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

linkedin-comment-engine

Skill9 starsChanged 4 months agoMITView on GitHub

Draft two authority-building comments to leave on someone else's post, warming through visibility instead of DMs. Use when you want a decision-maker to notice you and click your profile.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    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 two comment variants the user can pick from:

    line 16
  2. Distinctive:

    Add ONE genuine thing. Either a specific insight, a build detail, or a number from real work (attribute to "a post" or "a client", never a …

    line 17
  3. Distinctive:

    Leave a soft hook at the end that earns a profile click: a half-told result, a "here is what most miss", or a question that signals you …

    line 19
  4. Distinctive:

    Never pitch in a comment. Never argue to win.

    line 26
  5. Distinctive:

    Add value the author would thank you for, even if they never reply.

    line 27
  6. Distinctive:

    No em-dashes, no exclamation marks, no "great post", no "thanks for sharing".

    line 29

≈ “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 Engine

Warming starts in the comments, not the inbox. This skill writes comments that add real value to someone else's post and quietly pull profile views from the people watching.

Inputs

  • The post you want to comment on (paste the full text) and the author's relevance to your ICP (a buyer, a peer, a connector, an audience overlap): $ARGUMENTS
  • The brief (persona tone, pains, offer, voice) loads automatically.

Do this

Write two comment variants the user can pick from:

  1. Add ONE genuine thing. Either a specific insight, a build detail, or a number from real work (attribute to "a post" or "a client", never a named entity). Not "great post", not generic praise.
  2. Agree-then-extend, or respectfully reframe. Build on the author's point with a second-order observation, or offer a sharper angle without making them wrong.
  3. Leave a soft hook at the end that earns a profile click: a half-told result, a "here is what most miss", or a question that signals you operate in their world. No pitch, no link.
  4. Variant A is short and punchy (one or two lines). Variant B is a longer mini-teaching comment (three to five lines) that demonstrates competence.

Output

Two labelled comment variants (A short, B mini-teaching) plus a one-line note on which to use when: A for high-traffic posts where brevity wins attention, B when the author is a direct ICP and you want them to read your whole profile.

Rules

  • Never pitch in a comment. Never argue to win. The job is to make a decision-maker click your profile, not to score a point.
  • Add value the author would thank you for, even if they never reply.
  • Anonymise all proof: keep the numbers, drop the names.
  • No em-dashes, no exclamation marks, no "great post", no "thanks for sharing".
  • Draft only. Claude drafts, the operator reads and posts. When a reply comes back warm, hand it to /linkedin-reply-triager. Run /linkedin-humanizer on either variant if it reads stiff.

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.