brain-digest
Skill1 starsChanged 5 months agoMITView on GitHub
Generate a summary of brain activity: recent additions, pending inbox items, suggested connections, orphaned notes, and brain statistics.
In this repository14 other files it gives its agents.
- brain-addSkill
- brain-add-videoSkill
- brain-checkSkill
- brain-processSkill
- brain-saveSkill
- brain-searchSkill
- client-onboardSkill
- consulting-deckSkill
- good-morningSkill
- harvestSkill
- logSkill
- taskSkill
- weekly-reviewSkill
- wrap-sessionSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
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
- Very specific: line 41
Check meta/digests/ for the last 3 processing digests
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/brain-digest
Activity summary and brain health overview.
Steps
- Scan recent additions (last 7 days):
- Glob all .md files in brain/ (excluding meta/, mocs/, inbox/, .carl/, .claude/)
- Filter by
created:frontmatter date within last 7 days - List each with title, category, tags, status
- Check inbox status:
- Count files in
brain/inbox/(excluding.processed/) - List pending items by name and type
- Count files in
- Suggest connections between recent additions:
- For each note added in the last 7 days, check shared tags and [[wiki-links]] with other recent notes
- Highlight pairs that share topics but aren't linked to each other via
related:
- Surface orphaned notes:
- Find notes with no incoming [[wiki-links]] from other notes and empty
related:field - These are isolated — suggest connecting them or reviewing for relevance
- Find notes with no incoming [[wiki-links]] from other notes and empty
- Brain statistics:
- Total note count
- Count by category (professional, personal, admin, creative)
- Count by status (seed, growing, evergreen)
- Count MOCs in mocs/
- Most used tags (top 10)
- Inbox size
- Recent digests:
- Check
meta/digests/for the last 3 processing digests - Summarize what was processed
- Check
Present the report:
📊 Brain Digest — {date} ## Recent Additions (last 7 days) - {title} → {category}/{subcategory} [{status}] ... ## Inbox {count} items pending | Last processed: {date} ## Suggested Connections - {note A} ↔ {note B} (shared: #tag, [[topic]]) ... ## Orphaned Notes - {title} — no incoming links ... ## Stats Total: {X} notes | Professional: {X} | Personal: {X} | Admin: {X} | Creative: {X} Seeds: {X} | Growing: {X} | Evergreen: {X} MOCs: {X} | Inbox: {X} Top tags: #tag1 (X), #tag2 (X), ...
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.

