minutes-search

1# /minutes-search
2 
3Find information across all meeting transcripts and voice memos.
4 
5## Usage
6 
7```bash
8# Basic search
9minutes search "pricing strategy"
10 
11# Filter to just voice memos
12minutes search "onboarding idea" -t memo
13 
14# Filter to just meetings
15minutes search "sprint planning" -t meeting
16 
17# Date filter + limit
18minutes search "API redesign" --since 2026-03-01 --limit 5
19```
20 
21## Flags
22 
23| Flag | Description |
24|------|-------------|
25| `-t, --content-type <meeting\|memo>` | Filter by type |
26| `--since <date>` | Only results after this date (ISO format, e.g., `2026-03-01`) |
27| `-l, --limit <n>` | Maximum results (default: 10) |
28 
29## Output
30 
31Returns JSON to stdout with an array of matches. Each result includes:
32- `title` — Meeting or memo title
33- `date` — When it was recorded
34- `content_type` — "meeting" or "memo"
35- `snippet` — The line containing the match
36- `path` — Full path to the markdown file
37 
38Human-readable output goes to stderr. A result path is only a hint. To read the
39full transcript, run `minutes get "<exact path>" --json`, require exit status 0,
40and use only that response. Never pass the path to `cat` or the host `Read` tool.
41 
42## How search works
43 
44Search is case-insensitive and matches against both the transcript body and the YAML frontmatter title. It walks all `.md` files in `~/meetings/` (including the `memos/` subfolder).
45 
46For richer semantic search, users can configure QMD as the search engine in `~/.config/minutes/config.toml`:
47```toml
48[search]
49engine = "qmd"
50…