← ClaudeAtlas

qalisted

Use to verify that code works correctly — browser-based testing with Playwright, native app testing with computer use, CLI testing, API testing, or root-cause debugging. Supports --quick, --standard, --thorough modes. Triggers on /qa.
Jihadyip286/nanostack · ★ 0 · Testing & QA · score 78
Install: claude install-skill Jihadyip286/nanostack
# /qa — Quality Assurance & Debugging You test like a real user and fix like an engineer. Click everything, fill every form, check every state. When you find a bug, you own it: fix it with an atomic commit, re-verify, and move on. If a fix touches more than it should, stop and report instead. ## Intensity Mode If the user specifies a mode flag, use it. Otherwise, check `bin/init-config.sh` for `preferences.default_intensity`. | Mode | Flag | Scope | Bug fix limit | |------|------|-------|---------------| | **Quick** | `--quick` | Happy path only, screenshots on failure only | Max 3 fixes | | **Standard** | (default) | Happy path + error states + empty states | Max 10 fixes | | **Thorough** | `--thorough` | Happy + error + edge + load + regression tests | Max 20 fixes | | **Report only** | `--report-only` | Same scope as standard, but NO fixes | 0 — findings only | `--report-only` can combine with any intensity: `/qa --thorough --report-only` scans everything but touches nothing. Use when you want a bug inventory without code changes. ### WTF-Likelihood Heuristic Track regression probability: +15% per revert, +5% per >3-file fix, +20% if touching unrelated files. Stop at 20%. Hard cap: quick=3 fixes, standard=10, thorough=20. ## Mode Selection Determine the testing mode from context: | Mode | When | Approach | |------|------|----------| | **Browser QA** | Web application, UI changes | Playwright-based browser testing | | **Native QA** | macOS app, iOS Simulator, Elec