← Skills Library
Build & Deploy

Quality Check

Single-agent coverage scanner. Runs your test suite, ranks your top 5 riskiest untested paths by criticality, and gives you a prioritized fix list — no auto-fix, no parallel agents.

How It Works

  1. What should I test?: Single-agent coverage scan — no auto-fix
  2. Detect stack & run tests: JS · Python · Go — full suite with coverage enabled
  3. Score every gap by risk: Critical (auth · payments · writes) → High → Medium; ignores Low
  4. Prioritized fix list: Top 5 gaps with file:line + scenario, plus sub-5-minute quick wins
ↆ download card

Invocation Triggers

/quality-checkcheck qualitycoverage scanwhat should I test

Use Cases

  • Find your riskiest untested code paths in 60 seconds
  • Get a prioritized fix list before a PR review
  • Understand your coverage gaps without chasing the percentage

The Problem

Most coverage reports tell you a percentage. They don't tell you which uncovered path would take down your auth flow, corrupt your payments, or silently lose a write. You end up guessing where to add tests.

What It Does

  1. 1
    Detect stack and run tests

    Auto-detects JS, Python, or Go. Runs the full suite with coverage enabled.

  2. 2
    Score every gap by risk

    Critical (auth, payments, writes) → High (business logic) → Medium → Low. Ignores Low entirely.

  3. 3
    Produce the fix list

    Top 5 gaps with file:line, why it matters, and the specific scenario to test. Plus quick wins under 5 minutes each.

What You Get / What It Doesn't Do

What you get
  • Coverage percentage with pass/close/needs-work status
  • Top 5 gaps ranked Critical → High with file references
  • Security flags for manual review
  • Quick wins list ordered by time-to-fix
What it doesn't do
  • Does not write tests — that is quality-team (Pro)
  • Does not fix P0 security issues — reports them only
  • Does not replace a full behavioral audit

Tips

Start with quick wins

Momentum matters. Fix the 5-minute items first, then tackle Critical gaps.

Coverage % is a floor

If you're under 60%, don't chase the number — fix Critical gaps first.

Real assertions only

A test that asserts real behavior beats one that just checks the function runs.

Get the Skill

Free DownloadFREE

Quality Check

The full SKILL.md — copy it into ~/.claude/skills/ and trigger it by name.

Commonly Used With

Agent TeamsQuality TeamSpawn a 3-agent QA gate (Test Writer + Code Reviewer + Coverage Analyst) for pre-release quality assurance and coverage remediation.Audit & ReviewAudit SwarmComprehensive multi-agent code audit. Dispatches domain-specialized agents in parallel, writes findings to structured reports, and creates tickets for P0/P1 issues.Build & DeployVerifyPre-PR gate: runs your full build → lint → test → secrets scan loop and produces a PASS / CLOSE / FAIL verdict with a prioritized fix list. Single agent. No auto-fix.Build & DeployScaffold TestsZero to test suite in one command. Detects your stack, maps major modules, creates the directory structure, writes one real test file per module, and configures coverage. Gives you somewhere to start — not a finished suite.
// What's Next

New skills ship here first

That one's yours — keep it. The library grows every week. Get each new production skill the day it drops, free, and follow the build along the way.

Get every new skill free
// Follow the build
X@jeremyknoxInstagram@jeremyknox.aiDiscordThe Operators

30 production skills in the library — ready to install.

Browse all →Founders pricing →