Skip to main content Skills Marketplace Découvrez et explorez les compétences IA créées par la communauté.
Installer avec Codex ou Claude Copiez ce prompt, collez-le dans Codex, Claude ou un autre assistant, puis laissez-le vérifier la page du skill et l'installer pour vous.
Afficher les détails du prompt Une commande directe contourne le prompt de vérification. Examinez la source avant de l'exécuter.
npx skills add https://github.com/Aradotso/marketing-skills --skill marketing-pipeline-ai-content-automationLa commande reste sur une seule ligne. Faites défiler horizontalement pour la vérifier avant de la copier.
Vous préférez une copie locale ? Téléchargez les fichiers actuellement disponibles dans SkillsMP.
Télécharger Zip Téléchargement... Métiers associés SOC
Basé sur la classification professionnelle SOC
name marketing-pipeline-ai-content-automation description Automate end-to-end content creation from research to video generation using AI (Claude/OpenAI) and Remotion triggers ["how do I automate content creation with AI","set up an AI content pipeline for marketing","generate blog posts and videos automatically","use Claude and OpenAI for content automation","create automated content workflow with research","build AI-powered marketing content system","automate video generation from written content","set up content automation with Remotion"]
Marketing Pipeline AI Content Automation
Skill by ara.so — Marketing Skills collection.
Overview
Marketing Pipeline is a comprehensive TypeScript-based content automation system that creates a complete content production pipeline. It automatically:
Research - Scrapes and analyzes real-time data from sources like TechCrunch, a16z, Twitter, and LinkedInContent Generation - Uses Claude 3 and OpenAI to create content in multiple formats (Top lists, POV, Case Studies, How-to)Multi-language Output - Generates content in both English and Vietnamese with customizable toneVideo Rendering - Automatically converts content to videos and infographics using Remotion
Installation
Prerequisites
node >= 18.0.0
npm >= 9.0.0
Setup
git clone https://github.com/pennydinh/marketing-pineline-share.git
cd
cp
env
Environment Configuration Create a .env file with the following variables:
ANTHROPIC_API_KEY=your_claude_api_key_here
OPENAI_API_KEY=your_openai_api_key_here
RAPIDAPI_KEY=your_rapidapi_key_here
TWITTER_BEARER_TOKEN=your_twitter_bearer_token_here
DATABASE_URL=your_database_url_here
REMOTION_AWS_ACCESS_KEY_ID=your_aws_access_key_here
REMOTION_AWS_SECRET_ACCESS_KEY=your_aws_secret_key_here
Key Architecture
Project Structure marketing-pipeline-share/
├── src/
│ ├── research/ # Web scraping and data collection
│ ├── ai/ # AI content generation (Claude/OpenAI)
│ ├── video/ # Remotion video rendering
│ ├── utils/ # Shared utilities
│ └── app/ # Next.js application
├── remotion/ # Remotion video templates
└── public/ # Static assets
Core Workflows
1. Research & Data Collection
Scraping Recent Content import { ResearchEngine } from './src/research/engine' ;
const researcher = new ResearchEngine ({
sources : ['techcrunch' , 'a16z' , 'twitter' , 'linkedin' ],
timeframe : '24h' ,
keywords : ['AI' , 'marketing automation' ]
});
const insights = await researcher.gather ();
console .log (insights);
Custom Source Configuration import { SourceConfig } from './src/research/types' ;
const customSource : SourceConfig = {
name : 'custom-blog' ,
url : 'https://example.com/blog' ,
selectors : {
title : '.post-title' ,
content : '.post-content' ,
date : '.post-date'
},
rateLimit : 1000
};
const researcher = new ResearchEngine ({
customSources : [customSource]
});
2. AI Content Generation
Using Claude for Content Creation import { ClaudeContentGenerator } from './src/ai/claude' ;
