Skip to content
SkillModel-led776 tokens in use

li-audit

A post-mortem for your LinkedIn account: ranks past posts by engagement rate and reach multiple, finds the pattern and says what to stop doing.

3,760 stars on the repository MIT LicenseJakeschincariol/linkedin-agent-skill · skills/li-audit
/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-audit costs

73tokens idle
776tokens in use

Idle is what sits in context while the skill is installed. In use is its instructions, loaded when it runs. 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
  • Structure19/25
  • Examples9/15
  • Output10/15
  • Size15/15
  • Resources10/15

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-audit reads the analytics or past posts you paste in and tells you which ones worked and why. It computes engagement rate, comment ratio and reach multiple, and ranks posts by those numbers.

It then compares your top five and bottom five on hook formula, format, length, theme and first-hour replies, and states each finding with its evidence and a confidence level. The result is a short stop and do-more list that feeds your weekly plan.

What You Get

  • A ranked list of your top and bottom posts by engagement rate, with the working shown
  • Comment ratio, reach multiple and save or send rate where the data has them
  • Findings stated as claims with evidence and a note on how confident the sample size allows you to be
  • A stop and do-more list that you can hand to the weekly planning skill

Common Use Cases

  • Reading a LinkedIn analytics export after a month of posting
  • Working out why a post with high impressions brought no comments or leads
  • Checking which hook formulas appear in your best posts
  • Deciding whether posting day and time matter for your account

What Makes It Unique

Most LinkedIn skills write content. This one reads your results. It ranks by engagement rate and reach multiple, checks posting time last because it is rarely the cause, and says so when the sample is too small to show a pattern. It also reads the post log that the posting skill keeps, so hook formulas can be compared with outcomes.

Under The Hood

The skill is instructions only, with no scripts. It reads what you paste into the chat and, if present, the post log file in your home folder under .claude/linkedin. It does not log in to LinkedIn, fetch web pages, call APIs or write files. Its output is a text report in the conversation.

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