fetch-bookmarks
Pull bookmarks from an external service (X/Twitter today; Readwise, Pocket, GitHub stars planned) into a local directory that…
Launch an interactive canvas-based knowledge graph of your compiled wiki. Topics appear as nodes, concepts as connecting edges. Click any node to read the article.
> /plugin marketplace add ussumant/llm-wiki-compiler > /plugin install llm-wiki-compiler@llm-wiki-compiler
How it fires
How this command gets triggered: by you, by Claude, or both.
/wiki-visualizeContext preview
What this command does when you run it.
Launch an interactive canvas-based knowledge graph of your compiled wiki. Topics appear as nodes, concepts as connecting edges. Click any node to read the article.
Launch an interactive canvas-based knowledge graph of your compiled wiki. Topics appear as nodes, concepts as connecting edges. Click any node to read the article.
1. Check that `.wiki-compiler.json` exists in the project root 2. Check that the wiki has been compiled (output directory has `INDEX.md`) 3. If not compiled, suggest running `/wiki-compile` first
4. Start the visualization server:
node "${CLAUDE_PLUGIN_ROOT}/visualize/server.js" --wiki-dir "{output_path}"5. Open the browser:
open "http://localhost:3848"
6. Tell the user:
📊 Wiki Knowledge Graph running at http://localhost:3848 - Click nodes to read topic articles - Hover edges to see concept connections - Search to filter topics - The server reads your wiki files live — changes from /wiki-compile appear immediately Stop with Ctrl+C when done.
A Claude Code and Codex-compatible plugin that compiles knowledge into a topic-based wiki — from scattered markdown files or entire codebases. Reduce context costs by ~90% and give your agent a synthesized understanding of any project. Documentation
Pull bookmarks from an external service (X/Twitter today; Readwise, Pocket, GitHub stars planned) into a local directory that…
Capture a URL plus user context, normalize it into a durable markdown source, then connect it to the global wiki, local project…
Compile all configured markdown source files into a topic-based wiki.
Interactive workflow for adding one source file to the wiki. The LLM reads the file, discusses key takeaways with the user, then…