agentleFS
jqaisystemsjqaisystems/jqai-ai-skills/skills/backup-readiness-auditor/SKILL.md

backup-readiness-auditor

Skill3 starsChanged 6 months agoMITView on GitHub

Evaluate supplied backup manifests and verification evidence before a migration or recovery decision. Identify incomplete coverage, stale checks, failed integrity checks, and unresolved recovery tests without collecting files, running backups, restoring data, or authorizing destructive maintenance.

The file

We split this skill into the rules it gives an agent

6 rules. About 0 are common, 6 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈6

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Ask for the intended scope, evidence cutoff, and an approved metadata-only evidence pack.

    line 12
  2. Distinctive:

    Read the evidence contract.

    line 13
  3. Distinctive:

    Use the standard-library helper when the pack follows version 1:

    line 14
  4. Distinctive:

    Do not infer credential portability, cloud synchronization, encryption, or application consistency from filenames or installation state.

    line 27
  5. Distinctive:

    Do not open browser profiles, account exports, access files, databases, or configuration contents.

    line 28
  6. Distinctive:

    Keep real evidence packs and reports private.

    line 29

≈ “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

Backup Readiness Auditor

Separate a prepared backup procedure from evidence that the selected data can be recovered.

Workflow

  1. Ask for the intended scope, evidence cutoff, and an approved metadata-only evidence pack. Do not search personal drives or application profiles to fill gaps.
  2. Read the evidence contract. Map each required dataset to its own verification evidence. Keep unknowns explicit; a missing row is not an exclusion.
  3. Use the standard-library helper when the pack follows version 1:

    python scripts/audit_backup.py --input evidence.json --as-of 2026-10-14T12:00:00Z --json

    It reads only that JSON file and writes to stdout. Redirect output only to a user-approved private location. It does not inspect source/destination folders, fetch cloud files, or verify the claims independently.

  4. Investigate gaps with the user. File counts, matching sizes, a healthy disk, a successful copy command, or an encrypted archive alone do not establish recoverability. Distinguish hash verification, stable snapshot evidence, coverage, and an isolated restore test.
  5. Return the evidence verdict, reasons, required follow-up checks, and evidence cutoff. Use the report template for a fuller handoff.

Decisions and boundaries

  • BLOCKED: supplied evidence reports a failed check or missing required dataset.
  • REVIEW: no known failure, but evidence is incomplete, stale, future-dated, or untested.
  • EVIDENCE_COMPLETE: the supplied pack satisfies these checks. This is not independent certification of a backup and never permission to format, delete, or retire an original.
  • Do not infer credential portability, cloud synchronization, encryption, or application consistency from filenames or installation state.
  • Do not open browser profiles, account exports, access files, databases, or configuration contents. Do not copy, decrypt, restore, mount, schedule, install, or change permissions.
  • Keep real evidence packs and reports private. Public tests use fictional dataset IDs and synthetic counts, never actual inventories, account information, volume identifiers, or machine paths.

For software reinstall choices, use a separate inventory workflow. This skill evaluates backup evidence, not installed applications.

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.