---

name: llm-wiki description: "Karpathy's LLM Wiki: build/query interlinked markdown KB." version: 2.2.0 author: Hermes Agent license: MIT metadata: hermes: tags: [wiki, knowledge-base, research, notes, markdown, rag-alternative] category: research related_skills: [obsidian, arxiv]

Karpathy's LLM Wiki

Build and maintain a persistent, compounding knowledge base as interlinked markdown files. Based on Andrej Karpathy's LLM Wiki pattern.

Unlike traditional RAG (which rediscovers knowledge from scratch per query), the wiki compiles knowledge once and keeps it current. Cross-references are already there. Contradictions have already been flagged. Synthesis reflects everything ingested.

Division of labor: The human curates sources and directs analysis. The agent summarizes, cross-references, files, and maintains consistency.

When This Skill Activates

Use this skill when the user:

• Asks to create, build, or start a wiki or knowledge base
• Asks to ingest, add, or process a source into their wiki
• Asks a question and an existing wiki is present at the configured path
• Asks to lint, audit, or health-check their wiki
• References their wiki, knowledge base, or "notes" in a research context

Wiki Location

Location: ./wiki in this project

The wiki is just a directory of markdown files — open it in Obsidian, VS Code, or any editor. No database, no special tooling required.

Architecture: Three Layers

wiki/
├── SCHEMA.md           # Conventions, structure rules, domain config
├── index.md            # Sectioned content catalog with one-line summaries
├── log.md              # Chronological action log (append-only, rotated yearly)
├── raw/                # Layer 1: Immutable source material
│   ├── articles/       # Web articles, clippings
│   ├── papers/         # PDFs, arxiv papers
│   ├── transcripts/    # Meeting notes, interviews
│   └── assets/         # Images, diagrams referenced by sources
├── entities/           # Layer 2: Entity pages (people, orgs, products, models)
├── concepts/           # Layer 2: Concept/topic pages
├── comparisons/        # Layer 2: Side-by-side analyses
└── queries/            # Layer 2: Filed query results worth keeping

Layer 1 — Raw Sources: Immutable. The agent reads but never modifies these. Layer 2 — The Wiki: Agent-owned markdown files. Created, updated, and cross-referenced by the agent. Layer 3 — The Schema: SCHEMA.md defines structure, conventions, and tag taxonomy.

Resuming an Existing Wiki (CRITICAL — do this every session)

When the user has an existing wiki, always orient yourself before doing anything:

① Read SCHEMA.md — understand the domain, conventions, and tag taxonomy. ② Read index.md — learn what pages exist and their summaries. ③ Scan recent log.md — read the last 20-30 entries to understand recent activity.

Only after orientation should you ingest, query, or lint. This prevents:

• Creating duplicate pages for entities that already exist
• Missing cross-references to existing content
• Contradicting the schema's conventions
• Repeating work already logged

For large wikis (100+ pages), also run a quick grep -rl "<topic>" ./wiki/` for the topic at hand before creating anything new.

Initializing a New Wiki

When the user asks to create or start a wiki:

1. Determine the wiki path: `./wiki/' in the project repo
2. Create the directory structure above
3. Ask the user what domain the wiki covers — be specific
4. Write SCHEMA.md customized to the domain (see template below)
5. Write initial index.md with sectioned header
6. Write initial log.md with creation entry
7. Confirm the wiki is ready and suggest first sources to ingest

SCHEMA.md Template

Adapt to the user's domain. The schema constrains agent behavior and ensures consistency:

# Wiki Schema

## Domain
[What this wiki covers — e.g., "AI/ML research", "personal health", "startup intelligence"]

## Conventions
- File names: lowercase, hyphens, no spaces (e.g., `transformer-architecture.md`)
- Every wiki page starts with YAML frontmatter (see below)
- Use `[[wikilinks]]` to link between pages (minimum 2 outbound links per page)
- When updating a page, always bump the `updated` date
- Every new page must be added to `index.md` under the correct section
- Every action must be appended to `log.md`
- **Provenance markers:** On pages that synthesize 3+ sources, append `^[raw/articles/source-file.md]`
  at the end of paragraphs whose claims come from a specific source. This lets a reader trace each
  claim back without re-reading the whole raw file. Optional on single-source pages where the
  `sources:` frontmatter is enough.

