create-opc-wiki
Scaffold a personal LLM wiki on the Karpathy pattern in 30 seconds. Multi-agent native, MCP server built-in, SEO/GEO-optimized publish target.
What this skill does
Run the scaffolder against any folder and you get a complete personal-knowledge-base vault:
agent-rules/main.md — single source of truth, synced to 9 agent file formats (CLAUDE.md, AGENTS.md, .cursor/rules/main.mdc, .cursorrules, .github/copilot-instructions.md, .trae/rules.md, .openclaw/rules.md, .hermes/agent.md)- Three reusable skills:
/wiki-ingest, /wiki-query, /wiki-lint
- Five source recipes: arXiv paper, X thread, YouTube transcript, RSS article, podcast transcript
- Privacy-tagged frontmatter:
public | private | secret
- An MCP server with three tools (
wiki_query, wiki_list, wiki_read) and a hard privacy gate (privacy: secret pages never leave the box)
- Optional Astro static site target with sitemap.xml, llms.txt, robots.txt, RSS feed, OpenGraph + JSON-LD per page
How to invoke
The skill wraps the published npm package create-opc-wiki@latest. From any agent that can run a shell command:
npx -y create-opc-wiki@latest <path> --yes --agents=openclaw,claude,codex,cursor
Common one-liners:
| Agent |
Command |
| OpenClaw |
npx -y create-opc-wiki@latest ~/wiki --yes --agents=openclaw,claude |
| Claude Code |
npx -y create-opc-wiki@latest ~/wiki --yes --agents=claude |
| Codex CLI |
npx -y create-opc-wiki@latest ~/wiki --yes --agents=codex |
| Cursor |
npx -y create-opc-wiki@latest ~/wiki --yes --agents=cursor |
| All of them |
npx -y create-opc-wiki@latest ~/wiki --yes --agents=openclaw,claude,codex,cursor,hermes,vscode,trae |
Add --no-mcp, --no-site, --no-recipes, or --no-git to skip those layers. --json emits machine-readable result on stdout.
How to use the generated vault
- Open the folder in Obsidian (it's a valid Obsidian vault) — and/or
- Open the folder in your AI agent (it reads
CLAUDE.md / AGENTS.md / .openclaw/rules.md / etc.)
- From inside the agent, use the three skills:
/wiki-ingest <url-or-file> — drop a new source, agent files it into raw/ and synthesizes wiki pages/wiki-query <question> — natural-language query across compiled wiki/wiki-lint — health-check (contradictions, stale speculative claims, orphan pages)
The MCP server in mcp/server.mjs exposes the wiki to any MCP client (Claude Desktop, Cursor, Codex). Run npm install && npm start from the mcp/ directory.
Why a wiki and not just RAG
Most LLM-on-files setups re-derive answers from raw docs at every query. There's no accumulation. Quoting Karpathy's gist:
The LLM incrementally builds and maintains a persistent wiki — a structured, interlinked collection of markdown files that sits between you and the raw sources. The wiki keeps getting richer with every source you add and every question you ask.
This skill operationalizes exactly that, with concrete choices for ontology, agent rules, MCP, and publishing.
Privacy & security
privacy: secret pages never returned by the MCP server (enforced at mcp/server.mjs:38)privacy: public is the only level that publishes (enforced at site/build.mjs:53)- Default frontmatter privacy is
private — nothing publishes by accident
- The scaffolder runs once, locally, and exits — no telemetry, no network calls during scaffolding except the optional
npm install you trigger yourself
Links
License
MIT. Inspired by Andrej Karpathy's "LLM Wiki" gist; implementation choices are this project's. Full attribution in INSPIRATION.md.
