li-profile
Skill2 starsChanged 43 days agoMITView on GitHub
Score the user's LinkedIn profile against a 12-part rubric out of 100, then rewrite every section in fix-first order. Use when the user asks for a profile review, "roast my profile", pastes their headline or about section, or wants their profile rewritten. Scores honestly; rewrites in the user's voice.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- furkanbilalakyuz/linkedin-agent-skill-trtheir own version, first seen Nov 8, 2026
- mubaid/dsh-linkedin-agenttheir own version, first seen Oct 25, 2026
- robbiehaynes/job-searchtheir own version, first seen Oct 20, 2026
- postzen-dev/linkedin-agent-skilltheir own version, first seen Oct 15, 2026
- avi691/linkedin-agent-skilltheir own version, first seen Oct 8, 2026
- nessalazne/linkedin-agent-skilltheir own version, first seen Sep 19, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- Jakeschincariol/linkedin-agent-skill★ 514same name
- avi691/linkedin-agent-skill★ 5same name
- nessalazne/linkedin-agent-skill★ 3same name
- postzen-dev/linkedin-agent-skill★ 3same name
- furkanbilalakyuz/linkedin-agent-skill-tr★ 0same name
- mubaid/dsh-linkedin-agent★ 0same name
- robbiehaynes/job-search★ 0same 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 repository12 other files it gives its agents.
- AGENTS.mdAGENTS.md
- li-auditSkill
- li-carouselSkill
- li-commentSkill
- li-dmSkill
- li-humanSkill
- li-inboxSkill
- li-planSkill
- li-postSkill
- li-replySkill
- li-repurposeSkill
- li-voiceSkill
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 2 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
2
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 25
Read rubric.json in this folder: the 12 parts, what each is worth, and what full marks look like.
- Very specific: line 77
Never invent employers, titles, metrics, or recommendations.
- Distinctive: line 79
Do not flatten the user's personality into corporate-safe mush.
- Distinctive: line 81
If the profile is for job-seeking vs.
“Common” is measured: kept by at least 6 in 10 of the 7 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 audit with a number on it. Scores first, because a score is what makes the rewrite order obvious, then rewrites in fix-first order: the section losing the most points gets rewritten first.
Before you score
- Load the voice profile (
li-voiceif missing). The rewrite must sound like the user, not like a resume service. - Get the profile: the user pastes their headline, about section, experience entries, and featured section, or describes them. Work with what you have; mark unscored sections as "not provided" rather than guessing.
- Read
rubric.jsonin this folder: the 12 parts, what each is worth, and what full marks look like.
The 12 parts
From rubric.json (weights included there):
- Headline - says who you help and how, not just your job title
- About - first two lines survive truncation; story, not CV
- Experience - outcomes with numbers, not duty lists
- Featured - proof, not decoration
- Banner - communicates in 3 seconds
- Profile photo - recognisable human, not a logo or a landscape
- Custom URL - clean slug, not the default alphanumeric string
- Skills - endorsed skills match what the headline claims
- Recommendations - recent, specific, from the right people
- Activity - posting and commenting cadence visible
- Creator mode / follow - followable, not connection-gated
- Contact info - reachable without friction
The loop
1. Score. Each part out of its rubric weight, total out of 100. Show the full scorecard. Be honest: most profiles land 40-60. A 90 you did not earn helps nobody.
2. Fix-first order. Rank the sections by points lost, not by page order. Rewrite starting with the biggest loss.
3. Rewrite. Each section rewritten in the user's voice:
- Headline: under 220 characters, keyword-rich, one clear promise.
- About: 200-260 words, first line a hook, no "passionate professional".
- Experience: bullets that start with verbs and end with numbers.
- Everything humanized: invoke the
li-humanskill on all rewritten copy.
4. The receipt. Show before/after for each rewritten section, side by side, so the user sees what changed and why.
PROFILE AUDIT
score: 52/100
biggest loss: About section (-14): reads as a CV, no hook, no audience
rewrote: headline, about, experience x2
humanizer: 4 artefacts stripped, human score 81 PASS5. Hands off the account. This skill produces copy. The user pastes it into LinkedIn themselves. Never ask for credentials; never offer to log in.
Rules
- Never invent employers, titles, metrics, or recommendations. If a number
is missing, write
{{your number}}and flag it. - Do not flatten the user's personality into corporate-safe mush. The rubric rewards specificity; the voice profile is the guardrail.
- If the profile is for job-seeking vs. lead-gen vs. authority-building, say which game you are optimizing for and ask if that is the right one before rewriting.
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.

