maystudios/claude-skills

video-summarizer

Analyzes local MP4 video files using the Gemini API and generates structured Markdown summaries. Supports custom prompts to extract specific information instead of the default summary. Use when the user wants to summarize, analyze, or extract key points from video files in bulk. Triggers on requests like "summarize my videos", "create markdown summaries for the videos", "analyze videos with Gemini", "generate video summaries", or "extract X from my videos". Requires GEMINI_API_KEY environment v…

First seen May 8, 2026

Installation

$ npx skills add maystudios/claude-skills --skill video-summarizer

Similar popular skills

Related neighbors and high-traction skills in the same topics — useful to compare before installing.

Also in this package

Other skills from maystudios/claude-skills · top by installs.

npx skills add maystudios/claude-skills

Browse all from maystudios/claude-skills

More details

Agent compatibility

Declared targets from SKILL.md / docs. Unmarked agents are not listed — the skill may still install via the CLI.

Claude Code Not declared
Cursor Not declared
Codex Not declared
GitHub Copilot Not declared
Windsurf Not declared
Gemini CLI Not declared
Cline Not declared
OpenCode Not declared

Repository health

Stars 22
License LICENSE
Default branch main
Open issues 0
Status Active

Package contents

Files included with this skill beyond the listing page.

  • skill md SKILL.md 3,205 B
  • docs README.md 2,437 B
  • docs SUMMARY.md 549 B

History

  1. First seen on skills.sh
  2. First recorded snapshot · 44 installs

SKILL.md

Video Summarizer

Analyzes MP4 files in a directory via the Gemini API and writes a .md summary file next to each video.

Prerequisites

  • GEMINIAPIKEY env var must be set
  • google-genai installed: py -m pip install google-genai
  • Python available as py (Windows) or python3

Workflow

1. Determine the prompt

Check if the user provided a custom prompt or specific extraction instructions.

  • No custom prompt -> use the default (structured summary with Title, Summary, Key Points, Takeaways)
  • User provides custom instructions -> pass them via --prompt or --prompt-file

A custom prompt completely replaces the default. Examples of custom prompts:

  • "Extract all mentioned tools, their prices, and a one-line description for each"
  • "List every action item and deadline mentioned in this video"
  • "Create a transcript outline with timestamps"

2. Run the script

# Default summary — all videos in current directory (recursive)
py scripts/summarize_videos.py

# Default summary — specific directory
py scripts/summarize_videos.py "C:/path/to/videos"

# Custom prompt (inline) — replaces default summary format
py scripts/summarize_videos.py --prompt "Extract all product names and prices mentioned"

# Custom prompt (from file) — replaces default summary format
py scripts/summarize_videos.py --prompt-file my-prompt.txt

# Both directory and custom prompt
py scripts/summarize_videos.py "C:/path/to/videos" --prompt "List all key decisions made"

3. How Claude should handle user arguments

When the user invokes this skill:

  1. If the user specifies a custom prompt or extraction goal (e.g., "extract all tools mentioned",

"summarize focusing on pricing", "list action items"), pass it via --prompt "...".

  1. If the user provides a prompt file path, pass it via --prompt-file path/to/file.txt.
  2. If the user gives no specific instructions, run without --prompt to use the default format.
  3. If the user specifies a directory, pass it as the first positional argument.

4. Default output format (when no custom prompt is given)

# [Video Title]

## Summary
[2-3 sentence description]

## Key Points
- point 1
- point 2
- ...

## Core Content & Takeaways
[Central message and key insight]

---
*Auto-generated with Gemini API*

Notes

  • Language of the summary matches the language of the video
  • Files are auto-deleted from Gemini storage after processing (48h limit)
  • Already-summarized videos are skipped on re-runs
  • Script path: scripts/summarize_videos.py
  • Model: gemini-3-flash-preview