/llm-wiki

name: llm-wiki
description: |
  Build and maintain an LLM-curated knowledge base from papers, articles, transcripts, notes and project findings. Ingest sources into linked Markdown, answer questions with citations, lint or upgrade a wiki, and preserve useful synthesis across sessions and agents. Also capture verified task experience, consolidate success/failure patterns, and propose, evaluate, apply or roll back evidence-linked skill improvements. Trigger on "add this to my wiki", "what does the wiki say", "learn from this task", "improve this procedure", /wiki:learn or /wiki:evolve. Works on a local folder or a hosted wiki URL (MCP). Use index-first navigation, atomic pages and hybrid search.

LLM Wiki

A skill for building and maintaining an LLM-curated knowledge base at any user-chosen filesystem location, following the pattern Andrej Karpathy described in his April 2026 gist. One personal wiki can compound knowledge across projects, or a wiki can be isolated inside one project. The user curates sources and asks questions; the LLM does the bookkeeping.

The pattern in one paragraph

Conventional RAG re-derives knowledge from raw chunks on every query; nothing accumulates. The LLM Wiki pattern flips this: when a new source arrives, the LLM compiles it once into a persistent, structured wiki: extracting concepts, writing entity pages, updating cross-references, flagging contradictions. Subsequent queries read the pre-synthesized wiki rather than the raw sources. Knowledge compounds. The user is in charge of sourcing and asking good questions; the LLM handles the summarizing, linking, and consistency work that humans abandon wikis over.

When to use this skill

The trigger surface is broad. Any time the user is accumulating textual material over time (research papers, articles, transcripts, meeting notes, book chapters, customer calls, code repos, journal entries) and would benefit from having that material organized rather than dumped into a chat each session, this skill applies. It is equally useful for one source ("ingest this paper") and for the steady-state operations against an existing wiki ("what does my wiki say about diffusion models", "lint the wiki", "what's missing").

Resolve the wiki before doing anything else. Prefer, in order: a path or URL named by the user, a path or URL in the nearest project instructions, a path or URL in global agent instructions, then `wiki/` in the current project. Read the resolved wiki's `SCHEMA.md`; it may override defaults documented here. Never silently combine two wikis. If no wiki exists, run the bootstrap step below.

All relative `wiki/` and `raw/` paths in this skill refer to the resolved wiki and raw-source roots, not necessarily the current working directory.

Backends: local folder or hosted URL

A wiki has one of two backends. The workflows, page conventions and `SCHEMA.md` are the same for both.

• **Local folder.** Pages are files. Use file reads, `str_replace` and the bundled scripts.
• **Hosted URL.** Pages are on an LLM Wiki server (a Cloudflare Worker). Use the MCP tools `wiki_overview`, `wiki_read`, `wiki_search`, `wiki_commit`, `wiki_history`, `wiki_graph`, `wiki_lint` and `wiki_raw`. Without MCP, use `python3 scripts/wiki_remote.py` (stdlib only).

Select the hosted backend when the instructions give a wiki URL, or when the `wiki_overview` tool is available and no local path is given. In hosted mode:

1. Call `wiki_overview` first. It returns `SCHEMA.md` and `index.md`. 2. Make surgical changes with `wiki_commit` `edit` operations. Each `old` text must occur once. 3. Add `log.md` and index lines with `append` operations. They never conflict. 4. After a conflict (HTTP 409 or `isError`), read the page again, make the change again and retry. Never overwrite another agent's change. 5. Do not run extract or cache scripts. The server updates search, links and the graph on each commit.

A `pull` mirror of a hosted wiki is read-only. Do not edit it. Full procedure, tool map and limits: `references/hosted-mode.md`.

**Optional decision layer.** Small decision models can gate search relevance and flag weak graph evidence or untrusted text. The layer is off by default and never writes pages. Enable it only on the user's request: `references/decision-models.md`.

Architecture: three layers, three operations

The wiki has three layers and three operations. Internalize this vocabulary because the rest of the skill assumes it.

The three layers are **raw sources** (the user's curated source material: articles, papers, PDFs, transcripts; immutable, the LLM reads but never modifies them), **the wiki** (a directory of LLM-generated markdown pages: entity pages, concept pages, comparisons, summaries; the LLM owns this layer entirely), and **the schema** (a `SCHEMA.md` file at the wiki root that documents the conventions for this particular wiki: page types, naming rules, tag taxonomy, ingest workflow customizations; co-evolved with the user).

The three operations are **ingest** (a new source arrives; the LLM reads it, writes a summary page, updates relevant entity and concept pages, appends to the log), **query** (the user asks a question; the LLM navigates the wiki via the index, reads the relevant pages, and synthesizes an answer, often filing the answer back as a new page so the exploration compounds), and **lint** (a periodic health check; the LLM scans for contradictions, stale claims, orphan pages, missing concepts, broken links).

For the canonical write-up of these operations, read `references/architecture.md`. For the step-by-step procedures, read `references/ingest-workflow.md`, `references/query-workflow.md`, and `references/lint-workflow.md` as needed.

Graph layer (compiled, optional)

Pages can carry typed `graph:` metadata in frontmatter. A bundled extractor compiles every page into `wiki/graph/`: `nodes.jsonl`, `edges.jsonl`, `graph.sqlite`, `graph.graphml`. **Markdown is canonical**; the graph is a re