.cursor/skills/qa-smoke-test/SKILL.md
Fast pre-QA sanity check. Validates files exist, server responds, and basic page loads before running full test suite. Returns JSON with pass/fail status.
npx skillsauth add astro44/Autonom8-Agents qa-smoke-testInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Quick sanity check before running full QA. Catches obvious issues early to save time.
{
"project_dir": "/path/to/project",
"ticket_id": "TICKET-XXX",
"checks": ["files_exist", "server_responds", "page_loads", "no_console_errors"]
}
Verify critical files from ticket.files_created exist:
for file in ${ticket.files_created}; do
[ -f "$project_dir/$file" ] || echo "MISSING: $file"
done
Check dev server is running and healthy:
# Check if server is running
lsof -i :8080 | grep LISTEN
# Health check
curl -s -o /dev/null -w "%{http_code}" http://localhost:8080/
# Expected: 200
Verify main entry point loads without errors:
# Quick Playwright check
npx playwright test --grep "@smoke" --timeout=10000
Check browser console for errors on page load:
const errors = [];
page.on('console', msg => {
if (msg.type() === 'error') errors.push(msg.text());
});
await page.goto(url);
// errors.length should be 0
Verify CSS/JS/images return 200:
const failedRequests = [];
page.on('requestfailed', req => {
failedRequests.push(req.url());
});
await page.goto(url, { waitUntil: 'networkidle' });
// failedRequests.length should be 0
{
"skill": "qa-smoke-test",
"status": "pass|fail",
"duration_ms": 2340,
"checks": {
"files_exist": {
"passed": true,
"total": 5,
"missing": []
},
"server_responds": {
"passed": true,
"port": 8080,
"status_code": 200
},
"page_loads": {
"passed": true,
"load_time_ms": 1200
},
"console_errors": {
"passed": false,
"errors": ["Uncaught TypeError: Cannot read property 'x' of undefined"]
},
"assets_load": {
"passed": true,
"total": 12,
"failed": []
}
},
"summary": {
"total_checks": 5,
"passed": 4,
"failed": 1
},
"errors": [
{
"check": "console_errors",
"message": "JavaScript error on page load",
"details": "Uncaught TypeError in main.js"
}
],
"next_action": "proceed|fix"
}
Any check failed?
YES → status: "fail", next_action: "fix"
NO → status: "pass", next_action: "proceed"
| Check | Failure | Recommendation | |-------|---------|----------------| | files_exist | Missing files | Check ticket implementation | | server_responds | Server not running | Start dev server | | page_loads | Page timeout | Check entry point HTML | | console_errors | JS errors | Fix before proceeding | | assets_load | 404 on assets | Check file paths |
Basic smoke test:
{
"project_dir": "/projects/oxygen_site",
"ticket_id": "TICKET-OXY-001",
"checks": ["files_exist", "server_responds", "page_loads"]
}
Full smoke test:
{
"project_dir": "/projects/oxygen_site",
"ticket_id": "TICKET-OXY-001",
"checks": ["files_exist", "server_responds", "page_loads", "no_console_errors", "assets_load"]
}
development
Scores proposal complexity against codebase surface. Uses proposal text analysis and readiness stats to determine decomposition tier and agent count.
testing
Fast filesystem readiness scan — counts docs, source files, manifests, platform signals. Produces initial ReadinessReport for agent spawning decisions.
testing
Merges bookend agent reports into revised readiness, complexity, and decomposition plan. Produces the final evidence-backed assessment consumed by sprint-architect-agent.
development
Rigorously reasons about definitions, proofs, and computations in algebra, analysis, discrete math, probability, linear algebra, and applied math. Verifies derivations, spots invalid steps, and states assumptions clearly. Use when solving or proving math problems, reviewing mathematical arguments, modeling with equations, interpreting statistics, or when the user mentions proofs, lemmas, theorems, integrals, series, matrices, optimization, or numerical methods.