Tiktok Research

This is a full research pipeline for identifying what's actually working on TikTok right now. You point it at competitor accounts, it pulls recent videos via Apify, runs statistical analysis to find outliers (anything performing above mean plus 2 standard deviations), then uses AI to extract the actual hook formulas and content patterns from the top 5 videos. The output is a structured report with replicable techniques, not just metrics. It's legitimately useful if you're trying to reverse engineer viral content in a niche, though you'll need both Apify and Gemini API keys. The engagement scoring formula weights comments and shares heavily, which feels right for TikTok's algorithm.

skills.sh installs: 1.2K
GitHub stars: 309
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add bradautomates/head-of-content --skill tiktok-research --agent claude-code

Installs into .claude/skills of the current project.

Files

TikTok Research

Research high-performing TikTok videos, identify outliers, and analyze top video content for hooks and structure.

Prerequisites

APIFY_TOKEN environment variable or in .env
GEMINI_API_KEY environment variable or in .env
apify-client and google-genai Python packages
Accounts configured in .claude/context/tiktok-accounts.md

Verify setup:

python3 -c "
import os
try:
    from dotenv import load_dotenv
    load_dotenv()
except ImportError:
    pass
from apify_client import ApifyClient
from google import genai
assert os.environ.get('APIFY_TOKEN'), 'APIFY_TOKEN not set'
assert os.environ.get('GEMINI_API_KEY'), 'GEMINI_API_KEY not set'
" && echo "Prerequisites OK"

Workflow

1. Create Run Folder

RUN_FOLDER="tiktok-research/$(date +%Y-%m-%d_%H%M%S)" && mkdir -p "$RUN_FOLDER" && echo "$RUN_FOLDER"

2. Fetch Content

python3 .claude/skills/tiktok-research/scripts/fetch_tiktok.py \
  --days 30 \
  --limit 50 \
  --sorting latest \
  --output {RUN_FOLDER}/raw.json

SKILL.md on GitHub

Details

Repository: github.com/bradautomates/head-of-content
Categories: Frontend Development, Data Science & ML
First seen: Apr 16, 2026

More from bradautomates/head-of-content

All 4