## Frontmatter
  ```yaml
  ---
  title: Page Title
  created: YYYY-MM-DD
  updated: YYYY-MM-DD
  type: entity | concept | comparison | query | summary
  tags: [from taxonomy below]
  sources: [raw/articles/source-name.md]
  # Optional quality signals:
  confidence: high | medium | low        # how well-supported the claims are
  contested: true                        # set when the page has unresolved contradictions
  contradictions: [other-page-slug]      # pages this one conflicts with
  ---

confidence and contested are optional but recommended for opinion-heavy or fast-moving topics. Lint surfaces contested: true and confidence: low pages for review so weak claims don't silently harden into accepted wiki fact.

raw/ Frontmatter

Raw sources ALSO get a small frontmatter block so re-ingests can detect drift:

---
source_url: https://example.com/article   # original URL, if applicable
ingested: YYYY-MM-DD
sha256: <hex digest of the raw content below the frontmatter>
---

The sha256: lets a future re-ingest of the same URL skip processing when content is unchanged, and flag drift when it has changed. Compute over the body only (everything after the closing ---), not the frontmatter itself.

Tag Taxonomy

[Define 10-20 top-level tags for the domain. Add new tags here BEFORE using them.]

Example for AI/ML:

• Models: model, architecture, benchmark, training
• People/Orgs: person, company, lab, open-source
• Techniques: optimization, fine-tuning, inference, alignment, data
• Meta: comparison, timeline, controversy, prediction

Rule: every tag on a page must appear in this taxonomy. If a new tag is needed, add it here first, then use it. This prevents tag sprawl.

Page Thresholds

• Create a page when an entity/concept appears in 2+ sources OR is central to one source
• Add to existing page when a source mentions something already covered
• DON'T create a page for passing mentions, minor details, or things outside the domain
• Split a page when it exceeds ~200 lines — break into sub-topics with cross-links
• Archive a page when its content is fully superseded — move to _archive/, remove from index

Entity Pages

One page per notable entity. Include:

• Overview / what it is
• Key facts and dates
• Relationships to other entities ([[wikilinks]])
• Source references

Concept Pages

One page per concept or topic. Include:

• Definition / explanation
• Current state of knowledge
• Open questions or debates
• Related concepts ([[wikilinks]])

Comparison Pages

Side-by-side analyses. Include:

• What is being compared and why
• Dimensions of comparison (table format preferred)
• Verdict or synthesis
• Sources

Update Policy

When new information conflicts with existing content:

1. Check the dates — newer sources generally supersede older ones
2. If genuinely contradictory, note both positions with dates and sources
3. Mark the contradiction in frontmatter: contradictions: [page-name]
4. Flag for user review in the lint report

### index.md Template

The index is sectioned by type. Each entry is one line: wikilink + summary.

```markdown
# Wiki Index

> Content catalog. Every wiki page listed under its type with a one-line summary.
> Read this first to find relevant pages for any query.
> Last updated: YYYY-MM-DD | Total pages: N

## Entities
<!-- Alphabetical within section -->

## Concepts

## Comparisons

## Queries

Scaling rule: When any section exceeds 50 entries, split it into sub-sections by first letter or sub-domain. When the index exceeds 200 entries total, create a _meta/topic-map.md that groups pages by theme for faster navigation.

log.md Template

# Wiki Log

> Chronological record of all wiki actions. Append-only.
> Format: `## [YYYY-MM-DD] action | subject`
> Actions: ingest, update, query, lint, create, archive, delete
> When this file exceeds 500 entries, rotate: rename to log-YYYY.md, start fresh.

## [YYYY-MM-DD] create | Wiki initialized
- Domain: [domain]
- Structure created with SCHEMA.md, index.md, log.md

Core Operations

1. Ingest

When the user provides a source (URL, file, paste), integrate it into the wiki:

① Capture the raw source:

• URL → use WebFetch to get markdown, save to raw/articles/
• PDF → use WebFetch (handles PDFs), save to raw/papers/
• Pasted text → save to appropriate raw/ subdirectory
• Name the file descriptively: raw/articles/karpathy-llm-wiki-2026.md
• Add raw frontmatter (source_url, ingested, sha256 of the body). On re-ingest of the same URL: recompute the sha256, compare to the stored value — skip if identical, flag drift and update if different. This is cheap enough to do on every re-ingest and catches silent source changes.

