personal memory agent
transcripts: update SKILL.md for audio→transcripts / screen→percepts rename
Code renamed in March (f8bd2868, bf1cab94) but skill still taught the
deprecated --audio / --screen flags as primary. Update source-flag table,
source-type meanings, scan description, and example to match current code.
Keep --audio / --screen mentioned as hidden aliases. Also add "Invoke via
Bash" line and literal command names to TRIGGER.
Part of skills audit req_loq3e2lk pass 1+2.
+16
-12
+16
-12
apps/transcripts/talent/transcripts/SKILL.md
+16
-12
apps/transcripts/talent/transcripts/SKILL.md
···
7
7
Use when the owner asks about recordings, transcripts, what was said,
8
8
conversation content, or wants to review captured audio or screen activity.
9
9
TRIGGER: transcript, recording, audio, what was said, conversation,
10
-
segment, screen capture, recording coverage, monthly stats.
10
+
segment, screen capture, recording coverage, monthly stats,
11
+
sol call transcripts scan, sol call transcripts segments,
12
+
sol call transcripts read, sol call transcripts stats.
11
13
---
12
14
13
15
# Transcripts CLI Skill
14
16
15
-
Use these commands to inspect transcript availability and content from the terminal.
17
+
Inspect transcript availability and content. Invoke via Bash: `sol call transcripts <command> [args...]`.
16
18
17
19
**Environment defaults**: When `SOL_DAY` is set, commands that take a DAY argument will use it automatically. `SOL_SEGMENT` and `SOL_STREAM` provide defaults for `--segment` and `--stream` options.
18
20
···
30
32
sol call transcripts scan [DAY]
31
33
```
32
34
33
-
Show audio and screen coverage ranges.
35
+
Show transcript and percept coverage ranges. Output groups ranges under `Transcripts:` (microphone/system audio) and `Percepts:` (screen activity).
34
36
35
37
- `DAY`: day in `YYYYMMDD` (default: `SOL_DAY` env).
36
38
···
68
70
## read
69
71
70
72
```bash
71
-
sol call transcripts read [DAY] [--start HHMMSS --length MINUTES] [--segment KEY] [--segments KEYS] [--stream NAME] [--full] [--raw] [--audio] [--screen] [--agents]
73
+
sol call transcripts read [DAY] [--start HHMMSS --length MINUTES] [--segment KEY] [--segments KEYS] [--stream NAME] [--full] [--raw] [--transcripts] [--percepts] [--agents]
72
74
```
73
75
74
76
Read transcript content for a day, time range, segment, or span.
···
84
86
85
87
Source flags:
86
88
87
-
- `--full`: audio + screen + agents.
88
-
- `--raw`: audio + screen only (no agents).
89
-
- `--audio`: audio only.
90
-
- `--screen`: screen only.
89
+
- `--full`: transcripts + percepts + agents.
90
+
- `--raw`: transcripts + percepts (no agents).
91
+
- `--transcripts`: transcript content only.
92
+
- `--percepts`: screen percepts only.
91
93
- `--agents`: agent outputs only.
92
-
- Default with no source flags: audio + agents (no screen).
94
+
- Default with no source flags: transcripts + agents (no percepts).
95
+
96
+
`--audio` and `--screen` are hidden aliases for `--transcripts` and `--percepts` respectively. Prefer the primary flags in new code.
93
97
94
98
Rules:
95
99
···
98
102
99
103
Source type meanings:
100
104
101
-
- **Audio**: spoken-word transcripts from microphone/system audio.
102
-
- **Screen**: frame-level screen activity transcription.
105
+
- **Transcripts**: spoken-word transcripts from microphone/system audio.
106
+
- **Percepts**: frame-level screen activity transcription.
103
107
- **Agents**: AI-generated summaries and insights.
104
108
105
109
Examples:
···
109
113
sol call transcripts read 20260115 --start 090000 --length 30 --raw
110
114
sol call transcripts read 20260115 --segment 091500_300 --full
111
115
sol call transcripts read 20260115 --segments 091500_300,092000_300,092500_300 --transcripts --agents
112
-
sol call transcripts read 20260115 --audio
116
+
sol call transcripts read 20260115 --transcripts
113
117
```
114
118
115
119
## stats