wiki-ingestlisted

Read a source (file, URL, or pasted text), extract the entities and concepts that matter, and file them as wiki pages with cross-references. Updates the wiki's catalog.md, journal.md, and hot.md so future sessions can find what was ingested. Use this skill whenever the user says "ingest this", "add this to the wiki", "process this source", "file this article", "absorb this", "ingest <url>", "/wiki-ingest", or drops a file/URL with the implicit intent to incorporate it into their knowledge base.
tboome33/obsidian-mcp-router · ★ 1 · AI & Automation · score 74

Install: claude install-skill tboome33/obsidian-mcp-router

# wiki-ingest Take a source (URL, local file path, or pasted text) and do the structured work of: pulling it in, identifying what's worth keeping, writing wiki pages for the new entities/concepts, and updating the relevant cross-references — all idempotently so re-ingesting the same source doesn't duplicate. ## Pre-conditions 1. The target vault has a `wiki/` folder with `catalog.md`, `journal.md`, `hot.md`. If not, run the `wiki` skill first. 2. The vault is online (call `list_vaults`). 3. You have one of: a URL, a file path on disk, or text the user pasted. ## When to use - "ingest this URL" / "absorb this article" - The user pastes a long block of text and says "file this" - Batch mode: "ingest all of these" with multiple sources → fan out via the `wiki-ingest` sub-agent (in `agents/wiki-ingest.md`). ## When NOT to use - The user wants a quick answer without filing → just answer, don't ingest. - The source is already filed (check `wiki-meta/catalog.md` for the title or URL) → tell them; offer to refresh instead. - The "source" is the current conversation → use the `save` skill instead. ## Steps ### 1. Acquire the source content - **URL**: use the `defuddle` skill (v0.13.2+) — it returns `{markdown, metadata}` with deterministic title/author/published/image/site/lang/description/wordCount/readingMinutes from Schema.org/OG/meta tags. If you bypass defuddle for some reason (e.g. URL is already clean markdown), call `mcp__obsidian-router__extract_page_metadata({url})