By boykush
Build interconnected Scraps knowledge bases by generating concise Markdown scraps from natural language topics or web URLs. AI intelligently selects tags, suggests wiki-links and backlinks, researches content via WebSearch, and summarizes articles with source autolinks.
npx claudepluginhub boykush/scraps --plugin scraps-writerCreate a new scrap with intelligent tag selection and backlink suggestions. Use this skill whenever the user wants to create a new scrap, write about a topic, add documentation, or says something like "add a scrap about X" or "write about X".
Shared workflow for creating scraps with Wiki-link notation.
Summarize a web article and create a scrap with Wiki-link notation.
Scraps is a portable CLI knowledge hub for managing interconnected Markdown documentation with Wiki-link notation.
Learn more in the official documentation.
You can refer to the Getting Started document to quickly begin using Scraps.
Sample page in Japanese is here.
For any feature requests, please feel free to create an Enhancement feature issue.
Search, pagination, and Wiki-link navigation with Nord theme (Dark Mode)
We welcome contributions! 🎉
See CONTRIBUTING.md for detailed guidelines on how to contribute to Scraps.
By participating, you agree to abide by our Code of Conduct.
MIT
MCP server for Scraps - Manage interconnected Markdown documentation with Wiki-link notation
Share bugs, ideas, or general feedback.
LLM-maintained personal wiki skills for Claude Code. Implements Karpathy's LLM Wiki pattern — persistent, compounding knowledge base for research, codebase documentation, or any long-term knowledge accumulation.
Documentation review, cleanup, and generation with AI slop detection, style learning, and human-quality writing enforcement
Scrapbox/Cosense integration - read, search, create, and edit wiki pages
Technical documentation specialist for README files, API docs, user guides, specifications, and release notes with Obsidian vault management
A persistent LLM-maintained wiki for your knowledge base. Ingest sources, query your knowledge, and lint for consistency.