跳到主内容
智客 ZICQ

技能库 智客分类:媒体内容 marketing-pipeline-share-automation

Marketing Pipeline Share Automation

使用 Claude、OpenAI 和 Remotion 进行研究、脚本编写、张贴和视频生成的自动AI内容管道

752 安装量

官方网址:skills.sh

技能介绍

先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。

做什么

使用 Claude、OpenAI 和 Remotion 进行研究、脚本编写、张贴和视频生成的自动AI内容管道

何时用

官方 description 未单独写出 Use when。按规范,代理会在用户任务与这段 description 的关键词匹配时激活本技能。

代理如何加载

按 Agent Skills 渐进披露:启动时只加载 name 与 description(约 100 token);任务匹配后才读入整份 SKILL.md 正文;scripts/、references/、assets/ 仅在需要时再读。 本文件正文结构:Marketing Pipeline Share Automation、What This Project Does、Installation、Clone the repository、Install dependencies、or。

文件分析

文件分析:这是一份仅含 SKILL.md 的指令型技能,代理激活后整份正文进入上下文。 正文约 558 行,超过规范建议的 500 行,激活时仍会整份载入。

官方 description(原文)

Automated AI content pipeline for research, scriptwriting, posting, and video generation using Claude, OpenAI, and Remotion

Marketing Pipeline Share AutomationWhat This Project DoesInstallationClone the repositoryInstall dependenciesororSet up environment variablesRequired Environment VariablesAI Provider API KeysDatabase (if applicable)Next.js Configuration

来源分类:skills.sh agent-skill

SKILL.md 与 Agent 调用

官方规范 ↗
name
marketing-pipeline-share-automation
description
Automated AI content pipeline for research, scriptwriting, posting, and video generation using Claude, OpenAI, and Remotion
  1. 发现技能客户端向 Agent 提供名称与描述目录。
  2. 匹配与调用用户指定或任务匹配后,载入 SKILL.md 指令。
  3. 按需加载按步骤读取参考文档、使用脚本与素材。

具体调用语法与可用工具以目标 Agent 客户端为准。 查看调用机制说明 ↗

安装这个技能

Skills CLI ↗

先选择目标 Agent 和安装范围,保留技能包的附属文件,安装后检查客户端能否发现该技能。

交给 Agent 安装

复制安装指令给支持 Agent Skills 的代理,确认其中的目标目录与客户端匹配。

把 Agent Skill「marketing-pipeline-share-automation」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-1ae8757d0763133f-%E8%90%A5%E9%94%80%E7%AE%A1%E9%81%93%E8%82%A1%E4%BB%BD%E8%87%AA%E5%8A%A8%E5%8C%96.html
请存为 .cursor/skills/marketing-pipeline-share-automation/SKILL.md 或 .claude/skills/marketing-pipeline-share-automation/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。

GitHub 完整包 ↗

终端安装 · Skills CLI

需要 Node.js 与 npx。先查看仓库技能列表,确认实际名称。

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-automation'

