做什么
自动研究、生成脚本和与克洛德/OpenAI和Remotion创建视频的AI动力内容管道
技能库 智客分类:媒体内容 marketing-pipeline-share-content-automation
自动研究、生成脚本和与克洛德/OpenAI和Remotion创建视频的AI动力内容管道
官方网址:skills.sh
先看中文介绍;官方 description 原文单独保留,不改写 SKILL.md。
自动研究、生成脚本和与克洛德/OpenAI和Remotion创建视频的AI动力内容管道
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。
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 - AI Content Automation、Overview、Installation、Clone the repository、Install dependencies、or。
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。
AI-powered content pipeline that auto-researches, generates scripts, and creates videos with Claude/OpenAI and Remotion
Marketing Pipeline Share - AI Content AutomationOverviewInstallationClone the repositoryInstall dependenciesorSet up environment variablesRequired Environment VariablesAI ProvidersData Sources (RapidAPI)Optional: Custom endpointsProject Structure
来源分类:skills.sh agent-skill
namemarketing-pipeline-share-content-automationdescription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 ↗
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。
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-content-automation」安装到我的项目:SKILL.md 原文与官方 description 见 https://zicq.com/zh/skills/skl-cd14e97738f17eaf-%E8%90%A5%E9%94%80%E7%AE%A1%E9%81%93%E5%85%B1%E4%BA%AB%E5%86%85%E5%AE%B9%E8%87%AA%E5%8A%A8%E5%8C%96.html 请存为 .cursor/skills/marketing-pipeline-share-content-automation/SKILL.md 或 .claude/skills/marketing-pipeline-share-content-automation/SKILL.md,frontmatter 的 name 与 description 保持原样,不要改写。
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-content-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。
name: marketing-pipeline-share-content-automation description: AI-powered content pipeline that auto-researches, generates scripts, and creates videos with Claude/OpenAI and Remotion triggers:
Skill by ara.so — Marketing Skills collection.
Marketing Pipeline Share is an all-in-one TypeScript-based content automation system that:
This tool transforms a single keyword into full blog posts, social media content, and video assets.
# 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
# AI Providers
ANTHROPIC_API_KEY=your_claude_api_key
OPENAI_API_KEY=your_openai_api_key
# Data Sources (RapidAPI)
RAPIDAPI_KEY=your_rapidapi_key
# Optional: Custom endpoints
API_BASE_URL=http://localhost:3000
marketing-pineline-share/
├── src/
│ ├── app/ # Next.js app router pages
│ ├── components/ # React components
│ ├── lib/
│ │ ├── ai/ # AI integration (Claude, OpenAI)
│ │ ├── scraper/ # Web scraping modules
│ │ ├── content/ # Content generation logic
│ │ └── video/ # Remotion video rendering
│ └── types/ # TypeScript type definitions
├── remotion/ # Video templates
└── public/ # Static assets
import { researchTopic } from '@/lib/scraper';
// Auto-scrape trending news from multiple sources
async function gatherResearch(keyword: string) {
const research = await researchTopic({
keyword,
sources: ['techcrunch', 'twitter', 'linkedin'],
timeframe: '24h',
limit: 20
});
return {
articles: research.articles,
insights: research.insights,
statistics: research.stats
};
}
import { generateContent } from '@/lib/ai/content-generator';
// Generate blog post with Claude/OpenAI
async function createBlogPost(topic: string, research: any) {
const content = await generateContent({
provider: 'claude', // or 'openai'
model: 'claude-3-sonnet-20240229',
format: 'blog-post', // 'listicle', 'case-study', 'how-to'
topic,
research,
language: 'en', // or 'vi'
tone: 'professional', // 'friendly', 'humorous'
length: 'medium' // 'short', 'long'
});
return {
title: content.title,
body: content.body,
meta: content.metadata,
images: content.suggestedImages
};
}
import { ContentPipeline } from '@/lib/content/pipeline';
// Generate content in multiple formats from single input
async function generateMultiFormat(keyword: string) {
const pipeline = new ContentPipeline({
apiKey: process.env.ANTHROPIC_API_KEY
});
// Research phase
await pipeline.research(keyword);
// Generate multiple formats in parallel
const outputs = await pipeline.generateAll({
formats: [
{ type: 'blog-post', language: 'en' },
{ type: 'blog-post', language: 'vi' },
{ type: 'social-media', platform: 'linkedin' },
{ type: 'social-media', platform: 'twitter' },
{ type: 'video-script', duration: 60 }
]
});
return outputs;
}
import { renderVideo } from '@/lib/video/renderer';
import { bundle } from '@remotion/bundler';
import { renderMedia } from '@remotion/renderer';
// Convert blog post to video
async function createVideoFromPost(post: any) {
const videoConfig = {
compositionId: 'BlogPostVideo',
inputProps: {
title: post.title,
content: post.body,
style: 'modern',
duration: 90 // seconds
},
codec: 'h264',
outputLocation: `./output/${post.slug}.mp4`,
// Platform-specific ratios
width: 1080,
height: 1920 // 9:16 for TikTok/Reels/Shorts
};
const bundled = await bundle('./src/remotion/index.ts');
const result = await renderMedia({
composition: videoConfig,
serveUrl: bundled,
codec: 'h264',
outputLocation: videoConfig.outputLocation
});
return result;
}
If running as a Next.js server:
// Request
{
"keyword": "AI automation",
"sources": ["techcrunch", "twitter"],
"timeframe": "24h"
}
// Response
{
"articles": [...],
"insights": [...],
"trending": true
}
// Request
{
"topic": "AI content automation",
"format": "blog-post",
"language": "en",
"research": {...}
}
// Response
{
"title": "How AI is Transforming Content Creation",
"body": "...",
"metadata": {...},
"images": [...]
