Wiki Ingest

Obsidian Ingest — Document Distillation

You are ingesting source documents into an Obsidian wiki. Your job is not to summarize — it is to distill and integrate knowledge across the entire wiki.

Before You Start

1. Read .env to get OBSIDIAN_VAULT_PATH and OBSIDIAN_SOURCES_DIR
2. Read .manifest.json at the vault root to check what's already been ingested
3. Read index.md to understand current wiki content
4. Read log.md to understand recent activity

Language policy — wiki content is English-only

Distilled wiki pages are written in English, regardless of the source document's language. Translate Korean / Japanese / Chinese sources into English when distilling; keep at most one short verbatim quote per page (in source language with an English inline gloss when non-English) so attribution stays honest. Reasons:

• The Bagelcode hiring panel + future open-source contributors are the wiki's audience; English is the lowest-friction reading surface for both.
• A wiki rebuild / lint / cross-link pass operates on English token boundaries; mixed-language pages create false positives in wiki-lint and miss hits in wiki-query.
• Crumb's root CLAUDE.md mandates English for the codebase + commits + PRs (the wiki is a codebase artifact, not chat).

Ingest Modes

This skill supports three modes. Ask the user or infer from context:

Append Mode (default)

Only ingest sources that are new or modified since last ingest. Check the manifest using both timestamp and content hash:

• If a source path is not in .manifest.json → it's new, ingest it
• If a source path is in .manifest.json:
  • Compute the file's SHA-256 hash: sha256sum <file> (or shasum -a 256 <file> on macOS)
  • If the hash matches content_hash in the manifest → skip it, even if the modification time differs (file was touched but content is identical — git checkout, copy, NFS timestamp drift)
  • If the hash differs → it's genuinely modified, re-ingest it
• If a source path is in .manifest.json and has no content_hash (older entry) → fall back to mtime comparison as before

This is the right choice most of the time. It's fast and avoids redundant work even when timestamps are unreliable.

Full Mode

Ingest everything regardless of manifest state. Use when:

• The user explicitly asks for a full ingest
• The manifest is missing or corrupted
• After a wiki-rebuild has cleared the vault

Raw Mode

Process draft pages from the _raw/ staging directory inside the vault. Use when:

• The user says "process my drafts", "promote my raw pages", or drops files into _raw/
• After a paste-heavy session where notes were captured quickly without structure

In raw mode, each file in OBSIDIAN_VAULT_PATH/_raw/ (or OBSIDIAN_RAW_DIR) is treated as a source. After promoting a file to a proper wiki page, delete the original from _raw/. Never leave promoted files in _raw/ — they'll be double-processed on the next run.

The Ingest Process

Step 1: Read the Source

Read the document(s) the user wants to ingest. In append mode, skip files the manifest says are already ingested and unchanged. Supported formats:

• Markdown (.md) — read directly
• Text (.txt) — read directly
• PDF (.pdf) — use the Read tool with page ranges
• Web clippings — markdown files from Obsidian Web Clipper
• Images (.png, .jpg, .jpeg, .webp, .gif) — requires a vision-capable model. Use the Read tool, which renders the image into your context. Treat screenshots, whiteboard photos, diagrams, and slide captures as first-class sources. If your model doesn't support vision, skip image sources and tell the user which files were skipped so they can re-run with a vision-capable model.

Note the source path — you'll need it for provenance tracking.

Multimodal branch (images)

When the source is an image, your extraction job is interpretive — you're reading visual content, not text. Walk the image methodically:

1. Transcribe any visible text verbatim (UI labels, slide bullets, whiteboard handwriting, code snippets in screenshots). This is the only extracted content from an image.
2. Describe structure — for diagrams, list the boxes/nodes and the arrows/edges. For screenshots, name the app or context if recognizable.
3. Extract concepts — what is the image about? What ideas, entities, or relationships does it convey? Most of this is ^[inferred].
4. Note ambiguity — handwriting you can't read, arrows whose direction is unclear, cropped content. Use ^[ambiguous] and call it out.

Vision is interpretive by nature, so image-derived pages will skew heavily toward ^[inferred]. That's expected — the provenance markers exist precisely to surface this. Don't pretend an image's "meaning" was extracted when you really inferred it.

For PDFs that are mostly images (scanned docs, slide decks exported to PDF), use Read pages: "N" to pull specific pages and treat each page as an image source.

Step 1b: QMD Source Discovery (optional — requires QMD_PAPERS_COLLECTION in .env)

GUARD: If $QMD_PAPERS_COLLECTION is empty or unset, skip this entire step and proceed to Step 2.

No QMD? Skip this step entirely. Use Grep in Step 4 to check for existing pages on the same topic before creating new ones. See .env.example for QMD setup instructions.

