Back to Skills

content-os

majiayu000
Updated Today
1 views
58
9
58
View on GitHub
Metadesign

About

Content OS is a master orchestrator skill that generates all content types from a single seed idea in forward mode or splits long-form content into short-form pieces in backward mode. It coordinates a pipeline of specialized skills for research, writing, quality review, and visual generation, applying full quality gates to long-form output and a quick accuracy pass to short-form content. Use it as a unified "produce everything" button for multi-format content creation workflows.

Quick Install

Claude Code

Recommended
Plugin CommandRecommended
/plugin add https://github.com/majiayu000/claude-skill-registry
Git CloneAlternative
git clone https://github.com/majiayu000/claude-skill-registry.git ~/.claude/skills/content-os

Copy and paste this command in Claude Code to install this skill

Documentation

Content OS: Multi-Format Content Orchestrator

The "produce everything" button. Give one seed idea → get all content types. Or give long-form content → get it split into short-form pieces.

Quick Start

Forward Mode (Seed → All Content)

User: "Content OS: Statins myth-busting for Indians"

Output:
├── Long-form (quality-passed)
│   ├── YouTube script (Hinglish)
│   ├── Newsletter (B2C - patients)
│   ├── Newsletter (B2B - doctors)
│   ├── Editorial
│   └── Blog post
├── Short-form (accuracy-checked)
│   ├── 5-10 tweets
│   ├── 1 thread
│   └── Carousel content
└── Visual
    ├── Instagram carousel slides
    └── Infographic concepts

Backward Mode (Long-form → Split)

User: "Content OS: [paste your blog/script/newsletter]"

Output:
├── 5-10 tweets (key points)
├── 1 thread (condensed narrative)
├── Carousel slides (visual summary)
└── Snippets (quotable sections)

How It Works

Mode Detection

  • Forward Mode: Input is a topic/idea (short text, question, or concept)
  • Backward Mode: Input is existing long-form content (>500 words)

Forward Mode Pipeline

PHASE 1: RESEARCH
│
├── PubMed MCP
│   └── Search for relevant papers, trials, guidelines
│
├── knowledge-pipeline (RAG)
│   └── Query AstraDB for ACC/ESC/ADA guidelines, textbooks
│
├── social-media-trends-research (optional)
│   └── Check trending angles, audience questions
│
└── OUTPUT: research-brief.md
    └── Synthesized knowledge with citations

PHASE 2: LONG-FORM CONTENT (Full Quality Pipeline)
│
├── youtube-script-master
│   └── Hinglish script → Quality Review → Final
│
├── cardiology-newsletter-writer
│   └── B2C newsletter → Quality Review → Final
│
├── medical-newsletter-writer
│   └── B2B newsletter → Quality Review → Final
│
├── cardiology-editorial
│   └── Editorial → Quality Review → Final
│
└── cardiology-writer
    └── Blog post → Quality Review → Final

PHASE 3: SHORT-FORM CONTENT (Quick Accuracy Pass)
│
├── x-post-creator-skill
│   └── 5-10 tweets → Accuracy Check → Final
│
├── twitter-longform-medical
│   └── Thread → Accuracy Check → Final
│
└── Extract carousel content from long-form

PHASE 4: VISUAL CONTENT
│
├── carousel-generator
│   └── Generate Instagram slides from key points
│
└── cardiology-visual-system
    └── Infographic concepts (if data-heavy)

PHASE 5: OUTPUT
│
└── Organized folder structure with all content

Backward Mode Pipeline

PHASE 1: ANALYZE
│
└── Parse long-form content
    ├── Extract key points
    ├── Identify data/statistics
    ├── Find quotable sections
    └── Determine topic/theme

PHASE 2: SPLIT (Quick Accuracy Pass)
│
├── Generate tweets (5-10)
│   └── One key point per tweet
│
├── Generate thread
│   └── Condensed narrative
│
├── Extract carousel content
│   └── Key points for slides
│
└── Create snippets
    └── Quotable sections

PHASE 3: VISUAL
│
└── carousel-generator
    └── Generate slides from extracted content

PHASE 4: OUTPUT
│
└── All short-form pieces organized

Quality Gates

Long-Form Quality Pipeline (FULL)

Each long-form piece goes through:

  1. scientific-critical-thinking

    • Evidence rigor check
    • Citation verification
    • Claim accuracy
    • Statistical interpretation
  2. peer-review

    • Methodology review
    • Logical consistency
    • Completeness check
    • Counter-argument consideration
  3. content-reflection

    • Pre-publish QA
    • Audience appropriateness
    • Clarity check
    • Structure review
  4. authentic-voice

    • Anti-AI pattern removal
    • Voice consistency
    • Natural language check

Short-Form Accuracy Pass (QUICK)

Each short-form piece gets:

  1. Data Interpretation Check
    • Are trial results stated correctly?
    • Are statistics accurately represented?
    • Is the study conclusion not misrepresented?
    • Are effect sizes/NNT/HR correctly stated?

This is a sanity check, not full review. User can iterate manually.

