agentleFS
HemanthMChakravarthyHemanthMChakravarthy/linkedin-agent-skills/skills/li-profile/SKILL.md

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

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
  1. Very specific:

    Read rubric.json in this folder: the 12 parts, what each is worth, and what full marks look like.

    line 25
  2. Very specific:

    Never invent employers, titles, metrics, or recommendations.

    line 77
  3. Distinctive:

    Do not flatten the user's personality into corporate-safe mush.

    line 79
  4. Distinctive:

    If the profile is for job-seeking vs.

    line 81

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

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

  1. Load the voice profile (li-voice if missing). The rewrite must sound like the user, not like a resume service.
  2. 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.
  3. Read rubric.json in this folder: the 12 parts, what each is worth, and what full marks look like.

The 12 parts

From rubric.json (weights included there):

  1. Headline - says who you help and how, not just your job title
  2. About - first two lines survive truncation; story, not CV
  3. Experience - outcomes with numbers, not duty lists
  4. Featured - proof, not decoration
  5. Banner - communicates in 3 seconds
  6. Profile photo - recognisable human, not a logo or a landscape
  7. Custom URL - clean slug, not the default alphanumeric string
  8. Skills - endorsed skills match what the headline claims
  9. Recommendations - recent, specific, from the right people
  10. Activity - posting and commenting cadence visible
  11. Creator mode / follow - followable, not connection-gated
  12. 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-human skill 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 PASS

5. 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.

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.