Skip to content
SkillModel-led596 tokens in use

li-repurpose

Turns one long asset such as a video, podcast, newsletter or call transcript into a week of LinkedIn posts that each stand alone.

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

72tokens idle
596tokens 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
  • Structure8/25
  • Examples6/15
  • 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-repurpose reads a whole long asset before it extracts anything. It pulls out claims, numbers, stories, mechanisms, mistakes and quotable lines, lists what it found with counts, and tells you if the asset is too thin for four posts.

It then builds a week: each extract becomes one post that makes sense without the source, each gets a different hook formula, and the order puts the strongest claim first. It drafts one post at a time on request.

What You Get

  • A count of what the asset contains: claims, numbers, stories, mechanisms, mistakes and quotable lines
  • A week schedule with one post per extract, a different hook formula for each and the strongest claim first
  • A warning when the asset is thin and cannot support four posts
  • Single drafts on request, each written through the post skill and the humanizer

Common Use Cases

  • Turning a YouTube video into posts for the week
  • Mining a podcast transcript for stories and numbers
  • Reusing a newsletter issue as separate LinkedIn posts
  • Pulling post material out of a recorded client call

What Makes It Unique

It extracts the standalone pieces of an asset and leaves summaries out. Each post has to work for a reader who has never seen the source, so none points back to your latest video. It varies the hook shape across posts to avoid the look of a content mill, and drafts one post at a time so they do not all sound the same.

Under The Hood

The skill is instructions only, with no scripts. It reads the text you paste, or a transcript fetched by a transcript tool when your session has one and you give a YouTube URL. It hands the drafts to the post skill and the humanizer skill. It does not write files or post to LinkedIn.

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