gonzalezpazmonica/savia-flow-practice
.claude/skills/savia-flow-practice/SKILL.md
Implementación práctica de Savia Flow — dual-track, specs ejecutables, métricas de flujo
$ install --global
skillsauthnpx skillsauth add gonzalezpazmonica/pm-workspace savia-flow-practiceInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
Security Scan Results
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
3
Scanners Passed
9
Scanners in report
Clean
TrivyContainer and dependency vulnerability scanner
95%
Clean
SemgrepStatic code analysis for vulnerabilities
95%
Clean
mcp-scan (Snyk)Model Context Protocol security validation
95%
Skipped
Snyk (dep)Open source security scanning
50%
Skipped
Socket.devSupply chain security analysis
50%
Skipped
VirusTotalMulti-engine malware detection
50%
Skipped
CrowdStrikeAdvanced threat intelligence
50%
Skipped
OSV-ScannerOpen Source Vulnerability database check
50%
Skipped
OWASP Dep-Check
50%
Last scanned: Apr 16, 2026, 2:40 AM6.0s12 files scanned
SKILL.md
- name:
- savia-flow-practice
- description:
- Implementación práctica de Savia Flow — dual-track, specs ejecutables, métricas de flujo
- summary:
- |
- Implementacion practica de Savia Flow:
- dual-track (exploracion +
- Output:
- board configurado + metricas iniciales.
- maturity:
- stable
- globs:
- []
- category:
- pm-operations
- tags:
- ["savia-flow", "dual-track", "methodology", "outcomes"]
- priority:
- medium
Savia Flow — Implementación Práctica
Savia Flow es una metodología de desarrollo orientada a outcomes, flujo continuo y specs ejecutables. Esta skill lleva la teoría (docs/savia-flow/) a la práctica: configuración real, ejemplos y comandos.
Cuándo usar esta skill
- Configurar un proyecto nuevo con Savia Flow (
/flow-setup) - Visualizar el tablero dual-track (
/flow-board) - Mover specs listas a producción (
/flow-intake) - Consultar métricas de flujo (
/flow-metrics) - Crear specs desde outcomes de exploración (
/flow-spec)
Cuándo NO usar
- Si el equipo usa Scrum clásico → usar
sprint-management - Si solo necesitas descomponer PBIs → usar
pbi-decomposition - Si solo necesitas escribir specs → usar
spec-driven-development
Prerrequisitos (skills existentes)
| Skill | Uso en Savia Flow |
|---|---|
| azure-devops-queries | Queries WIQL, REST API, MCP tools |
| devops-validation | Auditar configuración del proyecto |
| spec-driven-development | Generar specs ejecutables |
| pbi-decomposition | Descomponer specs en tasks |
| capacity-planning | Calcular capacidad y WIP |
| product-discovery | JTBD + PRD en exploration track |
Conceptos clave
Dual-Track
Dos flujos paralelos que se alimentan mutuamente:
Exploration Track — Descubrir qué construir (Elena lidera): Discovery → Spec-Writing → Spec-Ready
Production Track — Construir lo que está listo (Ana + Isabel): Ready → Building → Gates → Deployed → Validating
Handoff
El puente entre tracks es la Spec-Ready: una spec completa con outcome, métricas de éxito, especificación funcional, restricciones técnicas y Definition of Done. Solo items Spec-Ready entran a Production.
Roles Savia Flow
| Rol Savia Flow | Quién | Foco | |---|---|---| | Flow Facilitator | PM/CTO | Optimizar flujo, desbloquear, métricas | | AI Product Manager | Producto/QA | Discovery, hypothesis, escribir specs | | Pro Builder | Devs | Orquestar IA, arquitectura, code review | | Quality Architect | QA | Diseñar gates, supervisar agentes, defect escapes |
Métricas (DORA + IA)
| Métrica | Target | Cálculo | |---|---|---| | Cycle Time | 3-7 días | Deploy Date - Build Start | | Lead Time | 7-14 días | Deploy Date - Idea Date | | Throughput | 8-12 items/sem | Items deployed / semana | | CFR | <5% | Deploys con incidente / Total deploys | | Spec-to-Built | <5 días | Build Start - Spec-Ready Date | | Rework Rate | <15% | Features reescritas / Total |
References
| Fichero | Contenido |
|---|---|
| azure-devops-config.md | Board columns, custom fields, area paths, tags |
| backlog-structure.md | Dos backlogs, prioridad, WIP limits, handoff |
| task-template-sdd.md | Plantilla spec 5 componentes, acceptance criteria |
| meetings-cadence.md | Cadencia reuniones, calendario equipo 4 personas |
| dual-track-coordination.md | Quién hace qué, capacidad por track, dependencias |
| example-socialapp.md | Ejemplo completo: SocialApp (Ionic + microservicios) |
| knowledge-priming.md | Knowledge Priming: 7 secciones, patrones Fowler, jerarquía contexto |
| role-evolution-ai.md | 6 categorías roles AI-era, mapping equipo, métricas madurez |
| multimodal-agents.md | Agentes VLM: visión + texto + código, roadmap integración |
Comandos
| Comando | Propósito |
|---|---|
| /flow-setup | Configurar Azure DevOps para Savia Flow |
| /flow-board | Visualizar tablero dual-track |
| /flow-intake | Mover Spec-Ready → Production |
| /flow-metrics | Dashboard métricas de flujo |
| /flow-spec | Crear spec desde outcome |
Compatibilidad
Savia Flow coexiste con Scrum. No es necesario migrar todo de golpe:
- Sprint-management sigue funcionando para equipos en Scrum
- Los comandos flow-* pueden usarse gradualmente
- Un equipo puede empezar con
/flow-metricspara medir, sin cambiar su proceso
Plataformas soportadas
| Plataforma | Estado | Reference |
|---|---|---|
| Azure DevOps | ✅ Completo | azure-devops-config.md |
| GitLab | 🔜 Planned | — |
| Jira Cloud | 🔜 Planned | — |
| GitHub Projects | 🔜 Planned | — |
Diseño agnóstico: los comandos abstraen "Exploration/Production track". Cada plataforma tendrá su propio reference de configuración.
Related Skills
gonzalezpazmonica/skill-creator
testing
VerifiedTrustedCommunity
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.
40SKILL.mdUpdated May 24, 2026
gonzalezpazmonica/mcp-builder
tools
VerifiedTrustedCommunity
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers to integrate external APIs or services, whether in Python (FastMCP) or Node/TypeScript (MCP SDK).
40SKILL.mdUpdated May 24, 2026
gonzalezpazmonica/wellbeing-guardian
tools
VerifiedTrustedCommunity
Sistema proactivo de bienestar individual
33SKILL.mdUpdated Apr 17, 2026
gonzalezpazmonica/web-research
development
VerifiedTrustedCommunity
Search the web to resolve context gaps — documentation, versions, CVEs, best practices. Auto-starts SearxNG Docker if available, falls back to WebSearch.
33SKILL.mdUpdated Apr 17, 2026