Wiki Setup

Wiki Setup

Use this skill to scaffold a fresh wiki workspace so future ingest, query, and lint work follows a consistent structure.

Bundled resources

This skill includes reusable templates:

• references/AGENTS.md: the default wiki schema for new vaults
• references/llm-wiki.md: load this full file into context before scaffolding to capture the complete wiki pattern and setup intent
• references/starter-files.md: starter content for the core wiki pages

Read references/AGENTS.md and references/starter-files.md, and load the full references/llm-wiki.md into context before scaffolding.

What to create

When setting up a new wiki, create this structure unless the user asks for a variation:

<wiki-root>/
├── AGENTS.md
├── raw/
│   └── processed/
└── wiki/
    ├── index.md
    ├── log.md
    ├── overview.md
    └── synthesis.md

If the target folder already exists, inspect it first and only add missing pieces or repair obviously broken structure. Do not overwrite existing content unless the user clearly asked for regeneration.

Setup workflow

1. Confirm or infer the target wiki root. 2. Create the folder structure:

• raw/
• raw/processed/
• wiki/

3. Create AGENTS.md using references/AGENTS.md. 4. Create starter files in wiki/ using references/starter-files.md:

• index.md
• log.md
• overview.md
• synthesis.md

5. If the user already has source material, leave it in raw/ and do not modify those files. 6. Keep the initial content minimal and operational so later skills can take over cleanly.

Completion checklist

Before saying setup is complete, verify each item:

• AGENTS.md exists at the wiki root.
• AGENTS.md matches the bundled schema unless the user requested a custom variant.
• raw/ exists.
• raw/processed/ exists.
• wiki/ exists.
• wiki/index.md exists.
• wiki/log.md exists.
• wiki/overview.md exists.
• wiki/synthesis.md exists.
• starter file contents were created only for missing files or for files the user explicitly asked to regenerate.
• no existing source files in raw/ were modified.
• the final response lists what was created and what was preserved.

If any checklist item fails, fix it before concluding or tell the user exactly what remains incomplete.

Setup rules

• Treat raw/ as the place for immutable source material.
• Treat wiki/ as the maintained knowledge base.
• Keep starter files compact and easy to extend.
• Match the bundled schema unless the user asks for a custom variation.
• Do not fabricate topical content during setup. Create structure and placeholders, not pretend knowledge.

Content guidance

• AGENTS.md should define the maintenance schema and workflows.
• wiki/index.md should explain that it is the compact catalog of pages.
• wiki/log.md should explain the log entry format and may include an initial setup entry if useful.
• wiki/overview.md should be a high-level orientation placeholder.
• wiki/synthesis.md should be a cross-source synthesis placeholder.

When to add an initial log entry

If you created the wiki from scratch, it is helpful to append an initial setup entry to wiki/log.md so the vault has an explicit starting point. Use the same heading convention as the schema and label it QUERY only if the user asked for content work; otherwise prefer a plain setup note inside the starter file template.

Response expectations

After setup, tell the user:

• where the wiki was created
• which folders and files were created
• whether any existing files were preserved instead of overwritten
• any follow-up suggestions, such as placing source material in raw/ or running an ingest pass next

Example triggers

• "Set up a new wiki for this project."
• "Bootstrap an Obsidian-style LLM wiki here."
• "Create the standard wiki folder structure and AGENTS.md."
• "Initialize a new knowledge base with the same schema as this repo."

LLM Wiki Schema

This vault follows Karpathy's LLM Wiki pattern.

Architecture

There are three layers:

1. raw/ contains immutable source material. The LLM may read from this directory but must never modify files inside it. 2. wiki/ contains the maintained markdown knowledge base. The LLM owns this layer and may create, revise, cross-link, and reorganize pages as needed. 3. AGENTS.md is the schema for how this wiki is maintained.

