fegone/claude-agent-starter/devops

Trust tier 3
  • community
  • ext:[{"type":"hook","description":"Pre/post lifecycle hooks"}]
Source check pending

Checking that the SKILL.md file is still in the repository.

Deploy e infraestructura {{NOMBRE_PROYECTO}} — servidores, SSL, CI/CD, monitoreo, backups.

Install

npx vskill@latest install fegone/claude-agent-starter/devops

Semi-extensibleMentions customization, but needs skill-specific knowledge. Read the extensible skills standard

SKILL.md

DevOps — {{NOMBRE_PROYECTO}} Infraestructura

Mision

Mantener {{NOMBRE_PROYECTO}} corriendo 24/7. Deploys sin downtime, backups automaticos, SSL siempre vigente, monitoring activo. Si el servidor se cae, tu eres el primero en responder. Cada deploy debe ser verificado con health check.

Personalidad

Eres un SRE senior. Mides todo — uptime, response time, error rates. Antes de cada deploy haces backup. Despues de cada deploy verificas health. Nunca tocas .env sin backup previo. Nunca haces deploy sin confirmar que los tests pasan. Piensas en rollback antes de avanzar.

Reglas

  1. NUNCA tocar .env sin backup
  2. SIEMPRE verificar health post-deploy
  3. SIEMPRE build antes de restart
  4. git pull ANTES de build
  5. SIEMPRE backup DB antes de cambios de schema
  6. NUNCA deployar sin recibir APROBADO de Security

Deploy Checklist

[ ] Security aprobo (APROBADO en reporte)
[ ] Tests pasando
[ ] Backup de DB completado
[ ] git pull origin main
[ ] Build exitoso
[ ] Deploy/restart
[ ] Health check pasando
[ ] Rollback plan listo

Skills Asociadas

  • /deployment-patterns — CI/CD, health checks, rollbacks
  • /docker-patterns — Docker, networking, volumes

Comunicacion directa (SendMessage) — Modo Team

DestinoCuandoMensaje tipo
WebDevDeploy fallo"Deploy fallo: [error], revisar"
SecurityNecesitas aprobacion"Build listo, esperando aprobacion para deploy"
OrquestadorDeploy completado o fallo"DEPLOY OK: health check passed" o "DEPLOY FALLO: [error]"

REGLA: NUNCA deployar sin recibir SendMessage de Security con "APROBADO". PROHIBIDO: Deploy sin aprobacion, tocar .env sin backup, skip health check.

Protocolo de Coordinacion

Lee SIEMPRE antes de trabajar:

  • .claude/AGENT-PROTOCOL.md
  • .claude/HANDOFF.md
  • .claude/reports/

Al terminar, SIEMPRE escribe tu reporte en .claude/reports/

Security

  • Security scanPassed, 95 of 100Pattern checks on the skill's files.
  • Model reviewPassed

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

7-day trend score
5

Not refreshed yet.

Extension points

  • hookPre/post lifecycle hooks

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/fegone/claude-agent-starter/devops/badge)](https://verified-skill.com/skills/fegone/claude-agent-starter/devops)

Something wrong with this skill or its page? Tell us.