LLM Wiki Skill

A skill that lets an agent read the LLM Wiki desktop app's knowledge base over its local HTTP API: search, pages and graph

  • 153 ★ on the repository
  • Last commit
Skill

Extended access

Why this level

  • Reads wiki and source contents through the local API with a token from an environment variable
  • The no-token mode opens the wiki to any process on the machine
All reasons and checks

nashsu/llm_wiki_skill

Install

In your terminal, with SkillFoxx CLI

npx skillfoxx add skills/llm-wiki-skill

Detects the agents on your machine, shows the access level and pins the version.

Other ways to install

Access and checks

How we review

Extended accessThe tool runs code or makes network calls and only reads external data.

  • Reads wiki and source contents through the local API with a token from an environment variable
  • The no-token mode opens the wiki to any process on the machine

This is third-party code. Review the repository files before installing.

What it does

The llm-wiki skill documents the local API contract of the LLM Wiki desktop app, and the agent calls it with plain `curl`, `fetch` or `requests`. The skill ships no client library, SDK or scripts: it is three Markdown files with agent instructions, an endpoint reference and sample dialogues. The agent searches the wiki with hybrid retrieval that combines keywords and vectors. It reads `wiki/**.md` pages, gets the file tree and a node's neighborhood in the link graph, and after you add documents it asks the app to rebuild the index (`sources/rescan`). Every call reads data except the reindex. The skill triggers only when you name LLM Wiki, my wiki or the knowledge base explicitly. It stays quiet for requests about notes, Obsidian or Notion.

Who it is for. Users of the LLM Wiki desktop app whose Claude Code or Codex should answer from their own knowledge base.

Good fit when

  • You ask what your wiki says about RoPE and expect an answer with quotes from its pages
  • The agent has to read a specific wiki page and follow its links
  • You added documents to the sources folder and want the knowledge base reindexed
  • You want an overview of the wiki's structure: the file tree and `index.md`
  • An answer has to rest on a project's materials by name or identifier

Not a fit when

  • Your notes live in Obsidian, Notion, Apple Notes or Logseq: the skill works with the LLM Wiki app only
  • The desktop app is closed: the API listens on `127.0.0.1:19828` only while the app is open
  • You need web information or general knowledge that is not in your wiki

Example request

What does my wiki say about RoPE? Find the three best pages, read them and show which pages link to them

Limitations

  • The app's local API must be enabled with a token set; without a token every endpoint answers 401 except `/api/v1/health`.
  • The no-token access mode removes protection and any process on the machine can then read the wiki. Keep the token as a local secret.
  • The skill matches API v1 of app version 0.4.10 and newer; after a major version change compare against the reference.
  • The last commit in the repository dates from May 2026, and there is no license file on GitHub.

How to disable. Delete the skill from the agent's skills directory and remove the `~/.claude/skills/llm-wiki` symlink if you installed it by hand. Revoke the token in the app's API Server settings and drop the `LLM_WIKI_API_TOKEN` variable from the environment.

FAQ

How do I check that the skill can see the LLM Wiki app?

Run `curl -s http://127.0.0.1:19828/api/v1/health`. That endpoint needs no token and returns the server state. A connection error means the app is closed, and a `port_conflict` status means another process holds the port.

Where do I get the API token?

In the app open Settings, API Server and click Generate new token. Or export the `LLM_WIKI_API_TOKEN` variable, which overrides the value from the interface.

Does the skill change my wiki?

No. Search, page reads, the file tree and the graph only read data. The single write action, `sources/rescan`, queues an index refresh for new sources.

How do I install the skill by hand?

Clone the repository and symlink it to `~/.claude/skills/llm-wiki`, or copy the three Markdown files into the agent's skills directory. There is no build or dependencies.

What if the API answers 401?

The token is missing or wrong. Create one on the app's API Server settings page, export `LLM_WIKI_API_TOKEN` and repeat the request. The no-token mode removes protection, so enable it only on a trusted machine.

Discussion

No questions or reviews yet.

Skills

A skill set that lets an agent run a personal Obsidian wiki: it compiles knowledge from documents and past sessions and answers with citations

SkillExtended access3.7KRepository stars

CLI for a personal Markdown knowledge base: the agent writes, searches and lints pages with wiki commands; the tool calls no model

CLIExtended access104Repository stars

Karpathy LLM Wiki

karpathy-llm-wiki

A skill for a personal knowledge base the model maintains: ingest sources, compile cited articles, lint integrity

SkillExtended access2.7KRepository stars

Turns session history of Claude Code, Codex, Cursor and Gemini CLI into a searchable wiki on Karpathy's LLM Wiki pattern, locally

PluginBroad access400Repository stars

LLM Wiki

llm-wiki

Knowledge bases that AI compiles: topics, import, llm-wiki lint checks, the /wiki:ingest and /wiki:archive commands. A plugin for Claude Code and Codex

WorkflowExtended access1.5KRepository stars

An agent saves web pages, PDFs and scans into a local vault, builds linked concepts and answers from them with source references.

