Pre-watch decision tool for YouTube videos. Use when the user pastes a YouTube URL and asks "is this worth watching", "should I watch this", "should I skip this", "watch or skip", "give me a verdict on this video", "is this YouTube video any good", or wants a pre-watch summary that ends in a recommendation. Returns WATCH or SKIP with a 0–10 score (5 and 6 disallowed — the tool commits), a best-minutes range, substance density (concrete vs vague claims, evidence shown, pitches), and a who-should-watch / who-should-skip split. Also catches clickbait thumbnails — when the host LLM has vision capability, the skill extracts text overlays and visual elements from the thumbnail and flags any specific outcome promise (e.g. "$10K/DAY") that the transcript doesn't substantiate. Every flag cites a verbatim quote — from the transcript with a timestamp, or from the thumbnail with the slot [thumb]. No hallucinated criticism. For neutral summaries with no judgment use youtube-summary instead. Saves the full report to ~/youtube-reports/ and prints a one-glance dashboard inline.
Install with
Claude CodeCodexCursorGitHub CopilotGemini CLI
Supported by the Atlas install prompt. Skill-specific requirements vary.
Skill stats
Skills1CategoryContent & writingStars0
About this skill
Pre-watch decision tool for YouTube videos. Use when the user pastes a YouTube URL and asks "is this worth watching", "should I watch this", "should I skip this", "watch or skip", "give me a verdict on this video", "is this YouTube video any good", or wants a pre-watch summary that ends in a recommendation. Returns WATCH or SKIP with a 0–10 score (5 and 6 disallowed — the tool commits), a best-minutes range, substance density (concrete vs vague claims, evidence shown, pitches), and a who-should-watch / who-should-skip split. Also catches clickbait thumbnails — when the host LLM has vision capability, the skill extracts text overlays and visual elements from the thumbnail and flags any specific outcome promise (e.g. "$10K/DAY") that the transcript doesn't substantiate. Every flag cites a verbatim quote — from the transcript with a timestamp, or from the thumbnail with the slot [thumb]. No hallucinated criticism. For neutral summaries with no judgment use youtube-summary instead. Saves the full report to ~/youtube-reports/ and prints a one-glance dashboard inline.
Quick start
Copy the install prompt. Use the green button above this README.
Send it to your agent. Paste it into your coding agent’s chat and send.
Review the setup. Your agent checks the skill’s instructions, requirements, and installation scope.
Pre-watch decision tool for YouTube videos. Use when the user pastes a YouTube URL and asks "is this worth watching", "should I watch this", "should I skip this", "watch or skip", "give me a verdict on this video", "is this YouTube video any good", or wants a pre-watch summary that ends in a recommendation. Returns WATCH or SKIP with a 0–10 score (5 and 6 disallowed — the tool commits), a best-minutes range, substance density (concrete vs vague claims, evidence shown, pitches), and a who-should-watch / who-should-skip split. Also catches **clickbait thumbnails** — when the host LLM has vision capability, the skill extracts text overlays and visual elements from the thumbnail and flags any specific outcome promise (e.g. "$10K/DAY") that the transcript doesn't substantiate. Every flag cites a verbatim quote — from the transcript with a timestamp, or from the thumbnail with the slot `[thumb]`. No hallucinated criticism. For neutral summaries with no judgment use `youtube-summary` instead. Saves the full report to ~/youtube-reports/ and prints a one-glance dashboard inline.
About this listing
Category
Content & writing
Reported license
Not specified
Listing language (estimated)
English
Review status
Not individually reviewed
Agent compatibility
Atlas installation supports Claude Code, Codex, and Cursor. Skill-specific dependencies and features are checked during setup.
Claude Code
Codex
Cursor
GitHub Copilot
Gemini CLI