1---2name: create-opc-wiki3description: Scaffold a personal LLM wiki (Karpathy pattern) — multi-agent, MCP-ready, with SEO/GEO publish target. Compiles knowledge into a persistent wiki instead of re-deriving from raw docs on every query. One paste from any agent (OpenClaw, Claude Code, Codex, Cursor, Hermes) installs it.4---56# create-opc-wiki78Scaffold a personal LLM wiki on the [Karpathy pattern](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f) in 30 seconds. Multi-agent native, MCP server built-in, SEO/GEO-optimized publish target.910## What this skill does1112Run the scaffolder against any folder and you get a complete personal-knowledge-base vault:1314- `agent-rules/main.md` — single source of truth, synced to **9 agent file formats** (CLAUDE.md, AGENTS.md, .cursor/rules/main.mdc, .cursorrules, .github/copilot-instructions.md, .trae/rules.md, **.openclaw/rules.md**, .hermes/agent.md)15- Three reusable skills: `/wiki-ingest`, `/wiki-query`, `/wiki-lint`16- Five source recipes: arXiv paper, X thread, YouTube transcript, RSS article, podcast transcript17- Privacy-tagged frontmatter: `public | private | secret`18- An MCP server with three tools (`wiki_query`, `wiki_list`, `wiki_read`) and a hard privacy gate (`privacy: secret` pages **never** leave the box)19- Optional Astro static site target with sitemap.xml, llms.txt, robots.txt, RSS feed, OpenGraph + JSON-LD per page2021## How to invoke2223The skill wraps the published npm package `create-opc-wiki@latest`. From any agent that can run a shell command:2425```bash26npx -y create-opc-wiki@latest <path> --yes --agents=openclaw,claude,codex,cursor27```2829Common one-liners:3031| Agent | Command |32|---|---|33| OpenClaw | `npx -y create-opc-wiki@latest ~/wiki --yes --agents=openclaw,claude` |34| Claude Code | `npx -y create-opc-wiki@latest ~/wiki --yes --agents=claude` |35| Codex CLI | `npx -y create-opc-wiki@latest ~/wiki --yes --agents=codex` |36| Cursor | `npx -y create-opc-wiki@latest ~/wiki --yes --agents=cursor` |37| All of them | `npx -y create-opc-wiki@latest ~/wiki --yes --agents=openclaw,claude,codex,cursor,hermes,vscode,trae` |3839Add `--no-mcp`, `--no-site`, `--no-recipes`, or `--no-git` to skip those layers. `--json` emits machine-readable result on stdout.4041## How to use the generated vault42431. **Open the folder in Obsidian** (it's a valid Obsidian vault) — and/or442. **Open the folder in your AI agent** (it reads `CLAUDE.md` / `AGENTS.md` / `.openclaw/rules.md` / etc.)453. From inside the agent, use the three skills:46 - `/wiki-ingest <url-or-file>` — drop a new source, agent files it into `raw/` and synthesizes wiki pages47 - `/wiki-query <question>` — natural-language query across compiled wiki48 - `/wiki-lint` — health-check (contradictions, stale `speculative` claims, orphan pages)4950The MCP server in `mcp/server.mjs` exposes the wiki to any MCP client (Claude Desktop, Cursor, Codex). Run `npm install && npm start` from the `mcp/` directory.5152## Why a wiki and not just RAG5354Most LLM-on-files setups re-derive answers from raw docs at every query. There's no accumulation. Quoting [Karpathy's gist](https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f):5556> The LLM **incrementally builds and maintains a persistent wiki** — a structured, interlinked collection of markdown files that sits between you and the raw sources. The wiki keeps getting richer with every source you add and every question you ask.5758This skill operationalizes exactly that, with concrete choices for ontology, agent rules, MCP, and publishing.5960## Privacy & security6162- `privacy: secret` pages **never** returned by the MCP server (enforced at `mcp/server.mjs:38`)63- `privacy: public` is the **only** level that publishes (enforced at `site/build.mjs:53`)64- Default frontmatter privacy is `private` — nothing publishes by accident65- The scaffolder runs once, locally, and exits — no telemetry, no network calls during scaffolding except the optional `npm` install you trigger yourself6667## Links6869- **npm**: <https://www.npmjs.com/package/create-opc-wiki>70- **GitHub**: <https://github.com/MackDing/create-opc-wiki>71- **Inspiration**: <https://gist.github.com/karpathy/442a6bf555914893e9891c11519de94f>72- **Stability scope**: see `STABILITY.md` in the repo for the semver-stable surface73- **Per-agent install recipes**: see `docs/INSTALL-FOR-AGENTS.md` in the repo7475## License7677MIT. Inspired by Andrej Karpathy's "LLM Wiki" gist; implementation choices are this project's. Full attribution in `INSPIRATION.md`.
Lord1Egypt