const generator = new ClaudeContentGenerator ({
apiKey : process.env .ANTHROPIC_API_KEY ,
model : 'claude-3-opus-20240229'
});
const content = await generator.create ({
research : insights,
format : 'toplist' ,
language : 'en' ,
tone : 'professional' ,
targetAudience : 'marketers' ,
wordCount : 1500
});
console .log (content);
OpenAI Integration import { OpenAIContentGenerator } from './src/ai/openai' ;
const openaiGen = new OpenAIContentGenerator ({
apiKey : process.env .OPENAI_API_KEY ,
model : 'gpt-4-turbo-preview'
});
const variations = await openaiGen.createVariations ({
baseContent : content,
formats : ['how-to' , 'case-study' , 'pov' ],
count : 3
});
Multi-language Generation import { MultiLanguageGenerator } from './src/ai/multilang' ;
const mlGenerator = new MultiLanguageGenerator ({
claudeKey : process.env .ANTHROPIC_API_KEY ,
openaiKey : process.env .OPENAI_API_KEY
});
const bilingualContent = await mlGenerator.generateParallel ({
research : insights,
languages : ['en' , 'vi' ],
format : 'toplist' ,
maintainTone : true
});
console .log (bilingualContent.en .title );
console .log (bilingualContent.vi .title );
3. Video Generation with Remotion
Basic Video Rendering import { bundle } from '@remotion/bundler' ;
import { renderMedia, selectComposition } from '@remotion/renderer' ;
import { ContentToVideoConverter } from './src/video/converter' ;
const converter = new ContentToVideoConverter ();
const videoProps = converter.transform (content);
const bundled = await bundle ({
entryPoint : './remotion/index.ts' ,
webpackOverride : (config ) => config
});
const composition = await selectComposition ({
serveUrl : bundled,
id : 'ContentVideo' ,
inputProps : videoProps
});
await renderMedia ({
composition,
serveUrl : bundled,
codec : 'h264' ,
outputLocation : `out/${content.title} .mp4` ,
inputProps : videoProps
});
Custom Video Template
import { AbsoluteFill , useCurrentFrame, useVideoConfig } from 'remotion' ;
export const ContentVideo : React .FC <{
title : string ;
points : string [];
branding : BrandConfig ;
}> = ({ title, points, branding } ) => {
const frame = useCurrentFrame ();
const { fps } = useVideoConfig ();
return (
<AbsoluteFill style ={{ backgroundColor: branding.bgColor }}>
<div style ={{ padding: 60 }}>
<h1 style ={{
fontSize: 60 ,
color: branding.textColor ,
opacity: Math.min (1 , frame / 30 )
}}>
{title}
</h1 >
{points.map((point, idx) => (
<p
key ={idx}
style ={{
fontSize: 40 ,
opacity: frame > (idx + 1) * fps ? 1 : 0,
transition: 'opacity 0.5s'
}}
>
{point}
</p >
))}
</div >
</AbsoluteFill >
Platform-Specific Export import { PlatformOptimizer } from './src/video/optimizer' ;
const optimizer = new PlatformOptimizer ();
const platforms = ['tiktok' , 'reels' , 'shorts' ];
for (const platform of platforms) {
const config = optimizer.getConfig (platform);
await renderMedia ({
composition,
serveUrl : bundled,
codec : 'h264' ,
outputLocation : `out/${platform} /${content.title} .mp4` ,
inputProps : videoProps,
width : config.width ,
height : config.height ,
fps : config.fps
});
}
4. Complete Pipeline Automation import { ContentPipeline } from './src/pipeline' ;
const pipeline = new ContentPipeline ({
research : {
sources : ['techcrunch' , 'a16z' ],
timeframe : '24h'
},
ai : {
provider : 'claude' ,
apiKey : process.env .ANTHROPIC_API_KEY ,
fallbackProvider : 'openai' ,
fallbackKey : process.env .OPENAI_API_KEY
},
video : {
enabled : true ,
platforms : ['tiktok' , 'reels' , 'shorts' ]
},
output : {
directory : './output' ,
formats : ['markdown' , 'html' , 'json' ]
}
});
const results = await pipeline.execute ({
keyword : 'AI marketing automation' ,
contentFormats : ['toplist' , 'how-to' ],
languages : ['en' , 'vi' ],
generateVideos : true
});
console .log (results);
API Reference
ResearchEngine class ResearchEngine {