② Discuss takeaways with the user — what's interesting, what matters for the domain. (Skip this in automated/cron contexts — proceed directly.)

③ Check what already exists — search index.md and use grep -rl to find existing pages for mentioned entities/concepts. This is the difference between a growing wiki and a pile of duplicates.

④ Write or update wiki pages:

• New entities/concepts: Create pages only if they meet the Page Thresholds in SCHEMA.md (2+ source mentions, or central to one source)
• Existing pages: Add new information, update facts, bump updated date. When new info contradicts existing content, follow the Update Policy.
• Cross-reference: Every new or updated page must link to at least 2 other pages via [[wikilinks]]. Check that existing pages link back.
• Tags: Only use tags from the taxonomy in SCHEMA.md
• Provenance: On pages synthesizing 3+ sources, append ^[raw/articles/source.md] markers to paragraphs whose claims trace to a specific source.
• Confidence: For opinion-heavy, fast-moving, or single-source claims, set confidence: medium or low in frontmatter. Don't mark high unless the claim is well-supported across multiple sources.

⑤ Update navigation:

• Add new pages to index.md under the correct section, alphabetically
• Update the "Total pages" count and "Last updated" date in index header
• Append to log.md: ## [YYYY-MM-DD] ingest | Source Title
• List every file created or updated in the log entry

⑥ Report what changed — list every file created or updated to the user.

A single source can trigger updates across 5-15 wiki pages. This is normal and desired — it's the compounding effect.

2. Query

When the user asks a question about the wiki's domain:

① Read index.md to identify relevant pages. ② For wikis with 100+ pages, also grep -rl "<term>" "./wiki" --include="*.md" for key terms — the index alone may miss relevant content. ③ Read the relevant pages using the Read tool. ④ Synthesize an answer from the compiled knowledge. Cite the wiki pages you drew from: "Based on [[page-a]] and [[page-b]]..." ⑤ File valuable answers back — if the answer is a substantial comparison, deep dive, or novel synthesis, create a page in queries/ or comparisons/. Don't file trivial lookups — only answers that would be painful to re-derive. ⑥ Update log.md with the query and whether it was filed.

3. Lint

When the user asks to lint, health-check, or audit the wiki:

Quick path: Use the reusable script (saves writing from scratch):

python <skill_dir>/scripts/wiki-lint.py "./wiki"

It runs all 11 checks below in one pass and prints a severity-grouped report. Results exit code: 0 = clean, 1 = issues found.

If the script isn't available or needs modification, write a Python script and run it via Bash. The key gotchas to handle yourself:

• Anchor links: [[page#heading]] is valid — strip the #heading part before checking if the page exists. Only the page name needs to be a valid slug. A link like [[daytona-sandbox-deep-agents#Integration-Architecture]] is NOT broken even though no file named daytona-sandbox-deep-agents#Integration-Architecture.md exists.
• Self-references: [[page#heading]] on the same page it references should NOT count as an inbound link for the orphan check.
• Frontmatter sources: field: This field can legitimately be an empty list [] for pages created without source ingestion — don't flag that as missing, only flag when the field is entirely absent from the frontmatter block.

Manual checks (in order of severity):

① Orphan pages: Pages with no inbound [[wikilinks]] from other pages (excluding the page linking to itself via [[page#anchor]]).

② Broken wikilinks: [[links]] that don't resolve to any page file. Handle [[page#anchor]] by checking only the page part.

③ Source drift: For each file in raw/ with a sha256: frontmatter, recompute the hash and flag mismatches. Mismatches indicate the raw file was edited (shouldn't happen — raw/ is immutable).

④ Contradictions: Pages with contested: true or contradictions: frontmatter — surface these for user review.

⑤ Stale content: Pages whose updated date is >90 days old.

⑥ Quality signals: Pages with confidence: low and pages with only one source but no confidence field set.

⑦ Frontmatter validation: Missing required fields (title, created, updated, type, tags, sources). Tags not in the SCHEMA.md taxonomy.

⑧ Page size: Pages over 200 lines — candidates for splitting.

⑨ Index completeness: Every wiki page should appear in index.md.

