storage-audit

Scan disk usage and propose confirmed cleanup actions for storage.

Updated Mar 13, 2026
One-click install
npx skills add https://github.com/Albatross679/0313temp --skill storage-audit
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: storage-audit
Source: https://github.com/Albatross679/0313temp/tree/main/.claude/skills/storage-audit/storage-audit
Command: npx skills add https://github.com/Albatross679/0313temp --skill storage-audit

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Audit machine storage and clean up disk space. Scans for large files, caches (pip, HuggingFace, W&B, torch, conda), model checkpoints, training output directories, duplicate git repos, and zombie/temp files. Presents categorized findings with sizes, then asks user for confirmation before deleting anything.

Core Features & Use Cases

  • Scan and summarize disk usage by category (large dirs, caches, training outputs, repos, and zombie files).
  • Identify caches and training outputs for safe cleanup while preserving important data.
  • Provide an interactive cleanup flow that asks for explicit user confirmation and respects a defined Safe-list before any deletion.

Quick Start

Run the storage-audit scan to generate a report and review the recommended cleanup actions before deleting anything.

Frequently Asked Questions about storage-audit

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I clean up disk space taken by pip, HuggingFace, and torch caches?

To clean up disk space, you can scan and summarize caches from pip, HuggingFace, W&B, torch, and conda. The audit categorizes these caches by size and proposes safe cleanup actions for explicit user confirmation before deletion.

What is the best way to find and remove large training outputs and model checkpoints?

The best way to find and remove large training outputs and model checkpoints is to run a storage audit. It scans for these specific directories, presents them with their sizes, and uses an interactive flow to confirm deletion while respecting a defined Safe-list.

How does interactive disk space cleanup protect important data from accidental deletion?

Interactive disk space cleanup protects data by enforcing a confirmation-based workflow and respecting a Safe-list. It presents categorized findings with sizes and requires explicit user approval before deleting any caches, repos, or zombie files.

Can I safely reclaim storage on a server where disk space is constrained?

Yes, you can safely reclaim storage on constrained workstations and servers. The audit scans for zombie files, duplicate git repos, and caches, then proposes evidence-based cleanup actions that require explicit confirmation before anything is removed.

Does disk space management work without accidentally removing active git repositories?

Disk space management identifies duplicate git repos and zombie files but enforces a Safe-list protection. It presents categorized findings and requires interactive confirmation, ensuring active repositories are preserved during routine maintenance.