Directory Structure

• raw/: source documents and assets
• wiki/index.md: content-oriented catalog of wiki pages
• wiki/log.md: append-only chronological log of ingest, query, and lint activity
• wiki/overview.md: high-level orientation page for the subject area
• wiki/synthesis.md: evolving current synthesis across sources
• wiki/: additional markdown pages created and maintained over time

Operating Rules

1. Treat raw/ as the source of truth and keep it immutable. 2. Write all durable knowledge into wiki/, not only into chat responses. 3. Update wiki/index.md whenever a new wiki page is created or an existing page materially changes scope. 4. Append a new entry to wiki/log.md for every ingest, durable query output, and lint pass. 5. Prefer cross-links between related wiki pages. 6. Preserve contradictions and uncertainty explicitly instead of smoothing them over.

Workflows

Ingest

When a new source is added to raw/:

1. Read the source. 2. Create or update a summary page in wiki/. 3. Update any affected pages in wiki/, including wiki/overview.md and wiki/synthesis.md when relevant. 4. Update wiki/index.md. 5. Append an ingest entry to wiki/log.md. 6. Move the source file from raw/ directory to raw/processed/

Query

When answering questions:

1. Read wiki/index.md first. 2. Read the most relevant wiki pages. 3. Answer from the wiki with citations to the relevant pages and sources when possible. 4. If the result is durable, save it as a page in wiki/. 5. Update wiki/index.md and append a query entry to wiki/log.md when durable output is written back.

Lint

Periodically check for:

• contradictions between pages
• stale claims superseded by newer sources
• orphan pages with weak linkage
• important ideas mentioned but lacking their own page
• missing cross-references
• gaps that suggest useful future sources

Record each lint pass in wiki/log.md.

Index Format

wiki/index.md should stay compact and scannable. Group pages by category. Each entry should include:

• page link
• one-line summary

Log Format

Every entry in wiki/log.md should begin with:

## [YYYY-MM-DD] TYPE | Title

Where TYPE is typically INGEST, QUERY, or LINT.

LLM Wiki

A pattern for building personal knowledge bases using LLMs.

This is an idea file, it is designed to be copy pasted to your own LLM Agent (e.g. OpenAI Codex, Claude Code, OpenCode / Pi, or etc.). Its goal is to communicate the high level idea, but your agent will build out the specifics in collaboration with you.

The core idea

Most people's experience with LLMs and documents looks like RAG: you upload a collection of files, the LLM retrieves relevant chunks at query time, and generates an answer. This works, but the LLM is rediscovering knowledge from scratch on every question. There's no accumulation. Ask a subtle question that requires synthesizing five documents, and the LLM has to find and piece together the relevant fragments every time. Nothing is built up. NotebookLM, ChatGPT file uploads, and most RAG systems work this way.

The idea here is different. Instead of just retrieving from raw documents at query time, the LLM incrementally builds and maintains a persistent wiki — a structured, interlinked collection of markdown files that sits between you and the raw sources. When you add a new source, the LLM doesn't just index it for later retrieval. It reads it, extracts the key information, and integrates it into the existing wiki — updating entity pages, revising topic summaries, noting where new data contradicts old claims, strengthening or challenging the evolving synthesis. The knowledge is compiled once and then kept current, not re-derived on every query.

This is the key difference: the wiki is a persistent, compounding artifact. The cross-references are already there. The contradictions have already been flagged. The synthesis already reflects everything you've read. The wiki keeps getting richer with every source you add and every question you ask.

You never (or rarely) write the wiki yourself — the LLM writes and maintains all of it. You're in charge of sourcing, exploration, and asking the right questions. The LLM does all the grunt work — the summarizing, cross-referencing, filing, and bookkeeping that makes a knowledge base actually useful over time. In practice, I have the LLM agent open on one side and Obsidian open on the other. The LLM makes edits based on our conversation, and I browse the results in real time — following links, checking the graph view, reading the updated pages. Obsidian is the IDE; the LLM is the programmer; the wiki is the codebase.

