llm-wiki-skills

Six agent skills for building and maintaining a personal knowledge wiki using Markdown files, wikilinks, and filesystem access. Developed on Claude with GUI install support; works on Claude Code, Gemini CLI, Codex CLI, and GitHub Copilot.

What this is

A set of agent skills for incrementally building and maintaining a structured, interlinked knowledge base on your local filesystem. You add sources; the agent reads, synthesises, and files them into wiki pages. You ask questions; the agent reads the wiki and answers with citations. The wiki compounds over time - each source and each good question makes it richer.

This is my personal implementation of the LLM wiki pattern (see below). It is not a product. It has no backend, no API, no cloud sync (unless you provide one), and no dependencies beyond your agent and filesystem access. Everything lives in Markdown files on your disk. If you can read .md files, you can use this in Obsidian, Logseq, VS Code, iA Writer, or a plain folder.

I built this on Claude, but the underlying skill instructions follow the agentskills.io open standard and work on Gemini CLI, Claude Code, OpenAI Codex CLI, and GitHub Copilot. The .skill packaging and Claude Desktop GUI install are Claude-specific; other agents install skills as folders. See Installation.

The skills are (hopefully) honest about what they are: structured instructions to a language model, not code. They are good at their job but not infallible. The wiki is only as good as the sources you feed it and the questions you ask.

Background