What is video-fetch-and-summarize?

A tool that downloads online videos and creates a Markdown summary for each one using Google’s Gemini API. Each video is stored with its downloaded MP4 file and summary in its own folder.

Use it with video URLs or a text file of URLs, with optional custom prompts, and with browser cookies for content requiring a login.

It removes the manual work of downloading videos and reviewing them before writing notes or extracting specific information.

video-fetch-and-summarize — Skill for Claude Code and Codex by maystud

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent

npx skills add maystudios/claude-skills --skill video-fetch-and-summarize

Clone the repo

git clone --depth 1 https://github.com/maystudios/claude-skills

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/skills/maystudios/claude-skills/video-fetch-and-summarize/github.svg)](https://agentmods.dev/skills/maystudios/claude-skills/video-fetch-and-summarize)

Your own site

<a href="https://agentmods.dev/skills/maystudios/claude-skills/video-fetch-and-summarize"><img src="https://agentmods.dev/badge/skills/maystudios/claude-skills/video-fetch-and-summarize/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/maystudios/claude-skills/video-fetch-and-summarize"><img src="https://agentmods.dev/badge/skills/maystudios/claude-skills/video-fetch-and-summarize.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 169 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,155 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

high YARA Match · line 54
YARA rule matched a known malware signature (reverse shell, backdoor, ransomware, C2 framework, or info stealer).

Fix: Remove the malware payload or compromised file entirely. Investigate how it entered the skill and audit all other artifacts for additional indicators of compromise.

How audits are shown

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00169	$0.01155
Opus 5	$0.00084	$0.00577
Sonnet 5	$0.00034	$0.00231
Haiku 4.5	$0.00017	$0.00115

Measured 12d ago against content hash 6290cdb04b70, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

video-fetch-and-summarize scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/fetch_and_summarize.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

video-fetch-and-summarize/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Video Fetch & Summarize

Downloads videos from URLs and generates a Markdown summary per video via Gemini. Fully self-contained — no other skills required.

Output Structure

<output_dir>/
  <Video_Title>/
      <uploader>_<id>.mp4
      summary.md

Prerequisites

GEMINI_API_KEY env var set
yt-dlp and google-genai — auto-installed on first run if missing
Python available as py (Windows) or python3

Script

scripts/fetch_and_summarize.py

Usage

# Direct URLs — default summary
py scripts/fetch_and_summarize.py "https://..." "https://..." -o ./output

# File containing URLs (TXT, Markdown, or any text file)
py scripts/fetch_and_summarize.py links.txt -o ./output

# Custom prompt (inline) — replaces default summary format
py scripts/fetch_and_summarize.py "https://..." --prompt "Extract all mentioned tools and prices"

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

# With browser cookies (for private/login-required content)
py scripts/fetch_and_summarize.py links.txt --cookies-from-browser chrome

How Claude should handle user arguments

When the user invokes this skill:

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 "...".
If the user provides a prompt file path, pass it via --prompt-file path/to/file.txt.
If the user gives no specific instructions, run without --prompt to use the default format.
A custom prompt completely replaces the default — it does not add to it.

Workflow

Extract all URLs from provided arguments and/or files (regex-based, works with any text format)
For each URL: a. Fetch video metadata via yt-dlp --dump-json to get the title for the folder name b. Download the video as best-quality MP4 into <output>/<Title>/ c. Upload MP4 to the Gemini Files API, wait for ACTIVE state d. Generate Markdown summary (using custom or default prompt), delete file from Gemini storage e. Save summary as <output>/<Title>/summary.md
Skip videos where both MP4 and summary.md already exist (idempotent re-runs)

Read the full file on GitHub · 127 lines

Files

What ships with it

2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

12d ago First seen · 127 lines · 169 tokens per session scan A 6290cdb04b70

Subscribe to this mod's changes

video-fetch-and-summarize is a skill published in the GitHub repository maystudios/claude-skills (22 stars, last pushed 27d ago), licensed MIT. It adds 169 tokens to every session and 1,155 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Code Creative and media Research agent-skills ai-coding claude-skills llama-cpp ue5

presentation-chef

Convert any content into a stunning Apple Keynote-style HTML presentation. Takes markdown, text descriptions, or structured data and generates a single self-contained .html file with cinematic animations, glassmorphism, and premium design. Inspired by ChronicleHQ.

sacredvoid/skillkit · 52 tokens

creative-code-lab

Use when user asks to create generative art, creative coding sketches, visual experiments, particle systems, shader effects, procedural graphics, interactive canvases, or any code-as-art project. Use when building animated backgrounds, flow fields, fractals, L-systems, noise-based visuals, text effects, fluid…

sacredvoid/skillkit · 113 tokens

icons8

Fetch icons, illustrations, and photos from Icons8. Search 1.5M+ icons across 116 styles, vector illustrations, and 500K+ stock photos. Supports API (with key) and free CDN fallback (no key needed).

sacredvoid/skillkit · 53 tokens

logo-generator

Generate custom logos with adaptive brainstorming and full brand kit export. Scans project context (README, package.json, CSS, existing assets) to inform design. Outputs favicons (16-512 + ICO), social images (OG, Twitter), dark/light/mono SVG variants, and an HTML preview.

sacredvoid/skillkit · 63 tokens

local-image-gen

Generate custom images locally using Stable Diffusion. Auto-detects your hardware (Apple Silicon, NVIDIA, AMD, CPU) and picks the best model and settings. Supports single and batch modes. Cross-platform: macOS, Linux, Windows.