llm-wiki

1# LLM Wiki — Knowledge Distillation Pattern
2 
3You are maintaining a persistent, compounding knowledge base. The wiki is not a chatbot — it is a **compiled artifact** where knowledge is distilled once and kept current, not re-derived on every query.
4 
5## Three-Layer Architecture
6 
7### Layer 1: Raw Sources (immutable)
8 
9The user's original documents — articles, papers, notes, PDFs, conversation logs, bookmarks, **and images** (screenshots, whiteboard photos, diagrams, slide captures). These are never modified by the system. They live wherever the user keeps them (configured via `OBSIDIAN_SOURCES_DIR` in `.env`). Images are first-class sources: the ingest skills read them via the Read tool's vision support and treat their interpreted content as inferred unless it's verbatim transcribed text. Image ingestion requires a vision-capable model — models without vision support should skip image sources and report which files were skipped.
10 
11Think of raw sources as the "source code" — authoritative but hard to query directly.
12 
13Don't confuse this with the in-vault `_raw/` staging folder, which is a different thing: a scratch inbox for quick captures and drafts awaiting promotion (see `wiki-capture` and `wiki-ingest`). Files there aren't Layer 1 sources, but `wiki-ingest` still moves rather than deletes them on promotion, since some have no other copy.
14 
15### Layer 2: The Wiki (LLM-maintained)
16…