grandamenium

Social Media Insights — Communication skill for Claude Code

Communication community

Social media post analysis skill with real Apify integration.

How to install Social Media Insights

This entry records only its repository, not the path inside it, so there is no exact command to give. Open grandamenium/social-media-insights and copy the folder into ~/.claude/skills/, or the file into ~/.claude/agents/.

What Social Media Insights does

Social media post analysis skill with real Apify integration.

Alternatives in Communication

Slack — Communication Slack integration via HTTP/OAuth MCP 14k ★
Pestle Analysis — PESTLE analysis across Political, Economic, Social, Tech, Legal, Environmental 7.8k ★
Social Media Agent — 📲 An agent for sourcing, curating, and scheduling social media posts with human-in-the-loop 2.8k ★

README

Social-Media-Insights Skill — Quick Start

What Is This?

A skill that analyzes social media posts (TikTok, Instagram, Twitter) and tells you:

What the post is about (sentiment: positive/negative/neutral)
What topics it covers
How relevant it is to your work
What you should do about it (specific recommendations)

I'm A New Agent — What Do I Do?

1. Give It Posts to Analyze

Create a file called `input.json`:

{
  "posts": [
    "https://www.tiktok.com/@someuser/video/123",
    "https://www.instagram.com/p/ABC123/",
    "https://twitter.com/someuser/status/456"
  ]
}

2. Run The Skill

bash ./social-media-insights/pipeline.sh --input-file input.json

3. Read The Results

Look for `output/2026-04-29-full-analysis.json` (or today's date).

The file contains:

extracted_posts: What the skill found in each post (text, author, likes, etc.)
analysis: Sentiment, topics, themes for each post
recommendations: Specific things you should do with this info

4. Act On Recommendations

Each recommendation has:

priority_score: How important (0 = ignore, 1 = urgent)
actions: What to do (investigate_topic, monitor_trend, etc.)
implementation_steps: Exact steps to follow
time_estimate_hours: How long it'll take

Pick the highest priority_score and do those steps.

Real-World Example

**Input**: TikTok video about AI automation

**Output**:

{
  "sentiment": {"score": 0.8, "label": "positive"},
  "topics": [
    {"topic": "AI/automation", "relevance": 0.9}
  ],
  "recommendations": [{
    "priority_score": 0.85,
    "actions": [{
      "action": "investigate_topic",
      "topic": "AI/automation",
      "implementation_steps": [
        "1. Review current workflows",
        "2. Compare against video insights",
        "3. Test improvement in sandbox",
        "4. Measure impact"
      ]
    }]
  }]
}

**You do**: Follow the 4 steps. Report results.