Skip to content
SkillModel-led1,328 tokens in use

linkedin-profile-optimizer

Audit nine parts of a LinkedIn profile against 2026 patterns and rewrite the headline, About, Featured and Experience for your goal.

6,078 stars on the repository MIT Licensesergebulaev/linkedin-skills · skills/linkedin-profile-optimizer
npx skills add sergebulaev/linkedin-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing linkedin-profile-optimizer costs

100tokens idle
1,328tokens in use
4,938tokens, 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 →
Excellent
  • Frontmatter15/15
  • Structure25/25
  • Examples6/15
  • Output15/15
  • 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 →
Excellent
  • Development activity96
  • Maintenance100
  • Community64
  • Maturity28
  • Momentum40

linkedin-profile-optimizer scores a pasted LinkedIn profile on nine components: photo, banner, headline, About, Featured, Experience, Skills, custom URL and recommendations. It returns a pass, fail or needs-work scorecard and ranks the fixes by impact.

It then writes before and after versions of each failing section, matched to your goal of winning clients, finding a job or building authority. It will not score a section you have not shown it.

What You Get

  • A nine-section scorecard with pass, fail or needs-work for each part
  • A ranked list of priority fixes
  • Before and after rewrites for the headline, About, Featured and Experience bullets
  • Draft recommendation requests that name a specific project or skill

Common Use Cases

  • Rewriting a resume-style profile before starting a content strategy
  • Tuning a founder profile for inbound leads
  • Preparing a profile for job seeking with a portfolio in Featured
  • Making the About hook fit before the see-more cut

What Makes It Unique

It states concrete pass criteria for every part, such as a 220 character headline format, an About hook inside the first 265 to 275 characters and Experience bullets built from an action verb plus a metric. Featured advice depends on whether your goal is clients, job seeking or authority. It refuses to infer profile content from a URL, since no tool reads profiles, and asks you to paste the text.

Under The Hood

This skill is instructions only. It reads five markdown reference files in its folder covering headline formulas, About templates, the Featured playbook, banner and photo specs and Experience and Skills rules. It works from the text and screenshots you give it in the conversation and writes the audit there. It does not run commands, call APIs, fetch web pages or write files.

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