Computers
Browse a site and extract
Drive a real browser on a computer to collect what search cannot reach.
Use this skill in a chatOpens a new chat with it attached.
What it asks you for
- Site or pagerequired
- Where to go.
- What to collectrequired
- The fields you want back.
What it tells the AI to do
The full instructions, exactly as they run.
Collect {{ extract }} from {{ target }}.
Try the cheap route first: a plain fetch, then the site's own API or feed if it
has one. A headless browser is for pages that genuinely need rendering or a
session, and it costs far more than a request.
When you do drive a browser on a computer:
- Respect the site's terms and `robots.txt`. Do not work around a paywall,
a login you were not given, or an anti-bot measure.
- Go at a human pace. A tight loop against someone else's server is an outage
you caused.
- Extract into a structured table, not prose, and include the source URL per row.
Report what you could not collect and why, rather than returning a short table
that looks complete.- computer
- browser
- scrape
- extract
More computers skills
Run it on your own work
idapt gives this skill your files, 200+ models, and a real computer to work on. Start a chat and it is already attached.
Use Browse a site and extract