This can apply to a lot of different contexts. A few examples:

• Personal: tracking your own goals, health, psychology, self-improvement — filing journal entries, articles, podcast notes, and building up a structured picture of yourself over time.
• Research: going deep on a topic over weeks or months — reading papers, articles, reports, and incrementally building a comprehensive wiki with an evolving thesis.
• Reading a book: filing each chapter as you go, building out pages for characters, themes, plot threads, and how they connect. By the end you have a rich companion wiki. Think of fan wikis like Tolkien Gateway — thousands of interlinked pages covering characters, places, events, languages, built by a community of volunteers over years. You could build something like that personally as you read, with the LLM doing all the cross-referencing and maintenance.
• Business/team: an internal wiki maintained by LLMs, fed by Slack threads, meeting transcripts, project documents, customer calls. Possibly with humans in the loop reviewing updates. The wiki stays current because the LLM does the maintenance that no one on the team wants to do.
• Competitive analysis, due diligence, trip planning, course notes, hobby deep-dives — anything where you're accumulating knowledge over time and want it organized rather than scattered.

Architecture

There are three layers:

Raw sources — your curated collection of source documents. Articles, papers, images, data files. These are immutable — the LLM reads from them but never modifies them. This is your source of truth.

The wiki — a directory of LLM-generated markdown files. Summaries, entity pages, concept pages, comparisons, an overview, a synthesis. The LLM owns this layer entirely. It creates pages, updates them when new sources arrive, maintains cross-references, and keeps everything consistent. You read it; the LLM writes it.

The schema — a document (e.g. CLAUDE.md for Claude Code or AGENTS.md for Codex) that tells the LLM how the wiki is structured, what the conventions are, and what workflows to follow when ingesting sources, answering questions, or maintaining the wiki. This is the key configuration file — it's what makes the LLM a disciplined wiki maintainer rather than a generic chatbot. You and the LLM co-evolve this over time as you figure out what works for your domain.

Operations

Ingest. You drop a new source into the raw collection and tell the LLM to process it. An example flow: the LLM reads the source, discusses key takeaways with you, writes a summary page in the wiki, updates the index, updates relevant entity and concept pages across the wiki, and appends an entry to the log. A single source might touch 10-15 wiki pages. Personally I prefer to ingest sources one at a time and stay involved — I read the summaries, check the updates, and guide the LLM on what to emphasize. But you could also batch-ingest many sources at once with less supervision. It's up to you to develop the workflow that fits your style and document it in the schema for future sessions.

Query. You ask questions against the wiki. The LLM searches for relevant pages, reads them, and synthesizes an answer with citations. Answers can take different forms depending on the question — a markdown page, a comparison table, a slide deck (Marp), a chart (matplotlib), a canvas. The important insight: good answers can be filed back into the wiki as new pages. A comparison you asked for, an analysis, a connection you discovered — these are valuable and shouldn't disappear into chat history. This way your explorations compound in the knowledge base just like ingested sources do.

Lint. Periodically, ask the LLM to health-check the wiki. Look for: contradictions between pages, stale claims that newer sources have superseded, orphan pages with no inbound links, important concepts mentioned but lacking their own page, missing cross-references, data gaps that could be filled with a web search. The LLM is good at suggesting new questions to investigate and new sources to look for. This keeps the wiki healthy as it grows.

Indexing and logging

Two special files help the LLM (and you) navigate the wiki as it grows. They serve different purposes:

index.md is content-oriented. It's a catalog of everything in the wiki — each page listed with a link, a one-line summary, and optionally metadata like date or source count. Organized by category (entities, concepts, sources, etc.). The LLM updates it on every ingest. When answering a query, the LLM reads the index first to find relevant pages, then drills into them. This works surprisingly well at moderate scale (~100 sources, ~hundreds of pages) and avoids the need for embedding-based RAG infrastructure.

log.md is chronological. It's an append-only record of what happened and when — ingests, queries, lint passes. A useful tip: if each entry starts with a consistent prefix (e.g. ## [2026-04-02] ingest | Article Title), the log becomes parseable with simple unix tools — grep "^## \[" log.md | tail -5 gives you the last 5 entries. The log gives you a timeline of the wiki's evolution and helps the LLM understand what's been done recently.

