llm-wiki
LLM Wiki creates and maintains a workspace-local markdown research vault with immutable source preservation, linked concept pages, and automatic indexing. Designed for Obsidian compatibility, it keeps your research organized across multiple modes—init, ingest, query, and refresh—while maintaining a live maintenance log and content map.
LLM Wiki builds a persistent, linked markdown research vault optimized for Obsidian and durable knowledge capture.
AI-generated summary based on this skill's SKILL.md
Decision gist · record as of 2026-07-27
LLM Wiki builds a persistent, linked markdown research vault optimized for Obsidian and durable knowledge capture. LLM Wiki creates and maintains a workspace-local markdown research vault with immutable source preservation, linked concept pages, and automatic indexing. Designed for Obsidian compatibility, it keeps your research organized across multiple modes—init, ingest, query, and refresh—while maintaining a live maintenance log and content map.
Use it when
- llm-wiki maintains your workspace research database through four core modes: init (setup), ingest (add sources), query (search concepts).
- Yes.
Verify before relying
Read SKILL.md below before installing (6 files). Open directory: indexed for reading, not audited.
Install
CoWork-OS/CoWork-OS/llm-wiki · repository language: TypeScript
Open directory. Skills are indexed for reading, not audited. Review a skill's body before installing it.
Frequently asked questions
AI-generated answers based on this skill's SKILL.md and metadata
How do I set up llm-wiki locally for obsidian?
llm-wiki initializes a local markdown research vault compatible with Obsidian. Use the init mode to create your workspace structure, then configure it to point to your Obsidian vault directory. The tool automatically generates the necessary folder structure and indexing files, letting you immediately start ingesting research sources and building your linked knowledge base.
What does llm-wiki do to maintain workspace research database?
llm-wiki maintains your workspace research database through four core modes: init (setup), ingest (add sources), query (search concepts), and refresh (update indexes). It preserves raw sources immutably, auto-generates linked concept pages, maintains a live maintenance log, and keeps a content map current. This automation ensures your research vault stays organized without manual index upkeep.
Can llm-wiki create persistent research vault with raw sources?
Yes. llm-wiki creates a persistent markdown research vault that preserves raw sources in their original form while building linked concept pages around them. Your vault persists locally with Obsidian compatibility, allowing you to reference sources across multiple concept notes. The immutable source preservation means your original research materials remain unchanged as you organize and link them.
How does llm-wiki implement the karpathy llm wiki pattern?
llm-wiki follows the Karpathy pattern for LLM-driven research organization: it ingests raw sources, automatically extracts and links concepts, maintains bidirectional references, and keeps everything in markdown format. The tool's ingest and refresh modes handle the pattern's core workflow—pulling in research material, parsing it for concepts, and maintaining those links as your vault grows.
What makes llm-wiki obsidian-friendly for knowledge management?
llm-wiki is built for Obsidian compatibility from the ground up. It generates standard markdown files with wiki-link syntax, respects Obsidian's vault structure, and outputs indexed concept maps that Obsidian's graph view can visualize. Your research vault works seamlessly in Obsidian while benefiting from llm-wiki's automated linking, source preservation, and maintenance logging.
Does llm-wiki automate wiki maintenance with indexed updates?
Yes. llm-wiki automates wiki maintenance through its refresh mode, which re-indexes your vault, updates concept links, and logs all changes to a live maintenance log. The tool tracks content changes and relationship updates without requiring manual intervention, keeping your indexed research database current as you add sources and evolve your knowledge structure.
SKILL.md
Rendered from the published skill. Quoted content, verbatim.
LLM Wiki
Purpose
Create and maintain a persistent markdown research vault with immutable raw sources, linked concept/entity pages, maps of content, and a maintenance log.
Routing
- Use when: The user wants a persistent research vault, markdown knowledge base, or Obsidian-style wiki instead of a one-off report.
- Do not use when: The task is a disposable summary or a normal one-off research answer that does not need durable notes.
- Outputs: A workspace-local wiki vault plus
{artifactDir}/wiki-manifest.mdand{artifactDir}/wiki-summary.md. - Success criteria: Raw sources are preserved, linked notes are updated, and
index.md,log.md, andinbox.mdremain current.
Parameters
| Name | Type | Required | Description |
|---|---|---|---|
| objective | string | No | Topic, question, or research objective. If omitted, ask one short scoping question before durable ingest work. |
| mode | string | No | auto, init, ingest, query, lint, or refresh |
| path | string | No | Workspace-relative or absolute vault path |
(truncated - see the full file via the links below)
File tree — 6 files
resources/skills/llm-wiki/SKILL.md
resources/skills/llm-wiki/scripts/wiki-graph-report.mjs
resources/skills/llm-wiki/scripts/wiki-import.mjs
resources/skills/llm-wiki/scripts/wiki-render.mjs
resources/skills/llm-wiki/scripts/wiki-search.mjs
resources/skills/llm-wiki/scripts/wiki-workbench-lib.mjs
Let your AI agent find skills like this
Example. Real query, live index.
You found this page by searching. An agent finds it by wishing: SkillFed indexes 56,283 agent skills by what they can do, searchable in plain language.
wish › “Create and maintain a persistent, linked markdown research vault”
Give your agent the search over MCP, or paste the wish link into any chat. No install? Search from any chat →
Related skills
Llm Wiki helps you create and sustain a markdown-based knowledge repository where an LLM handles ongoing maintenance and synthesis. Ingest raw sources—articles, papers, transcripts, screenshots—into immutable storage, then let the agent populate wiki pages, cross-links, and navigation files. Periodic lint passes keep the vault healthy and coherent.
Pi-librarian is a GitHub research subagent that searches external repositories, locates relevant files, and generates cited reports to inform your implementation decisions. It outputs a detailed research report and actionable summary, helping you compare patterns and gather concrete evidence from GitHub before coding.
Okf implements Google's Open Knowledge Format specification, letting you author structured knowledge atoms as YAML-frontmatter Markdown files organized into distributable bundles. Use it to build multi-agent context layers, publish portable knowledge that survives tool changes, and formalize LLM-wiki patterns into a vendor-neutral standard any agent can consume without translation.
wiki-all orchestrates the entire llmwiki workflow in sequence: initializing directories, syncing session data to markdown, constructing knowledge graphs with Graphify AI, compiling HTML output, running 14 quality checks, and launching a local server. Use it when you need to rebuild your wiki from scratch or refresh everything at once.
Memory Kit sets up a .cowork/ directory in your workspace to store rules, identity information, long-term notes, daily logs, and heartbeat templates. Use it when you need to establish persistent context and configuration for your work environment.
Pi-finder-subagent scans your local repository to pinpoint relevant files and code snippets, helping you narrow context before coding. It outputs a cited shortlist with line ranges and saves a focused report to guide your next steps.
More skills LLM Wiki Maintainer (MIT)