Inbox Digest
Summarize a time period—what happened, who's important, what needs attention
2
Construct Gmail query for the digest period. 'Today' → 'newer_than:1d', 'this week' → 'newer_than:7d'. State what period you're covering.
5
Synthesize, don't enumerate. Lead with what matters: (1) Quick overview—X emails from Y senders. (2) Key threads—multi-message conversations worth knowing about. (3) Action items—requests, questions, deadlines from snippets. (4) Top senders—who dominated, briefly what about.
6
Present conversationally. Offer to deep-dive specific threads or senders.
7
Save digest to
Inbox Digests as dated file (YYYY-MM-DD.yaml). Include timestamp, period, and synthesized insights.
To run this task you must have the following required information:
Time period (today, this week, specific dates), any focus areas (specific senders, topics)
If you don't have all of this information, exit here and respond asking for any extra information you require, and instructions to run this task again with ALL required information.
You MUST use a todo list to complete these steps in order. Never move on to one step if you haven't completed the previous step. If you have multiple read steps in a row, read them all at once (in parallel).
Add all steps to your todo list now and begin executing.
## Steps
1. [Read Inbox Intent Patterns]: Read the documentation in: `./skills/sauna//resources/context/gmail.inbox.intent.md` (Understand what digest they actually want)
2. Construct Gmail query for the digest period. 'Today' → 'newer_than:1d', 'this week' → 'newer_than:7d'. State what period you're covering.
3. [Gather Arguments: Fetch Gmail Messages] The next step has the following requirements for arguments, do not proceed until you have all the required information:
- `query`: Gmail query for digest period
- `maxResults` (default: "50"): 50-100 depending on period—today: 50, week: 100
- `outputPath` (default: "session/emails.json"): session/digest-data.json
4. [Run Code: Fetch Gmail Messages]: Call `run_script` with:
```json
{
"file": {
"path": https://sk.ills.app/code/gmail.inbox.fetch/preview,
"args": [
"query",
"maxResults",
"outputPath"
]
},
"packages": null
}
```
5. [Gather Arguments: Compute Gmail Stats] The next step has the following requirements for arguments, do not proceed until you have all the required information:
- `inputPath` (default: "session/emails.json"): session/digest-data.json
- `metrics` (default: "senders,volume"): senders,volume,response_times
6. [Run Code: Compute Gmail Stats]: Call `run_script` with:
```json
{
"file": {
"path": https://sk.ills.app/code/gmail.inbox.stats/preview,
"args": [
"inputPath",
"metrics"
]
},
"packages": null
}
```
7. Synthesize, don't enumerate. Lead with what matters: (1) Quick overview—X emails from Y senders. (2) Key threads—multi-message conversations worth knowing about. (3) Action items—requests, questions, deadlines from snippets. (4) Top senders—who dominated, briefly what about.
8. Present conversationally. Offer to deep-dive specific threads or senders.
9. Save digest to `./documents/documents/inbox/digests/*` as dated file (YYYY-MM-DD.yaml). Include timestamp, period, and synthesized insights.