Skip to content
SkillModel-led354 tokens in use

Content Repurposing

Turns social videos, transcripts, posts and creator research into LinkedIn posts, X threads, short-form scripts, newsletter ideas and content calendars.

6,856 stars on the repository MIT LicenseScrapeCreators/social-media-research-skills · skills/content-repurposing
npx skills add ScrapeCreators/social-media-research-skills
View source

Install command as written in the repository's README

Skill label

measured from its files

What installing Content Repurposing costs

52tokens idle
354tokens 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

shelldeclarednetworkdeclaredwrites filesdeclared

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 →
Excellent
  • Frontmatter15/15
  • Structure22/25
  • Examples9/15
  • 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 activity24
  • Maintenance8
  • Community40
  • Maturity24
  • Momentum40

Content Repurposing helps an agent convert source material into new content. It gathers URLs, transcripts or a research report, extracts content atoms such as hooks, stories, claims, frameworks and data points, and rewrites them for the user’s voice and the target platform.

It works best after the transcript, outlier and creator teardown skills in the same repository, and it can also start directly from URLs.

What You Get

  • A content pack listing the sources and a table of content atoms with the best format for each
  • LinkedIn post drafts and X thread drafts
  • Short-form scripts split into hook, body and CTA
  • Newsletter and blog ideas, plus content calendars built from winning ideas

Common Use Cases

  • Turning a TikTok or Reel into a LinkedIn post and an X thread
  • Repurposing a podcast or webinar transcript into a newsletter section
  • Adapting a competitor’s winning pattern into original scripts
  • Planning a content calendar from a research report

What Makes It Unique

It sits at the end of a research chain: it reuses the output of the transcript, outlier and teardown skills in the same repository. Its guardrails keep drafts original by adapting structure and insight, keep each platform’s native format, and preserve the original hook when it is the strongest part.

Under The Hood

The skill is one SKILL.md of instructions with no scripts. When started from URLs, the agent fetches transcripts and posts from the ScrapeCreators REST API using the SCRAPECREATORS_API_KEY environment variable, then writes the drafts itself. Its frontmatter allows the shell, file reading and writing, and web fetches, so the agent can run commands, make network calls and save the content pack to a file.

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