Skip to main content
ZICQ

Skills ZICQ category:Media marketing-pipeline-share-ai-content-automation

Marketing Pipeline Share Ai Content Automation

Automated content creation pipeline with AI research, scriptwriting, multi-format output, and video generation using Claude/OpenAI and Remotion

764 installs

Official URL:skills.sh

What this skill does

Intro in this page language first. The official description stays in its original wording; we do not rewrite SKILL.md.

What it does

Automated content creation pipeline with AI research, scriptwriting, multi-format output, and video generation using Claude/OpenAI and Remotion

When to use it

The official description does not include a separate “Use when”. Per the spec, agents activate this skill when the task matches keywords in that description.

How agents load it

Per Agent Skills progressive disclosure: name and description load at startup (~100 tokens); the full SKILL.md body loads when the skill activates; scripts/, references/, and assets/ load only as needed. This file's sections: Marketing Pipeline Share - AI Content Automation; What It Does; Installation; Clone the repository; Install dependencies; or.

File analysis

File analysis: instruction-only skill (SKILL.md). The agent loads the full body when activated. The body is about 701 lines, above the spec’s 500-line guidance; agents still load it in full on activation.

Marketing Pipeline Share - AI Content AutomationWhat It DoesInstallationClone the repositoryInstall dependenciesorSet up environment variablesConfigurationAI ServicesWeb Scraping (RapidAPI)Database (if using)Next.js

Source category:skills.sh agent-skill

SKILL.md & Agent activation

Official spec ↗
name
marketing-pipeline-share-ai-content-automation
description
Automated content creation pipeline with AI research, scriptwriting, multi-format output, and video generation using Claude/OpenAI and Remotion
  1. DiscoverThe client exposes names and descriptions to the agent.
  2. ActivateYour request or the task context selects the skill and loads its instructions.
  3. Load resourcesReferenced scripts, documentation and assets are used when needed.

Invocation syntax and available tools depend on your Agent client. Client integration guide ↗

Install this skill

Skills CLI ↗

Choose the target agent and installation scope, keep referenced package files, then verify the skill appears in the client's catalog.

Ask your Agent to install

Copy these instructions to a compatible agent and confirm the target directory matches your client.

Install the agent skill "marketing-pipeline-share-ai-content-automation" into my project. The full SKILL.md and official description are at https://zicq.com/en/skills/skl-5c23a0eaf877b012-Marketing-Pipeline-Share-Ai-Content-Auto.html
Save it as .cursor/skills/marketing-pipeline-share-ai-content-automation/SKILL.md or .claude/skills/marketing-pipeline-share-ai-content-automation/SKILL.md and keep the frontmatter name and description exactly as-is.

Full package on GitHub ↗

Install from the terminal · Skills CLI

Requires Node.js and npx. First inspect the repository's skill list to confirm the name.

npx skills add 'https://github.com/reason-machines/marketing-skills' --list

npx skills add 'https://github.com/reason-machines/marketing-skills' --skill 'marketing-pipeline-share-ai-content-automation'

The CLI lets you choose the agent interactively. The default scope is the project; use -g for user scope. Confirm package availability with the discovery command, then use npx skills list to inspect installed skills.

