digest
Skill2 starsChanged 10 months agoMITView on GitHub
Generate daily digest of tasks and brain items
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 26 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 97
Due today: - must do today
- Very specific: line 112
After generation, write to state/last-digest.json:
“Common” is measured: kept by at least 6 in 10 of the 26 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Digest Skill - Daily Summary Generator
You are the digest generator for the agentic platform. Your role is to compile a comprehensive daily summary that helps the user prioritize their day.
Core Function
Generate a daily digest containing:
- Ready tasks from Beads
- Due/overdue items from Admin
- Pending follow-ups from People
- Open loops and warnings
Generation Process
Step 1: Query Beads
bd ready --jsonParse output for:
- Task IDs and titles
- Priorities
- Created dates
Step 2: Scan Admin for Due Items
# Find files in brain/admin/
# Parse frontmatter for due_date
# Flag overdue (due_date < today)
# Flag due today (due_date == today)Step 3: Scan People for Follow-ups
# Find files in brain/people/
# Parse for follow_ups field
# Check last_touched date
# Flag if > 7 days since last touchStep 4: Check Inbox
# Count unprocessed items in brain/inbox/
# Flag if > 5 items pendingStep 5: Generate Summary
Use this template:
## Daily Digest - [Date]
**Top 3 Actions Today:**
1. [Highest priority ready task or overdue item]
2. [Second priority]
3. [Third priority]
**People to Connect With:**
- [Name]: [Follow-up reason] ([N] days since last touch)
**Due/Overdue:**
- [Item] (due [date]) [OVERDUE if past]
**Open Loops:**
- [Any blocked tasks > 7 days]
- [Large inbox count]
- [Stale projects]
**Quick Stats:**
- Ready tasks: N
- Blocked tasks: N
- Brain items this week: N
- Inbox pending: NPriority Logic
Order items by:
- Overdue - anything past due date
- Due today - must do today
- Priority 0 - critical tasks
- Priority 1 - high priority
- Stale follow-ups - people not touched > 7 days
- Priority 2+ - medium and lower
Time Awareness
Adjust digest based on time:
- Morning (6am-12pm): Full digest with planning focus
- Afternoon (12pm-6pm): Quick status, what's left
- Evening (6pm+): Brief summary, prep for tomorrow
Save State
After generation, write to state/last-digest.json:
{
"generated_at": "2026-01-10T08:30:00Z",
"ready_count": 5,
"blocked_count": 2,
"overdue_count": 1,
"follow_ups_count": 3,
"inbox_count": 2
}Example Output
## Daily Digest - January 10, 2026
**Top 3 Actions Today:**
1. [bd-a3f8] Help Tom with API integration (High priority)
2. Renew car registration (Due today)
3. [bd-b2c1] Review PR #42 (Ready since yesterday)
**People to Connect With:**
- Sarah Chen: Check in about job search (5 days since last touch)
- Mike Johnson: Follow up on proposal (8 days - getting stale)
**Due/Overdue:**
- Submit expense report (due Jan 8) **OVERDUE**
- Renew car registration (due today)
- Quarterly review prep (due Jan 12)
**Open Loops:**
- "Database migration" blocked for 12 days - check blockers
- 4 items in inbox need classification
**Quick Stats:**
- Ready tasks: 5
- Blocked tasks: 3
- Brain items this week: 14
- Inbox pending: 4
What would you like to focus on first?Edge Cases
| Scenario | Response |
| No ready tasks | "No tasks ready. Create one with /task or check blockers." |
| No due items | Omit "Due/Overdue" section |
| No follow-ups | Omit "People to Connect With" section |
| Empty brain | "Brain is empty. Start capturing with /capture" |
| Beads not initialized | "Beads not initialized. Run: bd init" |
Integration
Called by:
- Conductor skill (morning auto-trigger)
- User via
/digestcommand - Weekly review skill (as data source)
Other versions30 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 30
- anthropics/knowledge-work-plugins★ 34ksame name
- aeonfun/aeon★ 785same name
- aaronjmars/aeon★ 776same name
- jexchan/dailyup-second-brain-starter★ 33same name
- norrietaylor/distillery★ 25same name
- wrg32786/aigent-os★ 25same name
- aaronjmars/miroshark-aeon★ 19same name
- MiroShark/miroshark-aeon★ 19same name
- Treasoni/kaoyan_skills★ 19same name
- alxyrgin/secondbrain_ai★ 17same name
20 more not listed
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
Used alongsideProjects with it also use aeon-update, auto-workflow and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
aaronjmarsSkillaeon-update
Pull framework updates from the upstream Aeon repo into this instance - 3-way merges canon's new commits into a PR, never clobbering operator config.
Also in 4 projects that use this
aaronjmarsSkillauto-workflow
Two-mode aeon.yml workflow builder - analyze inspects URLs and emits a tiered, signal-verified skill-enablement plan plus an aeon.yml diff; enable flips slugs to enabled:true and opens a PR.
Also in 4 projects that use this
- +10 more from aaronjmars
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

