Wiki Ingest

Reads anything you throw at it (files, URLs, images, batches) and scatters the contents across your Obsidian vault as cross-referenced wiki pages. One source typically spawns 8-15 pages. Handles the whole pipeline: fetches web content with optional defuddle cleaning, OCRs images, tracks what's already been processed via hash manifests so you don't ingest twice, and respects whatever vault methodology you're running (LYT, PARA, Zettelkasten, or generic). The v1.7+ concurrency model uses per-file advisory locks so parallel ingests won't silently clobber each other. Built for people who want their vault to grow itself from raw inputs without manual filing.

skills.sh installs: 530
GitHub stars: 16.3K
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add agricidaniel/claude-obsidian --skill wiki-ingest --agent claude-code

Installs into .claude/skills of the current project.

Files

Ingest sources

Turn supplied material into grounded, cross-linked notes without changing the source. Treat inbox/ as visible staging and .raw/ as the legacy immutable source archive. Files already present in either location remain user-owned and read-only.

Resolve the portable core from this skill's installation. Resolve the user vault by explicit --vault, CLAUDE_OBSIDIAN_VAULT, workspace config, then current-directory discovery. Never select the plugin/product root.

PRODUCT_ROOT=/absolute/path/to/installed/claude-obsidian
CORE="$PRODUCT_ROOT/scripts/claude-obsidian.py"
test -f "$CORE"

Every ../wiki/references/ link in this file resolves the same way, relative to this skill's own directory under $PRODUCT_ROOT, never relative to the selected vault's wiki/ directory.

Agree on scope and egress

Before processing, list the inputs and set a budget for source count, source bytes/pages, existing-page reads, generated pages, and network requests. For a large batch, choose a bounded first tranche instead of promising exhaustive processing.

SKILL.md on GitHub