Readable layout
--- name: marketing-pipeline-share-ai-content-automation description: Automated content creation pipeline with AI research, scriptwriting, multi-format output, and video generation using Claude/OpenAI and Remotion triggers: - automate content creation with AI research and video generation - set up marketing pipeline with automatic article writing - generate social media content from trending topics automatically - build AI content automation with Claude and OpenAI - create automated video content from text using Remotion - implement content research and generation pipeline - automate multi-language content creation workflow - set up end-to-end marketing content automation --- # Marketing Pipeline Share - AI Content Automation > Skill by [ara.so](https://ara.so) — Marketing Skills collection. This project is an all-in-one AI-powered content automation pipeline that researches trending topics, generates multi-format articles in multiple languages, and automatically creates video content. It integrates Claude 3, OpenAI, web scraping for real-time research, and Remotion for video rendering. ## What It Does The Marketing Pipeline Share automates the entire content creation workflow: 1. **Auto-Research**: Crawls recent articles from TechCrunch, a16z, Twitter/X, LinkedIn (last 24h) 2. **AI Content Generation**: Creates articles in multiple formats (Top List, POV, Case Study, How-to) using Claude/OpenAI 3. **Multi-language Output**: Generates content in both English and Vietnamese with customizable tone 4. **Video Generation**: Automatically renders videos and infographics from written content using Remotion 5. **Platform Optimization**: Exports content optimized for Reels, TikTok, Shorts ## Installation ```bash # Clone the repository git clone https://github.com/pennydinh/marketing-pineline-share.git cd marketing-pineline-share # Install dependencies npm install # or yarn install # Set up environment variables cp .env.example .env ``` ## Configuration Create a `.env` file in the root directory with the following variables: ```bash # AI Services OPENAI_API_KEY=your_openai_key_here ANTHROPIC_API_KEY=your_claude_key_here # Web Scraping (RapidAPI) RAPIDAPI_KEY=your_rapidapi_key_here # Database (if using) DATABASE_URL=your_database_connection_string # Next.js NEXT_PUBLIC_APP_URL=http://localhost:3000 # Remotion (Video Rendering) REMOTION_AWS_ACCESS_KEY_ID=your_aws_access_key REMOTION_AWS_SECRET_ACCESS_KEY=your_aws_secret_key ``` ## Project Structure ``` marketing-pineline-share/ ├── src/ │ ├── app/ # Next.js app directory │ ├── components/ # React components │ ├── services/ # Core services │ │ ├── research/ # Web scraping & research │ │ ├── ai/ # AI content generation │ │ └── video/ # Video rendering │ ├── lib/ # Utilities and helpers │ └── types/ # TypeScript type definitions ├── remotion/ # Remotion video templates └── public/ # Static assets ``` ## Key API Services ### 1. Research Service The research service crawls and analyzes recent content from multiple sources. ```typescript // src/services/research/scraper.ts import axios from 'axios'; interface ResearchResult { title: string; url: string; summary: string; publishedAt: Date; source: string; } export async function researchTopic( keyword: string, sources: string[] = ['techcrunch', 'a16z', 'twitter'] ): Promise { const results: ResearchResult[] = []; for (const source of sources) { try { const data = await scrapeSource(source, keyword); results.push(...data); } catch (error) { console.error(`Failed to scrape ${source}:`, error); } } return results.filter( (r) => new Date(r.publishedAt) > new Date(Date.now() - 24 * 60 * 60 * 1000) ); } async function scrapeSource( source: string, keyword: string ): Promise { const response = await axios.get( `https://api.rapidapi.com/v1/${source}/search`, { params: { q: keyword, limit: 10 }, headers: { 'X-RapidAPI-Key': process.env.RAPIDAPI_KEY!, 'X-RapidAPI-Host': `${source}-api.rapidapi.com`, }, } ); return response.data.results.map((item: any) => ({ title: item.title, url: item.url, summary: item.description || item.content?.substring(0, 200), publishedAt: new Date(item.published_at), source: source, })); } ``` ### 2. AI Content Generation Generate articles using Claude or OpenAI based on research data. ```typescript // src/services/ai/content-generator.ts import Anthropic from '@anthropic-ai/sdk'; import OpenAI from 'openai'; const anthropic = new Anthropic({ apiKey: process.env.ANTHROPIC_API_KEY, }); const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY, }); interface ContentRequest { keyword: string; format: 'toplist' | 'pov' | 'case-study' | 'how-to'; language: 'en' | 'vi'; tone: 'professional' | 'friendly' | 'humorous'; researchData: any[]; } export async function generateContent( request: ContentRequest, provider: 'claude' | 'openai' = 'claude' ): Promise { const prompt = buildPrompt(request); if (provider === 'claude') { const message = await anthropic.messages.create({ model: 'claude-3-5-sonnet-20241022', max_tokens: 4096, messages: [{ role: 'user', content: prompt, }], }); return message.content[0].type === 'text' ? message.content[0].text : ''; } else { const completion = await openai.chat.completions.create({ model: 'gpt-4-turbo-preview', messages: [{ role: 'user', content: prompt, }], max_tokens: 4096, }); return completion.choices[0]?.message?.content || ''; } } function buildPrompt(request: ContentRequest): string { const formatInstructions = { 'toplist': 'Create a top 10 list format with numbered items', 'pov': 'Write from a personal perspective with strong opinions', 'case-study': 'Analyze as a detailed case study with data and insights', 'how-to': 'Write as a step-by-step tutorial guide', }; const toneInstructions = { 'professional': 'Use formal, expert tone with industry terminology', 'friendly': 'Use conversational, approachable language', 'humorous': 'Include witty observations and light humor', }; return ` You are an expert content writer specializing in marketing and technology. Topic: ${request.keyword} Format: ${formatInstructions[request.format]} Language: ${request.language === 'en' ? 