CLI 会交互选择目标 Agent,默认安装到项目;用户级安装使用 -g。先通过查看命令核对仓库内容,再用 npx skills list 检查已安装技能。

阅读排版
--- name: marketing-pipeline-share-automation description: Automated AI content pipeline for research, scriptwriting, posting, and video generation using Claude, OpenAI, and Remotion triggers: - automate content creation with AI pipeline - generate marketing content from research to video - set up automated content workflow with Claude - create AI-powered content generation system - build content pipeline with video rendering - automate blog posts and social media videos - integrate Claude and OpenAI for content automation - use Remotion to generate marketing videos --- # Marketing Pipeline Share Automation > Skill by [ara.so](https://ara.so) — Marketing Skills collection. This skill enables AI coding agents to work with the Ultimate AI Content Pipeline - an end-to-end automated content generation system that handles research, scriptwriting, content creation, and video generation using Claude 3, OpenAI, and Remotion. ## What This Project Does Marketing Pipeline Share is a comprehensive TypeScript-based automation system that: - **Auto-scans research**: Crawls real-time data from TechCrunch, a16z, Twitter/X, LinkedIn within 24 hours - **Generates multi-format content**: Creates articles in various formats (top lists, POV, case studies, how-to) using Claude/OpenAI - **Multi-language support**: Automatically produces content in both English and Vietnamese - **Auto-renders videos**: Converts written content into infographics and short-form videos using Remotion - **Platform optimization**: Exports videos optimized for Reels, TikTok, and 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 # or pnpm install # Set up environment variables cp .env.example .env ``` ### Required Environment Variables ```bash # AI Provider API Keys OPENAI_API_KEY=your_openai_key ANTHROPIC_API_KEY=your_claude_key RAPIDAPI_KEY=your_rapidapi_key # Database (if applicable) DATABASE_URL=your_database_url # Next.js Configuration NEXT_PUBLIC_APP_URL=http://localhost:3000 ``` ### Running the Application ```bash # Development mode npm run dev # Production build npm run build npm run start # Video rendering (Remotion) npm run render ``` ## Core Architecture ### Project Structure ``` marketing-pineline-share/ ├── src/ │ ├── app/ # Next.js app directory │ ├── components/ # React components │ ├── lib/ # Core libraries │ │ ├── ai/ # AI integration (Claude, OpenAI) │ │ ├── crawler/ # Research crawling logic │ │ ├── content/ # Content generation │ │ └── video/ # Remotion video rendering │ ├── types/ # TypeScript types │ └── utils/ # Utility functions ├── remotion/ # Video templates └── public/ # Static assets ``` ## Key Features & Usage ### 1. Research Crawling ```typescript import { crawlResearch } from '@/lib/crawler'; // Crawl latest news from multiple sources async function gatherResearch(keyword: string) { const sources = ['techcrunch', 'a16z', 'twitter', 'linkedin']; const research = await crawlResearch({ keyword, sources, timeRange: '24h', maxResults: 50 }); return research; } // Example usage const insights = await gatherResearch('AI marketing automation'); console.log(insights.articles); console.log(insights.trendingTopics); ``` ### 2. Content Generation with Claude ```typescript import Anthropic from '@anthropic-ai/sdk'; const anthropic = new Anthropic({ apiKey: process.env.ANTHROPIC_API_KEY, }); async function generateContent( topic: string, format: 'toplist' | 'pov' | 'case-study' | 'how-to', language: 'en' | 'vi' ) { const prompts = { toplist: `Create a top 10 list about ${topic} with data-backed insights`, pov: `Write a thought-provoking point of view article about ${topic}`, 'case-study': `Develop a detailed case study analyzing ${topic}`, 'how-to': `Create a comprehensive how-to guide for ${topic}` }; const message = await anthropic.messages.create({ model: 'claude-3-5-sonnet-20241022', max_tokens: 4096, messages: [{ role: 'user', content: `${prompts[format]}. Language: ${language}. Include recent data and trends.` }] }); return message.content[0].text; } // Generate bilingual content const contentEN = await generateContent('AI content automation', 'toplist', 'en'); const contentVI = await generateContent('AI content automation', 'toplist', 'vi'); ``` ### 3. OpenAI Integration ```typescript import OpenAI from 'openai'; const openai = new OpenAI({ apiKey: process.env.OPENAI_API_KEY, }); async function generateWithGPT(prompt: string, tone: string) { const toneInstructions = { expert: 'Use professional, authoritative language with industry terminology', friendly: 'Write in a conversational, approachable tone', humorous: 'Include light humor and engaging storytelling' }; const completion = await openai.chat.completions.create({ model: 'gpt-4-turbo-preview', messages: [ { role: 'system', content: `You are a marketing content expert. ${toneInstructions[tone]}` }, { role: 'user', content: prompt } ], temperature: 0.7, }); return completion.choices[0].message.content; } ``` ### 4. Video Generation with Remotion ```typescript // remotion/VideoComposition.tsx import { Composition } from 'remotion'; import { MarketingVideo } from './templates/MarketingVideo'; export const RemotionRoot: React.FC = () => { return ( <> ); }; // Render video programmatically import { bundle } from '@remotion/bundler'; import { renderMedia, selectComposition } from '@remotion/renderer'; async function renderContentVideo( contentData: { title: string; points: string[] } ) { const bundleLocation = await bundle({ entryPoint: './remotion/index.ts', webpackOverride: (config) => config, }); const composition = await selectComposition({ serveUrl: bundleLocation, id: 'MarketingVideo', inputProps: contentData, }); await renderMedia({ composition, serveUrl: bundleLocation, codec: 