Firecrawl agent

Skill arch3rPro/ark-space/plugins/ark-space/skills/firecrawl-agent

Use when running Firecrawl Agent for structured extraction, schema-guided web data collection, or ArkSpace structured_extract routing that selects Firecrawl.From its SKILL.md

Install

npx -y skills add arch3rPro/ark-space --skill firecrawl-agent

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

SKILL.md

2.2 KB, 461 tokens by cl100k_base, as published. Nobody here has run it

Firecrawl Agent

Use Firecrawl Agent as a CLI-backed structured_extract provider when the user needs schema-shaped data from one or more web pages, especially when the task is more than a simple scrape.

Source References

Official CLI: https://github.com/firecrawl/cli
Firecrawl OpenClaw guide: https://docs.firecrawl.dev/quickstarts/openclaw
OpenClaw tool guide: https://docs.openclaw.ai/tools/firecrawl

Before Use

Resolve the installed ArkSpace package root before running commands. Replace <installed-arkspace-path> with the directory two levels above this loaded SKILL.md, such as /Users/<user>/.claude/plugins/cache/ark-space/ark-space/0.1.2. Use the installed package path, not a repository-relative command.

Check configuration:

python3 <installed-arkspace-path>/scripts/arkspace.py provider check firecrawl --capability structured_extract

Set up Firecrawl:

python3 <installed-arkspace-path>/scripts/arkspace.py provider setup firecrawl --wizard

Missing Configuration Recovery

If the provider check reports missing configuration, ask whether to start setup with python3 <installed-arkspace-path>/scripts/arkspace.py provider setup firecrawl --wizard. Do not run Firecrawl Agent until the provider check succeeds.

Helper Script

Run a schema-guided extraction:

python3 <installed-arkspace-path>/scripts/arkspace.py structured extract --provider firecrawl \
  "extract product names and prices" \
  --urls "https://example.com/pricing" \
  --schema '{"type":"object"}' \
  --wait \
  --output json

Check a job:

python3 <installed-arkspace-path>/scripts/arkspace.py structured extract --provider firecrawl <job-id> --status --output json

Routing Notes

Use registry/structured-extract-providers.yaml before execution.
Prefer firecrawl-scrape for reading a known URL without schema extraction.
Prefer firecrawl-crawl for bulk extraction across many pages before synthesizing manually.

Gives 0 of the 12 instructions most context ai engineering skills give in 461 tokens

Counted across 1,193 of the 1,976 authors here whose files we hold, read 2026-08-07

Dispatch a fresh implementer subagent per taskin 48 of 1193, across 19 files
Dispatch a final code reviewer after all tasksin 33 of 1193, across 8 files
Provide full task text to the subagentin 30 of 1193, across 9 files
Review spec compliance before code qualityin 27 of 1193, across 10 files
Make the hook script executablein 26 of 1193, across 8 files
Re-snapshot after navigation or DOM changesin 25 of 1193, across 19 files
Read files before editing themin 22 of 1193, across 11 files
Answer subagent questions before proceedingin 22 of 1193, across 7 files
Mark task complete in TodoWrite after approvalin 22 of 1193, across 6 files
Merge hook into existing settingsin 21 of 1193, across 3 files
Ask if installation is global or projectin 20 of 1193, across 2 files
Copy the hook script to target locationin 20 of 1193, across 2 files

Said here and by no other author read

resolve installed package root before running commands
check provider capability before use
do not run until provider check succeeds
ask before starting setup
run schema-guided extraction via helper script
check job status via helper script

Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.