agentleFS
r0undm1dn1ghty-starr0undm1dn1ghty-star/ds_content-radar/.claude/skills/video-content-analyzer/SKILL.md

video-content-analyzer

Skill0 starsChanged 35 days agoMITView on GitHub

Analyze short-form videos with Gemini AI to extract hooks, content structure, and replicable patterns. Supports Instagram Reels, TikTok, and YouTube Shorts.

  • Reads credentials

2 other projects use a version of this, 2 of them edited.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Wrote their own version · 0

    None found.

    How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.

  • In this repository5 other files it gives its agents.

The file

Files
SKILL.md

Video Content Analyzer

Analyze short-form videos with Gemini AI to extract hooks, content structure, delivery style, and CTA strategies.

Prerequisites

  • GEMINI_API_KEY environment variable
  • google-genai and requests Python packages

Usage

python3 .claude/skills/video-content-analyzer/scripts/analyze_videos.py \
  --input outliers.json \
  --output video-analysis.json \
  --platform instagram \
  --max-videos 5

Parameters

ArgDescription
--input, -iInput JSON file with outlier posts (required)
--output, -oOutput JSON file for results (required)
--platform, -pPlatform: instagram, tiktok, or youtube (default: instagram)
--max-videos, -nMax videos to analyze (default: 5)

Input Format

Accepts outlier JSON from platform-specific research skills. Handles both formats:

  • Direct list: [{post1}, {post2}, ...]
  • Wrapped: {"outliers": [{post1}, {post2}, ...]}

The script automatically maps platform-specific fields:

PlatformVideo URL FieldsCaptionUsername
InstagramvideoUrlcaptionownerUsername
TikTokvideoUrl, video_url, webVideoUrltext, descauthorUsername
YouTubevideoUrl, urltitlechannelTitle

TikTok Note: The yt-dlp fetcher returns webVideoUrl (the TikTok page URL) rather than a direct video download URL. Gemini will attempt to analyze from this page URL.

Output

Returns JSON array with analysis for each video:

[
  {
    "post_id": "ABC123",
    "username": "creator",
    "url": "https://...",
    "platform": "instagram",
    "likes": 50000,
    "comments": 1200,
    "views": 500000,
    "analysis": {
      "hook": {
        "technique": "pattern-interrupt",
        "opening_line": "Stop scrolling if you...",
        "attention_grab": "Creates urgency and targets specific audience",
        "replicable_formula": "Stop scrolling if you [pain point]"
      },
      "content_structure": {
        "format": "problem-solution",
        "sections": [...],
        "pacing": "fast",
        "retention_techniques": ["pattern interrupts", "text overlays"]
      },
      "delivery_style": {
        "speaking": "direct-to-camera",
        "energy": "high-energy",
        "text_overlays": true,
        "visual_style": "quick cuts with b-roll"
      },
      "cta_strategy": {
        "type": "follow",
        "cta_text": "Follow for more tips",
        "placement": "end"
      },
      "why_it_works": "..."
    }
  }
]

Hook Techniques

The analyzer identifies these hook types:

  • pattern-interrupt - Breaks expected patterns
  • question - Opens with engaging question
  • bold-claim - Makes surprising statement
  • story-tease - Hints at compelling narrative
  • visual-shock - Striking visual opening
  • curiosity-gap - Creates information gap
  • direct-address - Speaks to specific audience
  • controversial-take - Polarizing opinion
  • relatable-pain - Targets common struggle
  • transformation-preview - Shows before/after

Content Formats

  • problem-solution - Present problem, offer fix
  • listicle - Numbered tips/items
  • story - Narrative arc
  • tutorial - Step-by-step how-to
  • before-after - Transformation reveal
  • day-in-life - Lifestyle content
  • reaction - Response to other content
  • hot-take - Opinion piece
  • tool-demo - Product/tool showcase

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.