minutes-mirror

1# /minutes-mirror
2 
3Self-coaching analysis based on your own meeting transcripts. Two modes:
4 
5- **Single-meeting mode** — review a specific meeting and surface what you did, what was unusual for you, and one concrete thing to try next time.
6- **Pattern mode** — surface trends across the last 30 days, including (if meetings are tagged) what behaviors correlate with winning vs losing.
7 
8The point is not to roast you. The point is to give you a kind, evidence-based mirror to behaviors that are usually invisible to you because you're inside them.
9 
10## How it works
11 
12### Phase 0: Identify "you"
13 
14Mirror needs to know which speaker label in the transcript is the user. Real transcripts use one of two formats:
15 
16- **Enrolled users**: `[Mat 0:00] Hey there.` — first-name labels from voice enrollment
17- **Non-enrolled users**: `[SPEAKER_0 0:00] Hey there.` — generic labels from diarization
18 
19Either way, mirror needs to know which label maps to the user. Check sources in order:
20 
21**1. Enrolled voice profile:**
22```bash
23minutes voices --json 2>/dev/null
24```
25 
26Returns a JSON array of enrolled profiles. The user's profile is the one with `source: "self-enrollment"` (or the first one if there's only one). Use the `name` field as the speaker label to look for in transcripts. Example response:
27 
28```json
29[{"person_slug": "mat", "name": "Mat", "source": "self-enrollment", ...}]
30```
31 
32→ Speaker label is `Mat`.
33 
34**2. Cached self name(s):**
35```bash
36cat ~/.minutes/config/self.txt 2>/dev/null
37```
38…