Back to Skills

social-analytics

guia-matthieu
Updated 2 days ago
7 views
111
20
111
View on GitHub
Otherdata

About

This skill analyzes social media profiles to calculate engagement rates, identify top-performing content, and track growth. It's used for competitor analysis, benchmarking metrics, and generating performance reports. Developers can integrate it via the MCP server to audit social presence and assess account health.

Quick Install

Claude Code

Recommended
Primary
npx skills add guia-matthieu/clawfu-skills -a claude-code
Plugin CommandAlternative
/plugin add https://github.com/guia-matthieu/clawfu-skills
Git CloneAlternative
git clone https://github.com/guia-matthieu/clawfu-skills.git ~/.claude/skills/social-analytics

Copy and paste this command in Claude Code to install this skill

Documentation

Social Analytics

Analyze social media profiles and calculate engagement metrics - understand what content works for competitors and your own accounts.

When to Use This Skill

  • Competitor analysis - Audit competitor social presence
  • Engagement benchmarking - Calculate and compare engagement rates
  • Content analysis - Identify top-performing post types
  • Profile audit - Assess social media health
  • Reporting - Generate social performance reports

What Claude Does vs What You Decide

Claude DoesYou Decide
Structures analysis frameworksMetric definitions
Identifies patterns in dataBusiness interpretation
Creates visualization templatesDashboard design
Suggests optimization areasAction priorities
Calculates statistical measuresDecision thresholds

Dependencies

pip install click pandas requests beautifulsoup4
# For authenticated API access:
pip install tweepy instaloader

Commands

Analyze Profile

python scripts/main.py analyze @competitor --platform twitter
python scripts/main.py analyze @brand --platform instagram

Calculate Engagement

python scripts/main.py engagement @profile --platform twitter --days 30
python scripts/main.py engagement @profile --platform linkedin --posts 50

Find Top Posts

python scripts/main.py top-posts @profile --platform twitter --count 10
python scripts/main.py top-posts @profile --metric likes

Export Data

python scripts/main.py export @profile --platform twitter --format csv
python scripts/main.py export @profile --platform instagram --output report.json

Compare Profiles

python scripts/main.py compare @brand1 @brand2 @brand3 --platform twitter

Examples

Example 1: Competitor Social Audit

# Analyze competitor profile
python scripts/main.py analyze @competitor_brand --platform twitter

# Output:
# Profile Analysis: @competitor_brand
# ─────────────────────────────────────
# Followers:      45,230
# Following:      1,234
# Total Posts:    2,456
# Avg Likes:      234
# Avg Retweets:   45
# Engagement:     2.3%
# Post Frequency: 3.2/day
# Top Hashtags:   #marketing, #growth, #startup

Example 2: Benchmark Engagement Rates

# Compare engagement across competitors
python scripts/main.py compare @brand1 @brand2 @brand3 --platform twitter

# Output:
# Engagement Comparison
# ─────────────────────
# Profile         Followers   Eng.Rate   Posts/Day
# @brand1         45,230      2.3%       3.2
# @brand2         32,100      3.1%       2.1
# @brand3         89,500      1.8%       4.5

# Winner: @brand2 (highest engagement despite fewer followers)

Example 3: Find Winning Content

# Identify top performing posts
python scripts/main.py top-posts @marketing_pro --platform twitter --count 10

# Output:
# Top 10 Posts by Engagement
# ──────────────────────────
# 1. "Here's what nobody tells you about..."
#    Likes: 2,345  RTs: 456  Eng: 6.2%
#    Type: Thread  Time: Tuesday 9am

# 2. "The biggest mistake I see founders make..."
#    Likes: 1,890  RTs: 312  Eng: 4.8%
#    Type: Single  Time: Wednesday 8am

Engagement Rate Benchmarks

Twitter/X

Account SizeGoodGreatExcellent
<10K1-3%3-6%>6%
10K-100K0.5-1%1-3%>3%
100K+0.2-0.5%0.5-1%>1%

Instagram

Account SizeGoodGreatExcellent
<10K3-6%6-10%>10%
10K-100K1-3%3-6%>6%
100K+0.5-1%1-3%>3%

LinkedIn

Account SizeGoodGreatExcellent
Personal2-4%4-8%>8%
Company0.5-1%1-2%>2%

Metrics Explained

MetricFormulaWhat It Measures
Engagement Rate(likes + comments + shares) / followersOverall content resonance
Amplificationshares / followersContent virality
Conversationcomments / followersCommunity engagement
Applauselikes / followersContent appreciation

Output Formats

FormatBest For
textQuick terminal review
csvSpreadsheet analysis
jsonProgrammatic use
mdReports and docs

Skill Boundaries

What This Skill Does Well

  • Structuring data analysis
  • Identifying patterns and trends
  • Creating visualization frameworks
  • Calculating statistical measures

What This Skill Cannot Do

  • Access your actual data
  • Replace statistical expertise
  • Make business decisions
  • Guarantee prediction accuracy

Related Skills

Skill Metadata

  • Mode: centaur
category: social
subcategory: analytics
dependencies: [pandas, requests, beautifulsoup4]
difficulty: intermediate
time_saved: 4+ hours/week

GitHub Repository

guia-matthieu/clawfu-skills
Path: skills/social/social-analytics
0
ai-skillsanthropicclaude-codeclaude-skillsmarketingmcp-server

Related Skills

llamaguard

Other

LlamaGuard is Meta's 7-8B parameter model for moderating LLM inputs and outputs across six safety categories like violence and hate speech. It offers 94-95% accuracy and can be deployed using vLLM, Hugging Face, or Amazon SageMaker. Use this skill to easily integrate content filtering and safety guardrails into your AI applications.

View skill

cost-optimization

Other

This Claude Skill helps developers optimize cloud costs through resource rightsizing, tagging strategies, and spending analysis. It provides a framework for reducing cloud expenses and implementing cost governance across AWS, Azure, and GCP. Use it when you need to analyze infrastructure costs, right-size resources, or meet budget constraints.

View skill

quantizing-models-bitsandbytes

Other

This skill quantizes LLMs to 8-bit or 4-bit precision using bitsandbytes, achieving 50-75% memory reduction with minimal accuracy loss. It's ideal for running larger models on limited GPU memory or accelerating inference, supporting formats like INT8, NF4, and FP4. The skill integrates with HuggingFace Transformers and enables QLoRA training and 8-bit optimizers.

View skill

dispatching-parallel-agents

Other

This Claude Skill dispatches multiple agents to investigate and fix 3+ independent problems concurrently. It is designed for scenarios involving unrelated failures that can be resolved without shared state or dependencies. The core capability is parallel problem-solving, assigning one agent per independent problem domain to maximize efficiency.

View skill