agentleFS
herreraspaintingba-hubherreraspaintingba-hub/second-brain-starter-kit/skills/brain-health/SKILL.md

brain-health

Skill0 starsChanged 43 days agoMITView on GitHub

Measures the health of the user's second brain with the same rules every month and keeps a history, so this month is compared with last month: broken links, orphan notes, notes outside the frontmatter contract, duplicates, backup files inside the vault, names Obsidian cannot link, and stale project Doors. Answers with a traffic light (green, yellow, red) and what to fix first. Use it for "brain health", "how is my brain doing?", "check my vault", "broken links", "orphan notes", "salud del cerebro", "¿cómo está mi cerebro?", "revisa el vault", "links rotos", and to manage the monthly schedule ("turn on the monthly check", "apaga la revisión mensual"). Bilingual EN+ES.

2 other projects use a version of this.

Adopted by

Most recently taken up by

  • Other versions2 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 2

    1. day-ai/gtm-brain★ 9same name
    2. t0ddharris/compound-marketing★ 1same name

    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.

  • In this repository8 other files it gives its agents.

The file

We split this skill into the rules it gives an agent

3 rules. About 0 are common, 2 are distinctive, and 1 is very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈2

    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
  1. Distinctive:

    If the monthly run already happened this month, read the history note instead of running it again.

    line 73
  2. Distinctive:

    Broken links: create the missing note as a short stub, or fix the link to the right name.

    line 84
  3. Very specific:

    Stale Doors: run project-door on that project to verify it, or set the project status: parked.

    line 90

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Brain Health: the same checkup, every month

A vault rots quietly: a renamed note leaves broken links, a quick save leaves an orphan, a copy is left as .bak. None of it hurts on the day it happens. Measured once a month with the same rules, it is caught while it is small.

What it measures

MeasureWhat it meansHealthy
NotesHow many, and per section 00 to 09Growing where the user works
Broken links[[links]] to notes that do not existGoing down
OrphansNotes nothing links to (MOCs, Doors, logs excluded)Few, and shrinking
No frontmatterNotes without the properties block0 for new notes
Contract% of notes that pass check_frontmatter.pyGoing up
.bak filesBackup copies sitting inside the vault0
DuplicatesNotes whose body is an exact copy of another0
Bad namesFile names with # ^ [ ] | :0
Stale DoorsProject Doors not verified in 30 days0

The light: RED if there are .bak files in the vault or broken links grew more than 10% since the last run. YELLOW if broken links grew at all, the contract % dropped, or there are bad names or stale Doors. GREEN otherwise. It compares against last month, not against perfection: an old vault starts with many broken links, and that is fine as long as the number goes down.

How to run it

T="{{VAULT_PATH}}/.brain/tools"
python3 "$T/brain_health.py"                     # measure and print; changes nothing
python3 "$T/brain_health.py" --write             # also add a row to the history note
python3 "$T/brain_health.py" --write --reindex   # the full monthly run

The history lives in 05 AI System/Brain Health History.md: the latest light and its reasons, the top broken links and orphans, and one row per run. Earlier rows are kept.

The monthly schedule

The kit can run the check by itself on the 1st of every month at 07:00:

bash "{{VAULT_PATH}}/.brain/tools/schedule_health.sh" install   # turn it on
bash "{{VAULT_PATH}}/.brain/tools/schedule_health.sh" status    # is it on? last log lines
bash "{{VAULT_PATH}}/.brain/tools/schedule_health.sh" remove    # turn it off
bash "{{VAULT_PATH}}/.brain/tools/schedule_health.sh" run       # run it now, like the schedule

macOS uses launchd, Linux uses cron, Windows gets a one-line schtasks command to paste. On a Mac with the vault in iCloud, the first run may need Python to have Full Disk Access (the script says how). The log is .brain/health.log.

How to answer the user

  1. If the monthly run already happened this month, read the history note instead of running it again.
  2. Lead with the light and the one reason that matters most.
  3. Show the measures as a short table, with last month next to this month.
  4. Give at most three fixes, the most repeated broken link first. Offer to do them.
  5. Two months in a row not green: offer a deeper review of the vault (contradictions, outdated notes, MOCs that no longer match), which the numbers cannot see.

How to fix what it finds

  • .bak files: move them to Archives/Backups/<date>/. Never delete.
  • Broken links: create the missing note as a short stub, or fix the link to the right name. One fix often repairs many links.
  • Orphans: link each from its MOC or a related note; archive what is truly dead.
  • Contract: python3 "$T/check_frontmatter.py" --all lists each note and what is wrong. Fix the newest notes first.
  • Bad names: rename the file and let Obsidian update the links.
  • Stale Doors: run project-door on that project to verify it, or set the project status: parked.

Without Python, do a lighter manual pass: search for .bak files, for [[ links whose target has no file, and read the Doors' verified: dates.

Changelog

  • 2.0.0 (2026-10-02): New skill. Nine measures, traffic light against last month, history note, monthly schedule on macOS, Linux and Windows.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.