Skip to content
Back to skills

Vault Setup

ASecurity

Configure and personalize a fresh VB AI Context without changing its core My Thinking and Knowledge Base boundaries. Use for first-run setup, user context, editor-neutral preferences, or a setup health check; not for ingesting sources or processing notes.

  • 2 stars
  • 0 votes
  • 0 copies
  • 1 view
  • Added October 11, 2026
ai-agents

Works with

  • cli
  • mcp

Security analysis

A100/100

Pro scans all 2 files and shows the line behind each finding

Scanned October 11, 2026

npx -y skills add viniciusbedum/vb-ai-context --skill vault-setup --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Vault Setup?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Vault Setup
[![Security: A β€” Skills Directory](https://www.skillsdirectory.com/api/skills/viniciusbedum-vault-setup/badge)](https://www.skillsdirectory.com/skills/viniciusbedum-vault-setup)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: vault-setup
description: Configure and personalize a fresh VB AI Context without changing its core My Thinking and Knowledge Base boundaries. Use for first-run setup, user context, editor-neutral preferences, or a setup health check; not for ingesting sources or processing notes.
---

# Vault setup

Set up the repository as a portable local knowledge base. Markdown files and folders remain the source of truth; do not require Obsidian, a server, an MCP, or a specific editor.

## Workflow

1. Inspect the repository map, existing configuration, and current indexes before proposing changes.
2. If this looks like a fresh copy (the fictional examples are still present and no real user notes exist yet), explain the project using the guidance in `## Explaining this project` in `AGENTS.md` before asking anything.
3. Ask only for missing choices that materially affect setup: preferred agent, language, name or alias, and optional Obsidian use. Do not request secrets.
4. Offer to walk the user through the fictional example conversationally: open [[example-promoted-restart-cost]] through [[small-context-packets-make-work-easier-to-resume]] for the My Thinking flow, and `cedar-lane-workshop.md` through [[example-query-context-recovery]] for the Knowledge Base flow, narrating what each file shows instead of listing paths for the user to open alone. Skip this if the user prefers to read [[1 START HERE]] on their own.
5. Offer to fill in the `## Personalize your working style` section at the end of `AGENTS.md`. If the user accepts, ask about tone and communication preferences, relevant domain or project context, and any exception to the behavior guidelines above β€” then write only what the user actually said into that section. Skip this step entirely if the user declines or has no preference.
6. Put durable user context in a clearly named note under `Z04 πŸ€– AI Workspace/briefings/`; keep credentials and machine-specific paths out of the repository.
7. Preserve the `X02 ✍️ My Thinking/` and `X03 πŸ—ƒοΈ Knowledge Base/` separation, folder names, relative links, and index rules from `AGENTS.md`.
8. Verify that templates, indexes, agent instructions, and chosen editor path are usable. Report optional integrations separately from the working local setup.

If the user only wants a health check, remain read-only. If a tool or editor integration is unavailable, document the manual Markdown workflow rather than installing a dependency or claiming it is configured.

Files in this skill

  • SKILL.md2.4 KB
  • agents/openai.yaml200 B

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…

Newsletter

Get the weekly list of safe new skills, and the ones we pulled.