video-content-analyzer_skill

This skill analyzes short-form videos to extract hooks, structure, and viral patterns, enabling replication and optimization across reels, TikTok, and Shorts.
  • Python

16

GitHub Stars

1

Bundled Files

2 months ago

Catalog Refreshed

4 months ago

First Indexed

Readme & install

Copy the install command, review bundled files from the catalogue, and read any extended description pulled from the listing source.

Installation

Preview and clipboard use veilstrat where the catalogue uses aiagentskills.

npx veilstrat add skill bradautomates/head-of-content --skill video-content-analyzer

  • SKILL.md4.0 KB

Overview

This skill analyzes short-form videos (Instagram Reels, TikTok, YouTube Shorts) with Gemini AI to extract hooks, content structure, delivery style, and replicable patterns. It converts raw outlier posts into actionable insights you can use to recreate high-performing formats and improve creative briefs.

How this skill works

The analyzer ingests a list of video posts and normalizes platform fields (video URL, caption/title, username). It uses Gemini to identify hook technique, map content structure (sections, pacing, retention tactics), characterize delivery and visual style, and summarize CTA strategies plus why the video likely performed well. Results are returned as a JSON array of per-video analyses, including replicable formulas and suggested hook templates.

When to use it

  • When you need to reverse-engineer viral short-form videos to replicate success
  • When auditing Reels, TikToks, or Shorts for content strategy improvements
  • When creating creative briefs that require specific hook and structure templates
  • When testing hypotheses about which elements drive retention and engagement
  • When generating A/B test ideas for new video variations

Best practices

  • Supply a clean outliers JSON with key fields (url, caption/title, username) to improve mapping accuracy
  • Limit analysis to a manageable sample (3–10 videos) for faster, more focused results
  • Use platform flag (instagram, tiktok, youtube) so the mapper selects correct fields
  • Combine AI output with quantitative metrics (views, watch time) to validate hypotheses
  • Treat the analyzer’s replicable formulas as starting points—iterate and adapt to your brand voice

Example use cases

  • Extract the opening hook technique and a repeatable opening line for a new Reel campaign
  • Map scene-by-scene structure of a viral how-to TikTok to create a templated tutorial format
  • Identify retention tactics (pattern interrupts, overlays) used across top Shorts for a creator playbook
  • Validate whether a high-engagement video succeeded because of delivery style vs. headline
  • Generate CTA placement recommendations and exact CTA phrasing to test in new videos

FAQ

It accepts either a direct list of posts or a wrapped object with an "outliers" array; the mapper handles common platform field variations.

Can it analyze videos without a direct download URL (e.g., TikTok page URL)?

Yes. If only a page URL is available, Gemini will attempt analysis from the page, though results are best with a direct video URL.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational