Kb Init

KB Init — PARA Knowledge Base Setup

Set up the Knowledge Base layer on an existing PARA-structured Obsidian vault.

What It Does

1. Detect vault — find .obsidian/ to confirm vault root, locate PARA directories
2. Create category indexes — _index.md in each PARA directory (Projects, Areas, Resources, Archive) using Templates/_index.md.template as the skeleton
3. Create top-level index — 0. Common/index.md (~30 lines, vault overview)
4. Create activity log — 0. Common/log.md (append-only)
5. Update AGENTS.md — append KB rules section, including Inbox README preservation rules (preserve existing content)
6. Detect obsidian CLI — check availability, configure fallback strategy

Prerequisites

An Obsidian vault with PARA-style numbered folders:

Vault/
├── 0. Common/        (shared: daily notes, dashboard, etc.)
├── 1. Projects/      (active projects with deliverables)
├── 2. Areas/         (ongoing responsibilities, no end date)
├── 3. Resources/     (reference material by topic)
├── 4. Archive/       (completed or paused items)
└── Inbox/            (optional — raw input landing zone)

Folder names are matched by number prefix (1., 2., 3., 4.), not exact name. Inbox/ is matched by name.

Execution Flow

Step 1: Detect vault root
  Find .obsidian/ directory → that parent is the vault root
  Verify PARA directories exist (at least 1-4 numbered folders)
  If missing directories → warn and offer to create them

Step 2: Check existing state
  If _index.md or index.md already exist:
    --force → overwrite
    Otherwise → ask user: overwrite, skip, or abort

Step 3: Scan and generate _index.md per category
  Read Templates/_index.md.template once
  For each PARA directory:
    List subdirectories and standalone .md files
    Read overview files for status (0.*.md, *-Project.md, project-overview.md)
    Generate _index.md by substituting template placeholders:
      - {{CATEGORY}} -> category name
      - {{DATE}} -> today
      - {{SUMMARY_LINE}} -> counts / brief overview
      - {{ENTRIES}} -> one line per item: **name** — status/description
    Target: 10-20 lines of content per index

Step 4: Generate top-level 0. Common/index.md
  Aggregate from category indexes:
    Projects: count + highlights
    Areas: count + major areas
    Resources: count + categories
    Archive: completed/paused counts
    Recent: placeholder for log entries
  Target: ~30 lines

Step 5: Create 0. Common/log.md
  Header + initial entry:
    "[date] init | KB initialized | N index files created"

Step 6: Update AGENTS.md
  If exists → read, append KB rules after existing content
  If missing → create from Templates/AGENTS.md.template
  KB rules section includes:
    Vault structure description
    KB operation rules (ingest/query/lint)
    Inbox README preservation rules for `Inbox/**/README.md`
    Tag conventions (#proj/, #type/, #topic/)
    Wikilink rules
    Index management rules

Step 7: Detect tooling
  which obsidian → if found:
    Run: obsidian version
    Run: obsidian tags sort=count counts limit=20
    Log "obsidian CLI v{version} detected — search, backlinks, tags available"
    Record existing tag conventions for future ingest/lint use
  If not found:
    Log "obsidian CLI not available — using grep/glob fallback"
    Note: All skills fully functional without CLI

Index Template Contract

• Templates/_index.md.template is the source of truth for per-category _index.md structure.
• Use it when creating missing indexes during init.
• Substitute placeholders only; do not handcraft a different frontmatter or heading layout.
• Later incremental updates may edit the generated _index.md directly; they do not need to re-render from the template.

Tag Conventions (Established at Init)

Detect existing tag patterns first via obsidian tags sort=count counts (or Grep fallback). Adapt to the vault's established conventions rather than imposing new ones.

Common patterns found in PARA vaults:

Important: If the vault already uses #study/paper instead of #type/paper, follow the existing convention. Consistency over idealism.

Arguments

After Init

Run these as needed:

• /kb-ingest — process documents in Inbox
• /kb-query "question" — search the knowledge base
• /kb-lint — check vault health
• /kb-index — rebuild all indexes