constructor (config : ResearchConfig gather (): Promise <ResearchInsights >;
addSource (source : SourceConfig ): void ;
setTimeframe (timeframe : string ): void ;
}
ClaudeContentGenerator class ClaudeContentGenerator {
constructor (config : ClaudeConfig create (params : ContentParams ): Promise <GeneratedContent >;
refine (content : string , instructions : string ): Promise <string >;
}
ContentPipeline class ContentPipeline {
constructor (config : PipelineConfig execute (params : ExecutionParams ): Promise <PipelineResults >;
schedule (params : ScheduleParams ): Promise <void >;
}
Common Patterns
Pattern 1: Daily Content Automation import cron from 'node-cron' ;
cron.schedule ('0 6 * * *' , async () => {
const pipeline = new ContentPipeline (defaultConfig);
const results = await pipeline.execute ({
keyword : 'trending tech news' ,
contentFormats : ['toplist' ],
languages : ['en' ],
generateVideos : true
});
await publishToWordPress (results.content [0 ]);
await uploadToYouTube (results.videos [0 ]);
});
Pattern 2: Multi-Topic Content Generation const topics = [
'AI marketing trends' ,
'Social media automation' ,
'Content creation tools'
];
const batchResults = await Promise .all (
topics.map (topic =>execute ({
keyword : topic,
contentFormats : ['how-to' ],
languages : ['en' , 'vi' ]
})
)
);
Pattern 3: Custom AI Prompt Engineering import { PromptTemplate } from './src/ai/prompts' ;
const customTemplate = new PromptTemplate ({
system : `You are an expert marketing content writer specializing in ${industry} .` ,
user : `Create a ${format} article about ${topic} targeting ${audience} .
Include:
- Data-backed insights from recent research
- Actionable takeaways
- SEO-optimized structure
Research data: ${researchData} `
});
const content = await generator.create ({
prompt : customTemplate.render ({
industry : 'SaaS' ,
format : 'case-study' ,
topic : insights.mainTrend ,
audience : 'startup founders' ,
researchData : JSON .stringify (insights)
})
});
Troubleshooting
Issue: API Rate Limits
import { retry } from './src/utils/retry' ;
const content = await retry (
() => generator.create (params),
{
maxAttempts : 3 ,
delayMs : 1000 ,
exponentialBackoff : true
}
);
Issue: Video Rendering Memory Issues
import pLimit from 'p-limit' ;
const limit = pLimit (2 );
const videoPromises = platforms.map (platform =>limit (() => renderForPlatform (platform, content))
);
await Promise .all (videoPromises);
Issue: Scraping Failures
const researcher = new ResearchEngine ({
sources : ['techcrunch' , 'a16z' ],
fallbackSources : ['medium' , 'dev.to' ],
onSourceFail : (source, error ) => {
console .warn (`Source ${source} failed:` , error);
},
minSourcesRequired : 1
});
Issue: Content Quality Validation import { ContentValidator } from './src/utils/validator' ;
const validator = new ContentValidator ({
minWordCount : 1000 ,
requireHeadings : true ,
checkReadability : true
});
const content = await generator.create (params);
if (!validator.validate (content)) {
content = await generator.refine (content, validator.getSuggestions ());
}
CLI Usage If the project includes CLI commands:
npm run generate -- --keyword "AI trends" --format toplist --lang en
npm run pipeline -- --config ./config/production.json
npm run render -- --input ./content/article.json --platform reels
npm run schedule -- --cron "0 6 * * *" --topics ./topics.json
Best Practices
Always use environment variables for API keysImplement rate limiting when scraping external sourcesCache research data to avoid redundant API callsValidate content quality before rendering videosUse concurrency limits for video rendering to manage resourcesSet up error monitoring for production pipelinesVersion control your prompt templates for reproducible results
Resources 