}
// Request
{
"content": {...},
"template": "modern",
"aspectRatio": "9:16"
}
// Response
{
"videoUrl": "https://...",
"thumbnail": "https://...",
"duration": 90
}
import { ContentAutomation } from '@/lib/automation';
async function fullContentPipeline(keyword: string) {
const automation = new ContentAutomation({
anthropicKey: process.env.ANTHROPIC_API_KEY,
openaiKey: process.env.OPENAI_API_KEY,
rapidApiKey: process.env.RAPIDAPI_KEY
});
// 1. Research
console.log('🔍 Researching topic...');
const research = await automation.research(keyword);
// 2. Generate content
console.log('✍️ Generating content...');
const content = await automation.generate({
topic: keyword,
research,
formats: ['blog', 'social', 'video-script']
});
// 3. Create visuals
console.log('🎬 Rendering video...');
const video = await automation.renderVideo({
script: content.videoScript,
style: 'professional'
});
// 4. Export all assets
return {
blogPost: content.blog,
socialPosts: content.social,
video: video.url,
publishReady: true
};
}
import { CronJob } from 'cron';
import { ContentAutomation } from '@/lib/automation';
// Auto-generate daily content
const dailyContentJob = new CronJob('0 9 * * *', async () => {
const automation = new ContentAutomation({
anthropicKey: process.env.ANTHROPIC_API_KEY
});
const trendingTopics = await automation.getTrendingTopics({
category: 'marketing',
count: 3
});
for (const topic of trendingTopics) {
const content = await fullContentPipeline(topic);
await automation.publishToQueue(content);
}
});
dailyContentJob.start();
import { ContentGenerator } from '@/lib/ai/content-generator';
// Create custom content template
const generator = new ContentGenerator({
provider: 'claude',
apiKey: process.env.ANTHROPIC_API_KEY
});
const customTemplate = {
name: 'product-launch',
structure: [
{ section: 'hook', prompt: 'Create attention-grabbing opening' },
{ section: 'problem', prompt: 'Describe pain points' },
{ section: 'solution', prompt: 'Introduce product benefits' },
{ section: 'features', prompt: 'List 5 key features' },
{ section: 'cta', prompt: 'Strong call-to-action' }
],
tone: 'exciting',
length: 800
};
const content = await generator.generateFromTemplate(
customTemplate,
{ product: 'AI Content Tool', audience: 'marketers' }
);
// src/config/content.ts
export const contentConfig = {
ai: {
defaultProvider: 'claude',
fallbackProvider: 'openai',
maxTokens: 4000,
temperature: 0.7
},
research: {
sources: ['techcrunch', 'twitter', 'linkedin', 'producthunt'],
maxArticles: 20,
timeframe: '24h'
},
video: {
defaultDuration: 60,
outputFormat: 'mp4',
quality: 'high',
aspectRatios: {
tiktok: '9:16',
youtube: '16:9',
instagram: '1:1'
}
}
};
// src/remotion/config.ts
export const videoConfig = {
fps: 30,
durationInFrames: 90 * 30, // 90 seconds
width: 1080,
height: 1920,
compositions: [
{
id: 'BlogPostVideo',
component: BlogPostComposition,
defaultProps: {
theme: 'dark',
animation: 'smooth'
}
}
]
};
// Implement retry logic with exponential backoff
import { retry } from '@/lib/utils/retry';
const content = await retry(
() => generateContent({ topic, research }),
{ maxAttempts: 3, delayMs: 1000 }
);
# Ensure Remotion CLI is installed
npm install -g @remotion/cli
# Check Remotion dependencies
npx remotion versions
# Common fix: Clear bundle cache
rm -rf .remotion
// Handle failed scrapes gracefully
try {
const research = await researchTopic(keyword);
} catch (error) {
console.warn('Scraping failed, using fallback');
// Use cached data or alternative source
const fallback = await getFallbackResearch(keyword);
}
// Process content in chunks
async function processLargeDataset(items: any[]) {
const chunkSize = 10;
const results = [];
for (let i = 0; i < items.length; i += chunkSize) {
const chunk = items.slice(i, i + chunkSize);
const processed = await Promise.all(
chunk.map(item => generateContent(item))
);
results.push(...processed);
}
return results;
}
# Development mode
npm run dev
# Build for production
npm run build
# Start production server
npm start
# Render single video (CLI)
npx remotion render BlogPostVideo output.mp4 --props='{"title":"My Post"}'
This skill enables AI agents to help developers build complete content automation workflows with research, generation, and video production capabilities.
媒体内容
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
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
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 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…