Firecrawl search
ArkSpace is a creative workspace for orchestrating agent skills, roles, and workflows across Claude Code and Code
npx -y skills add arch3rPro/ark-space --skill firecrawl-searchAssembled 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.
What its author says it does
Copied from the file, not written here
Use when querying Firecrawl through ArkSpace web_search routing, especially when search results may need full-page scraping, news/web source selection, or Firecrawl CLI-backed web discovery.
SKILL.md
3.6 KB, as published. Nobody here has run it
Firecrawl Search
Use Firecrawl as a CLI-backed web_search provider when ArkSpace routes search to Firecrawl or when the user explicitly asks for Firecrawl search.
Firecrawl configuration is managed by provider-manager; do not ask the user to edit config files by hand.
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 web_search
Set up Firecrawl once:
python3 <installed-arkspace-path>/scripts/arkspace.py provider setup firecrawl --wizard
For multiple API keys:
python3 <installed-arkspace-path>/scripts/arkspace.py provider setup firecrawl --wizard --key-count 2
The Firecrawl CLI must also be available as firecrawl, or npx must be available for the helper fallback.
Missing Configuration Recovery
If the provider check reports a missing Firecrawl API key:
- Ask the user whether to start setup now: "Firecrawl is not configured. Should I start the ArkSpace setup wizard now?"
- Present exactly two choices:
- "Start setup wizard" - start interactive setup with
python3 <installed-arkspace-path>/scripts/arkspace.py provider setup firecrawl --wizard. - "Not now" - leave Firecrawl unconfigured; if the user still wants results, ask whether to continue with another registered provider or a clearly labeled non-ArkSpace fallback.
- "Start setup wizard" - start interactive setup with
- Run the setup command only when the host shell can provide interactive secret input. If the shell is non-interactive, do not run
--wizardthrough that tool. - In Claude Code non-interactive tool sessions, offer:
- run
! python3 <installed-arkspace-path>/scripts/arkspace.py provider setup firecrawl --wizardin the Claude prompt or terminal, or - paste the API key in chat and let the agent save it with
python3 <installed-arkspace-path>/scripts/arkspace.py provider setup firecrawl --save-secret FIRECRAWL_API_KEY --secret-stdin.
- run
- Re-run the provider check after setup.
- If setup succeeds, rerun or tell the user to rerun the original invocation, such as
/ark-space:firecrawl-search <query>. - Do not return Firecrawl search results until the provider check succeeds.
Helper Script
Basic search:
python3 <installed-arkspace-path>/scripts/arkspace.py web search --provider firecrawl "agent skills" --output json
Search and scrape result pages:
python3 <installed-arkspace-path>/scripts/arkspace.py web search --provider firecrawl "OpenClaw documentation" \
--include-text \
--max-results 5 \
--output json
Routing Notes
- Use
registry/search-providers.yamlbefore execution. - Prefer Firecrawl when search results should be paired with scraped content or when Firecrawl-specific web/news/category controls matter.
- Use
firecrawl-scrapewhen the user provides a URL. - Use
firecrawl-maporfirecrawl-crawlfor known-site URL discovery or bulk extraction.