Consolidated testing and quality check utility for dev, pass, and full QA workflows.

Install

mkdir -p .claude/skills/qa-davidferra13 && curl -L -o skill.zip "https://agentskills.codes/api/skills/download/12099" && unzip -o skill.zip -d .claude/skills/qa-davidferra13 && rm skill.zip

Installs to .claude/skills/qa-davidferra13

Activation

This is the description your AI agent reads to decide when to run this skill — the better it matches your request, the more reliably it fires.

Unified QA pass using existing qa-* scripts. Runs appropriate quality checks based on scope (dev/pass/full). Use when user says /qa, "run tests", "quality check", "is it broken", or before shipping work.
203 chars✓ has a “when” trigger
Beginner

Key capabilities

  • Run quick sanity checks during development
  • Execute quality checks after completing a feature
  • Perform full quality assurance before shipping
  • Confirm dev server status
  • Run TypeScript compilation checks
  • Report QA results with failures

How it works

The skill acts as a single entry point for QA scripts, selecting the appropriate level of checks (dev, pass, full) based on context, running TypeScript compilation, and executing the chosen QA script.

Inputs & outputs

You give it
A project codebase
You get back
A QA report detailing TypeScript status, test results, and build status

When to use qa

  • Run quick quality check
  • Verify before shipping
  • Full test suite execution

About this skill

QA (Unified Quality Assurance Pass)

Purpose

Single entry point for all QA scripts. Pick the right level based on context.

Levels

LevelScriptWhenDuration
devscripts/qa-dev.mjsQuick sanity during development~30s
passscripts/qa-pass.mjsAfter completing a feature~2min
fullscripts/qa-full.mjsBefore shipping / end of session~5min

Procedure

Phase 1: Select Level

  • Default: pass (covers most cases)
  • If user says "quick": use dev
  • If user says "full" or "everything": use full
  • If about to /ship or /close-session: use full

Phase 2: Pre-Flight

  1. Confirm dev server at http://localhost:3100
  2. Run npx tsc --noEmit --skipLibCheck first (type errors = instant fail)
  3. If tsc fails: fix type errors, then continue

Phase 3: Execute

node scripts/qa-[level].mjs

Capture output. Parse results.

Phase 4: Report

## QA [level] Results [date]

TypeScript: PASS/FAIL
Tests: X passed, Y failed, Z skipped
Build: PASS/FAIL (if full level)

### Failures (if any)
- [test name]: [error summary]

Phase 5: Fix or Flag

  • If < 3 failures and they're in code you touched: fix them
  • If failures are in unrelated code: flag but don't block
  • If > 5 failures: something systemic, investigate root cause

Constraints

  • Never skip tsc check
  • Never report "all good" without actually running the script
  • If script doesn't exist or errors on startup, report that (don't fake results)

When not to use it

  • When not needing to run quality checks
  • When not needing to check TypeScript compilation
  • When not needing to report QA results

Limitations

  • Never skip tsc check
  • Never report "all good" without actually running the script
  • If script doesn't exist or errors on startup, report that

How it compares

This skill unifies various QA scripts into a single entry point with predefined levels and a pre-flight TypeScript check, unlike running individual QA scripts manually.

Compared to similar skills

qa side by side with the closest alternatives in the catalog.

SkillInstallsUpdatedSafetyDifficulty
qa (this skill)02moReviewBeginner
verify66moNo flagsBeginner
code-change-verification44moReviewBeginner
springboot-verification44moReviewIntermediate

Try saying

Example prompts that trigger this skill in your AI assistant.

Search skills

Search the agent skills registry