agentleFS
postoncehqpostoncehq/linkedin-mcp/skills/linkedin-profile-optimizer/SKILL.md

linkedin-profile-optimizer

Skill1 starsChanged 46 days agoMITView on GitHub

Rewrite the parts of a LinkedIn profile that decide whether people follow, hire or reply: About section, Featured items, banner copy and experience bullets. Use when the user asks for LinkedIn profile optimization, a LinkedIn summary or About section, a summary generator, experience bullets, banner text, or a LinkedIn profile review.

20 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use linkedin-comment-drafter, linkedin-content-planner and 9 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • sergebulaevSkill

    linkedin-comment-drafter

    Draft a LinkedIn comment on someone else's post from its URL, or reshare (repost) it to your feed with optional commentary. Use when the user pastes a post URL and asks to comment, engage, be first commenter, or repost with their thoughts. Produces 1-3 variants in the user's voice, picks a reaction, and publishes via Publora on approval. Not for replying to existing comments (use linkedin-reply-handler).

    Also in 7 projects that use this

  • sergebulaevSkill

    linkedin-content-planner

    Generate a 7-day LinkedIn content plan from a theme, audience, and pillars. Produces per-day post pillar, format, hook type, CTA, posting time, daily comment targets, and a weekly inbound-readiness check. Use when the user wants to plan a week or month of content, not draft a single post (use linkedin-post-writer).

    Also in 7 projects that use this

  • +9 more from sergebulaev

The file

We split this skill into the rules it gives an agent

3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 19 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never invent employers, dates, numbers or credentials.

    line 20
  2. Very specific:

    Use the linkedin-headline-generator skill (220 characters max).

    line 24
  3. Distinctive:

    If the environment can render HTML to PNG (for example headless Chrome or Playwright), build it as a 1584×396 HTML page and screenshot it.

    line 41

“Common” is measured: kept by at least 6 in 10 of the 19 edited versions of this file we could read. “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 profile optimizer

People check a profile after they see a post or a comment. The profile should tell them in seconds who this person helps and why to follow or reach out. Write the copy; the user pastes it into LinkedIn themselves. This server publishes posts; it can't read or edit profiles.

Inputs to get first

  • The goal: get hired (which role), win clients, build an audience, raise money, or hire.
  • The audience and the keywords they'd search.
  • Current profile text (ask the user to paste headline, About and recent roles).
  • Real proof: results, clients, projects, credentials, links to show off.

Never invent employers, dates, numbers or credentials.

Headline

Use the linkedin-headline-generator skill (220 characters max).

About section (up to 2,600 characters)

  • LinkedIn shows the first few lines before "see more", so open with who you help and what you do, not "I'm a passionate…".
  • Structure: what you do and for whom (2–3 lines), how you do it or what makes it different, 3–5 proof points, a clear next step ("Email me at…", "DM me about…", "Book a call: link").
  • Short paragraphs, first person, plain words. Include the keywords naturally.
  • Bullets with "•" are fine. Skip Unicode bold here; screen readers and LinkedIn search handle it poorly.

Featured section

Suggest 3–5 items in priority order: the best post (the user can publish one with linkedin-post-writer), a case study or portfolio link, a lead magnet or booking link, a talk or press mention. Give each a short title and a one-line description.

Banner copy

  • LinkedIn's recommended banner size is 1584×396 px. Keep text on the right two-thirds; the profile photo covers the lower left, and mobile crops the edges.
  • One line: what you do for whom, or a clear offer. Optional second line: proof or a URL.
  • If the environment can render HTML to PNG (for example headless Chrome or Playwright), build it as a 1584×396 HTML page and screenshot it. Otherwise give text and layout notes for a design tool.

Experience bullets

  • 3–5 bullets per role, newest roles in most detail.
  • Pattern: action verb, what you did, result or scope. For example: "Rebuilt onboarding emails; trial-to-paid rose from [X] to [Y]." Only real numbers; otherwise describe scope (team size, budget, markets).
  • One line of context under the title for small or unknown companies.

Output

Return each section ready to paste, with character counts for the headline and About section. List what to change first. Tell the user to paste each section into their LinkedIn profile. Offer to write a post that sends people to the updated profile, which can be published with the postonce skill.

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.