Skip to content
InfratoApp
InfratoApp / Resources / Agent skills / watch

watch

watch is an agent skill published by diffusionstudio, listed under research. It lives in the diffusionstudio/skills repository, which has 146 GitHub stars and is licensed under MIT; we last read it on 2026-10-12.

Answer questions about video or audio files, summarize content, find specific scenes, pull quotes, and describe events and their timing. Required when users need information, summaries, or specific moments located within footage.

Install

skills is a generic installer for any repository of Claude agent skills -- it reads diffusionstudio/skills’s own structure rather than assuming one, the same way this page reads the skill’s own SKILL.md rather than assuming a format.

npx skills add diffusionstudio/skills

Maintenance

Stars
146
State
listed
Licence
MIT
From the repository

Watch and understand footage with Diffusion Studio: answer questions about a video or audio file, summarize it, find scenes and moments, pull quotes, and describe what happens and when. Use whenever the user asks what's in a piece of footage, wants a summary or recap, wants to locate a moment ("where does X happen", "find the scene where..."), or needs a claim about a video or audio file checked.

watch compared with similar skills

watch compared with other skills for the same job, by publisher, what it does, repository stars and last update
SkillPublisherWhat it doesRepo starsLast update
watch (this page)diffusionstudioWatch and understand footage with Diffusion Studio: answer questions about a video or audio file, summarize i…1462026-10-22
researchmattpocockInvestigate a question against high-trust primary sources and capture the findings as a Markdown file in the…303,5492026-10-22
huggingface-paper-publisherhuggingfacePublish and manage research papers on Hugging Face Hub. Supports creating paper pages, linking papers to mode…11,2132026-10-23
huggingface-papershuggingfaceLook up and read Hugging Face paper pages in markdown, and use the papers API for structured metadata such as…11,2132026-10-23
amazon-alexa-qabrowser-actAmazon Alexa for Shopping Q&A automation: submits questions to Amazon's Alexa/Rufus AI shopping assistant and…6,2772026-08-24
amazon-best-selling-products-finder-api-skillbrowser-actThis skill helps users extract structured best-selling product data from Amazon via the BrowserAct API. Agent…6,2772026-08-24
amazon-competitor-analyzerbrowser-actScrapes Amazon product data from ASINs using browseract.com automation API and performs surgical competitive…6,2772026-08-24

Skills from the same repository first, then others for this job by repository stars. Figures are from each repository when we last read it.

Common questions about watch

What does watch do?
Answer questions about video or audio files, summarize content, find specific scenes, pull quotes, and describe events and their timing. Required when users need information, summaries, or specific moments located within footage.
How do I install watch?
Run npx skills add diffusionstudio/skills. The skills installer reads the repository’s own structure, so it works for any repository of agent skills.
Who publishes watch?
diffusionstudio.
Is watch maintained, and what licence does it use?
Its repository has 146 GitHub stars and its state in our directory is listed. Its last commit we recorded was on 2026-10-22. The repository declares the MIT licence.

More agent skills for research

All research entries →

Learn this on Infrato