agentleFS
jqaisystemsjqaisystems/jqai-ai-skills/skills/windows-reinstall-planner/SKILL.md

windows-reinstall-planner

Skill3 starsChanged 6 months agoMITView on GitHub

Prepare a metadata-only Windows software inventory and evidence-linked reinstall checklist without changing installed software. Use before replacing a computer or reinstalling Windows, or when organizing registered applications and unconfirmed shortcuts into a private review plan.

The file

We split this skill into the rules it gives an agent

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

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    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:

    Read collection and reporting boundaries.

    line 13
  2. Distinctive:

    Use a new local filename in an existing directory.

    line 18
  3. Very specific:

    Do not query Win32_Product, which can initiate installer repair checks.

    line 31
  4. Distinctive:

    Keep real inventories private, even when they contain no access data: software choices can identify a person or organization.

    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

Windows Reinstall Planner

Separate software evidence from reinstall decisions. An inventory is not a backup and does not authorize destructive maintenance.

Workflow

  1. Confirm the machine and private output location. Explain the limited collection scope before running it.
  2. Read collection and reporting boundaries.
  3. In Windows PowerShell 5.1, collect only the requested metadata:

    powershell.exe -NoProfile -File scripts/collect_software.ps1 -OutputPath inventory.json

    Use a new local filename in an existing directory. No elevation is required. From PowerShell 7, invoke Windows PowerShell as shown; unavailable adapters produce a partial-coverage report.

  4. Build reports with Python 3.11 or newer:

    python scripts/build_reinstall_plan.py --input inventory.json --output-dir private-report
  5. Review groups and uncertain duplicates. Keep unknown versions blank. Do not claim registrations prove an app still runs or reveal who originally installed it.
  6. Let the user select Yes, No, Later, or Undecided in the generated CSV. Verify official publisher download links only for selected software, without downloading or installing anything.
  7. Return the report locations, evidence counts, coverage gaps, and remaining decisions.

Boundaries

The collector reads names, versions, publishers, package identifiers, and evidence types from uninstall registry entries, current-user Store packages, and Start-menu app listings. It excludes account access data, activation values, shortcut arguments, configuration contents, browser profiles, and broad drive scans.

Do not query Win32_Product, which can initiate installer repair checks. Do not install, uninstall, erase, format, restore, or export application settings. No background task or remote inventory is created.

Keep real inventories private, even when they contain no access data: software choices can identify a person or organization. Public examples must be fictional. Checklists and CSV choices are independent, not silently synchronized.

Deliverables

  • One evidence row per source record, with unique IDs.
  • A conservatively grouped checklist linked to those IDs.
  • A coverage report distinguishing records, display groups, and unknown runtime state.
  • A reminder to verify separate file/settings backups before any later maintenance.

The report builder writes only new named reports and refuses to overwrite existing ones. It needs no third-party Python package.

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.