From llm-wiki
Start the wiki web server — browsable Wikipedia-style UI with live research, split-pane editor, AI assist, and themes. Manual trigger only: /wiki-serve, 'start wiki server', 'browse the wiki'.
How this skill is triggered — by the user, by Claude, or both
Slash command
/llm-wiki:serveThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
Launch a local web server that presents the wiki as a browsable, Wikipedia-style website with live background research, integrated chat, and a split-pane editor with AI assist.
references/architecture.mdscripts/__init__.pyscripts/chat_manager.pyscripts/markdown_renderer.pyscripts/rag_handler.pyscripts/research_queue.pyscripts/research_worker.pyscripts/server.pyscripts/wiki_store.pystatic/chat.jsstatic/editor.jsstatic/style.cssstatic/wiki.jstemplates/base.htmltemplates/canvas.htmltemplates/create.htmltemplates/edit.htmltemplates/error.htmltemplates/gaps.htmltemplates/graph.htmlLaunch a local web server that presents the wiki as a browsable, Wikipedia-style website with live background research, integrated chat, and a split-pane editor with AI assist.
Resolve .wiki/ from plugin install scope. Auto-create if missing.
/wiki-serve — start the server (default port 8420)/wiki-serve stop — stop the running serverThe FastAPI web server only runs when explicitly requested. There are two ways to start it:
/wiki-serve skill from Claude Code (recommended):
/wiki-serve
Dependencies are installed automatically by the plugin's SessionStart hook. To start the server manually from the command line:
python path/to/skills/serve/scripts/server.py --wiki-dir .wiki/ --port 8420
Replace path/to with the full path to your LLM-Wiki installation (typically .claude/plugins/llm-wiki).
If dependencies are missing, install manually: pip install -r requirements.txt
.wiki/templates/Kill the server process on port 8420. Either:
/wiki-serve stopnpx claudepluginhub oshayr/llm-wiki --plugin llm-wikiCreate and manage personal wikis with atomic notes, WikiLinks, Git-based auto-deployment. Supports setup, configuration, adding notes, publishing, research conversion, and recent updates.
Builds and maintains a 3-layer personal wiki (raw → wiki → schema) from raw sources. Supports init, ingest, query, lint, and update operations.
Creates, structures, and queries persistent markdown wikis with SQLite FTS5 full-text search. Supports multiple wiki flavors for research, projects, and codebases.