super-qa

Crawl application routes and generate Playwright end-to-end regression specs.

Updated May 20, 2026
One-click install
npx skills add https://github.com/samuelcastro/skills --skill super-qa
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: super-qa
Source: https://github.com/samuelcastro/skills/tree/main/super-qa
Command: npx skills add https://github.com/samuelcastro/skills --skill super-qa

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill requires git, gh, jq, node.js, playwright, claude, and includes references (resource) components.

What problem does it solve?

It eliminates the manual, time-consuming work of writing and maintaining end-to-end Playwright tests by automatically crawling your app, generating route-appropriate specs, and filing actionable failures.

Core Features & Use Cases

  • BFS app crawling for coverage growth: walks your app route tree and systematically expands until the traversal budget completes or only human-gated blockers remain.
  • Evidence-backed Playwright suite generation: creates specs under e2e/paths with forensics including screenshots, console errors, page errors, and network artifacts.
  • Issue-first bug reporting and governance: converts failing specs into product-readable GitHub issues with priority/labels, and routes fixes through PR/reviewer flow instead of direct-to-main.
  • Auth-aware, non-interactive bootstrapping: auto-discovers or creates test credentials from cached settings or env/admin keys, with a safe public-only fallback.

Quick Start

Run the QA crawler by telling your agent to execute the skill with ten iterations: /super-qa.

Frequently Asked Questions about super-qa

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I automatically generate Playwright e2e tests by crawling my app routes?

Automated Playwright e2e test generation uses a BFS queue-driven loop to crawl application routes and create type-appropriate specs. It systematically expands coverage until the traversal budget completes or only human-gated blockers remain.

How does QA automation capture evidence when a Playwright spec fails?

QA automation captures test forensics during Playwright execution by collecting screenshots, console errors, page errors, and network artifacts. This evidence is attached to failing specs to provide actionable debugging context.

Can I use GitHub issues for bug reporting from automated e2e test failures?

Yes, automated e2e test failures convert into product-readable GitHub issues with priority and labels. Fixes are routed through a PR and reviewer flow rather than direct-to-main commits to ensure governance.

Do I need to manually configure authentication for Playwright e2e test crawling?

No, the crawler uses auth-aware, non-interactive bootstrapping to auto-discover or create test credentials from cached settings or environment and admin keys, with a safe public-only fallback if credentials are unavailable.

What dependencies are required to run autonomous Playwright e2e suite generation?

Autonomous Playwright e2e suite generation requires git, gh, jq, node.js, playwright, and claude installed in your environment to execute the crawling, spec generation, and GitHub issue reporting workflows.

What are the limitations of route crawling for e2e test coverage?

Route crawling for e2e test coverage stops when the traversal budget completes or when only human-gated blockers remain, meaning it cannot bypass routes requiring manual intervention or complex interactive authentication flows.