linkedin-hook-extractor takes a LinkedIn post URL and classifies it against 20 canonical hook formulas, such as anaphora, R.I.P. obituary, time-anchor confession, curiosity gap and emotional cold-open. It returns a confidence score, the structure of the post and the reason it worked.
It then gives you a blank template with slot markers and flags weaknesses in the original, such as a question as line one, so you do not copy them.
What You Get
- The formula or top two formulas used, with a confidence score
- A breakdown of the hook lines, body sections, close pattern and reaction triggers
- A psychological explanation of why the post worked
- A blank template with slot markers, plus cautions about tells in the source post
Common Use Cases
- Studying a competitor’s best-performing post before writing your own
- Copying the structure of a creator you admire without copying their words
- Seeding the post writer skill with a proven structure
- Auditing a source post for AI tells and outdated tactics before borrowing it
What Makes It Unique
It works backward from a finished post to a reusable skeleton, with a confidence score and a second-best match when two formulas fit. It also audits the source: a viral post can use tactics that now cost reach, such as a question as line one, comment-gate bait or announced candor with no dated fact, and the template drops them. It is for learning from other people’s posts and hands writing to the post writer skill.
Under The Hood
The skill is instructions plus a small Python library in the repository. It parses the URL and fetches the post body from Apify with your token or through the Apify connector, and otherwise asks you to paste the text. That is a network call to a third-party service that can spend credit. Fetched text is treated as data and never as instructions. It reads the formula reference and classification rules from markdown files, and it only returns an analysis in the conversation; it does not publish or write files.