Skills Invoked

Research Skills

SkillPurpose
knowledge-pipelineRAG + PubMed synthesis
PubMed MCPDirect paper search
social-media-trends-researchTrending angles

Writing Skills

SkillContent TypeQuality Gate
youtube-script-masterYouTube script (Hinglish)Full
cardiology-newsletter-writerPatient newsletterFull
medical-newsletter-writerDoctor newsletterFull
cardiology-editorialEditorialFull
cardiology-writerBlog postFull
x-post-creator-skillTweetsQuick
twitter-longform-medicalThreadQuick

Quality Skills

SkillPurposeUsed For
scientific-critical-thinkingEvidence rigorLong-form
peer-reviewMethodology checkLong-form
content-reflectionPre-publish QALong-form
authentic-voiceAnti-AI cleanupLong-form

Visual Skills

SkillPurpose
carousel-generatorInstagram slides
cardiology-visual-systemInfographics

Repurposing Skills

SkillPurpose
cardiology-content-repurposerBackward mode splitting

Output Structure

/output/content-os/[topic-slug]/
├── research/
│   └── research-brief.md           # Foundation for all content
│
├── long-form/                       # Full quality pipeline
│   ├── youtube-script.md           ✓ Quality passed
│   ├── newsletter-b2c.md           ✓ Quality passed
│   ├── newsletter-b2b.md           ✓ Quality passed
│   ├── editorial.md                ✓ Quality passed
│   └── blog.md                     ✓ Quality passed
│
├── short-form/                      # Quick accuracy pass
│   ├── tweets.md                   ✓ Accuracy checked
│   ├── thread.md                   ✓ Accuracy checked
│   └── snippets.md                 ✓ Accuracy checked
│
├── visual/
│   ├── carousel/
│   │   └── slide-01.png...
│   └── infographic-concepts.md
│
└── summary.md                       # What was produced

Invocation Examples

Forward Mode

"Content OS: GLP-1 agonists cardiovascular benefits"
"Content OS: Statin myths for Indian patients"
"Content OS: When to get a CAC score"
"Content OS: SGLT2 inhibitors in heart failure"

Backward Mode

"Content OS: [paste your 2000-word blog post]"
"Content OS: [paste your YouTube script]"
"Content OS: [paste your newsletter]"

Configuration

What Gets Produced (Forward Mode)

Content TypeDefaultCan Skip
YouTube ScriptYesYes
Newsletter B2CYesYes
Newsletter B2BYesYes
EditorialYesYes
BlogYesYes
TweetsYesYes
ThreadYesYes
CarouselYesYes

Customization

"Content OS: Statins - only YouTube and tweets"
"Content OS: Heart failure - skip editorial"
"Content OS: CAC scoring - long-form only"

Integration with Existing System

Content OS orchestrates skills that already exist in your system. It doesn't replace them - it coordinates them.

You can still use individual skills directly:

  • youtube-script-master for just a script
  • x-post-creator-skill for just tweets
  • carousel-generator for just slides

Content OS is for when you want everything at once.

Notes

  • Long-form content takes longer due to quality pipeline
  • Short-form is faster (quick accuracy pass only)
  • Research phase runs once, shared by all content
  • Visual content generated from text output
  • All content uses same research foundation for consistency

Voice & Quality Standards

All content follows:

  • YouTube: Peter Attia depth + Hinglish (70% Hindi / 30% English)
  • Twitter/Writing: Eric Topol Ground Truths style
  • B2B (Doctors): JACC editorial voice
  • Anti-AI: No "It's important to note", no excessive hedging
  • Citations: Q1 journals, specific statistics, NNT/HR/CI when relevant

GitHub Repository

majiayu000/claude-skill-registry
Path: skills/content-os

Related Skills

content-collections

Meta

This skill provides a production-tested setup for Content Collections, a TypeScript-first tool that transforms Markdown/MDX files into type-safe data collections with Zod validation. Use it when building blogs, documentation sites, or content-heavy Vite + React applications to ensure type safety and automatic content validation. It covers everything from Vite plugin configuration and MDX compilation to deployment optimization and schema validation.

View skill

creating-opencode-plugins

Meta

This skill provides the structure and API specifications for creating OpenCode plugins that hook into 25+ event types like commands, files, and LSP operations. It offers implementation patterns for JavaScript/TypeScript modules that intercept and extend the AI assistant's lifecycle. Use it when you need to build event-driven plugins for monitoring, custom handling, or extending OpenCode's capabilities.

View skill

langchain

Meta

LangChain is a framework for building LLM applications using agents, chains, and RAG pipelines. It supports multiple LLM providers, offers 500+ integrations, and includes features like tool calling and memory management. Use it for rapid prototyping and deploying production systems like chatbots, autonomous agents, and question-answering services.

View skill

Algorithmic Art Generation

Meta

This skill helps developers create algorithmic art using p5.js, focusing on generative art, computational aesthetics, and interactive visualizations. It automatically activates for topics like "generative art" or "p5.js visualization" and guides you through creating unique algorithms with features like seeded randomness, flow fields, and particle systems. Use it when you need to build reproducible, code-driven artistic patterns.

View skill