMITView on GitHub

Draft 2-3 genuine value-add comments on a specific target's recent posts to warm them before you connect. Use to get on a prospect's radar ahead of an outreach connect.

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:

    Read each pasted post. Find the one real thing in it worth responding to: a claim to extend, a tension to name, a question they left open.

    line 16
  2. Distinctive:

    Write 2-3 comments, one per post, each adding a single genuine insight in your voice.

    line 17
  3. Distinctive:

    No pitch and no link inside a comment.

    line 26
  4. Distinctive:

    No em-dashes, no exclamation marks.

    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 Comment Warmer

Warming before connecting. This skill drafts real, value-add comments on a target's recent posts so your name and face register before you ever send the request.

Inputs

  • The target (name, role) and a paste of their recent post(s): $ARGUMENTS
  • The brief (your voice profile, the offer, the buyer's pains) loads automatically.

Do this

  1. Read each pasted post. Find the one real thing in it worth responding to: a claim to extend, a tension to name, a question they left open.
  2. Write 2-3 comments, one per post, each adding a single genuine insight in your voice. No pitch, no link, no "great post".
  3. Make each comment stand on its own as something a peer would say. Reference a specific line from their post.
  4. Sequence them so they read as authentic engagement over days, not a blitz: one comment, wait, then the next.

Output

2-3 ready comments, each tagged to the post it belongs on (Post 1, Post 2, Post 3). End with a one-line spacing note: leave a day or two between comments, never all in one sitting.

Rules

  • Real value only. One actual insight per comment. Never flattery, never "love this", never a thinly veiled pitch.
  • No pitch and no link inside a comment. The comment earns the recognition; the connect comes later.
  • Space them out. A blitz of comments in one hour reads as a tactic, not a person.
  • No em-dashes, no exclamation marks.
  • Draft only. Claude drafts, the operator reads each comment and posts it themselves. Posting comments is manual here, not the send layer.
  • Once they have engaged back or you have commented 2-3 times, hand the connect to /linkedin-connection-note and run /linkedin-humanizer on the draft before sending.

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.