li-profile
Skill5 starsChanged 37 days agoMITView on GitHub
Score a LinkedIn profile out of 100 against a 12-part rubric and rewrite the parts that lose points - headline, about, experience, featured, banner. Use when the user says "optimize my profile", "score my LinkedIn", "rewrite my headline", "fix my about section", or pastes their profile and asks how it reads.
7 other projects use a version of this, 2 of them edited.
Adopted by
Most recently taken up by
- furkanbilalakyuz/linkedin-agent-skill-tredited, first seen Nov 8, 2026
- HemanthMChakravarthy/linkedin-agent-skillstheir own version, first seen Nov 8, 2026
- mubaid/dsh-linkedin-agentword for word, first seen Oct 25, 2026
- robbiehaynes/job-searchword for word, first seen Oct 20, 2026
- postzen-dev/linkedin-agent-skilledited, first seen Oct 15, 2026
- nessalazne/linkedin-agent-skillword for word, first seen Sep 19, 2026
Other versions7 projects use a version of this.
Word for word · 4
- Jakeschincariol/linkedin-agent-skill★ 514100% same
- nessalazne/linkedin-agent-skill★ 3100% same
- mubaid/dsh-linkedin-agent★ 0100% same
- robbiehaynes/job-search★ 0100% same
Edited · 2
- postzen-dev/linkedin-agent-skill★ 398% same
- furkanbilalakyuz/linkedin-agent-skill-tr★ 082% same
Wrote their own version · 1
- HemanthMChakravarthy/linkedin-agent-skills★ 2same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository10 other files it gives its agents.
- li-auditSkill
- li-carouselSkill
- li-commentSkill
- li-dmSkill
- li-humanSkill
- li-inboxSkill
- li-planSkill
- li-postSkill
- li-replySkill
- li-repurposeSkill
The file
We split this skill into the rules it gives an agent
2 rules. 1 is common, 0 are distinctive, and 1 is very specific to this project.
1
Common
Most of the 3 edited versions we read keep these.
0
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
- Common: line 19
Ask the user to paste: headline, about section, current role and the last two experience entries, plus whether they have a banner and …
- Very specific: line 26
Read rubric.json in this folder.
“Common” is measured: kept by at least 6 in 10 of the 3 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.
Files
li-profile
A profile is not a resume. A resume answers "what have you done". A profile answers "should I message this person", and it answers it in about four seconds, from the headline and the first two lines of the about.
Input
Ask the user to paste: headline, about section, current role and the last two experience entries, plus whether they have a banner and featured section. A screenshot of the top card is enough for the first pass. Do not log into LinkedIn on their behalf.
Score it
Read rubric.json in this folder. Twelve items, 100 points, each with what
full marks looks like. Score every item, show the table, and give the total.
Be honest - most profiles land in the 30s and 40s on the first pass, and a
generous score is useless.
PROFILE SCORE 41/100
headline 3/12 job title only, no outcome, no audience
about first 2 lines 2/10 opens with "passionate about"
about body 4/10 history, not offer
featured 0/8 empty
banner 0/6 default blue
...Then rewrite, in this order
Fix in descending order of points lost. Do not rewrite everything at once - the user has to actually paste each of these in.
1. Headline (220 characters). The formula that works:
{what you do for whom} | {proof} | {how to start}. Not your job title. Not
"Helping X do Y" as the first three words, which every second profile now
opens with. Give three options.
2. About, first two lines. Everything after line 2 is behind "see more" on mobile, so those two lines are the whole about section for most readers. They must state who you help and what changes. No "passionate", no "results-driven", no third-person bio, no opening with your own name.
3. About body. Written to one reader, in the second person. Structure: the problem they have, what you do about it, one piece of proof with a number, what to do next. Under 1,400 characters even though the limit is 2,600.
4. Featured. Three items: the best post, the proof asset, the way to contact. An empty featured section is eight points and the only place on the profile you fully control.
5. Experience. Each role gets one line of scope and two to three bullets that are outcomes with numbers, not duties. Cut anything older than ten years to a single line.
6. Banner. One sentence of positioning and one way to reach you. The default blue gradient is the clearest signal on the page that nobody is home.
Output
Score table, then the rewrites as copy-ready blocks in fix-first order, each
one already run through /li-human. Re-score at the end and show the delta
honestly - if the rewrite gets to 88 and not 98, say 88, and say what the
remaining points need (usually recommendations, a real banner and posting
history, none of which a rewrite can create).
Nothing is saved to LinkedIn by this skill. The user pastes each section in.
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.

