Firecrawl page extraction brief
Use “Firecrawl page extraction brief” in Recued. It provides a read-only Firecrawl page extraction workflow.
How it works
Inspect the data fetches, transforms, gates, and output this recipe runs.
Process (9 steps)
normalized_url
trim
Trim whitespace from setting url
scrape
recued-core.firecrawl.page.scrape
Scrape page on firecrawl
links
default
Apply default
link_count
count
Count items in links
summarize
core.ai.summarize
AI generates a concise summary
link_rows
map
Extract from each item
link_table_rows
slice
Take a subset of
link_table
to_table
Format results as a data table
card
to_summary
Format results as a summary card
▼
Output
summary
card
table
link_table
Settings
Configurable at install. Defaults shown — change them anytime in Recued.
url
setting
=
focus
setting
=
Summarize the scraped page for a knowledge/RAG user: topic, key facts, useful links, missing sections, and any warnings. Do not invent facts outside the Firecrawl response.
formats
setting
=
markdown,links
max age ms
setting
=
172800000
max length
setting
=
900
timeout ms
setting
=
60000
exclude tags
setting
=
include tags
setting
=
only main content
setting
=
true
Uses (2 operations)
Pack operation
Scrape page on firecrawl
recued-core.firecrawl.page.scrape
AI models
AI generates a concise summary
core.ai.summarize
Trust & control
What installing this recipe would let it do. Recued grants these permissions at install — review them there before approving.
Permissions it requires
Declared by the recipe — Recued grants these at install, where you review them before approving.What it's allowed to do
Read
AI models
core.ai.summarize
read-only
1 more isn't listed here. You'll see it at install.