⑩ Tag audit: Tags in the schema that are never used anywhere — indicates dead taxonomy entries that could be cleaned up.

⑪ Log rotation: If log.md exceeds 500 entries, rotate it.

Report and fix workflow:

lint → present findings (grouped by severity) → ask user → apply fixes

Fixes typically span:

• SCHEMA.md — add missing tags to taxonomy (most common fix)
• Individual pages — add missing frontmatter fields, fix broken wikilinks
• Page split — new page for content >200 lines
• index.md — add new pages, bump total count & date
• log.md — append lint entry after fixes applied

Common pitfall: Tag taxonomy drift is the most frequent lint finding — agents use descriptive tags like architecture, tools, backend that aren't in the initial schema. Rather than changing pages to use schema-only tags (which reduces descriptiveness), expand the SCHEMA.md taxonomy to include the tags pages actually use.

Append to log.md: ## [YYYY-MM-DD] lint | N issues found

Working with the Wiki

Searching

# Find pages by content
grep -rl "transformer" "./wiki" --include="*.md"

# Find pages by filename
find "./wiki" -name "*.md" | sort

# Find pages by tag
grep -rl "tags:.*alignment" "./wiki" --include="*.md"

# Recent activity — use the Read tool on the last 20 lines of log.md

Bulk Ingest

When ingesting multiple sources at once, batch the updates:

1. Read all sources first
2. Identify all entities and concepts across all sources
3. Check existing pages for all of them (one search pass, not N)
4. Create/update pages in one pass (avoids redundant updates)
5. Update index.md once at the end
6. Write a single log entry covering the batch

Archiving

When content is fully superseded or the domain scope changes:

1. Create _archive/ directory if it doesn't exist
2. Move the page to _archive/ with its original path (e.g., _archive/entities/old-page.md)
3. Remove from index.md
4. Update any pages that linked to it — replace wikilink with plain text + "(archived)"
5. Log the archive action

Obsidian Integration

The wiki directory works as an Obsidian vault out of the box:

• [[wikilinks]] render as clickable links
• Graph View visualizes the knowledge network
• YAML frontmatter powers Dataview queries
• The raw/assets/ folder holds images referenced via ![[image.png]]

For best results:

• Set Obsidian's attachment folder to raw/assets/
• Enable "Wikilinks" in Obsidian settings (usually on by default)
• Install Dataview plugin for queries like TABLE tags FROM "entities" WHERE contains(tags, "company")

If using the Obsidian skill alongside this one, set OBSIDIAN_VAULT_PATH to the same directory as the wiki path.

Pitfalls

• Never modify files in raw/ — sources are immutable. Corrections go in wiki pages.
• Always orient first — read SCHEMA + index + recent log before any operation in a new session. Skipping this causes duplicates and missed cross-references.
• Always update index.md and log.md — skipping this makes the wiki degrade. These are the navigational backbone.
• Don't create pages for passing mentions — follow the Page Thresholds in SCHEMA.md. A name appearing once in a footnote doesn't warrant an entity page.
• Don't create pages without cross-references — isolated pages are invisible. Every page must link to at least 2 other pages.
• Frontmatter is required — it enables search, filtering, and staleness detection.
• Tags must come from the taxonomy — freeform tags decay into noise. Add new tags to SCHEMA.md first, then use them.
• Keep pages scannable — a wiki page should be readable in 30 seconds. Split pages over 200 lines. Move detailed analysis to dedicated deep-dive pages.
• Ask before mass-updating — if an ingest would touch 10+ existing pages, confirm the scope with the user first.
• Rotate the log — when log.md exceeds 500 entries, rename it log-YYYY.md and start fresh. The agent should check log size during lint.
• Handle contradictions explicitly — don't silently overwrite. Note both claims with dates, mark in frontmatter, flag for user review.

Related Tools

llm-wiki-compiler is a Node.js CLI that compiles sources into a concept wiki with the same Karpathy inspiration. It's Obsidian-compatible, so users who want a scheduled/CLI-driven compile pipeline can point it at the same vault this skill maintains. Trade-offs: it owns page generation (replaces the agent's judgment on page creation) and is tuned for small corpora. Use this skill when you want agent-in-the-loop curation; use llmwiki when you want batch compile of a source directory.