mac-software-storage-cleanup
Skill18 starsChanged 5 days agoMITView on GitHub
Use when auditing macOS app storage, cleaning priority caches, or recommending reclaimable disk space.
In this repository55 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- ax-extract-workflowSkill
- conversation-json-to-mdSkill
- feature-doc-splitterSkill
- frontend-quality-guardrailsSkill
- git-commit-onlySkill
- git-pushing-fastSkill
- git-push-secondary-merge-primarySkill
- git-stepwise-commitSkill
- git-weekly-reportSkill
- linkedinSkill
- logo-design-boardSkill
- multi-lang-readmeSkill
- novel-writerSkill
- react-component-hook-guidelinesSkill
- routerbase-api-integrationSkill
- routerbase-media-generationSkill
- routerbase-model-routingSkill
- topic-bookmarks-reorganizerSkill
- tree-ring-memorySkill
- tweetclaw-twitter-automationSkill
- ui-layout-analyzerSkill
- wechat-theme-extractorSkill
- weixin-article-to-obsidianSkill
- xquik-dataSkill
- x-twitter-scraperSkill
- yuque-lakebook-exportSkill
- ax-extract-workflow-cnSkill
- conversation-json-to-md-cnSkill
- feature-doc-splitter-cnSkill
- frontend-quality-guardrails-cnSkill
- git-commit-only-cnSkill
- git-pushing-fast-cnSkill
- git-push-secondary-merge-primary-cnSkill
- git-stepwise-commit-cnSkill
- git-weekly-report-cnSkill
- linkedin-cnSkill
- logo-design-board-cnSkill
- mac-software-storage-cleanup-cnSkill
- multi-lang-readme-cnSkill
- novel-writer-cnSkill
- react-component-hook-guidelines-cnSkill
- routerbase-api-integration-cnSkill
- routerbase-media-generation-cnSkill
- routerbase-model-routing-cnSkill
- topic-bookmarks-reorganizer-cnSkill
- tree-ring-memory-cnSkill
- tweetclaw-twitter-automation-cnSkill
- ui-layout-analyzer-cnSkill
- wechat-theme-extractor-cnSkill
- weixin-article-to-obsidian-cnSkill
- xquik-data-cnSkill
- x-twitter-scraper-cnSkill
- yuque-lakebook-export-cnSkill
The file
We split this skill into the rules it gives an agent
10 rules. About 0 are common, 7 are distinctive, and 3 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈7
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
- Distinctive: line 14
Use this skill when the user:
- Distinctive: line 22
Do not use this skill when:
- Very specific: line 29
Run scripts/report_sizes.sh first to inventory install sources and major storage consumers.
- Very specific: line 36
Only after explicit user confirmation, run scripts/cleanup_priority1.sh or an equivalent low-risk cleanup action.
- Very specific: line 37
After cleanup, recompute usage and show a before -> after -> reclaimed summary.
- Distinctive: line 62
Every cleanup action must include before-and-after comparison
- Distinctive: line 63
Do not delete priority-2 directories without explicit user approval
- Distinctive: line 67
Do not use destructive git commands
- Distinctive: line 68
Do not delete unconfirmed application data
- Distinctive: line 69
If a script fails, fall back to read-only inspection or the smallest safe cleanup scope
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.
Files
Mac Software Storage Cleanup
Overview
Audit installed software and storage usage on macOS, produce prioritized cleanup recommendations, and execute low-risk cleanup only after confirmation. The skill separates app inventory, cache cleanup, simulator data, and medium-risk application data so destructive actions remain explicit and reversible where possible.
When to Use
Use this skill when the user:
- Wants to inspect software installed under
/Applications,~/Applications, Homebrew Formula, or Homebrew Cask - Wants storage usage ranked by size across apps and common cache locations
- Wants to clean low-risk paths such as
~/Library/Cachesand~/Library/Developer/CoreSimulator - Wants reclaim recommendations with low-risk and medium-risk cleanup separated clearly
Do not use
Do not use this skill when:
- The user wants to uninstall one specific app instead of doing storage governance
- The user asks to delete application data directly without explicit confirmation
- The environment is not macOS or the target paths do not apply
Instructions
- Run
scripts/report_sizes.shfirst to inventory install sources and major storage consumers. - Classify cleanup candidates by priority:
- Priority 1: caches and simulator data, generally low risk.
- Priority 2: application data directories, report only and never delete by default.
- Priority 3: low-yield small caches or logs.
- Reports must show category totals, counts, and Top N largest entries.
- To inspect priority-2 candidates, run
scripts/list_priority2_candidates.sh [target_dir] [TopN]. - Only after explicit user confirmation, run
scripts/cleanup_priority1.shor an equivalent low-risk cleanup action. - After cleanup, recompute usage and show a
before -> after -> reclaimedsummary.
Workflow
Inventory install sources and storage usage
-> identify high-value cleanup targets
-> present prioritized recommendations
-> wait for user confirmation
-> run low-risk cleanup
-> verify reclaimed spaceRun commands
bash scripts/report_sizes.sh
bash scripts/list_priority2_candidates.sh ~/Library/Application\\ Support 20
bash scripts/cleanup_priority1.shOutput requirements
- Show counts and total size for each path category
- List Top N largest consumers so the user can decide quickly
- Every cleanup action must include before-and-after comparison
- Do not delete priority-2 directories without explicit user approval
Boundaries
- Do not use destructive git commands
- Do not delete unconfirmed application data
- If a script fails, fall back to read-only inspection or the smallest safe cleanup scope
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
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.

