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
- Kianzzz/Zhouxing-skill-publictheir own version, first seen Nov 8, 2026
- LazyIsEfficient/agentic-ostheir own version, first seen Oct 22, 2026
- claude-world/claude-world-studiotheir own version, first seen Oct 22, 2026
- Aravind7262/content-pipelinetheir own version, first seen Oct 20, 2026
- runxhq/runxtheir own version, first seen Oct 13, 2026
- JingHao-Leon/fde-case-labtheir own version, first seen Sep 13, 2026
Other versions17 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 17
- OrangeViolin/content-pipeline★ 217same name
- fivetaku/content-pipeline★ 100same name
- runxhq/runx★ 97same name
- claude-world/claude-world-studio★ 71same name
- coopersimson96/ai-content-system★ 17same name
- LazyIsEfficient/agentic-os★ 17same name
- zad111ak-ai/hermes-agent-skills★ 7same name
- Kianzzz/Zhouxing-skill-public★ 4same name
- PingPingE/ai-content-agents★ 2same name
- rami-maalouf/skills★ 2same name
7 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository24 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- analystSkill
- build-appSkill
- build-websiteSkill
- business-setupSkill
- content-writerSkill
- email-assistantSkill
- email-digestSkill
- ksuite-setupSkill
- meeting-prepSkill
- memorySkill
- odooSkill
- plugin-builderSkill
- qfieldcloudSkill
- qgisSkill
- quarto-slidesSkill
- research-leadSkill
- researchSkill
- r-sessionSkill
- schedulerSkill
- scrum-masterSkill
- skill-creatorSkill
- task-managerSkill
- weekly-reviewSkill
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
- Very specific: line 19
All content written in the user's voice using context/my-voice.md.
- Distinctive: line 31
If given a YouTube URL, extract the transcript:
- Distinctive: line 48
Avoid anti-patterns listed in the voice guide
- Distinctive: line 98
ALWAYS read the voice guide before writing
- Distinctive: line 99
Never use generic AI phrases (see content-writer skill for anti-patterns)
- Distinctive: line 101
Don't just summarize the video — extract insights that work as independent content
“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.
Files
Content Pipeline
Transform YouTube transcripts into LinkedIn posts and carousel PDFs.
Objective
Take a YouTube video transcript and produce:
- 3-5 LinkedIn text posts (different angles/formats)
- 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 URLthen 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 postscarousel-1.md— Carousel slide contentcarousel-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
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
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.

