agentsclimarketplace

Linkedin profile

Skill protosphinx/sphinxstack/skills/linkedin-profile

A stack of skills for your AI agent, made for people starting from zero. 103 skills and 149 project briefs — load one into Codex, Claude Code, Copilot, Gemini, or Cursor and do the thing.

Install
npx -y skills add protosphinx/sphinxstack --skill linkedin-profile

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

2 things to look at

  • 17 days oldThe repository was created 17 days ago. New is not bad, but a brand new repository carrying a familiar-sounding name is the shape a typosquat arrives in, and there has been no time for anyone else to find a problem with it.
  • 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Make the LinkedIn profile match the resume. Headline, about section, and experience entries, nothing padded. Use when they say "fix my LinkedIn", "set up LinkedIn", or a recruiter will see their profile.

SKILL.md

2.7 KB, 575 tokens by cl100k_base, as published. Nobody here has run it

linkedin-profile

Help someone set up or repair their LinkedIn profile. The profile is the resume a recruiter finds without asking, so the bar is the same: every entry true, consistent with the resume, and short enough that the real material is visible. You draft field by field with them; they paste each one in and confirm it saved.

Ground rules

  • The resume is the source of truth. If they have none, run build-resume first — writing a profile from scratch invents.
  • Nothing padded. No inflated titles ("Founder" of a two-person study group), no skill endorsement farming, no buzzword about section. A short profile that checks out beats a long one that does not.
  • You cannot log in for them and must not handle their password. They drive the browser; you draft text and check results by asking them to read back what the section shows.
  • Work section by section at doing-speed — the whole profile is one sitting.

Section pass

  1. Headline: what they are and what they are looking for, in plain words. "CS student at Lincoln High building web apps — seeking summer internship" beats any pipe-separated slogan.
  2. About: three or four sentences, first person, in their words. Ask what they would tell a stranger at the job itself; that answer, tightened, is the about section. They approve every sentence.
  3. Experience: one entry per resume job or project, same dates, same facts, same links. LinkedIn allows projects under Experience or Projects — put anything with a live link where a recruiter will actually see it. Where entries disagree with the resume, the resume wins or gets corrected; the two must match because interviewers compare them.
  4. Education, skills, photo: school and dates as on the resume; skills limited to what the profile itself evidences; a plain, recent photo of their face if they have one, no photo over a bad one.
  5. Housekeeping: custom URL (their name, no digits if free), profile set to visible, resume PDF not uploaded unless they want it public.

Done

  • Headline, about, experience, and education filled in and saved — they confirmed each on screen
  • Profile and resume tell the same story, date for date
  • Custom URL claimed and added to the resume header
  • Nothing on the profile they could not say to an interviewer

If the experience section came up thin, that is a resume problem inventing a professional persona — point at build-resume's "thin resume" path and the skills at https://sphinxstack.com/skills/.

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.