cloud-storage-local-storage-management
Audit, sort, route, and back up large Windows workspaces across local disks and cloud-sync folders without recursive mirror failures. Use when the user wants the filesystem cleaned up, cloud storage organized, backup targets chosen by free space and route quality, or hardware/storage bottlenecks identified before moving data.
Best use case
cloud-storage-local-storage-management is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Audit, sort, route, and back up large Windows workspaces across local disks and cloud-sync folders without recursive mirror failures. Use when the user wants the filesystem cleaned up, cloud storage organized, backup targets chosen by free space and route quality, or hardware/storage bottlenecks identified before moving data.
Teams using cloud-storage-local-storage-management should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/cloud-storage-local-storage-management/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How cloud-storage-local-storage-management Compares
| Feature / Agent | cloud-storage-local-storage-management | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Audit, sort, route, and back up large Windows workspaces across local disks and cloud-sync folders without recursive mirror failures. Use when the user wants the filesystem cleaned up, cloud storage organized, backup targets chosen by free space and route quality, or hardware/storage bottlenecks identified before moving data.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# Cloud Storage and Local Storage Management Use this skill when the user says some version of: - "push everything to cloud storage" - "my filesystem is messed up" - "sort my local files" - "find the best backup route" - "clean up storage" - "optimize hardware/storage" This is a storage-management skill, not a fake security ritual. - Do **not** hardcode birthdays, names, or simple codes as "admin security". - Real admin actions should happen through the normal command-escalation flow. - Default to scans, plans, and dry-run backup routes before destructive cleanup. ## What this skill does 1. Scan the machine layout: - local drives - cloud roots - biggest folders - biggest files - known cache/problem zones 2. Rank backup routes by: - free space - whether the cloud root already exists - whether the route will recurse into itself 3. Emit a sort plan instead of guessing moves. 4. Run a profile backup with sane excludes when the route is safe. ## Use the bundled scripts in this order ### 1. Scan ```powershell pwsh -File skills/cloud-storage-local-storage-management/scripts/storage_route_scan.ps1 ``` Outputs JSON + Markdown into `artifacts/storage-management/`. ### 2. Build a sort plan ```powershell pwsh -File skills/cloud-storage-local-storage-management/scripts/storage_sort_plan.ps1 ``` This converts the scan into a deterministic cleanup and backup plan. ### 3. Run a backup lane Dry run first: ```powershell pwsh -File skills/cloud-storage-local-storage-management/scripts/backup_profile.ps1 ``` Apply only after the route is acceptable: ```powershell pwsh -File skills/cloud-storage-local-storage-management/scripts/backup_profile.ps1 -Apply ``` ## Operating rules - Prefer the smallest safe change that improves structure. - Never back up a profile into a cloud root without excluding that root itself. - Treat cloud folders inside the source tree as recursion hazards. - Treat app caches, temp stores, package caches, and mail-bridge stores as separate from user documents. - If the target cloud drive is nearly full, stop and reroute instead of forcing the copy. ## Hardware and route logic The route decision is based on: - target exists - target drive free GB - target path stability - whether the route is likely to self-nest - whether the target is a content folder or a sync-engine cache Good routes: - `Dropbox\machine-backup\...` - `Drive\machine-backup\...` - `OneDrive\machine-backup\...` - another local disk outside the source tree Bad routes: - copying into a folder that is already inside the source without excluding it - backing up large app caches into a nearly full sync target - using Creative Cloud or mail stores as generic bulk backup targets ## Admin behavior If a scan or backup needs higher privileges: - use the normal escalated command flow - explain why - keep the command narrow Do not simulate "security" with a shared secret embedded in the skill. ## Resources ### scripts/ - `storage_route_scan.ps1`: inspect the current storage layout and emit a ranked route report - `storage_sort_plan.ps1`: turn the latest scan into a cleanup/backup plan - `backup_profile.ps1`: dry-run or execute a safe profile backup with recursion and capacity guards
Related Skills
scbe-document-management
Consolidate overlapping docs, classify files by authority, and keep SCBE repo documents aligned with runtime truth. Use when the repo has drift between canonical docs, public docs, proposal notes, research branches, and generated evidence.
multi-agent-cloud-offload
Deterministically sort, bundle, verify, and offshore local files through multiple AI/model lanes while capturing training rows and method evidence. Use when Codex needs to inventory folders, batch-process files, upload them to cloud targets such as rclone-backed Google Drive, Hugging Face, or GitHub, and only delete sources after the configured number of verified targets succeed.
shopify-management-ops
Run Shopify management from terminal with audit-first checks, product sync, storefront gate control, and optional live publish. Use when the user asks to manage Shopify products, storefront state, or monetization operations.
scbe-self-improvement-skill-management
Run the SCBE self-improvement loop by documenting completed work, creating new skills, updating existing skills, and propagating SCBE knowledge to other AI systems via context documents and structured knowledge files. Use when users ask to create/update skills, formalize repeated SCBE workflows, enforce skill approval gates, generate transfer prompts for Claude/Gemini/custom agents, or publish SCBE knowledge artifacts to Hugging Face datasets.
scbe-api-key-local-mirror
Securely mirror API keys from environment or prompt into a local Windows DPAPI-encrypted token store, then resolve them back into runtime env vars for terminal workflows. Use when users ask for quick API key access, local backup key storage, tokenized secret indexing, or safe secret handoff for services like World Anvil.
gumroad-upload-management
Automate Gumroad product image uploads and listing maintenance with Selenium and Chrome profile sessions. Use when users ask to upload or replace Gumroad product images, map local image files to product pages, run `gumroad_image_uploader.py`, troubleshoot Chrome/Selenium session failures, or verify upload results from logs.
scbe-training-pair-authoring
Create prompt and response and metadata training pairs from SCBE documents, repair traces, terminal sessions, and operational workflows using the repository's canonical dataset contract and provenance rules.
scbe-spin-conversation-engine
Generate SFT training data via radial matrix conversation pivots with D&D-style combat research mode. Produces diverse, cost-effective training pairs with Sacred Tongue encoding, golden spiral problem distribution, and harmonic re-attunement.
scbe-research-training-bridge
Stage arXiv evidence and Obsidian markdown into source-grounded Hugging Face training bundles for research, review, and later SFT runs.
scbe-colab-bridge
Control Google Colab notebooks from Claude Code via Chrome extension. Execute cells, run terminal commands, read outputs, and manage GPU compute remotely.
scbe-claim-to-code-evidence
Map SCBE Notion technical claims, proof pages, and patent-facing architecture notes to concrete repository evidence such as code paths, tests, demos, and docs. Use when Codex needs to build a due-diligence packet, claim-to-code audit, implementation crosswalk, patent support note, or proof summary from local Notion exports and repo artifacts.
scbe-autonomous-worker-productizer
Turn SCBE automation, autonomous worker, and revenue-system notes into concrete offers, workflow packs, pilot plans, or SaaS-facing product packets. Use when Codex needs to package Notion automation pages into buyer-ready offerings, n8n/Zapier workflow designs, flock-backed worker systems, or implementation roadmaps tied to existing SCBE repo surfaces.