Multi Video Synthesis Agent Skill
Performs high-density targeted extraction across 10+ videos to map semantic landscapes, consensus, and controversies.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/google/adk-samples --skill multi-video-synthesisThe instruction itself
1 sections, as written by the authorSkill: 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_youtubewithmax_results=15to 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_detailsto 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 usinggenerate_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
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.
Create and edit JSON Canvas files (.canvas) with nodes, edges, groups, and connections. Use when working with .canvas files, creating visual canvases, mind maps, flowcharts, or when the user mentions Canvas files in Obsidian.
Publish Markdown articles to X (Twitter) Articles editor with proper formatting. Use when user wants to publish a Markdown file/URL to X Articles, or mentions "publish to X", "post article to Twitter", "X article", or wants help with X Premium article publishing. Handles cover image upload and converts Markdown to rich text automatically.
Downloads videos from YouTube and other platforms for offline viewing, editing, or archival. Handles various formats and quality options.
Teaches the AI to design like a high-end agency. Defines the exact fonts, spacing, shadows, card structures, and animations that make a website feel expensive. Blocks all the common defaults that make AI designs look cheap or generic.
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.
How to use it
Take google/multi-video-synthesis from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
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.