docs(skill): note keyless free tier fallback in CLI skill#141
Merged
Conversation
The installed CLI skill stated agents must authenticate first, which does not match the code: search, scrape, and interact already work without an API key. Add a keyless free-tier fallback note while keeping browser login and API key as the preferred setup.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Why
The installed
firecrawl-cliskill told agents they "must be installed and authenticated" before doing any work. That does not match the CLI's actual behavior:search,scrape, andinteractalready run without an API key when no key is set. Agents that read the local skills afterinitwere being told to block on authentication that the code does not require, so a keyless agent could wrongly conclude it cannot proceed.This PR fixes the docs mismatch only. No CLI implementation changes.
Summary
skills/firecrawl-cli/SKILL.md: reworded Prerequisites so it is no longer API-key-only. Browser login (firecrawl init --browser) and aFIRECRAWL_API_KEYremain the preferred, conversion-first setup. Added a short fallback noting that search, scrape, and interact work without an API key on the keyless free tier (rate-limited), with a link to the canonical agent onboarding skill for full onboarding paths.skills/firecrawl-cli/rules/install.md: added the same fallback note in the Authentication section, after the browser/API key options. Browser login stays recommended.Both notes point to https://www.firecrawl.dev/agent-onboarding/SKILL.md rather than duplicating onboarding content. The existing authenticated flow is preserved.
Test Plan
firecrawl scrapewith no API key set and it succeeded, confirming the documented fallback matches code.git diffscanned for forbidden terms (credit counts, "per IP", "credits/mo", rate-limit mechanics) — none present.--status/--browserare pre-existing CLI flags, not prose).