linkedin-profile-auditor
Skill9 starsChanged 4 months agoMITView on GitHub
Audit the user's own LinkedIn profile as a conversion asset, scoring each element against the buyer who lands there after a post and rewriting the weakest one. Use to turn a passive profile into one that earns the follow, the connect, or the DM.
In this repository28 other files it gives its agents.
- linkedin-booking-closerSkill
- linkedin-carousel-writerSkill
- linkedin-cold-reviverSkill
- linkedin-comment-engineSkill
- linkedin-comment-warmerSkill
- linkedin-connection-noteSkill
- linkedin-content-calendarSkill
- linkedin-engage-planSkill
- linkedin-engager-analyticsSkill
- linkedin-first-dmSkill
- linkedin-followup-adapterSkill
- linkedin-hook-labSkill
- linkedin-humanizerSkill
- linkedin-icp-definerSkill
- linkedin-objection-handlerSkill
- linkedin-onboardSkill
- linkedin-outreachSkill
- linkedin-post-autopsySkill
- linkedin-post-writerSkill
- linkedin-reply-triagerSkill
- linkedin-repurposerSkill
- linkedin-sell-by-chatSkill
- linkedin-signal-stackSkill
- linkedin-story-minerSkill
- linkedin-strategistSkill
- linkedin-voice-profilerSkill
- linkedin-warm-list-builderSkill
- linkedin-warm-trackerSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
- Distinctive: line 31
No em-dashes. Use a comma, a period, or " - ".
≈ “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.
Files
LinkedIn Profile Auditor
Your profile is the page a curious decision-maker lands on the second your post earns their attention. Every element has one job: turn that curiosity into a follow, a connect, or a DM. This skill judges each element against that job and rewrites the weakest.
Inputs
- The user's profile: headline, about, banner description, featured section, recent activity: $ARGUMENTS
- The brief (positioning, voice, offer, pains, proof) loads automatically.
Do this
Score each element against the one job it has, then name the weakest and rewrite it.
- Headline. Does a buyer get what you do, for whom, with what outcome, in two seconds? Or is it a job title?
- Banner. Does it carry one proof point or one offer? Or is it a stock graphic doing nothing?
- About. Does it open with the operator story and a real outcome, then the offer? Or does it list duties and skills?
- Featured. Is the lead magnet pinned with visible proof, the same one your posts point to? Or is it empty or off-message?
- Activity. Does the recent feed prove the competence you sell? Or does it contradict the headline?
- Name the single weakest element and rewrite it in full. Then rewrite the headline and the about-opening regardless.
Output
An element-by-element scorecard (each element: score out of 10, the one-line verdict, the gap). Then a rewritten headline and a rewritten about-opening, both in the brief's voice. End with the single highest-impact fix to make first, and why it beats the others.
Rules
- The profile must prove the operator, not list duties. Outcomes and specifics, not adjectives.
- Positioning is Revenue Partner who uses AI to do the heavy lifting. Never "AI consultant", "AI Growth Partner", or "AI agency".
- Real numbers are fine, attribute to "a post" or "a client", never a named person or company.
- No em-dashes. Use a comma, a period, or " - ".
- One highest-impact fix at the end, not a list. If the about needs a full rewrite, run /linkedin-humanizer on the result before it goes live.
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
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.