'English' : 'Vietnamese'} Tone: ${toneInstructions[request.tone]} Research Data: ${request.researchData.map((r, i) => ` ${i + 1}. ${r.title} Source: ${r.source} Summary: ${r.summary} URL: ${r.url} `).join('\n')} Requirements: - Use the research data to create an original, insightful article - Include specific data points and examples from the research - Make it engaging and actionable for the target audience - Length: 1500-2000 words - Include a compelling headline and subheadings - Add a clear call-to-action at the end Generate the complete article now: `; } ``` ### 3. Multi-Language Content Generation Generate content in both English and Vietnamese simultaneously. ```typescript // src/services/ai/multi-lang-generator.ts import { generateContent, ContentRequest } from './content-generator'; interface MultiLangContent { en: string; vi: string; metadata: { keyword: string; format: string; generatedAt: Date; }; } export async function generateMultiLanguageContent( request: Omit ): Promise { const [enContent, viContent] = await Promise.all([ generateContent({ ...request, language: 'en' }), generateContent({ ...request, language: 'vi' }), ]); return { en: enContent, vi: viContent, metadata: { keyword: request.keyword, format: request.format, generatedAt: new Date(), }, }; } ``` ### 4. Video Generation with Remotion Render videos from generated content using Remotion. ```typescript // src/services/video/renderer.ts import { bundle } from '@remotion/bundler'; import { renderMedia, selectComposition } from '@remotion/renderer'; import path from 'path'; interface VideoConfig { content: string; format: 'reels' | 'tiktok' | 'shorts'; aspectRatio: '9:16' | '16:9' | '1:1'; } export async function renderContentVideo( config: VideoConfig, outputPath: string ): Promise { const compositionId = getCompositionId(config.format); const bundleLocation = await bundle( path.join(process.cwd(), 'remotion/index.ts') ); const composition = await selectComposition({ serveUrl: bundleLocation, id: compositionId, inputProps: { content: config.content, aspectRatio: config.aspectRatio, }, }); await renderMedia({ composition, serveUrl: bundleLocation, codec: 'h264', outputLocation: outputPath, inputProps: { content: config.content, aspectRatio: config.aspectRatio, }, }); return outputPath; } function getCompositionId(format: string): string { const compositionMap = { 'reels': 'InstagramReels', 'tiktok': 'TikTokVideo', 'shorts': 'YouTubeShorts', }; return compositionMap[format] || 'InstagramReels'; } ``` ### 5. Remotion Video Template ```typescript // remotion/compositions/Reels.tsx import { AbsoluteFill, useCurrentFrame, useVideoConfig } from 'remotion'; import React from 'react'; interface ReelsProps { content: string; aspectRatio: '9:16' | '16:9' | '1:1'; } export const InstagramReels: React.FC = ({ content, aspectRatio }) => { const frame = useCurrentFrame(); const { fps } = useVideoConfig(); const opacity = Math.min(1, frame / (fps / 2)); const sections = content.split('\n\n').filter(Boolean); const currentSection = Math.floor(frame / (fps * 3)) % sections.length; return (
{sections[currentSection]}
); }; ``` ## Complete Content Pipeline Workflow ```typescript // src/services/pipeline/content-pipeline.ts import { researchTopic } from '../research/scraper'; import { generateMultiLanguageContent } from '../ai/multi-lang-generator'; import { renderContentVideo } from '../video/renderer'; interface PipelineConfig { keyword: string; format: 'toplist' | 'pov' | 'case-study' | 'how-to'; tone: 'professional' | 'friendly' | 'humorous'; generateVideo: boolean; videoFormat?: 'reels' | 'tiktok' | 'shorts'; } export async function runContentPipeline(config: PipelineConfig) { console.log(`Starting content pipeline for: ${config.keyword}`); // Step 1: Research console.log('Step 1: Researching topic...'); const researchData = await researchTopic(config.keyword); console.log(`Found ${researchData.length} relevant articles`); // Step 2: Generate Content console.log('Step 2: Generating multi-language content...'); const content = await generateMultiLanguageContent({ keyword: config.keyword, format: config.format, tone: config.tone, researchData, }); // Step 3: Generate Video (if requested) let videoPath: string | null = null; if (config.generateVideo && config.videoFormat) { console.log('Step 3: Rendering video...'); videoPath = await renderContentVideo( { content: content.en, format: config.videoFormat, aspectRatio: '9:16', }, `output/video-${Date.now()}.mp4` ); console.log(`Video rendered: ${videoPath}`); } return { content, videoPath, researchSources: researchData.length, completedAt: new Date(), }; } ``` ## API Routes (Next.js) ```typescript // src/app/api/generate/route.ts import { NextRequest, NextResponse } from 'next/server'; import { runContentPipeline } from '@/services/pipeline/content-pipeline'; export async function POST(request: NextRequest) { try { const body = await request.json(); const result = await runContentPipeline({ keyword: body.keyword, format: body.format || 'toplist', tone: body.tone || 'professional', generateVideo: body.generateVideo || false, videoFormat: body.videoFormat || 'reels', }); return NextResponse.json({ success: true, data: result, }); } catch (error) { console.error('Pipeline error:', error); return NextResponse.json( { success: false, error: error.message }, { status: 500 } ); } } ``` ## Frontend Component Example ```typescript // src/components/ContentGenerator.tsx 'use client'; import { useState } from 'react'; export default function ContentGenerator() { const [keyword, setKeyword] = useState(''); const [loading, setLoading] = useState(false); const [result, setResult] = useState(null); async function handleGenerate() { setLoading(true); try { const response = await fetch('/api/generate', { method: 'POST', headers: { 'Content-Type': 'application/json' }, body: JSON.stringify({ keyword, format: 'toplist', tone: 'professional', generateVideo: true, videoFormat: 'reels', }), }); const data = await response.json(); setResult(data.data); } catch (error) { console.error('Generation failed:', error); } finally { setLoading(false); } } return (

