Skip to content
SkillModel-led1,054 tokens in use

linkedin-hook-extractor

Reverse-engineer the hook behind a viral LinkedIn post: which of 20 formulas it uses, why it worked, and a blank template for your own topic.

6,078 stars on the repository MIT Licensesergebulaev/linkedin-skills · skills/linkedin-hook-extractor
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-hook-extractor costs

101tokens idle
1,054tokens in use
2,229tokens, 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
  • Frontmatter11/15
  • Structure25/25
  • Examples6/15
  • Output10/15
  • Size10/15
  • 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-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.

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