llm-wiki is agent-read markdown (skill) from jellydn/my-ai-tools: Build a persistent compounding wiki from raw sources using the LLM Wiki pattern.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
What the file says
# LLM Wiki
Build and maintain a persistent, compounding knowledge wiki from raw sources.
Based on [Karpathy's LLM Wiki pattern](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f): the LLM incrementally integrates each new source into a structured wiki of markdown files — updating entity pages, flagging contradictions, strengthening cross-references. Synthesis is compiled once and kept current, not re-derived on every query.
## Usage
`/llm-wiki <ACTION> [ARGUMENTS]`
## Actions
- **init [DIRECTORY]** - Initialize a new wiki (default: `wiki/`)
- **ingest <SOURCE>** - Process a source file and integrate it into the wiki
- **query <QUESTION>** - Answer a question using the wiki as the knowledge base
- **lint** - Health-check the wiki for contradictions, orphan pages, and stale content
- **status** - Show a summary of the wiki's current state
---
## Architecture
```
your-wiki/
├── raw/ # Immutable source documents — you add, LLM never modifies
│ └── assets/ # Downloaded images referenced by sources
├── wiki/ # LLM-generated and maintained pages
│ ├── index.md # Catalog of all pages with one-line summaries
…
Pin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
A 17 of 17 checks passed. Deterministic, no model, same answer every run.
pass: Frontmatter block present
pass: Frontmatter declares a name
pass: Frontmatter declares a description
pass: Size between 200 bytes and 200 KB (6276 bytes)
pass: No zero-width or bidi control characters
pass: No instruction hidden inside an HTML comment
pass: No link to an exfiltration or paste host
pass: No credential-shaped string
pass: No instruction to send local credentials anywhere
pass: No text hidden with inline styles
pass: No prompt-injection phrasing
pass: No curl or wget piped into a shell
pass: No recursive delete of root, home or parent
pass: No instruction to read or print local credentials
pass: No base64 blob over 200 characters
pass: No link to a raw IP address
pass: No script tag
Source
GitHub
jellydn/my-ai-tools · 121 stars · license MIT · pushed 2026-09-24 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_ytckrtgdrnu4qofb
GET https://markdownregistry.com/api/v1/resolve?ref=jellydn/my-ai-tools/llm-wiki
GET https://markdownregistry.com/api/v1/blob/d79afb94388416f1bdcbfcafe66710736c209469e00ba96421ce8305a96ea9d7
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.
jellydn/my-ai-tools · configs/amp/plugins/my-ai-tools-skills/skills/accountable-engineering/SKILL.md · Use explicit human checkpoints for architecture, security, rollout, or operational decisions.
jellydn/my-ai-tools · configs/amp/plugins/my-ai-tools-skills/skills/blindspot-pass/SKILL.md · Inspect history and architecture for hidden constraints before risky cross-cutting changes.
jellydn/my-ai-tools · configs/amp/plugins/my-ai-tools-skills/skills/capability-experiments/SKILL.md · Build an interactive report or experiment when the user asks to explore model capabilities.
jellydn/my-ai-tools · configs/amp/plugins/my-ai-tools-skills/skills/code-quality-review/SKILL.md · Audit a diff for structural maintainability and unnecessary complexity.
jellydn/my-ai-tools · configs/amp/plugins/my-ai-tools-skills/skills/code-review/SKILL.md · Review a branch, PR, or worktree diff for repository conventions and stated intent.
jellydn/my-ai-tools · configs/amp/plugins/my-ai-tools-skills/skills/codemap/SKILL.md · Create a seven-document architecture map when the user asks to map a codebase.
jellydn/my-ai-tools · configs/amp/plugins/my-ai-tools-skills/skills/commit-atomic/SKILL.md · Group staged changes into atomic commits with commitizen convention
jellydn/my-ai-tools · configs/amp/plugins/my-ai-tools-skills/skills/context-discovery/SKILL.md · Use MCP tools to trace behavior that spans multiple modules or history sources.
ar9av/obsidian-wiki · .skills/llm-wiki/SKILL.md · The foundational knowledge distillation pattern for building and maintaining an AI-powered Obsidian wiki. Based on…
cowork-os/cowork-os · resources/skills/llm-wiki/SKILL.md · Build and maintain a workspace-local, Obsidian-friendly research vault using Karpathy's LLM Wiki pattern.
infranodus/skills · skill-llm-wiki/SKILL.md · Guide users through setting up a personal LLM-maintained wiki — a persistent, compounding knowledge base where the LLM…
praneybehl/llm-wiki-plugin · skills/llm-wiki/SKILL.md · Build and maintain an LLM-curated knowledge base from papers, articles, transcripts, notes and project findings. Ingest…
akillness/jeo-skills · .agent-skills/llm-wiki/SKILL.md · Build and maintain a persistent markdown wiki that an LLM updates on the user's behalf, usually inside an Obsidian…
dreadnode/capabilities · capabilities/llm-wiki/skills/llm-wiki/SKILL.md · Use when building, querying, revising, or linting a persistent LLM-maintained wiki from source material in Dreadnode…