AI Content Generator

setKeyword(e.target.value)} placeholder="Enter topic keyword..." className="w-full p-4 border rounded-lg mb-4" /> {loading ? 'Generating...' : 'Generate Content'} {result && (

English Content

{result.content.en}

Vietnamese Content

{result.content.vi}
{result.videoPath && (

Generated Video

{result.videoPath}

)}
)}
); } ``` ## Common Patterns ### Batch Content Generation ```typescript // Generate multiple articles at once async function batchGenerate(keywords: string[]) { const results = await Promise.all( keywords.map((keyword) => runContentPipeline({ keyword, format: 'toplist', tone: 'professional', generateVideo: false, }) ) ); return results; } ``` ### Content Scheduling ```typescript // Schedule content generation for later import { scheduleJob } from 'node-schedule'; scheduleJob('0 9 * * *', async () => { // Run daily at 9 AM const trendingTopics = await getTrendingTopics(); await batchGenerate(trendingTopics); }); ``` ### Custom Video Templates ```typescript // remotion/compositions/CustomTemplate.tsx export const CustomTemplate: React.FC<{ title: string; points: string[] }> = ({ title, points, }) => { const frame = useCurrentFrame(); return (

{title}

{points.map((point, i) => (
(i + 1) * 30 ? 1 : 0, marginBottom: 20, }} > {i + 1}. {point}
))}
); }; ``` ## Troubleshooting ### API Rate Limits ```typescript // Implement rate limiting and retry logic import pRetry from 'p-retry'; async function generateWithRetry(request: ContentRequest) { return pRetry( () => generateContent(request), { retries: 3, onFailedAttempt: (error) => { console.log( `Attempt ${error.attemptNumber} failed. Retrying...` ); }, } ); } ``` ### Memory Issues with Video Rendering ```typescript // Reduce memory usage by processing videos sequentially async function renderVideosSequentially(configs: VideoConfig[]) { const results = []; for (const config of configs) { const result = await renderContentVideo( config, `output/video-${Date.now()}.mp4` ); results.push(result); // Allow garbage collection between renders await new Promise((resolve) => setTimeout(resolve, 1000)); } return results; } ``` ### Research Data Quality ```typescript // Filter and validate research results function validateResearchData(results: ResearchResult[]): ResearchResult[] { return results.filter((r) => { const hasValidContent = r.summary && r.summary.length > 50; const isRecent = new Date(r.publishedAt) > new Date(Date.now() - 48 * 60 * 60 * 1000); const hasValidUrl = r.url && r.url.startsWith('http'); return hasValidContent && isRecent && hasValidUrl; }); } ``` ## Development Commands ```bash # Start development server npm run dev # Build for production npm run build # Start production server npm start # Run type checking npm run type-check # Render a single video composition npm run remotion render ``` This skill enables AI coding agents to effectively utilize the Marketing Pipeline Share project for automated content creation, from research through video generation, with full TypeScript integration and Next.js deployment.

Related skills

Media

Nano Banana Pro

Generate/edit images with Nano Banana Pro (Gemini 3 Pro Image). Use for image create/modify requests incl. edits. Supports text-to-image + i…

Media

Youtube Watcher

Fetch and read transcripts from YouTube videos. Use when you need to summarize a video, answer questions about its content, or extract infor…

Media

Atxp

Access ATXP paid API tools for web search, AI image generation, music creation, video generation, X/Twitter search, email, and agent account…

Media

Youtube

YouTube Data API integration with managed OAuth. Search videos, manage playlists, access channel data, and interact with comments. Use this …