gstack-qa

Tests web applications for bugs and iteratively fixes them with atomic commits.

Updated Jun 24, 2026
One-click install
npx skills add https://github.com/tayiorbeii/paperclip-factory-kit-hermes --skill gstack-qa-tayiorbeii
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: gstack-qa
Source: https://github.com/tayiorbeii/paperclip-factory-kit-hermes/tree/main/skills/paperclip/gstack-qa
Command: npx skills add https://github.com/tayiorbeii/paperclip-factory-kit-hermes --skill gstack-qa-tayiorbeii

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Manually QA testing a web application and then tracking down and fixing each bug is slow and error-prone. This Skill runs systematic QA testing against a site, then iteratively fixes the bugs it finds in source code, committing each fix atomically and re-verifying until the app is ready to ship. ## Core Features & Use Cases - Tiered QA Testing: Choose Quick (critical/high severity only), Standard (adds medium), or Exhaustive (adds cosmetic) depending on how deep the pass should go. - Test-and-Fix Loop: Each confirmed bug is fixed in source, committed atomically, and re-verified rather than just reported. - Ship-Readiness Reporting: Produces before/after health scores, fix evidence, and a ship-readiness summary; a report-only mode is available via /qa-only. - Use Case: After finishing a new feature, ask the agent to QA the site. It crawls the app, finds a broken form submission and a console error, fixes both in the codebase with separate commits, and reports the improved health score. ## Quick Start Ask the agent to QA test this site and fix whatever bugs it finds, using the standard tier.

Frequently Asked Questions about gstack-qa

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

FAQPage Schema
How do I QA test a website and fix bugs automatically?▼

Invoke the skill with a request like "qa test this site and fix what's broken". It runs a structured QA pass, fixes each confirmed bug in source code with an atomic commit, re-verifies the fix, and reports before/after health scores.

What QA testing tiers does this skill support?▼

Three tiers are available: Quick covers critical and high severity issues only, Standard adds medium severity, and Exhaustive adds cosmetic issues. Pick the tier based on how thorough the pre-ship pass needs to be.

Can I get a QA report without changing any code?▼

Yes, use the report-only mode via /qa-only. It runs the same testing workflow and produces findings and health scores but does not modify source code or create commits.

Why does the skill stop with BLOCKED — AskUserQuestion unavailable?▼

The workflow depends on an AskUserQuestion tool variant (native or host MCP) for decision gates. If no variant is registered in the environment, the skill halts and reports BLOCKED rather than auto-deciding on your behalf.

Does the QA skill work in plan mode or spawned sessions?▼

Yes. In plan mode the skill's instructions take precedence and its first AskUserQuestion acts as the plan-mode gate. In spawned orchestrator sessions it skips interactive prompts, auto-chooses recommended options, and ends with a completion report.