'h264', outputLocation: `out/${contentData.title}.mp4`, }); } ``` ### 5. Complete Pipeline Workflow ```typescript import { crawlResearch } from '@/lib/crawler'; import { generateContent } from '@/lib/ai/claude'; import { renderContentVideo } from '@/lib/video/remotion'; import { publishToSocial } from '@/lib/social/publisher'; async function runContentPipeline(keyword: string) { try { // Step 1: Research console.log('🔍 Gathering research...'); const research = await crawlResearch({ keyword, sources: ['techcrunch', 'twitter'], timeRange: '24h' }); // Step 2: Generate content console.log('✍️ Generating content...'); const content = await generateContent( keyword, 'toplist', 'en' ); // Step 3: Create video console.log('🎬 Rendering video...'); const videoData = { title: keyword, points: extractKeyPoints(content), insights: research.trendingTopics.slice(0, 5) }; await renderContentVideo(videoData); // Step 4: Publish console.log('📤 Publishing...'); await publishToSocial({ content, video: `out/${keyword}.mp4`, platforms: ['facebook', 'linkedin', 'twitter'] }); return { success: true, content, videoPath: `out/${keyword}.mp4` }; } catch (error) { console.error('Pipeline error:', error); throw error; } } // Helper function function extractKeyPoints(content: string): string[] { // Parse markdown or structured content const lines = content.split('\n'); return lines .filter(line => line.match(/^\d+\.|^-|^•/)) .map(line => line.replace(/^\d+\.\s*|^-\s*|^•\s*/, '')) .slice(0, 10); } ``` ## API Integration Patterns ### RapidAPI for Data Enrichment ```typescript import axios from 'axios'; async function enrichWithRapidAPI(topic: string) { const options = { method: 'GET', url: 'https://api.rapidapi.com/search', params: { q: topic, limit: '10' }, headers: { 'X-RapidAPI-Key': process.env.RAPIDAPI_KEY, 'X-RapidAPI-Host': 'your-api-host.rapidapi.com' } }; try { const response = await axios.request(options); return response.data; } catch (error) { console.error('RapidAPI error:', error); return null; } } ``` ## Configuration ### Content Generation Config ```typescript // src/config/content.ts export const contentConfig = { formats: ['toplist', 'pov', 'case-study', 'how-to'], languages: ['en', 'vi'], tones: ['expert', 'friendly', 'humorous'], ai: { claude: { model: 'claude-3-5-sonnet-20241022', maxTokens: 4096, temperature: 0.7 }, openai: { model: 'gpt-4-turbo-preview', maxTokens: 3000, temperature: 0.7 } }, video: { defaultFps: 30, platforms: { reels: { width: 1080, height: 1920 }, tiktok: { width: 1080, height: 1920 }, youtube: { width: 1920, height: 1080 } } } }; ``` ### Crawler Configuration ```typescript // src/config/crawler.ts export const crawlerConfig = { sources: { techcrunch: { baseUrl: 'https://techcrunch.com', selectors: { article: '.post-block', title: '.post-block__title', content: '.article-content' } }, twitter: { apiVersion: 'v2', maxResults: 100 } }, rateLimits: { requestsPerMinute: 30, concurrent: 5 } }; ``` ## Common Patterns ### Batch Content Generation ```typescript async function batchGenerateContent(keywords: string[]) { const results = await Promise.allSettled( keywords.map(async (keyword) => { const content = await generateContent(keyword, 'toplist', 'en'); const contentVI = await generateContent(keyword, 'toplist', 'vi'); return { keyword, en: content, vi: contentVI }; }) ); return results .filter(r => r.status === 'fulfilled') .map(r => r.value); } ``` ### Error Handling & Retries ```typescript async function withRetry( fn: () => Promise, maxRetries = 3, delay = 1000 ): Promise { for (let i = 0; i < maxRetries; i++) { try { return await fn(); } catch (error) { if (i === maxRetries - 1) throw error; await new Promise(resolve => setTimeout(resolve, delay * (i + 1))); } } throw new Error('Max retries exceeded'); } // Usage const content = await withRetry(() => generateContent('AI trends', 'toplist', 'en') ); ``` ### Scheduling Content ```typescript import cron from 'node-cron'; // Schedule daily content generation at 9 AM cron.schedule('0 9 * * *', async () => { const keywords = ['AI marketing', 'content automation', 'video trends']; for (const keyword of keywords) { await runContentPipeline(keyword); } }); ``` ## Troubleshooting ### API Rate Limits ```typescript // Implement queue system import PQueue from 'p-queue'; const queue = new PQueue({ concurrency: 2, interval: 60000, // 1 minute intervalCap: 30 // 30 requests per minute }); async function queuedGenerate(prompt: string) { return queue.add(() => generateContent(prompt, 'toplist', 'en')); } ``` ### Video Rendering Memory Issues ```bash # Increase Node.js memory limit NODE_OPTIONS="--max-old-space-size=4096" npm run render ``` ### Claude API Errors ```typescript async function generateContentSafe(topic: string) { try { return await generateContent(topic, 'toplist', 'en'); } catch (error) { if (error.status === 529) { console.log('API overloaded, waiting...'); await new Promise(resolve => setTimeout(resolve, 5000)); return generateContent(topic, 'toplist', 'en'); } throw error; } } ``` ### Missing Environment Variables ```typescript function validateEnv() { const required = [ 'OPENAI_API_KEY', 'ANTHROPIC_API_KEY', 'RAPIDAPI_KEY' ]; const missing = required.filter(key => !process.env[key]); if (missing.length > 0) { throw new Error( `Missing required environment variables: ${missing.join(', ')}` ); } } // Call at startup validateEnv(); ``` ## Advanced Usage ### Custom Video Templates ```typescript // remotion/templates/CustomTemplate.tsx import { AbsoluteFill, useCurrentFrame, interpolate } from 'remotion'; export const CustomMarketingVideo: React.FC<{ title: string; points: string[]; }> = ({ title, points }) => { const frame = useCurrentFrame(); const opacity = interpolate(frame, [0, 30], [0, 1], { extrapolateRight: 'clamp', }); return (

