Skip to content
SkillModel-led721 tokens in use

li-profile

Scores your LinkedIn profile out of 100 on a 12-part rubric and rewrites the parts that lost points, starting with the biggest losses.

3,760 stars on the repository MIT LicenseJakeschincariol/linkedin-agent-skill · skills/li-profile
/plugin marketplace add Jakeschincariol/linkedin-agent-skill /plugin install linkedin-agent
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing li-profile costs

73tokens idle
721tokens in use
1,364tokens, up to

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. Up to adds the files its instructions link. Counts are approximate, made offline with cl100k_base.

Model dependence Model-led

Script-ledMixedModel-led

Mostly instructions, so how well it works depends on the model that follows them.

This describes the skill's structure, how much of it is scripts. It does not say how well it works.

Touches

Nothing detected: no shell, network, file writes, git or credentials in its files.

Declared tags come from the skill's frontmatter; detected ones from its scripts, its code blocks and the commands it names in inline code. This is detected, not audited.

How it scores

Quality

How well the skill is written, counted from its own files: its frontmatter, its steps, examples, stated output and constraints, its size and whether every file it ships is one it names.How we score it →
Good
  • Frontmatter12/15
  • Structure8/25
  • Examples6/15
  • Output10/15
  • Size15/15
  • Resources15/15

Security

Starts at 100 and loses points for each thing in the skill's files that a reader should look at first.How we score it →
Excellent

No findings.

Repository health

Pre-computed score based on development activity, maintenance, community, maturity, and trend momentum.How we score it →
Needs attention
  • Development activity28
  • Maintenance4
  • Community52
  • Maturity16
  • Momentum40

li-profile reads the headline, about section, recent roles and featured and banner details you paste in, and scores them against a 12-item rubric worth 100 points. It shows the table with a note for each item and the total.

It then rewrites in descending order of points lost: headline in three options, the first two lines of the about section, the about body, featured items, experience bullets and the banner. Each rewrite is humanized and you paste it in yourself. A final re-score shows the delta.

What You Get

  • A score table out of 100 with a one-line note on each of the twelve items
  • Three headline options using the formula of what you do for whom, proof and how to start
  • Rewrites of the about opening, about body, featured section, experience bullets and banner line
  • A re-score at the end, with the remaining points explained when some cannot come from a rewrite

Common Use Cases

  • Rewriting a headline that only states a job title
  • Replacing an about section that opens with passion and a third-person bio
  • Choosing what to put in the featured section
  • Checking how a profile reads before a job search or outreach push

What Makes It Unique

The scoring comes from a rubric file with full-marks definitions for each item, covering headline, about, featured, banner, photo, roles, skills, recommendations, activity and contact. It scores strictly, expecting first passes in the 30s and 40s, and it reports what a rewrite cannot create, such as recommendations and posting history.

Under The Hood

The skill reads rubric.json in its folder and works from the profile text or top-card screenshot that you paste. It does not log in to LinkedIn, fetch web pages, call APIs, run commands or write files. The rewrites are shown in the chat and passed through the humanizer skill, and you paste them into your profile yourself.

Join founders building with open source

Opinionated takes, migration guides, cost-saving tips, and insights from the open source ecosystem.

Subscribe on SubstackJoin 750+ subscribers