gonzalezpazmonica/knowledge-graph
.claude/skills/knowledge-graph/SKILL.md
Construye y consulta grafos de conocimiento de entidades PM y sus relaciones
$ install --global
skillsauthnpx skillsauth add gonzalezpazmonica/pm-workspace knowledge-graphInstall 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 24, 2026, 8:50 PM1.8s1 file scanned
SKILL.md
- name:
- knowledge-graph
- description:
- Construye y consulta grafos de conocimiento de entidades PM y sus relaciones
- summary:
- |
- Consulta en lenguaje natural. Output:
- grafo Mermaid.
- maturity:
- stable
- context:
- fork
- agent:
- architect
- context_cost:
- medium
- category:
- communication
- tags:
- ["knowledge-graph", "entities", "relations", "queries"]
- priority:
- medium
Skill: knowledge-graph
Grafo de entidades y relaciones PM. Almacenamiento persistente en JSONL. Consultas en lenguaje natural.
Concepto
Un grafo de conocimiento PM conecta 8 tipos de entidades (Project, PBI, Task, Member, Skill, Risk, Decision, Sprint) a través de 7 tipos de relaciones. Almacenado en JSONL para durabilidad. Soporta consultas en lenguaje natural que se traducen a traversals de grafo.
Entidades
| Tipo | Descripción | Atributos clave | |---|---|---| | Project | Proyecto PM | nombre, descripción, equipo, estado | | PBI | Product Backlog Item | ID, título, descripción, estado, storypoints | | Task | Tarea técnica | ID, descripción, estimación, estado, dueña | | Member | Miembro del equipo | nombre, skills, capacidad, disponibilidad | | Skill | Habilidad técnica | nombre, nivel (junior/mid/senior), demanda | | Risk | Riesgo identificado | descripción, probabilidad, impacto, mitigación | | Decision | Decisión arquitectónica | descripción, fecha, ADR ref, rationale | | Sprint | Ciclo de trabajo | número, fechas, capacidad, velocity |
Relaciones
| Tipo | Desde | Hacia | Significado | |---|---|---|---| | HAS_PBI | Project | PBI | El proyecto contiene este PBI | | DECOMPOSES_TO | PBI | Task | El PBI se descompone en estas tareas | | ASSIGNED_TO | Task | Member | La tarea está asignada a este miembro | | HAS_SKILL | Member | Skill | El miembro domina esta habilidad | | HAS_RISK | Task | Risk | Esta tarea enfrenta este riesgo | | AFFECTS | Decision | Task | Esta decisión impacta esta tarea | | CONTAINS | Sprint | Task | Este sprint contiene estas tareas |
Almacenamiento
Ubicación: data/knowledge-graph/{proyecto}.jsonl
Formato JSONL (una entidad por línea):
{"type":"Project","id":"sala-reservas","name":"Sala Reservas","team":["Alice","Bob"]}
{"type":"PBI","id":"AB#1234","title":"API Reservas","status":"active","project":"sala-reservas"}
{"type":"Task","id":"AB#1234.1","title":"Diseñar endpoints","assigned":"Alice","sprint":"2026-04"}
{"type":"Member","id":"alice","name":"Alice","skills":["TypeScript","API"]}
{"type":"Skill","id":"typescript","name":"TypeScript","level":"mid"}
{"type":"Risk","id":"R001","desc":"Delay BD","prob":0.4,"impact":5}
{"type":"Decision","id":"ADR-001","desc":"GraphQL","adr":"projects/adr/ADR-001.md"}
{"type":"Sprint","id":"2026-04","number":"2026-04","capacity":80}
Construcción (fuentes)
El grafo se construye escaneando:
- Azure DevOps — work items, iteraciones, asignaciones, capacidades
- equipo.md — miembros, skills, roles
- reglas-negocio.md — decisiones, restricciones, riesgos
- agent-notes — contexto acumulado, decisiones, hallazgos
Consultas
Traduce preguntas en lenguaje natural a graph traversals:
| Pregunta | Traversal | Ejemplo | |---|---|---| | "¿Quién sabe TypeScript?" | Member→HAS_SKILL→Skill | Alice, Bob (senior), Charlie (junior) | | "¿De qué depende Task #123?" | Task←DECOMPOSES_TO←PBI | PBI AB#456: "Migrar BD" | | "¿Qué riesgos afectan a este sprint?" | Sprint→CONTAINS→Task→HAS_RISK | R001: "Delay", R004: "API down" | | "¿Impacto de cambiar decisión ADR-5?" | Decision→AFFECTS→Task | Tasks AB#123, AB#124, AB#125 | | "¿Capacidad de Alice el próximo sprint?" | Member→(ASSIGNED_TO←Task←CONTAINS) | 32/80 SP asignados en Sprint 2026-05 |
Máximo 130 líneas
Documentación comprimida. Detalles de implementación en comandos /graph-*.
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