npx claudepluginhub psypeal/claude-knowledge-vault --plugin knowledge-vault## Procedure
1. Run: `bash "${CLAUDE_PLUGIN_ROOT}/scripts/init.sh"`
- Creates `.vault/` with empty structure and appends instructions to CLAUDE.md.
2. **Interview the user** for `.vault/preferences.md`. Ask one at a time; skip questions obvious from project context. If user says "skip" or wants defaults, generate sensible preferences from project context.
a. **Domain**: "What domain is this vault for?" (e.g., ML research, biomedical science, web development, general)
b. **Source types**: "What sources will you mainly use?" (papers, articles, code repos, meeting notes, web clips).../initInitializes beads issue tracking database in current directory with optional prefix (defaults to dir name). Shows DB location, prefix, workflow overview, next steps; displays stats if already set up.
/initInitializes guided UI design for dashboards, apps, and tools. Assesses intent, proposes styles with rationale, builds components, and offers to save patterns.
/initDownloads and installs/updates the platform-specific notification binary for claude-notifications plugin from GitHub into the plugin's bin directory.
/initInitializes or re-boots llmdoc/ directory structure, runs multi-themed project investigations with investigator, and generates initial stable docs via recorder.
/initInitializes AI task harness with ai/tasks/ directory for modular backlog, progress log, bootstrap script, and CLAUDE.md instructions. Supports --mode new|scan and --task-type ops|data|infra|manual.
/initScans ~/.claude/agents/ for custom agent files, lets user select which to import/register into orchestration plugin registry, updates JSON registry and documentation.
Run: bash "${CLAUDE_PLUGIN_ROOT}/scripts/init.sh"
.vault/ with empty structure and appends instructions to CLAUDE.md.Interview the user for .vault/preferences.md. Ask one at a time; skip questions obvious from project context. If user says "skip" or wants defaults, generate sensible preferences from project context.
a. Domain: "What domain is this vault for?" (e.g., ML research, biomedical science, web development, general) b. Source types: "What sources will you mainly use?" (papers, articles, code repos, meeting notes, web clips) c. Priority rules: "Any priority for sources?" (e.g., peer-reviewed over blog posts, recent over old) d. Concept detail: "How granular should concepts be?" (broad / balanced / granular) e. Compilation focus: "Any special instructions for summarization?" (e.g., always extract methodology, focus on clinical relevance)
Write .vault/preferences.md:
---
title: Vault Preferences
updated: "ISO timestamp"
---
## Domain
[from interview]
## Source Priority
[ranked list]
## Concept Granularity
[broad | balanced | granular]
## Compilation Focus
[specific instructions]
## Custom Rules
[any additional preferences]
Confirm vault is ready.
Suggest opening .vault/ in Obsidian for visual navigation.
Suggest running /knowledge-vault:setup-sources to configure research MCP servers.