agentleFS
davekilleendavekilleen/Dex/.agents/skills/backup-now/SKILL.md

backup-now

Skill509 starsChanged 3 months agoMITView on GitHub

Run a vault backup right now and report the verified result. Use when the user says 'back up now', 'take a backup before I do this', or is about to make a big change. Not for scheduling or changing where backups go (`backup-setup`); not for getting files back (`backup-restore`).

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 1 is distinctive, and 3 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.

  • 3

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    If backups have never been configured, the run will fail with a clear message.

    line 20
  2. Very specific:

    Read System/.dex/backup-last-run.json and report what actually happened, not what was attempted:

    line 24
  3. Distinctive:

    Never infer success from the command finishing.

    line 29
  4. Very specific:

    If the previous successful run was more than two days before this one, mention it once, quietly and without alarm, and offer /backup-setup …

    line 33

≈ “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
<!-- Generated from `.claude/skills/backup-now/SKILL.md` by `scripts/generate-agents-skills.py`. Do not edit. -->

Backup Now

Take an immediate backup of the vault, on top of whatever the schedule is doing. Worth suggesting before anything sweeping: a bulk edit, a big reorganisation, a system update, or a migration.

Run it

python3 core/backup/backup_vault.py

It takes well under a minute for a typical vault. The command handles archiving, verifying, storing, and pruning old copies in one pass.

If backups have never been configured, the run will fail with a clear message; offer /backup-setup rather than improvising a destination.

Report honestly

Read System/.dex/backup-last-run.json and report what actually happened, not what was attempted:

  • On success: the set name, total size, where it went, and how many older sets were pruned. Say plainly that the version history in the set was verified as complete.
  • On failure: the recorded error, verbatim. Do not soften it and do not claim a backup exists. Common causes worth naming: the destination folder is missing or not mounted, a cloud remote is not reachable, or the disk is full.

Never infer success from the command finishing. The run record is the evidence.

If it has not run in a while

If the previous successful run was more than two days before this one, mention it once, quietly and without alarm, and offer /backup-setup to check the schedule. A silent scheduling failure is the most common way backups die.

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.