agentleFS
pobstetapobsteta/aigora/.claude/skills/content-pipeline/SKILL.md

content-pipeline

Skill0 starsChanged 45 days agoMITView on GitHub

Automated LinkedIn content creation pipeline. YouTube transcript to LinkedIn posts and carousel PDFs. Run with /content-pipeline or ask to run the LinkedIn pipeline.

  • Installs packages

17 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 5 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 11 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    All content written in the user's voice using context/my-voice.md.

    line 19
  2. Distinctive:

    If given a YouTube URL, extract the transcript:

    line 31
  3. Distinctive:

    Avoid anti-patterns listed in the voice guide

    line 48
  4. Distinctive:

    ALWAYS read the voice guide before writing

    line 98
  5. Distinctive:

    Never use generic AI phrases (see content-writer skill for anti-patterns)

    line 99
  6. Distinctive:

    Don't just summarize the video — extract insights that work as independent content

    line 101

“Common” is measured: kept by at least 6 in 10 of the 11 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Content Pipeline

Transform YouTube transcripts into LinkedIn posts and carousel PDFs.

Objective

Take a YouTube video transcript and produce:

  1. 3-5 LinkedIn text posts (different angles/formats)
  2. 1-2 carousel PDFs (slide-based visual content)

All content written in the user's voice using context/my-voice.md.

Inputs Required

  • YouTube video URL or transcript text
  • context/my-voice.md (voice guide — MANDATORY)
  • context/my-business.md (business context)

Execution Steps

Step 1: Get Transcript

If given a YouTube URL, extract the transcript:

  • With the open-source tool yt-dlp (pip install yt-dlp): yt-dlp --skip-download --write-auto-subs --sub-langs fr,en --sub-format vtt -o .tmp/content-pipeline/%(id)s URL then clean the .vtt into plain text
  • Or ask user to paste the transcript

Step 2: Chunk and Analyze

Break the transcript into key themes/segments:

  • Identify 3-5 distinct insights or stories
  • For each, note: the core idea, supporting example, lesson/takeaway
  • Rank by LinkedIn engagement potential (controversial > practical > inspirational)

Step 3: Read Voice Guide

MANDATORY — Read context/my-voice.md before writing anything.

  • Match the user's tone, phrases, and style
  • Avoid anti-patterns listed in the voice guide

Step 4: Write LinkedIn Posts

For each insight, write a post in one of these formats:

Story Post (~800-1200 chars)

  • Hook (first line — must stop the scroll)
  • Story/example from the video
  • Lesson/insight
  • CTA or question

Insight Post (~400-600 chars)

  • Bold statement or contrarian take
  • 3-5 supporting points
  • Punchline

List Post (~600-800 chars)

  • "X things I learned about [topic]:"
  • Numbered list with one-line items
  • Closing thought

Step 5: Create Carousel Content

For the best 1-2 insights, create carousel slide content:

  • Slide 1: Hook/title (large text, minimal)
  • Slides 2-8: One point per slide (key phrase + supporting sentence)
  • Last slide: Summary + CTA

Output as markdown, or as a Quarto document (quarto-slides skill) rendered to PDF for LinkedIn carousels.

Step 6: Quality Check

For each piece of content:

  • Does it sound like the user (not AI)?
  • Is the hook strong enough to stop scrolling?
  • Is there a clear takeaway?
  • Is it the right length for the format?
  • Would the user actually post this?

Step 7: Save Output

Save all content to .tmp/content-pipeline/[date]/:

  • posts.md — All LinkedIn posts
  • carousel-1.md — Carousel slide content
  • carousel-2.md — Second carousel (if created)

Rules

  • ALWAYS read the voice guide before writing
  • Never use generic AI phrases (see content-writer skill for anti-patterns)
  • Each post should be a complete, standalone piece
  • Don't just summarize the video — extract insights that work as independent content
  • Carousels need visual hierarchy: big text for key phrases, small text for supporting points

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.