Skip to content

Fastest way to scaffold your LLM powered personal knowledge base - Obsidian, Claude Code, qmd, Github

docs: replace removed /setup skill with pnpm qmd:reindex in quick-start

jessepinkman9900ee3e3e60e91c
diff --git a/README.md b/README.md
index 6ffb695..d678f15 100644
--- a/README.md
+++ b/README.md
@@ -71,19 +71,14 @@ The CLI will ask:
Creates the brain at `~/.claude-second-brain/my-brain/`, registers it in `~/.claude-second-brain/config.toml`, installs `mise` + `node` + `pnpm`, runs `pnpm install`, and `git init`.
-**Step 2 — Initialize inside Claude Code**
+**Step 2 — Generate vector embeddings**
```bash
-cd ~/.claude-second-brain/my-brain && claude
+cd ~/.claude-second-brain/my-brain
+pnpm qmd:reindex
```
-Then run:
-
-```
-/setup
-```
-
-Registers the qmd collections and generates local vector embeddings. First run downloads ~2GB of GGUF models — once.
+First run downloads ~2GB of GGUF models — once per machine. qmd collections are already registered by the CLI during scaffolding.
**Step 3 — Open in Obsidian (and push to GitHub if not done)**
diff --git a/template/README.md b/template/README.md
index d1ea013..b9726c5 100644
--- a/template/README.md
+++ b/template/README.md
@@ -13,23 +13,14 @@ Inspired by [Andrej Karpathy's approach to LLM-powered knowledge management](htt
## Quick start
```bash
-# 1. Install tools (node + pnpm via mise)
-mise install
+# 1. Generate vector embeddings (first run downloads ~2GB of GGUF models — once per machine)
+pnpm qmd:reindex
-# 2. Install dependencies
-pnpm install
-
-# 3. Open Claude Code
+# 2. Open Claude Code
claude
```
-Inside Claude Code, run:
-
-```
-/setup
-```
-
-Registers the qmd collections and generates local vector embeddings. First run downloads ~2GB of GGUF models — once.
+qmd collections are already registered by the CLI during scaffolding — `pnpm qmd:reindex` just needs to build the index.
**Then open this folder in Obsidian.** The Git plugin is pre-configured — enable it in Obsidian settings and your wiki syncs automatically.