@staff0rd/assist 0.338.0 → 0.339.0
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 +3 -4
- package/allowed.cli-reads +1 -0
- package/allowed.cli-writes +0 -2
- package/claude/commands/transcripts.md +49 -0
- package/claude/settings.json +2 -4
- package/dist/allowed.cli-reads +1 -0
- package/dist/allowed.cli-writes +0 -2
- package/dist/commands/sessions/web/bundle.js +1 -1
- package/dist/index.js +187 -490
- package/package.json +1 -1
- package/claude/commands/transcript-format.md +0 -7
- package/claude/commands/transcript-summarise.md +0 -3
package/README.md
CHANGED
|
@@ -72,8 +72,7 @@ After installation, the `assist` command will be available globally. You can als
|
|
|
72
72
|
- `/sql` - Query a MSSQL database via assist sql
|
|
73
73
|
- `/verify` - Run all verification commands in parallel
|
|
74
74
|
- `/verify-new` - Add a new verify:\* run command to assist.yml
|
|
75
|
-
- `/
|
|
76
|
-
- `/transcript-summarise` - Summarise transcripts missing summaries
|
|
75
|
+
- `/transcripts` - Format and summarise meeting transcripts end to end
|
|
77
76
|
- `/voice-setup` - Download required voice models (VAD, STT)
|
|
78
77
|
- `/voice-start` - Start the voice interaction daemon
|
|
79
78
|
- `/voice-stop` - Stop the voice interaction daemon
|
|
@@ -254,8 +253,8 @@ The first backlog command in a repository that still has a local `.assist/backlo
|
|
|
254
253
|
- `assist complexity maintainability [pattern]` - Calculate maintainability index per file (`--ignore <glob>`, repeatable, excludes extra files on top of `complexity.ignore`). A file can declare its own threshold with a `// assist-maintainability-override: N` comment in its first ~10 lines (integer 0-100); that value replaces the global `--threshold` for that file only and the output annotates it with `(override: N)`
|
|
255
254
|
- `assist complexity sloc [pattern]` - Count source lines of code per file
|
|
256
255
|
- `assist transcript configure` - Configure transcript directories
|
|
257
|
-
- `assist transcript
|
|
258
|
-
- `assist transcript
|
|
256
|
+
- `assist transcript list` - List raw .vtt filenames waiting in the pick-up directory
|
|
257
|
+
- `assist transcript move <file>` - Convert a raw .vtt to a dated markdown transcript and archive the original
|
|
259
258
|
- `assist voice setup` - Download required voice models (VAD, STT)
|
|
260
259
|
- `assist voice start` - Start the voice daemon (always-on, listens for wake word)
|
|
261
260
|
- `assist voice start --foreground` - Start in foreground for debugging
|
package/allowed.cli-reads
CHANGED
package/allowed.cli-writes
CHANGED
|
@@ -0,0 +1,49 @@
|
|
|
1
|
+
---
|
|
2
|
+
description: Format and summarise meeting transcripts end to end
|
|
3
|
+
---
|
|
4
|
+
|
|
5
|
+
Drain the transcript pick-up directory: for every raw `.vtt`, convert it to a dated markdown transcript and write a summary alongside it. Loop until nothing is left.
|
|
6
|
+
|
|
7
|
+
Repeat the steps below until `assist transcript list` prints nothing.
|
|
8
|
+
|
|
9
|
+
## Step 1: List
|
|
10
|
+
|
|
11
|
+
```bash
|
|
12
|
+
assist transcript list
|
|
13
|
+
```
|
|
14
|
+
|
|
15
|
+
Each line is the bare filename of a raw `.vtt` waiting to be processed.
|
|
16
|
+
|
|
17
|
+
- **No output** — every transcript is done. Stop.
|
|
18
|
+
- **One or more lines** — take the first filename and process it with the remaining steps, then return here.
|
|
19
|
+
|
|
20
|
+
## Step 2: Determine the client and date
|
|
21
|
+
|
|
22
|
+
Work out the **client** and meeting **date** (`YYYY-MM-DD`) for the file:
|
|
23
|
+
|
|
24
|
+
- Prefer a client name and `YYYY-MM-DD` date already present in the filename.
|
|
25
|
+
- If the filename isn't clear, read the raw `.vtt` to infer them from the meeting content. The file lives at `<vttDir>/<filename>`, where `vttDir` is the `transcript.vttDir` value in `.claude/assist.yml` (or `assist.yml`).
|
|
26
|
+
- Only if you still cannot confidently determine the client or date, ask the user for the missing value(s). Do **not** ask when you can infer them.
|
|
27
|
+
|
|
28
|
+
## Step 3: Move
|
|
29
|
+
|
|
30
|
+
Convert the raw `.vtt` to a dated markdown transcript and archive the original:
|
|
31
|
+
|
|
32
|
+
```bash
|
|
33
|
+
assist transcript move "<filename>" --date <YYYY-MM-DD> --client "<client>"
|
|
34
|
+
```
|
|
35
|
+
|
|
36
|
+
`move` prints two paths:
|
|
37
|
+
|
|
38
|
+
- **line 1** — the formatted transcript it just wrote
|
|
39
|
+
- **line 2** — the summary target path to create in the next step
|
|
40
|
+
|
|
41
|
+
## Step 4: Write the summary
|
|
42
|
+
|
|
43
|
+
Read the formatted transcript (line 1) and write a concise summary to the summary target path (line 2). The summary must start with a link back to the transcript:
|
|
44
|
+
|
|
45
|
+
```
|
|
46
|
+
[Full Transcript](<relative path from the summary file's directory to the formatted transcript>)
|
|
47
|
+
```
|
|
48
|
+
|
|
49
|
+
Then return to Step 1.
|
package/claude/settings.json
CHANGED
|
@@ -38,8 +38,7 @@
|
|
|
38
38
|
"SlashCommand(/devlog)",
|
|
39
39
|
"SlashCommand(/refactor)",
|
|
40
40
|
"SlashCommand(/review-comments)",
|
|
41
|
-
"SlashCommand(/
|
|
42
|
-
"SlashCommand(/transcript-summarise)",
|
|
41
|
+
"SlashCommand(/transcripts)",
|
|
43
42
|
"SlashCommand(/voice-setup)",
|
|
44
43
|
"SlashCommand(/voice-start)",
|
|
45
44
|
"SlashCommand(/voice-stop)",
|
|
@@ -52,8 +51,7 @@
|
|
|
52
51
|
"Skill(devlog)",
|
|
53
52
|
"Skill(refactor)",
|
|
54
53
|
"Skill(review-comments)",
|
|
55
|
-
"Skill(
|
|
56
|
-
"Skill(transcript-summarise)",
|
|
54
|
+
"Skill(transcripts)",
|
|
57
55
|
"Skill(journal)",
|
|
58
56
|
"Skill(standup)",
|
|
59
57
|
"Skill(voice-setup)",
|
package/dist/allowed.cli-reads
CHANGED