Summary
Spins up a structured Markdown wiki where raw sources stay immutable in a raw/ folder and an LLM maintains derived knowledge pages under wiki/. The whole system runs on a single SCHEMA.md contract that lives inside each wiki, with thin pointer files for Claude Desktop and GitHub Copilot. You get a concept table, automatic indexing, and optional local BM25 search if you want full-text lookup without hitting an API. It asks for preferences once, batches setup questions, and won't silently fall back to defaults. Good for anyone who wants persistent, citations-backed knowledge extraction with clear separation between evidence and interpretation. The progressive disclosure model keeps context windows lean.
Install to Claude Code
npx -y skills add nanzhipro/karpathy-llm-wiki-bootstrap-skill --skill llm-wiki-bootstrap --agent claude-codeInstalls into .claude/skills of the current project.
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
Files
SKILL.md
Select a file.
Featured
Keep your Mac awake while Claude Code and 40+ AI agents run. Sleeps when they're idle.
One time payment $9 →Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →On Capafy, your Skill runs online 24/7 as an agent product, and you get paid every time someone uses it.
Start earning →
