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.