When QMD_PAPERS_COLLECTION is set:

Before extracting knowledge from a document, check whether related papers are already indexed that could enrich the page you're about to write:

mcp__qmd__query:
  collection: <QMD_PAPERS_COLLECTION>   # e.g. "papers"
  intent: <what this document is about>
  searches:
    - type: vec    # semantic — finds papers on the same topic even with different vocabulary
      query: <topic or thesis of the source being ingested>
    - type: lex    # keyword — finds papers citing the same methods, tools, or authors
      query: <key terms, author names, method names from the source>

Use the returned snippets to:

1. Surface related papers you may not have thought to link — add them as cross-references in the wiki page
2. Identify recurring themes across the corpus — these deserve their own concept pages
3. Find contradictions between this source and indexed papers — flag with ^[ambiguous]
4. Avoid duplicate pages — if the corpus already covers this concept heavily, merge rather than create

If the QMD results show that 3+ papers touch the same concept, that concept almost certainly warrants a global concepts/ page.

Skip this step if QMD_PAPERS_COLLECTION is not set.

Step 2: Extract Knowledge

From the source, identify:

• Key concepts that deserve their own page or belong on an existing one
• Entities (people, tools, projects, organizations) mentioned
• Claims that can be attributed to the source
• Relationships between concepts (what connects to what)
• Open questions the source raises but doesn't answer

Track provenance per claim as you go. For each claim you extract, mentally tag it as:

• Extracted — the source explicitly states this
• Inferred — you're generalizing across sources, drawing an implication, or filling a gap
• Ambiguous — sources disagree, or the source is vague

You'll apply markers in Step 5. Don't conflate these — the wiki's value depends on the user being able to tell signal from synthesis.

Step 3: Determine Project Scope

If the source belongs to a specific project:

• Place project-specific knowledge under projects/<project-name>/<category>/
• Place general knowledge in global category directories
• Create or update the project overview at projects/<name>/<name>.md (named after the project — never _project.md, as Obsidian uses filenames as graph node labels)

If the source is not project-specific, put everything in global categories.

Step 4: Plan Updates

Before writing anything, plan which pages to update or create. Aim for 10-15 pages per ingest. For each:

• Does this page already exist? (Check index.md and use Glob to search OBSIDIAN_VAULT_PATH)
• If it exists, what new information does this source add?
• If it's new, which category does it belong in?
• What [[wikilinks]] should connect it to existing pages?

Step 5: Write/Update Pages

For each page in your plan:

If creating a new page:

• Use the page template from the llm-wiki skill (frontmatter + sections)
• Place in the correct category directory
• Add [[wikilinks]] to at least 2-3 existing pages
• Include the source in the sources frontmatter field

If updating an existing page:

• Read the current page first
• Merge new information — don't just append
• Update the updated timestamp in frontmatter
• Add the new source to the sources list
• Resolve any contradictions between old and new information (note them if unresolvable)

Write a summary: frontmatter field on every new page (1–2 sentences, ≤200 characters) answering "what is this page about?" for a reader who hasn't opened it. When updating an existing page whose meaning has shifted, rewrite the summary to match the new content. This field is what wiki-query's cheap retrieval path reads — a missing or stale summary forces expensive full-page reads.

Apply provenance markers per the convention in llm-wiki (Provenance Markers section):

• Inferred claims get a trailing ^[inferred]
• Ambiguous/contested claims get a trailing ^[ambiguous]
• Extracted claims need no marker
• After writing the page, count rough fractions and write them to a provenance: frontmatter block (extracted/inferred/ambiguous summing to ~1.0). When updating an existing page, recompute and update the block.

Step 6: Update Cross-References

After writing pages, check that wikilinks work in both directions. If page A links to page B, consider whether page B should also link back to page A.

Step 7: Update Manifest and Special Files

.manifest.json — For each source file ingested, add or update its entry:

{
  "ingested_at": "TIMESTAMP",
  "size_bytes": FILE_SIZE,
  "modified_at": FILE_MTIME,
  "content_hash": "sha256:<64-char-hex>",
  "source_type": "document",  // or "image" for png/jpg/webp/gif and image-only PDFs
  "project": "project-name-or-null",
  "pages_created": ["list/of/pages.md"],
  "pages_updated": ["list/of/pages.md"]
}

content_hash is the SHA-256 of the file contents at ingest time. Always write it — it's the primary skip signal on subsequent runs.

Also update stats.total_sources_ingested and stats.total_pages.

If the manifest doesn't exist yet, create it with version: 1.

index.md — Add entries for any new pages, update summaries for modified pages.

log.md — Append an entry:

- [TIMESTAMP] INGEST source="path/to/source" pages_updated=N pages_created=M mode=append|full

Handling Multiple Sources

When ingesting a directory, process sources one at a time but maintain a running awareness of the full batch. Later sources may strengthen or contradict earlier ones — that's fine, just update pages as you go.

Quality Checklist

After ingesting, verify:

• Every new page has frontmatter with title, category, tags, sources
• Every new page has at least 2 wikilinks to existing pages
• No orphaned pages (pages with zero incoming links)
• index.md reflects all changes
• log.md has the ingest entry
• Source attribution is present for every new claim
• Inferred and ambiguous claims are marked with ^[inferred] / ^[ambiguous]; provenance: frontmatter block is present on new and updated pages
• Every new/updated page has a summary: frontmatter field (1–2 sentences, ≤200 chars)

Reference

Read references/ingest-prompts.md for the LLM prompt templates used during extraction.