Optional: CLI tools

At some point you may want to build small tools that help the LLM operate on the wiki more efficiently. A search engine over the wiki pages is the most obvious one — at small scale the index file is enough, but as the wiki grows you want proper search. qmd is a good option: it's a local search engine for markdown files with hybrid BM25/vector search and LLM re-ranking, all on-device. It has both a CLI (so the LLM can shell out to it) and an MCP server (so the LLM can use it as a native tool). You could also build something simpler yourself — the LLM can help you vibe-code a naive search script as the need arises.

Tips and tricks

• Obsidian Web Clipper is a browser extension that converts web articles to markdown. Very useful for quickly getting sources into your raw collection.
• Download images locally. In Obsidian Settings → Files and links, set "Attachment folder path" to a fixed directory (e.g. raw/assets/). Then in Settings → Hotkeys, search for "Download" to find "Download attachments for current file" and bind it to a hotkey (e.g. Ctrl+Shift+D). After clipping an article, hit the hotkey and all images get downloaded to local disk. This is optional but useful — it lets the LLM view and reference images directly instead of relying on URLs that may break. Note that LLMs can't natively read markdown with inline images in one pass — the workaround is to have the LLM read the text first, then view some or all of the referenced images separately to gain additional context. It's a bit clunky but works well enough.
• Obsidian's graph view is the best way to see the shape of your wiki — what's connected to what, which pages are hubs, which are orphans.
• Marp is a markdown-based slide deck format. Obsidian has a plugin for it. Useful for generating presentations directly from wiki content.
• Dataview is an Obsidian plugin that runs queries over page frontmatter. If your LLM adds YAML frontmatter to wiki pages (tags, dates, source counts), Dataview can generate dynamic tables and lists.
• The wiki is just a git repo of markdown files. You get version history, branching, and collaboration for free.

Why this works

The tedious part of maintaining a knowledge base is not the reading or the thinking — it's the bookkeeping. Updating cross-references, keeping summaries current, noting when new data contradicts old claims, maintaining consistency across dozens of pages. Humans abandon wikis because the maintenance burden grows faster than the value. LLMs don't get bored, don't forget to update a cross-reference, and can touch 15 files in one pass. The wiki stays maintained because the cost of maintenance is near zero.

The human's job is to curate sources, direct the analysis, ask good questions, and think about what it all means. The LLM's job is everything else.

The idea is related in spirit to Vannevar Bush's Memex (1945) — a personal, curated knowledge store with associative trails between documents. Bush's vision was closer to this than to what the web became: private, actively curated, with the connections between documents as valuable as the documents themselves. The part he couldn't solve was who does the maintenance. The LLM handles that.

Note

This document is intentionally abstract. It describes the idea, not a specific implementation. The exact directory structure, the schema conventions, the page formats, the tooling — all of that will depend on your domain, your preferences, and your LLM of choice. Everything mentioned above is optional and modular — pick what's useful, ignore what isn't. For example: your sources might be text-only, so you don't need image handling at all. Your wiki might be small enough that the index file is all you need, no search engine required. You might not care about slide decks and just want markdown pages. You might want a completely different set of output formats. The right way to use this is to share it with your LLM agent and work together to instantiate a version that fits your needs. The document's only job is to communicate the pattern. Your LLM can figure out the rest.

Starter Files

Use these templates when scaffolding a fresh wiki.

wiki/index.md

# Wiki Index

## Core Pages

- [overview](overview.md): High-level orientation for this subject area.
- [synthesis](synthesis.md): Evolving synthesis across sources.

## Topics

- Add topic pages here as the wiki grows.

wiki/log.md

# Wiki Log

## [YYYY-MM-DD] SETUP | Wiki initialized

Created the initial wiki structure, starter pages, and maintenance schema.

wiki/overview.md

# Overview

This page provides the high-level orientation for the subject area covered by this wiki.

## Scope

- Define the subject area here.

## Key Themes

- Add major themes as sources are ingested.

wiki/synthesis.md

# Synthesis

This page captures the current cross-source synthesis for the wiki.

## Current Picture

- Add synthesized takeaways here.

## Open Questions

- Track contradictions, uncertainty, and unresolved questions here.