How do I install the QA skill?

Run npx skillmds@latest add infometa/qa in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the QA skill do?

Systematic QA testing with test-fix-verify loop. Three tiers: Quick, Standard, Exhaustive. Includes issue taxonomy and report templates. Triggers: QA test, test the app, find bugs, smoke test, regression test. It is listed under Docs & Writing on SkillMD.

This skill has not completed SkillMD's automated safety review yet. Independent scanners report: SkillSpector: PASS, Skill Scanner: PASS. Capability flags: docs only. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with QA?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

infometa (@infometa) published this skill. Their other Agent Skills are listed on their SkillMD profile.

QA by infometa — Agent Skill

Name: QA
Rating: 4.2 (5 reviews)
Author: infometa

File contents

QA Test → Fix → Verify

Systematically test a web application, find bugs, fix them with atomic commits, and re-verify.

Modes

Mode	Description
Quick	30-second smoke test
Standard	Systematic exploration, 5-10 issues
Exhaustive	Deep testing, comprehensive coverage
Regression	Compare against baseline
Diff-aware	Auto-detect affected pages from branch diff

Resources

Issue Taxonomy: references/issue-taxonomy.md — classification of bug types
Report Template: templates/qa-report-template.md — structured QA report format

Workflow

Initialize: Parse URL, tier, mode, scope
Authenticate: Handle login/auth if needed
Orient: Map the application, detect framework
Explore: Per-page checklist — visual scan, interactive elements, forms, navigation, states, console, responsiveness
Document: Two evidence tiers — interactive bugs vs static bugs
Triage: Sort by severity, decide which to fix based on tier
Fix Loop: Locate source → minimal fix → one commit per fix → re-test → classify
Final QA: Re-run QA, compute final health score
Report: Structured report with health score, top issues, console health

Output

Health score (0-100)
Issue list with severity, repro steps, evidence
Before/after comparison
Ship-readiness assessment

Frequently asked questions

QA