Mode d’emploi
- Copiez la commande et examinez le paquet avant de l’installer dans votre environnement agent.
- Consultez le document original pour les outils, identifiants et environnements requis.
- Décrivez les entrées et le livrable souhaité ; comparez la sortie aux sources.
npx skills add https://github.com/sergekostenchuk/ui-ux-agent-skill-system --skill launch-readiness-auditorAvant de commencer
- L’installation n’inclut ni abonnement au modèle, ni quota API, ni accès aux fichiers.
- Étoiles et installations reflètent l’activité, pas un test indépendant de qualité ou de sécurité.
Document Skill original
Rendu depuis le dépôt source en conservant titres, exemples, code, tableaux, liens et images.
Launch Readiness Auditor
This skill is the final launch gate. It checks whether evidence exists before production launch.
Operating Modes
pre-launch-audit: compile required launch checks and evidence.blocker-register: list blockers, owners, and required approvals.go-no-go: produce launch decision with rollback and monitoring.
Required Checks
- SEO metadata, canonical, sitemap, robots, schema, llms.txt when relevant.
- Accessibility and responsive UI smoke.
- Performance and asset loading.
- SSL/TLS, security headers, cookies, backups, monitoring.
- Redirects and migration checks when existing site is involved.
- Analytics and webmaster verification plan.
- Explicit production approval for deploy, DNS, registrar, server, and account mutations.
Safety Rules
- Do not mark
Readywithout evidence or explicit skipped rationale. - Do not perform production actions; route execution back to specialists after approval.
Validation
bash
python3 $CODEX_HOME/skills/.system/skill-creator/scripts/quick_validate.py $CODEX_HOME/skills/launch-readiness-auditor
python3 $CODEX_HOME/skills/senior-skill-architect/scripts/lint_production_skill.py $CODEX_HOME/skills/launch-readiness-auditor
python3 -m json.tool $CODEX_HOME/skills/launch-readiness-auditor/evals/evals.json >/dev/null
