firecrawl

# Firecrawl Use this skill for unauthenticated public web ingestion when HTTP fetch and server-side parsing are enough. Firecrawl is the cheap path for public pages and docs. Use the browser skill instead when the task needs login, interaction, form filling, visual inspection, or client-side state. Do not use Firecrawl to bypass access controls. ## Credential Rules For managed mode, store the Firecrawl API key in HybridClaw encrypted runtime secrets: ```bash hybridclaw secret set FIRECRAWL_API_KEY "<fc-api-key>" ``` For a self-hosted Firecrawl instance, set the gateway-reachable base URL in the runtime environment or pass it explicitly to the helper: ```bash export FIRECRAWL_SELF_HOST_BASE_URL="http://firecrawl:3002" ``` The helper accepts base URLs with or without `/v2` and normalizes them to the v2 API path. If your self-hosted Firecrawl deployment enables API authentication, store that token separately: ```bash hybridclaw secret set FIRECRAWL_SELF_HOST_API_KEY "<self-host-api-key>" ``` Use HTTPS for any self-host endpoint outside a trusted private network, especially when `--self-host-auth` is enabled; plain HTTP can expose bearer tokens on untrusted networks. For live calls, run the colocated helper to build an `http_request` payload and pass only the emitted `httpRequest` object to the built-in `http_request` tool. The helper sets `bearerSecretName: "FIRECRAWL_API_KEY"` so the gateway injects the managed token server-side. In self-host mode, pass `--self-host-a...