.claude/skills/personal-vault/SKILL.md
Gestion del repositorio personal del usuario — perfil, preferencias, memoria, instintos, cache. Nivel N3 (USUARIO). Invocada por comandos vault-*.
npx skillsauth add gonzalezpazmonica/pm-workspace personal-vaultInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Nivel de confidencialidad: N3 (USUARIO) Solo visible para la persona que usa el workspace.
Repositorio git dedicado que consolida TODOS los datos personales del usuario en un unico lugar versionado y portable. Sustituye la dispersion actual de datos en 5+ ubicaciones sin historial ni portabilidad.
~/.savia/personal-vault/VAULT_PATH en pm-config.local.md~/.savia/personal-vault/
├── .git/
├── CLAUDE.md ← config para Savia
├── README.md ← documentacion
├── profile/ ← identity, tone, workflow, tools, preferences, accessibility
├── rules/ ← reglas personales (*.md)
├── globals/ ← CLAUDE.md personal (preferencias globales)
├── instincts/ ← registry.json (patrones aprendidos)
├── memory/ ← MEMORY.md + topic files (memoria cross-project N3)
├── cache/ ← confidence-log.jsonl, context-usage.log
└── history/ ← sync-log.jsonl
El vault es la fuente de verdad. Las ubicaciones originales se convierten en junctions (Windows NTFS) o symlinks (Unix) que apuntan al vault:
.claude/profiles/users/{slug}/ → vault/profile/~/.claude/rules/ → vault/rules/~/.claude/CLAUDE.md → vault/globals/CLAUDE.md.claude/instincts/ → vault/instincts/Excepcion: auto-memory (~/.claude/projects/*/memory/) usa copia
unidireccional porque mezcla datos N3 y N4. Solo las entradas N3
(feedback, workspace features) se copian al vault.
/vault-init — Crear vault, migrar datos, crear junctions/vault-sync — Commit + push al remote/vault-status — Salud: junctions, cambios, remote/vault-restore — Clonar desde remote + recrear junctions/vault-export — Archivo cifrado AES-256 portabletesting
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.
tools
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).
tools
Sistema proactivo de bienestar individual
development
Search the web to resolve context gaps — documentation, versions, CVEs, best practices. Auto-starts SearxNG Docker if available, falls back to WebSearch.