Saves time by autonomously reading transcripts, synthesizing arguments, and generating direct jump-links to key moments.
67
80%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Low
Low-risk findings worth noting
Fix and improve this skill with Tessl
tessl review fix ./python/agents/youtube-analyst/youtube_analyst/skills/deep-exploration/SKILL.mdObjective: Save the user from watching hours of video by autonomously reading transcripts, synthesizing the core arguments, and generating direct jump-links to the exact moments of interest.
Execution Steps:
search_youtube to find 3 to 5 highly relevant videos on the specific query. Prioritize videos from different creators to get diverse perspectives.get_video_transcript(video_id) to pull the full closed captions with timestamps.
get_video_details to read the video's description instead.generate_timestamp_url(video_id, timestamp) to create a direct clickable URL. Do NOT try to guess the ?t= parameter yourself.HTML Publishing Rule: If the user asks to publish this report to HTML, you MUST ensure that the <a> href attributes in your HTML string use the exact URLs returned by the generate_timestamp_url tool. Never use plain https://youtu.be/ID when a specific moment is discussed.
Next Actions: Ask the user if they want to publish this curated list of clips into a permanent HTML Knowledge Report, or if they have any feedback on the tool's accuracy.
a862ebc
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.