Skip to content
SkillModel-led1,458 tokens in use

linkedin-repurposer

Rebuild a tweet, thread, video, blog post or newsletter as a native LinkedIn post with a new hook, the right length and links moved to the first comment.

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

108tokens idle
1,458tokens 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
  • Frontmatter11/15
  • Structure19/25
  • Examples3/15
  • Output10/15
  • Size10/15
  • 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 →
Excellent
  • Development activity96
  • Maintenance100
  • Community64
  • Maturity28
  • Momentum40

linkedin-repurposer takes content you already made and rebuilds it for LinkedIn. It pulls the one claim, story or number worth keeping, writes a new hook that lands before the see-more fold and expands the idea to the 900 to 1300 character range with short paragraphs.

It removes artifacts from the source platform, moves links to the first comment, runs a humanizer pass and publishes through Publora only after you approve.

What You Get

  • A LinkedIn post rebuilt from your source with the original claim and numbers intact
  • An approval card that maps source elements to the new post and states the formula used
  • A note on which link goes into the first comment
  • A suggested posting window and character count

Common Use Cases

  • Adapting a tweet that did well on X into a longer LinkedIn post
  • Unrolling an X thread into one flowing post
  • Leading with the payoff of a YouTube video and linking it in a comment
  • Pulling the most quotable claim from a newsletter issue

What Makes It Unique

It has native-fit rules for each source type: a tweet is a hook to expand, a thread is unrolled into prose, a video leads with its payoff and a blog post contributes one claim and one proving story, with no full summary. It refuses copy-paste with light edits, strips artifacts such as link in bio and hashtag walls, and keeps the source’s facts and numbers unchanged.

Under The Hood

The skill is instructions plus a small Python library in the repository. It reads the hook formula and algorithm reference files and your voice profile and story bank when filled in. On your approval it calls the Publora API with your API key to publish or schedule the post, and it can cancel a queued post. That is a network call to a third-party service, and nothing is sent before you approve 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