agentleFS
the-abraham-brandthe-abraham-brand/my-business-brain/skills/heal/SKILL.md

heal

Skill0 starsChanged 51 days agoMITView on GitHub

My Business Brain full health check. Scans the whole brain for conflicts, duplicates, overlaps, stale and unsourced entries, broken links, supersede errors and contract deadlines; fixes housekeeping automatically and brings the user each decision with a recommended answer and a health score. Use when the user runs /my-business-brain:heal, or asks to check, clean up, audit or fix their business brain.

1 other project uses a version of this.

Adopted by

Most recently taken up by

  • Other versions1 project uses a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 1

    1. jbellsolutions/hermes-super-agent★ 4same 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 repository9 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, 1 is distinctive, and 2 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈1

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Keep the brain trustworthy.

    line 8
  2. Very specific:

    Write open items to _system/decisions-needed.md, grouped and High first.

    line 14
  3. Very specific:

    Run scripts/lexicon.py <brain-folder> build and scripts/distill.py <brain-folder> so the lexicon and playbook match the healed brain.

    line 18

≈ “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.

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

/my-business-brain:heal

Keep the brain trustworthy.

  1. Load the my-business-brain skill from this plugin (via the Skill tool). If it cannot be loaded, read ../my-business-brain/SKILL.md and ../my-business-brain/references/self-healing.md directly.
  2. Run scripts/brain_health.py <brain-folder> from the core skill folder (it also replays the golden questions, lists outputs built on changed facts, flags unstable facts and saves a daily snapshot), then scripts/brain_index.py <brain-folder>, scripts/decide.py stats <brain-folder> --write scripts/brain_diff.py diff <brain-folder> scripts/dashboard.py <brain-folder> and scripts/toolkit.py <brain-folder> detect (refresh what the brain can use) (references/knowledge-regression.md, references/decision-gates.md). Where scripts cannot run, perform the same checks by reading the entries.
  3. Apply the automatic fixes (index, register, formatting, id and folder mismatches, archiving superseded entries) and log them.
  4. Review what the script cannot judge (use scripts/brain_search.py to find related entries): statements in different entries that contradict each other without sharing a key, and overlaps worth merging. Re-vet stale official information.
  5. Write open items to _system/decisions-needed.md, grouped and High first; within a group, most urgent first (the urgency and stakes scores).
  6. Report: Brain health score and trend, Fixed automatically (one line), Needs your decision (each with a recommendation and a one-word answer the user can give), Knowledge regressions (golden questions answering differently: accept or restore), Outdated past outputs (who received the old value, with an offer to draft follow-ups), What changed this week (the diff, in a few lines), Changed outside the brain (files edited, added or deleted without a record: confirm or restore each), Mentioned but not saved (from _system/unsaved-facts.md), Decision accuracy (any decision type whose bar was raised or whose confidence is being corrected, in plain words such as "domain calls said 95% sure but were right 80% of the time; I now ask when unsure", and any proposed rule), and the next contract deadlines.
  7. Apply the user's answers: supersede, merge, confirm or archive; record each in the changelog and any repeated mistake as a lesson.
  8. Mention that the dashboard is at _system/dashboard.html (offer to open it). At the start of a month, offer the journal for the month just ended (references/briefings-and-journal.md).
  9. Run scripts/lexicon.py <brain-folder> build and scripts/distill.py <brain-folder> so the lexicon and playbook match the healed brain. Mention overdue promises and delegations (commitments.py list --overdue, delegations.py list --overdue) and any agent whose work now gets an independent check (delegate.py scorecard).
  10. Mention open leads in one line (scripts/signals.py <brain> list --open --kind lead). If there is no Sunday evening review scheduled (/my-business-brain:review), offer one once.

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.