Firecrawl Qa
Exploratory and pre-launch QA on a live URL with navigation, forms, responsive checks, and evidence-backed bug reports via Firecrawl.
Overview
Firecrawl QA is an agent skill most often used in Ship (also Validate prototype) that produces a unified live-site QA report using Firecrawl map, browser, and scrape.
Install
npx skills add https://github.com/firecrawl/firecrawl-workflows --skill firecrawl-qaWhat is this skill?
- Unified QA report from map discovery plus browser interactions and scrape evidence
- Parallel modes: Full (nav, forms, content, errors), Forms, Navigation, Responsive, Performance
- Onboarding limited to 1–3 questions for URL, focus area, or protected-flow credentials
- Form workflows: discovery, happy path, edge cases, and validation passes
- Responsive checks across desktop, tablet, and mobile interaction viewports
- 5 parallel QA focus modes (Full, Forms, Navigation, Responsive, Performance)
- At most 1–3 onboarding questions when blocked
Adoption & trust: 11.5k installs on skills.sh; 29 GitHub stars; 2/3 security scanners passed (skills.sh audits).
What problem does it solve?
Your app is live or staging-public but you have not systematically clicked through flows, forms, and breakpoints to catch regressions.
Who is it for?
Indie founders doing pre-launch sweeps or post-deploy smoke QA without a dedicated QA hire.
Skip if: Replacing playwright in CI, load testing at scale, or auditing apps you cannot legally access without supplied credentials.
When should I use this skill?
User wants exploratory QA, form testing, navigation/link checks, responsive checks, performance observations, bug reports, or a pre-launch quality review.
What do I get? / Deliverables
You get an evidence-backed QA report with navigation, form, responsive, and error findings you can turn into ship-blocking fixes.
- Unified QA report
- Per-area findings (nav, forms, responsive, errors)
- Reproduction notes with scrape evidence
Recommended Skills
Journey fit
Spans multiple journey phases - primary shelf plus alternate fits below.
Live-site QA belongs on the ship/testing shelf—last-mile quality before users hit production. Uses map, browser interactions, and scrape to validate links, forms, layouts, and error states—the testing subphase for web products.
Where it fits
Run a full nav-and-forms pass on production before announcing v1.
Click through a staging signup funnel and log validation edge cases.
Re-test checkout after a hotfix using focused form QA mode.
How it compares
Agent-driven exploratory web QA—not a Playwright test generator or accessibility WCAG certification tool.
Common Questions / FAQ
Who is firecrawl-qa for?
Solo builders and tiny teams who need structured exploratory testing on a deployed URL with screenshots and scrape-backed notes.
When should I use firecrawl-qa?
Use it in Ship before release or hotfix validation, in Validate on a staging prototype URL, or after Operate incidents when verifying a fix on production.
Is firecrawl-qa safe to install?
It exercises live URLs and may use credentials you provide for protected flows; review the Security Audits panel on this page and scope tests to environments you control.
SKILL.md
READMESKILL.md - Firecrawl Qa
# 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 ```markdown # 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.