Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →ar9av/llm-wiki
The foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki. Based on Andrej Karpathy's LLM Wiki architecture.
Passed 22 of 22 test cases with the skill, and 11 of 22 without it.
and 15 more in the full report
11 fixed11 passed either way0 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
This benchmark measured an earlier version of the skill.
A newer attempt on gemini-3.8-flash on 10/18/2026 did not produce a publishable comparison (not comparable). The snapshot above is the previously measured run.
One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.
Where should a newly installed setup store its global configuration file when `$XDG_CONFIG_HOME` is set to `/home/user/.config` and no legacy directory exists?
| Checked | Without skill | With skill |
|---|---|---|
| Resolves the global configuration path under /home/user/.config/obsidian-wiki/config. | Missed | Passed |
The instructions your model reads when the skill loads.
You 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.
The 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.
Think of raw sources as the "source code" — authoritative but hard to query directly.
Don'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.
A collection of interconnected Obsidian-compatible markdown files organized by category. This is the compiled knowledge — synthesized, cross-referenced, and navigable. Each page has:
[[wikilinks]] connecting related conceptsThe wiki lives at the path configured via OBSIDIAN_VAULT_PATH in .env.
The rules governing how the wiki is structured — categories, conventions, page templates, and operational workflows. The schema tells the LLM how to maintain the wiki.
The vault has two levels of structure: categories (what kind of knowledge) and projects (where the knowledge came from).
Organize pages into these default categories (customizable in .env):
| Category | Purpose | Example |
|---|---|---|
concepts/ | Ideas, theories, mental models | concepts/transformer-architecture.md |
entities/ | People, orgs, tools, projects | entities/andrej-karpathy.md |
test cases passed, vs 11 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.