Social Media Content Extraction

Extract Threads and Instagram post content with nested replies into Markdown.

210|49|Updated Jan 17, 2026
One-click install
npx skills add https://github.com/treylom/knowledge-manager --skill social-media-content-extraction
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: Social Media Content Extraction
Source: https://github.com/treylom/knowledge-manager/tree/main/.agent/skills/km-social-media
Command: npx skills add https://github.com/treylom/knowledge-manager --skill social-media-content-extraction

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

This Skill automates the extraction of content from social media platforms like Threads and Instagram, including replies, to provide a comprehensive view of discussions.

Core Features & Use Cases

  • Multi-platform Support: Extracts content from Threads and Instagram.
  • Reply Collection: Gathers replies to posts, with control over the depth of collection.
  • URL Normalization: Ensures consistent processing of various URL formats.
  • Use Case: Gather all comments and replies on an Instagram post to understand public sentiment or collect user feedback.

Quick Start

Extract content from the Threads post at https://threads.com/@user/post/123 with replies.

Frequently Asked Questions about Social Media Content Extraction

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

FAQPage Schema
How do I extract social media posts and replies from Threads and Instagram?

To extract social media posts and replies, you can use a web scraping tool that normalizes URLs and gathers nested replies. This process automates collecting content from Threads and Instagram, outputting the discussion in Markdown format.

Can I control the reply depth when scraping Instagram or Threads comments?

Yes, you can control the reply depth when scraping Instagram or Threads comments. The extraction process supports configurable reply collection depths of 1 or 2, allowing you to gather either direct replies or nested sub-replies.

Does web scraping for social media content require stealth mode to bypass restrictions?

Web scraping for social media content often requires stealth mode to bypass restrictions. Utilizing a hyperbrowser with stealth mode ensures consistent processing of various URL formats and successful content extraction from platforms like Threads.

What is the best way to normalize URLs for extracting nested replies from social media?

The best way to normalize URLs for extracting nested replies is through automated URL normalization prior to web scraping. This ensures consistent processing of various social media link formats, enabling accurate reply collection and Markdown output.

How does extracting social media content in Markdown format help analyze public sentiment?

Extracting social media content in Markdown format helps analyze public sentiment by providing a structured, readable text output of posts and replies. This allows you to easily review gathered comments and collect user feedback from discussions.

Are there limitations when collecting replies from Threads or Instagram posts?

Limitations when collecting replies from Threads or Instagram posts include a maximum supported reply collection depth of 2. Additionally, successful web scraping relies on utilizing a hyperbrowser in stealth mode to handle platform restrictions.