PluginBench
Skill
Official
Review
Audit score 70

firecrawl-qa

firecrawl/firecrawl-workflows

QA test live websites with Firecrawl browser and scrape evidence for comprehensive quality reports.

What is firecrawl-qa?

Firecrawl QA automates exploratory testing of live websites, including form testing, navigation checks, responsive design validation, and performance observations. Use it when you need a pre-launch quality review, bug discovery, or structured QA evidence collection.

  • Discover and map website pages using Firecrawl map
  • Test forms, interactions, and navigation with Firecrawl browser
  • Extract page content and validate links via scraping
  • Run parallel test streams (navigation, forms, responsive, performance)
  • Generate structured QA reports with severity levels and reproduction steps
  • Capture evidence and screenshots for bug documentation

How to install firecrawl-qa

npx skills add https://github.com/firecrawl/firecrawl-workflows --skill firecrawl-qa
Prerequisites
  • Firecrawl API key (FIRECRAWL_API_KEY environment variable)
  • Target website URL (public or accessible)
  • Optional: credentials or constraints for protected flows
Claude Code
Cursor
Windsurf
Cline

How to use firecrawl-qa

  1. 1.Provide the target website URL and QA focus area (full, forms, navigation, responsive, or performance)
  2. 2.The skill infers context and asks 1-3 clarifying questions only if needed
  3. 3.Firecrawl maps pages and runs parallel test streams based on focus
  4. 4.Each tester returns findings with severity, URL, description, and reproduction steps
  5. 5.Review the final QA report with health score, categorized issues, and positive observations

Use cases

Good for
  • Pre-launch quality review of a staging or production site
  • Exploratory testing to discover functional bugs and edge cases
  • Form validation and happy-path testing across multiple flows
  • Navigation and link integrity checks across site structure
  • Responsive design verification across desktop, tablet, and mobile viewports
Who it's for
  • QA engineers and testers
  • Product managers preparing for launch
  • Developers validating site changes
  • DevOps teams running pre-deployment checks

firecrawl-qa FAQ

What QA areas does this skill cover?

Navigation and links, forms and interactions, content and visual checks, error states, responsive design across devices, and page load performance.

Do I need to set up anything before using this skill?

You need a Firecrawl API key set as FIRECRAWL_API_KEY. The skill handles the rest, including page discovery and test execution.

Can it test protected or authenticated pages?

Yes, if you provide credentials or constraints during the onboarding interview. The skill will ask for them if needed.

What format is the QA report in?

A structured markdown report with summary, categorized issues (critical/major/minor), positive observations, pages tested, and rerun inputs for reproducibility.

How does it avoid reporting speculative bugs?

The skill requires evidence and reproduction steps for all functional issues, and deduplicates findings across parallel testers to ensure quality.

Full instructions (SKILL.md)

Source of truth, from firecrawl/firecrawl-workflows.


name: firecrawl-qa description: QA test a live website with Firecrawl browser and scrape evidence. Use when the user wants exploratory QA, form testing, navigation/link checks, responsive checks, performance observations, bug reports, or a pre-launch quality review. license: ISC metadata: author: firecrawl version: "0.1.0" homepage: https://www.firecrawl.dev source: https://github.com/firecrawl/firecrawl-workflows inputs:

  • name: FIRECRAWL_API_KEY description: Firecrawl API key for hosted Firecrawl requests. required: true

Firecrawl QA

Use this to test a live site and return a unified QA report.

Onboarding Interview

Infer the URL, QA focus, and output format from context. If the target URL is clear, proceed immediately.

Ask at most 1-3 concise questions only if blocked, such as the URL, the focus area, or credentials/constraints for protected flows.

Firecrawl Collection Plan

Use Firecrawl map to discover pages. Use Firecrawl browser for interactions, forms, navigation, and responsive/manual checks when available. Use scrape for page content and link extraction.

Parallel Work

If appropriate, use sub-agents or equivalent parallel task runners:

  • Full: Navigation and Links, Forms and Interactions, Content and Visual, Error States.
  • Forms: Form Discovery, Happy Path, Edge Cases, Validation.
  • Navigation: Sitemap, Nav Testing, Link Checker, Routing.
  • Responsive: Desktop, Tablet, Mobile, Interaction.
  • Performance: Page Load, Asset Audit, Content Efficiency, Comparison.

Each tester should return severity, URL, description, evidence, and reproduction steps.

Final Deliverable

# QA Report: [Site]

## Summary
- Health score: [x/10]
- Pages tested: [count]
- Issues found: [critical/major/minor]

## Critical Issues
[C-1] URL | Description | Steps to reproduce | Expected vs actual

## Major Issues
[M-1] URL | Description | Steps to reproduce

## Minor Issues
[m-1] URL | Description

## Positive Observations
[What works well]

## Pages Tested
[URLs]

## Agent/Test Summary
[Who tested what]

## Rerun Inputs
workflow: firecrawl-qa
url: [url]
focus: [full/forms/navigation/responsive/performance]

Quality Bar

  • Include reproduction steps for functional issues.
  • Do not report speculative bugs without evidence.
  • Deduplicate findings across testers.