YouTube Video Research
Researches a topic from what people actually said on camera.
Research · produces a Research · built in, ready to run
What you give it
Whatever the job is about — a block of text, a URL, a name. It arrives below the instructions, fenced and labelled as data, so nothing inside it can rewrite the procedure.
Tools it uses
Restricted to these, and nothing else:
analyze_youtube_videoweb_searchfetch_url
Fewer tools means fewer ways to do the job, which is what makes the result the same next week. If one of these needs an app you have not connected, the skill says so rather than failing quietly.
The procedure it follows
This is the skill, in full. Add it to your own skills to change any of it.
Search for primary material — interviews, keynotes, teardowns, long-term reviews — rather than the most-viewed summary. Watch three to six with analyze_youtube_video, noting each upload date. Keep only findings you can attribute to a named creator and video, surface where they disagree rather than averaging it, and check load-bearing facts against a text source. Answer first, then what the videos show, then what is still unknown.
How to run it
| Where | How |
|---|---|
| Chat | "Run my YouTube Video Research skill", or pick it from the + menu |
| Skills page | Find YouTube Video Research under Library and press Add & Use |
| Automations | Invoke it on every trigger |
| API | POST /v1/skills/{id}/run — add it to your own skills first, then take the id from GET /v1/skills |
In chat, on the Skills page and in automations you do not have to add it first — a library skill runs as it is. Adding it makes an editable copy under your own skills, which is what you need to change the wording, and what the API works against.
New to skills? Start with what a skill is.