Start a Firecrawl extract job
Approval-gated Firecrawl workflow for starting one structured extract job from explicit URLs. It calls recued-core.firecrawl.extract.create with an optional prompt/schema and immediately reads the new extract status. It does not crawl arbitrary routes outside the supplied URLs, register webhooks, send custom headers/cookies, run browser actions, mutate team settings, or call arbitrary Firecrawl API routes.
How it works
Inspect the data fetches, transforms, gates, and output this recipe runs.
Process (5 steps)
create_extract
?
extract_status
?
invalid_urls
default
Apply default
invalid_count
count
Count items in invalid urls
card
to_summary
Format results as a summary card
Settings
Configurable at install. Defaults shown — change them anytime in Recued.
urls
setting
=
prompt
setting
=
Extract the main facts, entities, prices, dates, and source URLs that a downstream workflow would need. Return concise structured data only.
schema
setting
=
[object Object]
formats
setting
=
markdown
firecrawl
setting
=
show sources
setting
=
true
enable web search
setting
=
false
only main content
setting
=
true
include subdomains
setting
=
false
Trust & control
What installing this recipe would let it do. Recued grants these permissions at install — review them there before approving.