LLM-compiled knowledge base. Topic-isolated wikis, parallel multi-agent research (topic + question auto-detect), thesis-driven investigation with verdicts, repo assessment, Obsidian dual-linking, retardmax mode, and --min-time sustained research.
npx claudepluginhub nvk/llm-wiki --plugin wikiAssess a local repo against the wiki's research body and the broader market. Gap analysis, opportunities, competitive landscape.
Compile raw sources into wiki articles. Synthesizes, cross-references, and organizes knowledge.
Ingest source material into the wiki. Accepts URLs, file paths, freeform text, or processes the inbox. Supports tweets via Grok MCP.
Run health checks on the wiki. Find broken links, missing indexes, stale content, inconsistencies, and suggest improvements.
Generate output artifacts from wiki content — summaries, reports, study guides, slide outlines, timelines, glossaries, comparisons. Outputs are filed back into the wiki.
Ask questions against the compiled wiki. Supports three depth levels: quick (indexes only), standard (full articles), deep (everything + raw + sibling wikis). Answers from wiki content only, with citations.
Deep multi-agent research on a topic. Launches parallel agents to search the web across multiple angles, ingests sources, and compiles them into wiki articles. Can create a new topic wiki automatically.
Search the wiki for content by keyword, tag, or category.
Thesis-driven research. Provide a specific claim or hypothesis — agents research evidence for and against, compile a focused wiki, and deliver a verdict. The thesis is the scope constraint — no bloat.
LLM wiki knowledge base — initialize, show status, or list wikis. Subcommands: ingest, compile, query, lint, search, output, research.
Upstash Context7 MCP server for up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your LLM context.
OpenAPI specification generation, Mermaid diagram creation, tutorial writing, API reference documentation
Complete developer workflow toolkit. Includes 34 reference skills, 34 specialized agents, and 21 slash commands covering TDD, debugging, code review, architecture, documentation, refactoring, security, testing, git workflows, API design, performance, UI/UX design, plugin development, and incident response. Full SDLC coverage with MCP integrations.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
AI-powered wiki generator for code repositories. Generates comprehensive, Mermaid-rich documentation with dark-mode VitePress sites, onboarding guides, deep research, and source citations. Inspired by OpenDeepWiki and deepwiki-open.
Create skills from documentation folders and project codebases. Review, test, and package Anthropic Agent Skills for Claude.ai and Claude Code. 13 commands including from-docs, from-project, beginner tutorial, interactive wizard, templates, quality auditing, and distribution packaging.