claude-second-brain 0.5.1 → 1.0.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +48 -32
- package/bin/create.js +826 -84
- package/package.json +3 -2
- package/template/.claude/skills/brain-ingest/SKILL.md +21 -4
- package/template/.claude/skills/brain-rebuild/SKILL.md +9 -9
- package/template/.claude/skills/brain-refresh/SKILL.md +18 -5
- package/template/.claude/skills/brain-search/SKILL.md +17 -5
- package/template/CLAUDE.md +7 -7
- package/template/README.md +17 -19
- package/template/scripts/qmd/reindex.ts +31 -19
- package/template/scripts/qmd/setup.ts +45 -36
- package/template/.claude/skills/qmd-cli/SKILL.md +0 -168
- package/template/.claude/skills/setup/SKILL.md +0 -66
|
@@ -1,66 +0,0 @@
|
|
|
1
|
-
---
|
|
2
|
-
name: setup
|
|
3
|
-
description: "Initialize this claude-second-brain vault. Registers qmd collections and generates vector embeddings. Use when: setting up for the first time, re-registering collections, or re-indexing after a bulk ingest session. Trigger phrases: /setup, setup vault, initialize collections, reindex, register qmd."
|
|
4
|
-
argument-hint: "Optional: 'reindex' to skip registration and only re-index files"
|
|
5
|
-
---
|
|
6
|
-
|
|
7
|
-
# Vault Setup
|
|
8
|
-
|
|
9
|
-
## When to Use
|
|
10
|
-
- First-time setup after cloning
|
|
11
|
-
- Re-registering qmd collections (e.g., after config changes)
|
|
12
|
-
- Re-indexing after a bulk wiki ingest session (run step 2 only)
|
|
13
|
-
|
|
14
|
-
## Procedure
|
|
15
|
-
|
|
16
|
-
All commands run from the vault root.
|
|
17
|
-
|
|
18
|
-
### Full Setup (first time)
|
|
19
|
-
|
|
20
|
-
**Step 1 — Register collections and contexts**
|
|
21
|
-
|
|
22
|
-
Run:
|
|
23
|
-
```bash
|
|
24
|
-
pnpm qmd:setup
|
|
25
|
-
```
|
|
26
|
-
|
|
27
|
-
Registers the two core qmd collections (`wiki`, `raw-sources`) and their path-level context descriptions. Idempotent — safe to re-run.
|
|
28
|
-
|
|
29
|
-
**Step 2 — Index files and generate embeddings**
|
|
30
|
-
|
|
31
|
-
Run:
|
|
32
|
-
```bash
|
|
33
|
-
pnpm qmd:reindex
|
|
34
|
-
```
|
|
35
|
-
|
|
36
|
-
Scans all collections for new/changed files and generates vector embeddings. The first run downloads ~2GB of local GGUF models — this will take a while.
|
|
37
|
-
|
|
38
|
-
### Re-index Only (after bulk ingest)
|
|
39
|
-
|
|
40
|
-
Skip step 1 and run only:
|
|
41
|
-
```bash
|
|
42
|
-
pnpm qmd:reindex
|
|
43
|
-
```
|
|
44
|
-
|
|
45
|
-
Do **not** re-run after every single file edit — batch it after a session.
|
|
46
|
-
|
|
47
|
-
### Step 3 — Verify installation
|
|
48
|
-
|
|
49
|
-
Run these three commands to confirm everything is working:
|
|
50
|
-
|
|
51
|
-
```bash
|
|
52
|
-
# List registered collections (expect: wiki, raw-sources)
|
|
53
|
-
INDEX_PATH=__QMD_PATH__ pnpm dlx @tobilu/qmd collection list
|
|
54
|
-
|
|
55
|
-
# List registered contexts
|
|
56
|
-
INDEX_PATH=__QMD_PATH__ pnpm dlx @tobilu/qmd context list
|
|
57
|
-
|
|
58
|
-
# Show index status and embedding counts
|
|
59
|
-
INDEX_PATH=__QMD_PATH__ pnpm dlx @tobilu/qmd status
|
|
60
|
-
```
|
|
61
|
-
|
|
62
|
-
Both collections should appear in `collection list`. `status` should show non-zero document and embedding counts — if embeddings are 0, re-run step 2.
|
|
63
|
-
|
|
64
|
-
## Notes
|
|
65
|
-
- `node` and `pnpm` are managed via `mise` — ensure `mise install` and `pnpm install` have been run before setup
|
|
66
|
-
- If `pnpm dlx @tobilu/qmd` commands fail after setup, re-run step 1 then step 2
|