SkillExtended access127Repository stars

Comparison with similar tools

Cards that share the main search query, and how they differ.

ToolOfficialRepository starsMain difference
LLM Wiki Skill (this card)no153
LLM Wikino1,509a plugin for Claude Code and Codex that compiles a knowledge base with /wiki:ingest; it does not read an app's finished wiki
llmwikino400builds a wiki from agent session history; it does not read a wiki from the LLM Wiki app

README in short

The README explains that the skill is documentation without client code, shows three install routes and lists the requirements: a running app, an enabled API and a token. Then come a four-request curl smoke test, a troubleshooting table, security notes and the API version.

README badge

Original SKILL.md

---
name: llm-wiki
description: "Query the user's LLM Wiki knowledge base (the LLM Wiki desktop app at 127.0.0.1:19828 — NOT Obsidian, Notion, Apple Notes, Logseq, or any other PKM tool). Trigger ONLY when the user explicitly names LLM Wiki, says 'my wiki', 'my 知识库 / 知识库 / knowledge base', or asks things like 'what does my wiki say about X', 'read wiki page Y', 'show my wiki graph / 知识图谱', 'search in my LLM Wiki project', 'rescan my wiki sources / 重新索引', or names a wiki project by ID. DO NOT trigger on generic 'search my notes', 'find in my notebook', 'check my Obsidian', etc. — those belong to other tools the user may have installed. Covers wiki page search, file listing, content read, knowledge graph navigation, and source rescan against the running LLM Wiki desktop app. Read-only except for source rescan."
---

# LLM Wiki Local API Skill

Talk to the user's locally-running LLM Wiki app over its built-in HTTP API. This is a **standard JSON API** — call it directly with whatever HTTP tool is already in your environment (`curl`, `fetch`, `requests`, `http` middleware, etc.). No client library to install, no SDK to learn.

Treat the wiki as a **private, structured knowledge base** the user has been curating: pages live as `wiki/**.md`, raw documents under `raw/sources/`, wikilinks form a graph.

## When to invoke

Invoke **only** when the user is clearly referring to **LLM Wiki** specifically — by app name, by `wiki` framing, or by `知识库` framing. Concretely:

- asks a question framed as "what does my **wiki** / my **knowledge base** / 我的**知识库** / **LLM Wiki** say about X"
- asks to "search **my wiki** / **LLM Wiki** project / 我的**知识库** for X"
- references a **wiki page** by stem / title and wants to read or cross-link
- asks for the **wiki graph / 知识图谱 / wiki overview / wiki structure**
- has just added or edited files under the LLM Wiki **source folder** and wants ingest re-run / **重新索引**
- says "use **my wiki** for context" / "ground your answer in **my wiki**" / "check **my LLM Wiki**"
- names a wiki project (by ID, by absolute path, or by `current`)

**Do NOT invoke when the user says:**

- "search **my notes**" without further qualification — likely Obsidian / Apple Notes / Notion / Logseq / Bear / etc.
- "find in **my notebook**" — likely Jupyter / OneNote / Notability
- "check **my Obsidian / Notion / Roam / Logseq vault**" — explicitly a different tool
- "look up **my Anki / Readwise / Pocket**" — different tool
- "search **my files / my Documents folder**" — generic filesystem, not the wiki
- general world knowledge, current events, or anything the user clearly wants from the open web

When in doubt about which knowledge tool the user means, ask: *"Do you mean your LLM Wiki specifically, or another tool?"* — don't silently call the LLM Wiki API on what might be an Obsidian vault.

## Quick start

The whole API is plain HTTP + JSON. The fastest path:

```bash
BASE=http://127.0.0.1:19828
TOKEN="${LLM_WIKI_API_TOKEN:-<paste-from-Settings>}"

# 1. probe state — no auth needed
curl -s $BASE/api/v1/health

# 2. list projects
curl -s -H "Authorization: Bearer $TOKEN" $BASE/api/v1/projects

# 3. search
curl -s -H "Authorization: Bearer $TOKEN" \

Report a problem

Foxx AILLM Wiki Skill
Foxx AI

I am Foxx AI and I have already vetted this tool. Ask about install, setup or anything else, and I will keep it simple.