Multi Video Synthesis Agent Skill

by google

Performs high-density targeted extraction across 10+ videos to map semantic landscapes, consensus, and controversies.

592 tokens

context cost

the whole folder, loaded on every use

files

instructions only

copies elsewhere

how many repositories repackaged it

10025

stars on the repo

on the repository, not the skill itself

Install

one command, takes just this skill from the repository

npx skills add https://github.com/google/adk-samples --skill multi-video-synthesis

The instruction itself

1 sections, as written by the author

Skill: Autonomous Multi-Video Synthesis Pipeline

Objective: (ATTENTION GUARDIAN) Perform a high-density Targeted Extraction across a massive amount of video content (10+ videos) to extract the absolute truth, map the semantic landscape, and save the user from hour-long research.

Execution Steps:

Broad Search: Use search_youtube with max_results=15 to cast a wide net across the topic.
RoA Filtering (MANDATORY):
Fetch details for ALL videos using get_video_details.
Calculate engagement metrics with calculate_engagement_metrics.
Identify the top 10 videos that have the highest "Return on Attention" (high engagement, relevant keywords, authoritative channels).
Explicitly tell the user which videos you are ignoring and why (e.g., "Filtering out 5 videos that appear to be clickbait/low-engagement").
Massive Ingestion:
For the top 10 videos, attempt to retrieve all transcripts using get_video_transcript.
If any transcripts are unavailable, use get_video_details to read their metadata and descriptions as a high-signal fallback.
Semantic Mapping & Synthesis:
Cross-reference all transcripts simultaneously.
Map the "Semantic Vectors": Identify the Consensus (arguments shared by 3+ creators), the Controversies (conflicting viewpoints), and the Hidden Gems (unique insights mentioned by only one expert).
Precision Targeting:
For every major argument or insight in your synthesis, you MUST provide at least one direct ?t=... jump-link using generate_timestamp_url.
Unified Report Delivery:
Provide a structured "Multi-Video Intelligence Briefing".
Include a "Consensus vs. Controversy" table.
Provide a "Clips of Interest" list with direct timestamp URLs.
Always ask if the user wants to see a visualization of these findings (e.g., a chart of creator sentiment) or publish this to a shareable HTML report.

Key Design Principle: You are the orchestrator of this pipeline. You are not just summarizing videos; you are synthesizing a new, high-density knowledge artifact that does not exist elsewhere on the web.

Other skills for the same job

different authors, same section of the catalogue

Canvas Design

by anthropics

vendor ×13

Create beautiful visual art in .png and .pdf documents using design philosophy. You should use this skill when the user asks to create a poster, piece of art, design, or other static piece. Create original visual designs, never copying existing artists' work to avoid copyright violations.

Creating algorithmic art using p5.js with seeded randomness and interactive parameter exploration. Use this when users request creating art using code, generative art, algorithmic art, flow fields, or particle systems. Create original algorithmic art rather than copying existing artists' work to avoid copyright violations.

Improves the quality of images, especially screenshots, by enhancing resolution, sharpness, and clarity. Perfect for preparing images for presentations, documentation, or social media posts.

Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.

Lightweight WSI tile extraction and preprocessing. Use for basic slide processing tissue detection, tile extraction, stain normalization for H&E images. Best for simple pipelines, dataset preparation, quick tile-based analysis. For advanced spatial proteomics, multiplexed imaging, or deep learning pipelines use pathml.

Microscopy data management platform. Access images via Python, retrieve datasets, analyze pixels, manage ROIs/annotations, batch processing, for high-content screening and microscopy workflows.

Python library for working with DICOM (Digital Imaging and Communications in Medicine) files. Use this skill when reading, writing, or modifying medical imaging data in DICOM format, extracting pixel data from medical images (CT, MRI, X-ray, ultrasound), anonymizing DICOM files, working with DICOM metadata and tags, converting DICOM images to other formats, handling compressed DICOM data, or processing medical imaging datasets. Applies to tasks involving medical image analysis, PACS systems, radiology workflows, and healthcare imaging applications.

This skill should be used when working with pre-trained transformer models for natural language processing, computer vision, audio, or multimodal tasks. Use for text generation, classification, question answering, translation, summarization, image classification, object detection, speech recognition, and fine-tuning models on custom datasets.

13k tokens

How to use it

Copy the folder

Take google/multi-video-synthesis from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.