qa-preview — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited qa-preview (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Centralize the last quality gate before any real campaign action. Validate compliance, SSL, previews, and creative coverage. Return an explicit go/no-go decision packet.
Do not use if creatives are not yet associated to line items — associate first, then run QA. Do not use for post-launch monitoring — that belongs in deploy-reporting.
scan_creative_compliance if source payload or uploaded bundle needs a compliance scan.validate_creative_ssl (single) or validate_creative_ssl_batch (multiple).get_preview_urls (line-item scope) or get_campaign_preview_urls (order scope).check_creative_coverage before any activation request.deploy-reporting only if QA gate is acceptable.scan_creative_compliance — compliance scanvalidate_creative_ssl / validate_creative_ssl_batch — SSL checkget_preview_urls / get_campaign_preview_urls — preview generationcheck_creative_coverage — coverage gap detectionRender go/no-go verdict as a prominent artifact:
✅ GO — all checks passed
or
❌ BLOCKED — [list numbered blockers]<handoff>
complianceFindings: [...]
sslStatus: passed | failed | partial
previewUrls: [...]
coverageStatus: complete | incomplete
goNoGo: go | blocked
nextRecommendedSkill: deploy-reporting
</handoff>Never suggest deployment in the same turn as a blocking finding — force a separate user confirmation.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.