{title}

{points.map((point, i) => (

{point}

))}
); }; ``` This skill provides comprehensive guidance for AI coding agents to effectively use the Marketing Pipeline Share automation system for end-to-end content creation workflows.

相关技能

媒体内容

Nano Banana Pro

以纳米·香蕉Pro(Gemini 3 Pro Image)来生成/编辑图像. 用于创建/修改请求,包括编辑。 支持文本到图像+图像到图像; 1K/2K/4K; 使用 -- input-image.

媒体内容

Youtube Watcher

从YouTube视频中获取并读取文字记录. 需要汇总视频时使用,回答有关视频内容的问题,或者从中提取信息.

媒体内容

Atxp

Access ATXP支付API工具用于网页搜索,AI图像生成,音乐创建,视频生成,X/Twitter搜索,电子邮件,代理账户管理. 当用户需要实时网络搜索时使用,AI生成的媒体(图像,音乐,视频),X/Twitter搜索,发送/接收电子邮件,或创建和资助代理账户. 需要通过“ …

媒体内容

Youtube

YouTube Data API与管理的OAuth的集成. 搜索视频,管理播放列表,访问频道数据,并与评论互动. 用户想与YouTube互动时使用此技能. 对于其他第三方应用,使用api-gateway技能(https://clawhub.ai/byungkyu/api-gate…