scrapper

Aggregate recent X, TikTok, Instagram, and GitHub items into normalized JSON.

Updated Mar 31, 2026
One-click install
npx skills add https://github.com/Tanguyvans/claude-config --skill scrapper
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: scrapper
Source: https://github.com/Tanguyvans/claude-config/tree/main/skills/scrapper
Command: npx skills add https://github.com/Tanguyvans/claude-config --skill scrapper

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

This Skill provides a generic multi-platform scraping tool that can fetch posts from X/Twitter, TikTok, Instagram (via ScrapeCreators), and GitHub trending AI (via the official GitHub API). It outputs data in a normalized JSON format that can be consumed by other skills (for example: video-ideas, tech-digest). It triggers on phrases such as "scrape", "scrapper", "fetch posts from", "tweets from", "trending GitHub AI", "social listening", and "fetch X/TikTok/Insta".

Core Features & Use Cases

  • Multi-platform scraping across X/Twitter, TikTok, Instagram, and GitHub AI trends.
  • Normalized JSON output suitable for downstream skills like video ideas or tech digests.
  • Configurable sources (accounts, hashtags, topics) and engagement thresholds, with parallel orchestration and a single runner.

Quick Start

Ask Claude to fetch the latest posts from X, TikTok, Instagram, and GitHub using the scrapper.

Frequently Asked Questions about scrapper

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I scrape posts from Twitter, TikTok, and Instagram in one request?

Multi-platform scraping fetches posts from X, TikTok, Instagram, and GitHub simultaneously by querying specified accounts and hashtags in parallel. It returns a normalized JSON payload containing recent items across all configured sources.

Can I fetch trending GitHub AI repositories alongside social media posts?

Yes, fetching trending GitHub AI repositories works alongside social scraping by using the official GitHub API. The unified output aggregates repository content and social posts into a single JSON payload for downstream consumption.

How do I configure which accounts and hashtags to scrape across social platforms?

Scraping sources are configured using a local config.json file where you specify target accounts, hashtags, topics, and day windows. This configuration tailors the parallel queries executed across X, TikTok, and Instagram.

What happens if I hit API rate limits while scraping multiple social platforms?

Robust error handling guards against missing APIs and rate limits during multi-platform scraping. The execution logic catches these errors to prevent the entire process from failing, returning available data within the JSON payload.

Does multi-platform scraping require external dependencies to run?

No external dependencies are required to run the multi-platform scraping tool. It operates as a standalone skill that queries X, TikTok, Instagram via ScrapeCreators, and GitHub via the official API to produce normalized JSON output.

How do I use scraped social media JSON data for content ideation?

The normalized JSON output from scraped social media and GitHub content supports modular integration with downstream skills. You can feed the aggregated payload directly into tools for video ideas or tech digests for further processing.